Adequate bowel preparation is crucial for effective colonoscopy, especially in elderly patients who face a high risk of inadequate preparation. This study develops and validates a machine learning model to predict bowel preparation adequacy in elderly patients before colonoscopy.

The study adhered to the TRIPOD AI guidelines. Clinical data from 471 elderly patients collected between February and December 2023 were utilized for developing and internally validating the model, while 221 patients' data from March to June 2024 were used for external validation. The Boruta algorithm was applied for feature selection. Models including logistic regression, light gradient boosting machines, support vector machines (SVM), decision trees, random forests, and extreme gradient boosting were evaluated using metrics such as AUC, accuracy, sensitivity, and specificity. The SHAP algorithm helped rank feature importance. A web-based application was developed using the Streamlit framework to enhance clinical usability.

The Boruta algorithm identified 7 key features. The SVM model excelled with an AUC of 0.895 (95% CI: 0.822-0.969), and high accuracy, sensitivity, and specificity. In external validation, the SVM model maintained robust performance with an AUC of 0.889. The SHAP algorithm further explained the contribution of each feature to model predictions.

The study developed an interpretable and practical machine learning model for predicting bowel preparation adequacy in elderly patients, facilitating early interventions to improve outcomes and reduce resource wastage.

The S100 family of calcium-binding proteins (S100s) had been tightly related to the biological processes of various cardiovascular diseases. This study aims to investigate the expression of S100s in Atherosclerosis (AS) and explore their potential as diagnostic biomarkers and therapeutic targets.

We analyzed multiple sequencing datasets from the GEO database to compare the expression profiles of S100s in AS tissues versus normal samples. Employing unsupervised clustering techniques, AS subtypes were discerned based on the intricate variations in S100-related gene expression profiles. Subsequent analyses delved into immune cell infiltration and GSVA pathway enrichment, shedding light on the nuanced immune landscape characterizing diverse AS subtypes. Machine learning techniques were employed to develop a diagnostic model for AS. Single-cell RNA analysis was utilized to investigate the cellular distribution of S100 hub genes in AS.

Unsupervised clustering analysis identified two distinct AS subtypes (C1 and C2), characterized by specific S100 gene expression patterns. The RF-based diagnostic model exhibited the highest efficacy (AUC=0.881), and the top five genes (S100A4, S100A10, S100A11, S100A13, S100Z) were used to construct a diagnostic nomogram.

This study systematically elucidates the roles of S100s in AS, offering insights into molecular subtyping, immune characteristics, and diagnostic model construction. The findings provide valuable implications for the precise treatment and prognosis assessment of AS and pave the way for further research into related mechanisms.

This study investigates brake wear particle (BWP) emissions from light-duty electric vehicles (EVs) and heavy-duty vehicles (HDVs) using a self-developed whole-vehicle testing system and a modified brake dynamometer. The results show that regenerative braking significantly reduces emissions: weak and strong regenerative braking modes reduce brake wear PM2.5 by 75 % and 87 %, and brake wear PM10 by 90 % and 95 %, respectively. HDVs with drum brakes produce lower emissions and higher PM2.5/PM10 ratios than those with disc brakes. A machine learning model (XGBoost) was developed to analyze the relationship between BWP emissions and factors (11 for light-duty EVs and 8 for HDVs, based on kinematic, vehicle, and braking parameters). SHapley Additive exPlanations (SHAP) were used for model interpretation. For light-duty EVs, reducing high kinetic energy losses (Ike > 6500 J) and initial speeds (V > 45 km/h) braking events significantly lowers emissions. Additionally, the emission reduction effect of regenerative braking intensity (BI) stabilizes when BI exceeds 900 J. For HDVs, controlling braking temperature (Avg.T < 200°C) and initial speed (V < 50 km/h) effectively reduces emissions. Our findings provide new insights into the emission characteristics and control strategies for BWPs. SYNOPSIS: The construction and interpretation of a machine learning based model of brake wear emissions provides new insights into the refined assessment and control of non-exhaust emissions.

Multiple sclerosis (MS) is an autoimmune inflammatory disorder that causes neurological disability. Dysregulated lipid metabolism contributes to the pathogenesis of MS. This study aimed to identify lipid metabolism-related gene markers and construct a diagnostic model for MS.

