Atomic force microscopy (AFM) is powerful nanobiotechnology for characterizing the nanotopographic and nanobiomechanical properties of live cells. Current limitations in AFM analysis of nanomechanobiology include the unjustified selection of nesting indices and filters, leading to the inaccurate reporting of waviness and roughness parameters, and inadequacies in the selection of the mathematical model for the Young's modulus. Critical biomechanical factors such as total deformation energy, elastic energy, and plastic energy are often overlooked. Here we refine and optimize the selection of the nesting index and filters for cellular analysis and develop an artificial intelligence-based classifier that can differentiate between normal and cancer cells. The application of AFM for detecting surface waviness and roughness, further enhanced by artificial intelligence (AI), represents a substantial advancement in cancer diagnostics. Although still in the experimental phase, AFM holds the potential to revolutionize cell biology and oncology by facilitating early cancer detection and advancing precision medicine. Moreover, this study's innovative exploration of the relationship between cellular nanomechanobiology and thermodynamics introduces important perspectives on cancer cell behavior at the nanoscale, unlocking opportunities for therapeutic interventions and cutting-edge oncological research. This paradigm shift may significantly influence the future trajectory of cancer biology and therapy.

This study aims to develop a comprehensive simulation framework to connect radiation effects from the microscopic to the nanoscopic scale.

The process begins with a Geant4-DNA simulation based on the example "molecularDNA", producing a dataset of twelve different types of early DNA damages within an Escherichia coli (E. coli) bacterium, generated by proton irradiation at different kinetic energies, giving a nano-scale view of the particle-matter interaction. Then we pass to the micro-scale with a Geant4 simulation, based on the example "radiobiology", providing a microscopic view of proton interactions with matter through the Linear Energy Transfer (LET). Then GANDALF (Generative ANsatz for DNA damage evALuation and Forecast) Machine Learning (ML) toolkit, a Neural Network (NN)-based regression system, is employed to correlate the micro-scale LET data with the nano-scale occurrences of DNA damages in the E. coli bacterium.

The trained ML algorithm provides a practical tool to convert LET curves versus depth in a water phantom into DNA damage curves for twelve distinct types of DNA damage. To assess the performance, we evaluated the choice and optimization of the regression system based on its interpolation and extrapolation capabilities, ensuring the model could reliably predict DNA damage under various conditions.

Through the synergistic integration of Geant4, Geant4-DNA and ML, the study provides a tool to easily convert the results at the micro-scale of Geant4 to those at the nano-scale of Geant4-DNA without having to deal with the high CPU time requirements of the latter.

Machine learning (ML) models are being increasingly employed to predict the risk of developing and progressing diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). However, the performance of these models still varies, which limits their widespread adoption and practical application. Therefore, we conducted a systematic review and meta-analysis to summarize and evaluate the performance and clinical applicability of these risk predictive models and to identify key research gaps.

We conducted a systematic review and meta-analysis to compare the performance of ML predictive models. We searched PubMed, Embase, the Cochrane Library, and Web of Science for English-language studies using ML algorithms to predict the risk of DKD in patients with T2DM, covering the period from database inception to April 18, 2024. The primary performance metric for the models was the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI). The risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist.

26 studies that met the eligibility criteria were included into the meta-analysis. 25 studies performed internal validation, but only 8 studies conducted external validation. A total of 94 ML models were developed, with 81 models evaluated in the internal validation sets and 13 in the external validation sets. The pooled AUC was 0.839 (95% CI 0.787-0.890) in the internal validation and 0.830 (95% CI 0.784-0.877) in the external validation sets. Subgroup analysis based on the type of ML showed that the pooled AUC for traditional regression ML was 0.797 (95% CI 0.777-0.816), for ML was 0.811 (95% CI 0.785-0.836), and for deep learning was 0.863 (95% CI 0.825-0.900). A total of 26 ML models were included, and the AUCs of models that were used three or more times were pooled. Among them, the random forest (RF) models demonstrated the best performance with a pooled AUC of 0.848 (95% CI 0.785-0.911).

This meta-analysis demonstrates that ML exhibit high performance in predicting DKD risk in T2DM patients. However, challenges related to data bias during model development and validation still need to be addressed. Future research should focus on enhancing data transparency and standardization, as well as validating these models' generalizability through multicenter studies.

https://inplasy.com/inplasy-2024-9-0038/, identifier INPLASY202490038.

Machine learning (ML) integration of clinical, metabolite, and genetic data reveals variable results in predicting cardiometabolic health (CMH) outcomes. Therefore, we aim to (1) evaluate whether a multi-modal approach incorporating all three data types using ML algorithms can improve CMH outcome prediction compared to single-modal or paired-modal models, and (2) compare the methodologies used in existing prediction models.

We systematically searched five databases from 1998 to 2024 for ML predictive modelling studies using the multi-modal approach for CMH outcomes. Risk-of-bias assessment tools were used to assess methodological quality. Study characteristics, ML algorithms, data preprocessing, evaluation methods and metrics, feature selections, and feature importance parameters were synthesized narratively to show methodological heterogeneity.

Of the four included studies (3 ML algorithms), three were at low risk of bias, and one was at high risk. The multi-modal approach consistently improved T2D and BP prediction compared to single-modal or paired-modal models. Genetics showed the lowest predictive performance in three studies. Logistic regression (n = 2 studies) and random forest (n = 1) were used in T2D studies, while XGBoost was used in one BP study. One study with missing data and variations in feature selection across all studies hindered a comprehensive comparison of feature importance.

Our review emphasizes the potential improvement in T2D and BP prediction using ML algorithms with the multi-modal approach. However, further studies using diverse ML algorithms with optimized methodologies on single-modal, paired-modal, and multi-modal models are needed to gain insights into biomarker selection for predicting CMH outcomes.

Pelvic organ prolapse (POP) is a common condition, affecting women worldwide and is known to have a significant impact on Health Related Quality of Life (HRQoL). Although there are various treatment options available, including pelvic floor muscle training and support pessaries, many women opt for or require surgery, with a lifetime risk of needing surgery of 12%-19%. As with any operation, this does not come without its complications and the reoperation rate following POP surgery is up to 36%. This International Consultation on Incontinence-Research Society (ICI-RS) report aims to look at the different factors which may play a role in objective and subjective outcomes following pelvic floor surgery and to summarize the evidence and uncertainties regarding prediction of POP surgical outcomes, how to optimize them and the tools available to predict them. Research question proposals to further this field have been highlighted.

At ICI-RS 2024, the evidence for predicting the outcomes from POP surgery and methods to optimize outcomes were discussed and presented in this paper.

There are many reasons why POP surgery may fail, such as variations in lifestyle and occupation, persistent constipation, failure in the perineal body, connective tissue types or the shape of the pelvis. There may also be inherent conditions of the vagina, such as hormonal or microbial features. The literature lacks evidence about the potential use of advanced statistical modeling or supervised machine learning in the development of management plans for patients with POP. Furthermore, future research is needed to determine the role of UDS in the preoperative evaluation of POP patients.

High-quality powered studies are required to assess optimization for long-term outcomes of pelvic surgery and then, once these are well established, and possible interventions are elucidated, prediction modeling can have a real impact clinically.

Machine learning is increasingly being applied in polymer chemistry to link chemical structures to macroscopic properties of polymers and to identify chemical patterns in the polymer structures that help improve specific properties. To facilitate this, a chemical dataset needs to be translated into machine readable descriptors. However, limited and inadequately curated datasets, broad molecular weight distributions, and irregular polymer configurations pose significant challenges. Most off the shelf mathematical models often need refinement for specific applications. Addressing these challenges demand a close collaboration between chemists and mathematicians as chemists must formulate research questions in mathematical terms while mathematicians are required to refine models for specific applications. This review unites both disciplines to address dataset curation hurdles and highlight advances in polymer synthesis and modeling that enhance data availability. It then surveys ML approaches used to predict solid-state properties, solution behavior, composite performance, and emerging applications such as drug delivery and the polymer-biology interface. A perspective of the field is concluded and the importance of FAIR (findability, accessibility, interoperability, and reusability) data and the integration of polymer theory and data are discussed, and the thoughts on the machine-human interface are shared.

Many obesity indicators have been linked to adiposity and its distribution. Utilizing a combination of multidimensional obesity indicators may yield different values to assess the risk of moderate-to-severe obstructive sleep apnea (OSA). We aimed to develop and validate the performances of automated machine-learning models for moderate-to-severe OSA, employing multidimensional obesity indicators as compact representations. We trained, validated, and tested models with logistic regression and other 5 machine learning algorithms on the clinical dataset and a community dataset. Light gradient boosting machine (LGB) had better performance of calibration and clinical utility than other algorithms in both clinical and community datasets. The model with the LGB algorithm demonstrated the feasibility of predicting moderate-to-severe OSA with considerable accuracy using 19 obesity indicators in clinical and community settings. The useable interface with deployment of the best performing model could scale-up well into real-word practice and help effectively detection for undiagnosed moderate-to-severe OSA.

Evaluating high-throughput soil profile information is essential in safflower precision agriculture, as it facilitates efficient resource management and design of an experiment that promotes sustainable production. We collected soil from representative target environments (TE) of safflower cultivation and evaluated 14 soil physio-chemical features for constructing fine-resolution maps. The robustness, versatility, and predictive ability of two statistical learning models in correctly classifying the soil profile to clusters were tested. Calcium, sand, soil organic carbon, phosphorous, potassium, and sodium were found to be most influential in classifying the representative TE. Random Forest model was found to be the best performing with average prediction accuracy above 85% in all test settings which reached 100% in some. The optimal training population size for prediction was found to be 70-80%. The spatial distribution of sodium in Delhi was found to be aligned with the low yield of safflower emphasizing the importance of fine-resolution soil mapping to design a field experiment and optimize the nutrient supply. Fine-resolution mapping not only enhance soil management strategies but also support government initiatives such as soil health cards, delineation of cultivable land, and risk assessments in crop-growing areas.

The selection and optimization of carbon and nitrogen sources are essential for enhancing pullulan production in Aureobasidium pullulans. In this study, combinations of carbon (sucrose, fructose, glucose) and nitrogen sources ((NH4)2SO4, urea, NaNO3) were screened, where sucrose and NaNO3 offered the highest pullulan yield (9.33 g L-1). Plackett-Burman design of experiment identified KH2PO4, NaCl, and sucrose as significant factors, which were further optimized using a central composite design. A hyperparameter-optimized artificial neural network (ANN) model with a 3-6-2-1 architecture demonstrated superior predictive accuracy (R2: 0.96) and generalizability (R2CV: 0.74) over a reduced quadratic model (R2: 0.82). The predicted pullulan yield (31.9 g L-1) under ANN model optimized conditions (sucrose: 79.9 g L-1, KH2PO4: 0.25 g L-1, NaCl: 4.3 g L-1) closely matched with the observed yield (30.17 g L-1), while quadratic model showed a significant deviation (39.7 g L-1 vs. 21.0 g L-1), highlighting the reliability of the ANN model.

This study aimed to develop machine learning (ML) prediction models for identifying bloodstream infection (BSI) and septic shock (SS) in pediatric patients with cancer who presenting febrile neutropenia (FN) at emergency department (ED) visit.

A retrospective study was conducted on patients, younger than 18 years of age, who visited a tertiary university-affiliated hospital ED due to FN between January 2004 and August 2022. ML models, based on XGBoost, were developed for BSI and SS prediction.

After applying the exclusion criteria, we identified 4423 FN events during the study period. We identified 195 (4.4%) BSI and 107 (2.4%) SS events. The BSI and SS models demonstrated promising performance, with area under the receiver operating characteristic curve values of 0.87 and 0.88, respectively, which were superior to those of the logistic regression models. Clinical features, including body temperature, some laboratory results, vital signs, and diagnosis of acute myeloblastic leukemia were identified as significant predictors.

The ML-based prediction models, which use data obtainable at ED visits may be valuable tools for ED physicians to predict BSI or SS.

To explore the differences and associations of hypoxic parameters among distinct types of respiratory events in patients with obstructive sleep apnea (OSA) and to construct prediction models for the types of respiratory events based on hypoxic parameters.

A retrospective analysis was conducted on a cohort of 67 patients with polysomnography (PSG). All overnight recorded respiratory events with pulse oxygen saturation (SpO2) desaturation were categorized into four categories: hypopnea (Hyp, 3409 events), obstructive apnea (OA, 5561 events), central apnea (CA, 1110 events) and mixed apnea (MA, 1372 events). All event recordings were exported separately from the PSG software as comma-separated variable (.csv) files, which were imported into custom-built MATLAB software for analysis. Based on 13 hypoxic parameters, artificial neural network (ANN) and binary logistic regression (BLR) were separately used for construction of Hyp, OA, CA and MA models. Receiver operating characteristic (ROC) curves were employed to compare the various predictive indicators of the two models for different respiratory event types, respectively.

Both ANN and BLR models suggested that 13 hypoxic parameters significantly influenced the classification of respiratory event types; The area under the ROC curves of the ANN models surpassed those of traditional BLR models respiratory event types.

The ANN models constructed based on the 13 hypoxic parameters exhibited superior predictive capabilities for distinct types of respiratory events, providing a feasible new tool for automatic identification of respiratory event types using sleep SpO2.

Currently, most assisted reproduction units transfer a single embryo to avoid multiple pregnancies. Embryologists must select the embryo to be transferred from a cohort produced by a couple during a cycle. This selection process should be accurate, non-invasive, inexpensive, reproducible, and available to in vitro fertilization (IVF) laboratories worldwide. Embryo selection has evolved from static and morphological criteria to the use of morphokinetic embryonic characteristics using time-lapse systems and artificial intelligence, as well as the genetic study of embryos, both invasive with preimplantation genetic testing for aneuploidies (PGT-A) and non-invasive (niPGT-A). However, despite these advances in embryo selection methods, the overall success rate of IVF techniques remains between 25 and 30%. This review summarizes the different methods and evolution of embryo selection, their strengths and limitations, as well as future technologies that can improve patient outcomes in the shortest possible time. These methodologies are based on procedures that are applied at different stages of embryo development, from the oocyte to the cleavage and blastocyst stages, and can be used in laboratory routine.