Gene expression profiles for MS were obtained from the Gene Expression Omnibus database. Differentially expressed lipid metabolism-related genes (LMRGs) were identified and performed functional enrichment analysis. Least absolute shrinkage and selection operator (LASSO), random forest (RF), and protein-protein interaction (PPI) analysis were employed to screen hub genes. The predictive power of hub genes was evaluated using receiver operating characteristic (ROC) curves. We developed an artificial neural network (ANN) model and validated its performance in three test sets. Immune cell infiltration analysis, Gene set enrichment analysis, and ceRNA network construction were performed to explore the role of lipid metabolism in the pathogenesis of MS. Drugs prediction and molecular docking were utilized to identify potential therapeutic drugs.

We identified 40 differentially expressed LMRGs, with significant enrichment in Arachidonic acid metabolism, Steroid hormone biosynthesis, Fatty acid elongation, and Sphingolipid metabolism. AKR1C3, NFKB1, and ABCA1 were identified as gene markers for MS, and their expression was upregulated in the MS group. The areas under the ROC curve (AUCs) for AKR1C3, NFKB1, and ABCA1 in the training set were 0.779, 0.703, and 0.726, respectively. The ANN model exhibited good discriminative ability in both the training and test sets, achieving an AUC of 0.826 on the training set and AUC values of 0.822, 0.890, and 0.833 on the test sets. Gamma.delta.T.cell, Natural.killer.T.cell, Plasmacytoid.dendritic.cell, Regulatory.T.cell, and Type.1.T.helper.cell were highly expressed in the MS group. A ceRNA network showed a complex regulatory interplay involving hub genes. Luteolin, isoflavone, and thalidomide had good binding affinities to the hub genes.

Our study emphasized the crucial role of lipid metabolism in MS, identifing AKR1C3, NFKB1, and ABCA1 as gene markers. The ANN model exhibited good performance on both the training and testing sets. These findings offer valuable insights into the molecular mechanisms underlying MS, and establish a scientific foundation for future research.

Our study aimed toconstruct a web-based calculator to predict high risk patients of interstitial lung disease (ILD) in systemic lupus erythematosus (SLE).

This retrospective study comprised training and test cohorts, including 581 and 86 patients, respectively. Univariate, least absolute shrinkage and selection operator (LASSO), random forest (RF), eXtreme Gradient Boosting (XGBoost), and logistic regression (LR) analyses were performed. A Venn diagram was used to investigate critical features. Receiver operating characteristic (ROC) analysis and decision curve analysis were used to evaluate the model's performance. Risk stratification was performed using the best ROC cut-off value. The web-based calculator was established using Streamlit software.

Characteristics such as Raynaud's phenomenon, pulmonary artery systolic pressure, serositis, anti-U1RNP antibodies, anti-Ro52 antibodies, C-reactive protein, age, and disease course were associated with SLE complicated by ILD (SLE-ILD). LR-Venn, RF-Venn, XGBoost-Venn, LASSO-logic, RF, and XGBoost models were constructed. In training cohort, the XGBoost model demonstrated the highest area under the ROC curve (AUC, 0.890; cut-off value, 0.197; sensitivity, 0.793; specificity, 0.836) and provideda netbenefitin decision curve analysis (odds ratio [OR] for SLE-ILD [high- vs. low-risk], 19.6). The model was validated in the test cohort (AUC, 0.866; sensitivity, 0.722; specificity, 0.897; OR, 22.7). Furthermore, an XGBoost model-based web calculator was developed.

Our web calculator (https://st-xgboost-app-kcv9qm.streamlit.app/) greatly improved risk prediction for SLE-ILD and was implemented effectively.

Patients with lung metastasis of colorectal cancer typically have a poor prognosis. Therefore, establishing an effective screening and diagnosis model is paramount. Our study seeks to construct and verify a predictive model utilizing machine learning (ML) that can evaluate the risk of lung metastasis with newly diagnosed colorectal cancer (CRC) using Shapley Additive exPlanations (SHAP). Using the Surveillance, Epidemiology, and End Results database, 39,674 were extracted for model development, all of whom had been pathologically diagnosed with CRC. The data spans from 2010 to 2015. Our study has constructed seven ML algorithms based on the data mentioned above, including Random Forest (RF), Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, eXtreme Gradient Boosting, and Gradient Boosting Machine. We selected the best algorithm and visualized it using SHAP. We conducted a validation of the model utilizing data from a Chinese hospital to assess its practicality. Based on this, we have constructed an open web calculator. 39,674 patient data were included in our study, among whom 1369 (3.5%) presented with distant lung metastasis. The Random Forest (RF) algorithm demonstrated the highest predictive capability within the internal test set (AUC of 0.980, AUPR of 0.941). Furthermore, the random forest algorithm also exhibited excellent performance in external validation sets. Meanwhile, we have also established a web calculator ( http://121.43.117.60:8003/ ). The RF algorithm has demonstrated excellent predictive performance. It can assist clinicians in devising more personalized treatment plans.