Background: Accurate prediction of neurorehabilitation outcomes following Spinal Cord Injury (SCI) is crucial for optimizing healthcare resource allocation and improving rehabilitation strategies. Artificial Neural Networks (ANNs) may identify complex prognostic factors in patients with SCI. However, the influence of psychological variables on rehabilitation outcomes remains underexplored despite their potential impact on recovery success. Methods: A cohort of 303 patients with SCI was analyzed with an ANN model that employed 17 input variables, structured into two hidden layers and a single output node. Clinical and psychological data were integrated to predict functional outcomes, which were measured by the Spinal Cord Independence Measure (SCIM) at discharge. Paired Wilcoxon tests were used to evaluate pre-post differences and linear regression was used to assess correlations, with Pearson's coefficient and the Root Mean Square Error calculated. Results: Significant improvements in SCIM scores were observed (21.8 ± 15.8 at admission vs. 57.4 ± 22.5 at discharge, p < 0.001). The model assigned the highest predictive weight to SCIM at admission (10.3%), while psychological factors accounted for 36.3%, increasing to 40.9% in traumatic SCI cases. Anxiety and depression were the most influential psychological predictors. The correlation between the predicted and actual SCIM scores was R = 0.794 for the entire sample and R = 0.940 for traumatic cases. Conclusions: The ANN model demonstrated the strong impact, especially for traumatic SCI, of psychological factors on functional outcomes. Anxiety and depression emerged as dominant negative predictors. Conversely, self-esteem and emotional regulation functioned as protective factors increasing functional outcomes. These findings support the integration of psychological assessments into predictive models to enhance accuracy in SCI rehabilitation outcomes.

Infrastructural development and urbanization effects have been investigated over the past decades with novel approaches and adaptation strategies. Road network expansions are more useful for the socio-economic development from urban to rural areas where 75 % of the passenger, and goods transportation sectors are influenced by the road. Road infrastructure and urbanization are perpendicular to each other, and this research investigation indicates that the novel approaches and adaptation strategies for road infrastructure and urbanization effects. This study evaluated the trend in the road network and urbanization-related literature from 2010 to 2022 with some measurable keywords. Around 370 pieces of research literature are analysis and around 85 research evaluations for the road network and urbanization-related Land use and land cover (LULC) studies while numerous road network analysis approaches and LULC-related investigations are evaluated in this research. Three major parts road network analysis-related approaches, LULC, and urbanization-related approaches related to road network expansion and urbanization, were investigated. In this work, many research publications' approaches to LULC simulation, kernel density, shortage distance, and picture classification are discussed and assessed. The survey is more valuable for urban planners, future disaster management teams, and administrators to implement the shortage distance analysis, reduction of road accidents, and urbanization effects on the environment.

Embryonic ploidy is critical for the success of embryo transfer. Currently, preimplantation genetic testing for aneuploidy (PGT-A) is the gold standard for detecting ploidy abnormalities. However, PGT-A has several inherent limitations, including invasive biopsy, high economic burden, and ethical constraints. This paper provides the first comprehensive systematic review and meta-analysis of the performance of artificial intelligence (AI) algorithms using embryonic images for non-invasive prediction of embryonic ploidy.

Comprehensive searches of studies that developed or utilized AI algorithms to predict embryonic ploidy from embryonic imaging, published up until August 10, 2024, across PubMed, MEDLINE, Embase, IEEE, SCOPUS, Web of Science, and the Cochrane Central Register of Controlled Trials were performed. Studies with prospective or retrospective designs were included without language restrictions. The summary receiver operating characteristic curve, along with pooled sensitivity and specificity, was estimated using a bivariate random-effects model. The risk of bias and study quality were evaluated using the QUADAS-AI tool. Heterogeneity was quantified using the inconsistency index (I 2 ), derived from Cochran's Q test. Predefined subgroup analyses and bivariate meta-regression were conducted to explore potential sources of heterogeneity. This study was registered with PROSPERO (CRD42024500409).

Twenty eligible studies were identified, with twelve studies included in the meta-analysis. The pooled sensitivity, specificity, and area under the curve of AI for predicting embryonic euploidy were 0.71 (95% CI: 0.59-0.81), 0.75 (95% CI: 0.69-0.80), and 0.80 (95% CI: 0.76-0.83), respectively, based on a total of 6879 embryos (3110 euploid and 3769 aneuploid). Meta-regression and subgroup analyses identified the type of AI-driven decision support system, external validation, risk of bias, and year of publication as the primary contributors to the observed heterogeneity. There was no evidence of publication bias.

Our findings indicate that AI algorithms exhibit promising performance in predicting embryonic euploidy based on embryonic imaging. Although the current AI models developed cannot entirely replace invasive methods for determining embryo ploidy, AI demonstrates promise as an auxiliary decision-making tool for embryo selection, particularly for individuals who are unable to undergo PGT-A. To enhance the quality of future research, it is essential to overcome the specific challenges and limitations associated with AI studies in reproductive medicine.

This work was supported by the National Key R&D Program of China (2022YFC2702905), the Shengjing Freelance Researcher Plan of Shengjing Hospital and the 345 talent project of Shengjing Hospital.

Despite the widespread public concern regarding abduction, research on this type of crime is scarce. This lack of research is even more pronounced when looking at cases that end with the death of the victim. In fact, all of the research looking at lethal outcomes in cases of abductions has focused exclusively on child victims and has failed to consider the interactions at the multivariate level between the factors related to the death of the victim. Therefore, the aim of the study is to identify offender and crime characteristics - as well as their interactions - associated with a lethal outcome in sexually-motivated abductions using a combination of logistic regression and neural network analyses on a sample of 281 cases (81 cases ending with a lethal outcome, random sample of 200 comparison cases). Findings show that sexually-motivated abductions ending with a lethal outcome are more likely to be characterized by an offender who is a loner, forensically aware, and who who uses a weapon and restraints, and who sexually penetrates and beats a known victim. The neural network analysis show that three different pathways lead to a lethal outcome in sexually-motivated abductions. Such findings are important for correctional practices.

To analyze influencing factors and establish a prediction model for delayed behavior of early ambulation after surgery for varicose veins of the lower extremity (VVLE).

A prospective case-control study.

Patients with VVLE were recruited from 2 local hospitals.

In total, 498 patients with VVLE were selected using convenience sampling and divided into a training set and a test set.

Not applicable.

We collected information from the selected participants before surgery and followed up until the day after surgery, then divided them into a normal and delayed ambulation group. Propensity score matching was applied to all participants by type of surgery and anesthesia. All the characteristics in the 2 groups were compared using logistic regression, back propagation neural network (BPNN), and decision tree models. The accuracy, sensitivity, specificity, and area under the curve (AUC) values of the 3 models were compared to determine the optimal model.