Major depressive disorder (MDD) is a multifactorial disorder involving genetic and environmental factors, with unclear pathogenesis. This study aims to explore the pathogenic pathway of MDD and its relationship with immune responses and to discover its potential targets by bioinformatics methods. We first applied gene set variation analysis (GSVA) and seven different immune infiltration algorithms to the GSE98793 dataset to determine the differences in signaling pathways, metabolic pathways, and immune cell infiltration between MDD patients and healthy controls. Differentially expressed genes between MDD patients and controls were obtained from five datasets (GSE98793, GSE32280, GSE38206, GSE39653, and GSE52790), and 113 machine learning methods were employed to construct MDD diagnostic models. Based on the constructed MDD diagnostic models, MDD patients were divided into high-risk and low-risk groups. GSVA and immune microenvironment analyses were conducted to investigate the differences between the two groups. Furthermore, potential drugs and therapeutic targets for the high-risk MDD group were explored to provide new insights and directions for the precise treatment of MDD. GSVA and immune infiltration results indicate that patients with MDD exhibit differences from normal individuals in various aspects, including biological processes, signaling pathways, metabolic processes, and immune cells. To investigate the functions and biological significance of differentially expressed genes in MDD patients, we performed GO and KEGG enrichment analyses on the differentially expressed genes from five databases (GSE98793, GSE32280, GSE38206, GSE39653, and GSE52790). By comparing the enrichment results across the five datasets, we found that the cell-killing signaling pathway was consistently present in the enriched signaling pathways of all datasets, suggesting that this pathway may play a crucial role in the pathogenesis of MDD. The random forest algorithm (AUC = 0.788) was selected as the optimal algorithm from 113 machine learning algorithms, leading to the development of a robust and predictive MDD algorithm, highlighting the important role of NPL in MDD. By dividing MDD into high and low-risk subgroups based on diagnostic model scores, enrichment pathways, and immunological results further demonstrated that high-risk MDD is associated with increased levels of reactive oxygen species, inflammation, and numbers of T cells and B cells. Through GSEA scoring, five upregulated pathways in the high-risk MDD group were identified, and multiple potential drugs such as Mibefradil, LY364947, ZLN005, STA- 5326, and vemurafenib were screened. Patients with MDD show differences in signaling pathways, metabolic pathways, and immune mechanisms. By constructing an MDD diagnostic model, we predicted the key genes of MDD and the characteristic pathways associated with a higher risk of MDD. This provides new insights for risk stratification identification and offers new perspectives for the clinical application of precision immunotherapy and drug development.

Diabetic peripheral neuropathy (DPN) is a common and serious complication of diabetes, which can lead to foot deformity, ulceration, and even amputation. Early identification is crucial, as more than half of DPN patients are asymptomatic in the early stage. This study aimed to develop and validate multiple risk prediction models for DPN in patients with type 2 diabetes mellitus (T2DM) and to apply the Shapley Additive Explanation (SHAP) method to interpret the best-performing model and identify key risk factors for DPN.

A single-centre retrospective cohort study.

The study was conducted at a tertiary teaching hospital in Hainan.

Data were retrospectively collected from the electronic medical records of patients with diabetes admitted between 1 January 2021 and 28 March 2023. After data preprocessing, 73 variables were retained for baseline analysis. Feature selection was performed using univariate analysis combined with recursive feature elimination (RFE). The dataset was split into training and test sets in an 8:2 ratio, with the training set balanced via the Synthetic Minority Over-sampling Technique. Six machine learning algorithms were applied to develop prediction models for DPN. Hyperparameters were optimised using grid search with 10-fold cross-validation. Model performance was assessed using various metrics on the test set, and the SHAP method was used to interpret the best-performing model.