A total of 406 participants were included after propensity score matching. The AUC values for the training sets of logistic regression, BPNN, and decision tree models were 0.850, 0.932, and 0.757, respectively. The AUC values for the test sets were 0.928, 0.984, and 0.776, respectively. A BPNN was the optimal model. Social Support Rating Scale score, preoperative 30-second sit-stand test score, Clinical-Etiology-Anatomy-Pathophysiology (CEAP) grade, Medical Coping Modes Questionnaire score, and whether you know the need for early ambulation, in descending order of the result of a BPNN model. A probability value greater than 0.56 indicated delayed behavior of early ambulation.

Clinicians should pay more attention to those with lower Social Support Rating Scale scores, poor lower limb strength, a higher CEAP grade, and poor medical coping ability, and make patients aware of the necessity and importance of early ambulation, thereby assisting decision-making regarding postoperative rehabilitation. Further research is needed to improve the method, add more variables, and transform the model into a scale to screen and intervene in the delayed behavior of early ambulation of VVLE in advance.

Early predictors of postoperative complications can risk-stratify patients undergoing colorectal cancer surgery. However, conventional regression models have limited power to identify complex nonlinear relationships among a large set of variables. We developed artificial neural network models to optimize the prediction of major postoperative complications and risk of readmission in patients undergoing colorectal cancer surgery.

This study aimed to develop an artificial neural network model to predict postoperative complications using postoperative laboratory values and compare the accuracy of models to standard regression methods.

This retrospective study included patients who underwent elective colorectal cancer resection between January 1, 2016, and July 31, 2021. Clinical data, cancer stage, and laboratory data from postoperative days 1 to 3 were collected. Complications and readmission risk models were created using multivariable logistic regression and single-layer neural networks.

National Cancer Institute-Designated Comprehensive Cancer Center.

Adult patients with colorectal cancer.

The accuracy of predicting postoperative major complications, readmissions, and anastomotic leaks using the area under the receiver operating characteristic curve.

Neural networks had larger areas under the curve for predicting major complications compared to regression models (neural network 0.811; regression model 0.724, p < 0.001). Neural networks also showed an advantage in predicting anastomotic leak ( p = 0.036) and readmission using postoperative day 1 to 2 values ( p = 0.014).

Single-center, retrospective design limited to cancer operations.

In this study, we generated a set of models for the early prediction of complications after colorectal surgery. The neural network models provided greater discrimination than the models based on traditional logistic regression. These models may allow for early detection of postoperative complications as early as postoperative day 2. See the Video Abstract .

ANTECEDENTES:Los predictores tempranos de complicaciones postoperatorias pueden estratificar el riesgo de los pacientes sometidos a cirugía de cáncer colorrectal. Sin embargo, los modelos de regresión convencionales tienen un poder limitado para identificar relaciones no lineales complejas entre un gran conjunto de variables. Desarrollamos modelos de redes neuronales artificiales para optimizar la predicción de complicaciones postoperatorias importantes y riesgo de reingreso en pacientes sometidos a cirugía de cáncer colorrectal.OBJETIVO:El objetivo de este estudio fue desarrollar un modelo de red neuronal artificial para predecir complicaciones postoperatorias utilizando valores de laboratorio postoperatorios y comparar la precisión de estos modelos con los métodos de regresión estándar.DISEÑO:Este estudio retrospectivo incluyó a pacientes que se sometieron a resección electiva de cáncer colorrectal entre el 1 de enero de 2016 y el 31 de julio de 2021. Se recopilaron datos clínicos, estadio del cáncer y datos de laboratorio del día 1 al 3 posoperatorio. Se crearon modelos de complicaciones y riesgo de reingreso mediante regresión logística multivariable y redes neuronales de una sola capa.AJUSTE:Instituto Nacional del Cáncer designado Centro Oncológico Integral.PACIENTES:Pacientes adultos con cáncer colorrectal.PRINCIPALES MEDIDAS DE RESULTADO:Precisión de la predicción de complicaciones mayores postoperatorias, reingreso y fuga anastomótica utilizando el área bajo la curva característica operativa del receptor.RESULTADOS:Las redes neuronales tuvieron áreas bajo la curva más grandes para predecir complicaciones importantes en comparación con los modelos de regresión (red neuronal 0,811; modelo de regresión 0,724, p < 0,001). Las redes neuronales también mostraron una ventaja en la predicción de la fuga anastomótica ( p = 0,036) y el reingreso utilizando los valores del día 1-2 postoperatorio ( p = 0,014).LIMITACIONES:Diseño retrospectivo de un solo centro limitado a operaciones de cáncer.CONCLUSIONES:En este estudio, generamos un conjunto de modelos para la predicción temprana de complicaciones después de la cirugía colorrectal. Los modelos de redes neuronales proporcionaron una mayor discriminación que los modelos basados en regresión logística tradicional. Estos modelos pueden permitir la detección temprana de complicaciones posoperatorias tan pronto como el segundo día posoperatorio. (Traducción-Dr. Mauricio Santamaria ).

In orthopaedics, wound care is crucial as surgical site infections carry disease burden due to increased length of stay, decreased quality of life and poorer patient outcomes. Artificial Intelligence (AI) has a vital role in revolutionising wound care in orthopaedics: ranging from wound assessment, early detection of complications, risk stratifying patients, and remote patient monitoring. Incorporating AI in orthopaedics has reduced dependency on manual physician assessment which is time-consuming. This article summarises current literature on how AI is used for wound assessment and management in the orthopaedic community.

Imbalanced datasets pose significant challenges in predictive modeling, leading to biased outcomes and reduced model reliability. This study addresses data imbalance in diabetes prediction using machine learning techniques. Utilizing data from the Fasa Adult Cohort Study (FACS) with a 5-year follow-up of 10,000 participants, we developed predictive models for Type 2 diabetes.

We employed various data-level and algorithm-level interventions, including SMOTE, ADASYN, SMOTEENN, Random Over Sampling and KMeansSMOTE, paired with Random Forest, Gradient Boosting, Decision Tree and Multi-Layer Perceptron (MLP) classifier. We evaluated model performance using F1 score, AUC, and G-means-metrics chosen to provide a comprehensive assessment of model accuracy, discrimination ability, and overall balance in performance, particularly in the context of imbalanced datasets.

our study uncovered key factors influencing diabetes risk and evaluated the performance of various machine learning models. Feature importance analysis revealed that the most influential predictors of diabetes differ between males and females. For females, the most important factors are triglyceride (TG), basal metabolic rate (BMR), and total cholesterol (CHOL), whereas for males, the key predictors are body Mass Index (BMI), serum glutamate Oxaloacetate Transaminase (SGOT), and Gamma-Glutamyl (GGT). Across the entire dataset, BMI remains the most important variable, followed by SGOT, BMR, and energy intake. These insights suggest that gender-specific risk profiles should be considered in diabetes prevention and management strategies. In terms of model performance, our results show that ADASYN with MLP classifier achieved an F1 score of 82.17 ± 3.38, AUC of 89.61 ± 2.09, and G-means of 89.15 ± 2.31. SMOTE with MLP followed closely with an F1 score of 79.85 ± 3.91, AUC of 89.7 ± 2.54, and G-means of 89.31 ± 2.78. The SMOTEENN with Random Forest combination achieved an F1 score of 78.27 ± 1.54, AUC of 87.18 ± 1.12, and G-means of 86.47 ± 1.28.

These combinations effectively address class imbalance, improving the accuracy and reliability of diabetes predictions. The findings highlight the importance of using appropriate data-balancing techniques in medical data analysis.

Despite rising rates of multimorbidity, existing risk assessment tools are mostly limited to a single outcome of interest. This study tests the feasibility of producing multiple disease risk estimates with at least 70% discrimination (area under the receiver operating curve, AUROC) within the time and information constraints of the existing primary care health check framework.

Observational prospective cohort study SETTING: UK Biobank.

228 240 adults from the UK population.

None.

Myocardial infarction, atrial fibrillation, heart failure, stroke, all-cause dementia, chronic kidney disease, fatty liver disease, alcoholic liver disease, liver cirrhosis and liver failure.

Using a set of predictors easily gathered at the standard primary care health check (such as the National Health Service Health Check), we demonstrate that it is feasible to simultaneously produce risk estimates for multiple disease outcomes with AUROC of 70% or greater. These predictors can be entered once into a single form and produce risk scores for stroke (AUROC 0.727, 95% CI 0.713 to 0.740), all-cause dementia (0.823, 95% CI 0.810 to 0.836), myocardial infarction (0.785, 95% CI 0.775 to 0.795), atrial fibrillation (0.777, 95% CI 0.768 to 0.785), heart failure (0.828, 95% CI 0.818 to 0.838), chronic kidney disease (0.774, 95% CI 0.765 to 0.783), fatty liver disease (0.766, 95% CI 0.753 to 0.779), alcoholic liver disease (0.864, 95% CI 0.835 to 0.894), liver cirrhosis (0.763, 95% CI 0.734 to 0.793) and liver failure (0.746, 95% CI 0.695 to 0.796).

Easily collected diagnostics can be used to assess 10-year risk across multiple disease outcomes, without the need for specialist computing or invasive biomarkers. Such an approach could increase the utility of existing data and place multiorgan risk information at the fingertips of primary care providers, thus creating opportunities for longer-term multimorbidity prevention. Additional work is needed to validate whether these findings would hold in a larger, more representative cohort outside the UK Biobank.

Global estimations suggest energy content within municipal solid waste (MSW) is underutilized, compromising efforts to reduce fossil CO2 emissions and missing the opportunities for pursuing circular economy in energy consumption. The energy content of the MSW, represented by heating values (HVs), is a major determinant for the suitability of incinerating the waste for energy and managing waste flows. Literature reveals limitations in traditional statistical HV modelling approaches, which assume a linear and additive relationship between physiochemical properties of MSW samples and their HVs, as well as overlook the impact of non-combustible substances in MSW mixtures on energy harvest. Artificial intelligence (AI)-based models show promise but pose challenges in interpretation based on established combustion theories. From the variable selection perspectives, using MSW physical composition categories as explanatory variables neglects intra-category variations in energy contents while applying environmental or socio-economic factors emerges to address waste composition changes as society develops. The article contributes by showing to professionals and modellers that leveraging AI technology and incorporating societal and environmental factors are meaningful directions for advancing HV prediction in waste management. These approaches promise more precise evaluations of incinerating waste for energy and enhancing sustainable waste management practices.

A session at the 2023 International Consultation on Incontinence - Research Society (ICI-RS) held in Bristol, UK, focused on the question: Is the time right for a new initiative in mathematical modeling of the lower urinary tract (LUT)? The LUT is a complex system, comprising various synergetic components (i.e., bladder, urethra, neural control), each with its own dynamic functioning and high interindividual variability. This has led to a variety of different types of models for different purposes, each with advantages and disadvantages.

When addressing the LUT, the modeling approach should be selected and sized according to the specific purpose, the targeted level of detail, and the available computational resources. Four areas were selected as examples to discuss: utility of nomograms in clinical use, value of fluid mechanical modeling, applications of models to simplify urodynamics, and utility of statistical models.

A brief literature review is provided along with discussion of the merits of different types of models for different applications. Remaining research questions are provided.

Inadequacies in current (outdated) models of the LUT as well as recent advances in computing power (e.g., quantum computing) and methods (e.g., artificial intelligence/machine learning), would dictate that the answer is an emphatic "Yes, the time is right for a new initiative in mathematical modeling of the LUT."

Background: Prediction of neurorehabilitation outcomes after a Spinal Cord Injury (SCI) is crucial for healthcare resource management and improving prognosis and rehabilitation strategies. Artificial neural networks (ANNs) have emerged as a promising alternative to conventional statistical approaches for identifying complex prognostic factors in SCI patients. Materials: a database of 1256 SCI patients admitted for rehabilitation was analyzed. Clinical and demographic data and SCI characteristics were used to predict functional outcomes using both ANN and linear regression models. The former was structured with input, hidden, and output layers, while the linear regression identified significant variables affecting outcomes. Both approaches aimed to evaluate and compare their accuracy for rehabilitation outcomes measured by the Spinal Cord Independence Measure (SCIM) score. Results: Both ANN and linear regression models identified key predictors of functional outcomes, such as age, injury level, and initial SCIM scores (correlation with actual outcome: R = 0.75 and 0.73, respectively). When also alimented with parameters recorded during hospitalization, the ANN highlighted the importance of these additional factors, like motor completeness and complications during hospitalization, showing an improvement in its accuracy (R = 0.87). Conclusions: ANN seemed to be not widely superior to classical statistics in general, but, taking into account complex and non-linear relationships among variables, emphasized the impact of complications during the hospitalization on recovery, particularly respiratory issues, deep vein thrombosis, and urological complications. These results suggested that the management of complications is crucial for improving functional recovery in SCI patients.

Machine learning (ML) risk prediction models, although much more accurate than traditional statistical methods, are inconvenient to use in clinical practice due to their nontransparency and requirement of a large number of input variables.

We aimed to develop a precise, explainable, and flexible ML model to predict the risk of in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI).

This study recruited 18,744 patients enrolled in the 2013 China Acute Myocardial Infarction (CAMI) registry and 12,018 patients from the China Patient-Centered Evaluative Assessment of Cardiac Events (PEACE)-Retrospective Acute Myocardial Infarction Study. The Extreme Gradient Boosting (XGBoost) model was derived from 9616 patients in the CAMI registry (2014, 89 variables) with 5-fold cross-validation and validated on both the 9125 patients in the CAMI registry (89 variables) and the independent China PEACE cohort (10 variables). The Shapley Additive Explanations (SHAP) approach was employed to interpret the complex relationships embedded in the proposed model.

In the XGBoost model for predicting all-cause in-hospital mortality, the variables with the top 8 most important scores were age, left ventricular ejection fraction, Killip class, heart rate, creatinine, blood glucose, white blood cell count, and use of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs). The area under the curve (AUC) on the CAMI validation set was 0.896 (95% CI 0.884-0.909), significantly higher than the previous models. The AUC for the Global Registry of Acute Coronary Events (GRACE) model was 0.809 (95% CI 0.790-0.828), and for the TIMI model, it was 0.782 (95% CI 0.763-0.800). Despite the China PEACE validation set only having 10 available variables, the AUC reached 0.840 (0.829-0.852), showing a substantial improvement to the GRACE (0.762, 95% CI 0.748-0.776) and TIMI (0.789, 95% CI 0.776-0.803) scores. Several novel and nonlinear relationships were discovered between patients' characteristics and in-hospital mortality, including a U-shape pattern of high-density lipoprotein cholesterol (HDL-C).

The proposed ML risk prediction model was highly accurate in predicting in-hospital mortality. Its flexible and explainable characteristics make the model convenient to use in clinical practice and could help guide patient management.

ClinicalTrials.gov NCT01874691; https://clinicaltrials.gov/study/NCT01874691.

Risk prediction models are commonly performed with logistic regression analysis but are limited by skewed datasets. We utilised neural networks (NNs) model to identify independent predictors of poor outcomes in cerebral venous thrombosis (CVT) due to the limitations of logistic regression (LR) analysis with complex datasets.

We evaluated 1309 adult CVT patients from the prospective BEAST (Biorepository to Establish the Aetiology of Sinovenous Thrombosis) study. The area under the receiver operating characteristic (AUROC) curve confirmed the goodness-of-fit of prediction models. The normalised importance (NI) of the NNs determines the significance of independent predictors.

The stepwise logistic regression model found thrombolysis (OR 32.1; 95% CI 3.6-287.0; P=0.002), craniotomy (OR 6.9; 95% CI 1.3-36.8; P=0.02), and cerebral haemorrhage (OR 4.5; 95% CI 1.3-15.4; P=0.01) as predictors of poor clinical outcome with the AUROC of 0.71. Conversely, the NNs model identified major independent predictors of long-term poor clinical outcomes as cerebral haemorrhage (NI 100%) and thrombolysis (NI 98%), as well as trivial predictors of age (NI 2.8%) and altered mental status (NI 3.5%). The accuracy of the NNs model was 95.1% and 94.1% for self-learned randomly selected training and testing samples with an AUROC of 0.82. Positive and negative predictive values for poor outcomes were 13.2% and 97.1% for the LR model, compared with the NNs model of 18.8% and 98.7%, respectively.

Cerebral haemorrhage and thrombolysis was a strong independent predictor, whereas age merely impacts the long-term poor clinical outcome in adult CVT. Integrating unorthodox neural networks risk prediction model can improve decision-making as it outperforms conventional logistic regression with complex datasets.

The unconfined compressive strength (UCS) of intact rocks is crucial for engineering applications, but traditional laboratory testing is often impractical, especially for historic buildings lacking sufficient core samples. Non-destructive tests like the Schmidt hammer rebound number and compressional wave velocity offer solutions, but correlating these with UCS requires complex mathematical models. This paper introduces a novel approach using an artificial neural network (ANN) to simultaneously correlate UCS with three non-destructive test indexes: Schmidt hammer rebound number, compressional wave velocity, and open-effective porosity. The proposed ANN model outperforms existing methods, providing accurate UCS predictions for various rock types. Contour maps generated from the model offer practical tools for geotechnical and geological engineers, facilitating decision-making in the field and enhancing educational resources. This integrated approach promises to streamline UCS estimation, improving efficiency and accuracy in engineering assessments of intact rock materials.

Coronavirus disease 2019 (COVID-19), a global public health crisis, continues to pose challenges despite preventive measures. The daily rise in COVID-19 cases is concerning, and the testing process is both time-consuming and costly. While several models have been created to predict mortality in COVID-19 patients, only a few have shown sufficient accuracy. Machine learning algorithms offer a promising approach to data-driven prediction of clinical outcomes, surpassing traditional statistical modeling. Leveraging machine learning (ML) algorithms could potentially provide a solution for predicting mortality in hospitalized COVID-19 patients in Ethiopia. Therefore, the aim of this study is to develop and validate machine-learning models for accurately predicting mortality in COVID-19 hospitalized patients in Ethiopia.

Our study involved analyzing electronic medical records of COVID-19 patients who were admitted to public hospitals in Ethiopia. Specifically, we developed seven different machine learning models to predict COVID-19 patient mortality. These models included J48 decision tree, random forest (RF), k-nearest neighborhood (k-NN), multi-layer perceptron (MLP), Naïve Bayes (NB), eXtreme gradient boosting (XGBoost), and logistic regression (LR). We then compared the performance of these models using data from a cohort of 696 patients through statistical analysis. To evaluate the effectiveness of the models, we utilized metrics derived from the confusion matrix such as sensitivity, specificity, precision, and receiver operating characteristic (ROC).

The study included a total of 696 patients, with a higher number of females (440 patients, accounting for 63.2%) compared to males. The median age of the participants was 35.0 years old, with an interquartile range of 18-79. After conducting different feature selection procedures, 23 features were examined, and identified as predictors of mortality, and it was determined that gender, Intensive care unit (ICU) admission, and alcohol drinking/addiction were the top three predictors of COVID-19 mortality. On the other hand, loss of smell, loss of taste, and hypertension were identified as the three lowest predictors of COVID-19 mortality. The experimental results revealed that the k-nearest neighbor (k-NN) algorithm outperformed than other machine learning algorithms, achieving an accuracy of 95.25%, sensitivity of 95.30%, precision of 92.7%, specificity of 93.30%, F1 score 93.98% and a receiver operating characteristic (ROC) score of 96.90%. These findings highlight the effectiveness of the k-NN algorithm in predicting COVID-19 outcomes based on the selected features.

Our study has developed an innovative model that utilizes hospital data to accurately predict the mortality risk of COVID-19 patients. The main objective of this model is to prioritize early treatment for high-risk patients and optimize strained healthcare systems during the ongoing pandemic. By integrating machine learning with comprehensive hospital databases, our model effectively classifies patients' mortality risk, enabling targeted medical interventions and improved resource management. Among the various methods tested, the K-nearest neighbors (KNN) algorithm demonstrated the highest accuracy, allowing for early identification of high-risk patients. Through KNN feature identification, we identified 23 predictors that significantly contribute to predicting COVID-19 mortality. The top five predictors are gender (female), intensive care unit (ICU) admission, alcohol drinking, smoking, and symptoms of headache and chills. This advancement holds great promise in enhancing healthcare outcomes and decision-making during the pandemic. By providing services and prioritizing patients based on the identified predictors, healthcare facilities and providers can improve the chances of survival for individuals. This model provides valuable insights that can guide healthcare professionals in allocating resources and delivering appropriate care to those at highest risk.

Fertility-sparing treatment (FST) might be considered an option for reproductive patients with low-risk endometrial cancer (EC). On the other hand, the matching rates between preoperative assessment and postoperative pathology in low-risk EC patients are not high enough. We aimed to predict the postoperative pathology depending on preoperative myometrial invasion (MI) and grade in low-risk EC patients to help extend the current criteria for FST.

This ancillary study (KGOG 2015S) of Korean Gynecologic Oncology Group 2015, a prospective, multicenter study included patients with no MI or MI <1/2 on preoperative MRI and endometrioid adenocarcinoma and grade 1 or 2 on endometrial biopsy. Among the eligible patients, Groups 1-4 were defined with no MI and grade 1, no MI and grade 2, MI <1/2 and grade 1, and MI <1/2 and grade 2, respectively. New prediction models using machine learning were developed.

Among 251 eligible patients, Groups 1-4 included 106, 41, 74, and 30 patients, respectively. The new prediction models showed superior prediction values to those from conventional analysis. In the new prediction models, the best NPV, sensitivity, and AUC of preoperative each group to predict postoperative each group were as follows: 87.2%, 71.6%, and 0.732 (Group 1); 97.6%, 78.6%, and 0.656 (Group 2); 71.3%, 78.6% and 0.588 (Group 3); 91.8%, 64.9%, and 0.676% (Group 4).

In low-risk EC patients, the prediction of postoperative pathology was ineffective, but the new prediction models provided a better prediction.

Heart failure (HF) contributes greatly to morbidity, mortality, and health care costs worldwide. Hospital readmission rates are tracked closely and determine federal reimbursement dollars. No current modality or technology allows for accurate measurement of relevant HF parameters in ambulatory, rural, or underserved settings. This limits the use of telehealth to diagnose or monitor HF in ambulatory patients.

This study describes a novel HF diagnostic technology using audio recordings from a standard mobile phone.

This prospective study of acoustic microphone recordings enrolled convenience samples of patients from 2 different clinical sites in 2 separate areas of the United States. Recordings were obtained at the aortic (second intercostal) site with the patient sitting upright. The team used recordings to create predictive algorithms using physics-based (not neural networks) models. The analysis matched mobile phone acoustic data to ejection fraction (EF) and stroke volume (SV) as evaluated by echocardiograms. Using the physics-based approach to determine features eliminates the need for neural networks and overfitting strategies entirely, potentially offering advantages in data efficiency, model stability, regulatory visibility, and physical insightfulness.

Recordings were obtained from 113 participants. No recordings were excluded due to background noise or for any other reason. Participants had diverse racial backgrounds and body surface areas. Reliable echocardiogram data were available for EF from 113 patients and for SV from 65 patients. The mean age of the EF cohort was 66.3 (SD 13.3) years, with female patients comprising 38.3% (43/113) of the group. Using an EF cutoff of ≤40% versus >40%, the model (using 4 features) had an area under the receiver operating curve (AUROC) of 0.955, sensitivity of 0.952, specificity of 0.958, and accuracy of 0.956. The mean age of the SV cohort was 65.5 (SD 12.7) years, with female patients comprising 34% (38/65) of the group. Using a clinically relevant SV cutoff of <50 mL versus >50 mL, the model (using 3 features) had an AUROC of 0.922, sensitivity of 1.000, specificity of 0.844, and accuracy of 0.923. Acoustics frequencies associated with SV were observed to be higher than those associated with EF and, therefore, were less likely to pass through the tissue without distortion.

This work describes the use of mobile phone auscultation recordings obtained with unaltered cellular microphones. The analysis reproduced the estimates of EF and SV with impressive accuracy. This technology will be further developed into a mobile app that could bring screening and monitoring of HF to several clinical settings, such as home or telehealth, rural, remote, and underserved areas across the globe. This would bring high-quality diagnostic methods to patients with HF using equipment they already own and in situations where no other diagnostic and monitoring options exist.

Venous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study's best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.

The attacks like distributed denial-of-service (DDoS) are termed as severe defence issues in data centres, and are considered real network threat. These types of attacks can produce huge disturbances in information technologies. In addition, it is a complex task to determine and fully alleviate DDoS attacks. The new strategy is developed to identify and alleviate DDoS attacks in the Software-Defined Internet of Things (SD-IoT) model. SD-IoT simulation is executed to gather data. The data collected through nodes of SD-IoT are fed to the selection of feature phases. Here, the hybrid process is considered to select features, wherein features, like wrapper-based technique, cosine similarity-based technique, and entropy-based technique are utilized to choose the significant features. Thereafter, the attack discovery process is done with Elephant Water Cycle (EWC)-assisted deep neuro-fuzzy network (DNFN). The EWC is adapted to train DNFN, and here EWC is obtained by grouping Elephant Herd Optimization (EHO) and water cycle algorithm (WCA). Finally, attack mitigation is carried out to secure the SD-IoT. The EWC-assisted DNFN revealed the highest accuracy of 96.9%, TNR of 98%, TPR of 90%, precision of 93%, and F1-score of 91%, when compared with other related techniques.

Falls among older individuals contribute significantly to the rise in ambulance transport use. To recognize the importance of future countermeasures, we estimated the projected number and percentage of fall-related emergency medical service (EMS) calls.

We examined the sex, age group, and location of falls among patients aged ≥ 65 years who contacted emergency services in Sapporo City from 2013 to 2021. Annual fall-related calls per population subgroup were calculated, and trends were analyzed. Four models were used to estimate the future number of fall-related calls from the 2025-2060 projected population: (1) based on the 2022 data, estimates from the 2013-2022 data using (2) Poisson progression, (3) neural network, (4) estimates from the 2013-2019 data using neural network. The number of all EMS calls was also determined using the same method to obtain the ratio of all EMS calls.

During 2013-2022, 70,262 fall-related calls were made for those aged ≥ 65 years. The rate was higher indoors among females and outdoor among males in most age groups and generally increased with age. After adjusting for age, the rate increased by year. Future estimates of the number of fall calls are approximately double the number in 2022 in 2040 and three times in 2060, with falls accounting for approximately 11% and 13% of all EMS calls in 2040 and 2060, respectively.

The number of fall-related EMS calls among older people is expected to increase in the future, and the percentage of EMS calls will also increase; therefore, countermeasures are urgently needed.

Delayed cerebral ischemia (DCI) is a common and severe complication after subarachnoid hemorrhage (SAH). Logistic regression (LR) is the primary method to predict DCI, but it has low accuracy. This study assessed whether other machine learning (ML) models can predict DCI after SAH more accurately than conventional LR. PubMed, Embase, and Web of Science were systematically searched for studies directly comparing LR and other ML algorithms to forecast DCI in patients with SAH. Our main outcome was the accuracy measurement, represented by sensitivity, specificity, and area under the receiver operating characteristic. In the six studies included, comprising 1828 patients, about 28% (519) developed DCI. For LR models, the pooled sensitivity was 0.71 (95% confidence interval [CI] 0.57-0.84; p < 0.01) and the pooled specificity was 0.63 (95% CI 0.42-0.85; p < 0.01). For ML models, the pooled sensitivity was 0.74 (95% CI 0.61-0.86; p < 0.01) and the pooled specificity was 0.78 (95% CI 0.71-0.86; p = 0.02). Our results suggest that ML algorithms performed better than conventional LR at predicting DCI.Trial Registration: PROSPERO (International Prospective Register of Systematic Reviews) CRD42023441586; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=441586.

To identify and describe existing models for predicting knee pain in patients with knee osteoarthritis.

The electronic databases PubMed, EMBASE, CINAHL, Web of Science, and Cochrane Library were searched from their inception to May 2023 for any studies to develop and validate a prediction model for predicting knee pain in patients with knee osteoarthritis. Two reviewers independently screened titles, abstracts, and full-text qualifications, and extracted data. Risk of bias was assessed using the PROBAST. Data extraction of eligible articles was extracted by a data extraction form based on CHARMS. The quality of evidence was graded according to GRADE. The results were summarized with descriptive statistics.

The search identified 2693 records. Sixteen articles reporting on 26 prediction models were included targeting occurrence (n = 9), others (n = 7), progression (n = 5), persistent (n = 2), incident (n = 1), frequent (n = 1), and flares (n = 1) of knee pain. Most of the studies (94%) were at high risk of bias. Model discrimination was assessed by the AUROC ranging from 0.62 to 0.81. The most common predictors were age, BMI, gender, baseline pain, and joint space width. Only frequent knee pain had a moderate quality of evidence; all other types of knee pain had a low quality of evidence.

There are many prediction models for knee pain in patients with knee osteoarthritis that do show promise. However, the clinical extensibility, applicability, and interpretability of predictive tools should be considered during model development.

The use of mechanoregulatory schemes based on finite element (FE) analysis for the evaluation of bone ingrowth around porous surfaces is a viable approach but requires significant computational time and effort. The aim of this study is to develop a combined macro-micro FE and artificial neural network (ANN) framework for rapid and accurate prediction of the site-specific bone ingrowth around the porous beaded-coated tibial implant for total ankle replacement (TAR). A macroscale FE model of the implanted tibia was developed based on CT data. Subsequently, a microscale FE model of the implant-bone interface was created for performing bone ingrowth simulations using mechanoregulatory algorithms. An ANN was trained for rapid and accurate prediction of bone ingrowth. The results predicted by ANN are well comparable to FE-predicted results. Predicted site-specific bone ingrowth using ANN around the implant ranges from 43.04 to 98.24%, with a mean bone ingrowth of around 74.24%. Results suggested that the central region exhibited the highest bone ingrowth, which is also well corroborated with the recent explanted study on BOX®. The proposed methodology has the potential to simulate bone ingrowth rapidly and effectively at any given site over any implant surface.

Objective: The co-occurrence of anxiety disorders, depressive disorders, and substance use problems was examined. Methods: The Mental Health Client-Level Data dataset was used to conduct logistic regression models and an artificial neural network analysis. Logistic regression analyses were conducted among adults with anxiety (n = 547,473) or depressive disorders (n = 1,610,601) as their primary diagnosis who received treatment in a community mental health center. The artificial neural network analysis was conducted with the entire sample (N = 2,158,074). Results: Approximately 30% of the sample had co-occurring high-risk substance use or substance use disorder. Characteristics including region of treatment receipt, age, education, gender, race and ethnicity, and the presence of co-occurring anxiety and depressive disorders were associated with the co-occurring high-risk substance use or a substance use disorder. Conclusions: Findings from this study highlight the importance of mental health facilities to screen for and provide integrated treatment for co-occurring disorders.

Bacterial infections and resistance to antibiotic drugs represent the highest challenges to public health. The search for new and promising compounds with anti-bacterial activity is a very urgent matter. To promote the development of platforms enabling the discovery of compounds with anti-bacterial activity, Fourier-Transform Mid-Infrared (FT-MIR) spectroscopy coupled with machine learning algorithms was used to predict the impact of compounds extracted from Cynara cardunculus against Escherichia coli. According to the plant tissues (seeds, dry and fresh leaves, and flowers) and the solvents used (ethanol, methanol, acetone, ethyl acetate, and water), compounds with different compositions concerning the phenol content and antioxidant and antimicrobial activities were obtained. A principal component analysis of the spectra allowed us to discriminate compounds that inhibited E. coli growth according to the conventional assay. The supervised classification models enabled the prediction of the compounds' impact on E. coli growth, showing the following values for accuracy: 94% for partial least squares-discriminant analysis; 89% for support vector machine; 72% for k-nearest neighbors; and 100% for a backpropagation network. According to the results, the integration of FT-MIR spectroscopy with machine learning presents a high potential to promote the discovery of new compounds with antibacterial activity, thereby streamlining the drug exploratory process.

Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two artificial neural network (ANN)-based ML models using a training sample of 165 out of 290 (56.9%) patients, and then tested their predictive performance against Model of End-stage Liver Disease-Sodium (MELD-Na) and MELD 3.0 scores using a different validation sample of 125 out of 290 (43.1%) patients. The area under the ROC curve (AUC) for predicting 28-day mortality for the ML model was 0.811 (95%CI: 0.714- 0.907; p < 0.001), while the AUC for the MELD-Na score was 0.577 (95%CI: 0.435-0.720; p = 0.226) and for MELD 3.0 was 0.600 (95%CI: 0.462-0.739; p = 0.117). The area under the ROC curve (AUC) for predicting 90-day mortality for the ML model was 0.839 (95%CI: 0.776- 0.884; p < 0.001), while the AUC for the MELD-Na score was 0.682 (95%CI: 0.575-0.790; p = 0.002) and for MELD 3.0 was 0.703 (95%CI: 0.590-0.816; p < 0.001). Our study demonstrates that ML-based models for predicting short-term mortality in patients with acute decompensation of liver cirrhosis perform significantly better than MELD-Na and MELD 3.0 scores in a validation cohort.

The aim of the study was to estimate future groundwater potential zones based on machine learning algorithms and climate change scenarios. Fourteen parameters (i.e., curvature, drainage density, slope, roughness, rainfall, temperature, relative humidity, lineament density, land use and land cover, general soil types, geology, geomorphology, topographic position index (TPI), topographic wetness index (TWI)) were used in developing machine learning algorithms. Three machine learning algorithms (i.e., artificial neural network (ANN), logistic model tree (LMT), and logistic regression (LR)) were applied to identify groundwater potential zones. The best-fit model was selected based on the ROC curve. Representative concentration pathways (RCP) of 2.5, 4.5, 6.0, and 8.5 climate scenarios of precipitation were used for modeling future climate change. Finally, future groundwater potential zones were identified for 2025, 2030, 2035, and 2040 based on the best machine learning model and future RCP models. According to findings, ANN shows better accuracy than the other two models (AUC: 0.875). The ANN model predicted that 23.10 percent of the land was in very high groundwater potential zones, whereas 33.50 percent was in extremely high groundwater potential zones. The study forecasts precipitation values under different climate change scenarios (RCP2.6, RCP4.5, RCP6, and RCP8.5) for 2025, 2030, 2035, and 2040 using an ANN model and shows spatial distribution maps for each scenario. Finally, sixteen scenarios were generated for future groundwater potential zones. Government officials may utilize the study's results to inform evidence-based choices on water management and planning at the national level.