The study included 3343 T2DM inpatients, with a median age of 60 years (IQR 53-69), and 88.6% (2962/3343) had DPN. The RFE method identified 12 key factors for model construction. Among the six models, XGBoost showed the best predictive performance, achieving an area under the curve of 0.960, accuracy of 0.927, precision of 0.969, recall of 0.948, F1-score of 0.958 and a G-mean of 0.850 on the test set. The SHAP analysis highlighted C reactive protein, total bile acids, gamma-glutamyl transpeptidase, age and lipoprotein(a) as the top five predictors of DPN.

The machine learning approach successfully established a DPN risk prediction model with excellent performance. The use of the interpretable SHAP method could enhance the model's clinical applicability.

Hepatocellular carcinoma (HCC) has limited therapeutic options and a poor prognosis. The endoplasmic reticulum (ER) plays a crucial role in tumor progression and response to stress, making it a promising target for HCC stratification. This study aimed to develop a risk stratification model using ER stress-related signatures.

We utilized transcriptome data from The Cancer Genome Atlas and Gene Expression Omnibus, which encompass whole-genome expression profiles and clinical annotations. Machine learning algorithms, including the least absolute shrinkage and selection operator, random forest, and support vector machine recursive feature elimination, were applied to the key genes associated with HCC prognosis. A prognostic system was developed using univariate Cox hazard analysis and least absolute shrinkage and selection operator Cox regression, followed by validation using Kaplan-Meier analysis and receiver operating characteristic curves. Tumor immune dysfunction and exclusion tools were used to predict immunotherapy responsiveness.

Two distinct clusters associated with ER stress were identified in HCC, each exhibiting unique clinical and biological features. Using a computational approach, a prognostic risk model, namely the ER stress-related signature, was formulated, demonstrating enhanced predictive accuracy compared with that of existing prognostic models. An effective clinical nomogram was established by integrating the risk model with clinicopathological factors. Patients with lower risk scores exhibited improved responsiveness to various chemotherapeutic, targeted, and immunotherapeutic agents.

The critical role of ER stress in HCC is highlighted. The ER stress-related signature developed in this study is a powerful tool to assess the risk and clinical treatment of HCC.

Bladder compliance assessment is crucial for diagnosing bladder functional disorders, with urodynamic study (UDS) being the principal evaluation method. However, the application of UDS is intricate and time-consuming in children. So it'S necessary to develop an efficient bladder compliance screen approach before UDS. In this study, We constructed a dataset based on UDS and designed a 1D-CNN model to optimize and train the network. Then applied the trained model to a dataset obtained solely through a proposed perfusion experiment. Our model outperformed other algorithms. The results demonstrate the potential of our model to alert abnormal bladder compliance accurately and efficiently.

Enteral nutrition is an important clinical nutritional supplementation method, especially for adult patients who are unable to eat normally or require additional nutritional support. However, many patients experience intolerance to enteral nutrition, such as delayed gastric emptying, bloating, and diarrhea, which not only affect the patient's nutritional status but also increase the risk of medical complications. In recent years, medical researchers have been dedicated to identifying and analyzing various factors that contribute to enteral nutrition intolerance, including the patient's disease status, nutritional formula, feeding method, and rate. In addition, research is also exploring the establishment of risk prediction models to more accurately predict which patients may develop enteral nutrition intolerance. These models typically combine clinical parameters, biomarkers, and patient individual characteristics, aiming to assist clinicians in better planning and adjusting nutritional treatment plans, thereby reducing the occurrence of intolerance events. This review summarizes the research progress on enteral nutrition intolerance in adult patients, with a focus on the latest developments in intolerance factors and risk prediction models, providing valuable guidance for clinical practice and helping improve patients' nutritional status and overall health.

Abdominal aortic aneurysm (AAA) and peripheral arterial disease (PAD) are two cardiovascular diseases associated with considerable morbidity, mortality and quality of life impairment. As they are multifactorial diseases, several factors contribute to their pathogenesis, including oxidative stress and lipid peroxidation, and these may have key roles in the development of these pathologies. Alterations of the lipid metabolism and lipid profile have been reported in cardiovascular diseases but to a lesser extent in AAA and PAD. Modifications in the profile of some molecular lipid species, in particular, native phospholipid and triglyceride species were mainly reported for AAA, while alterations in the fatty acid profile were noticed in the case of PAD. Oxidized phospholipids were also reported for AAA. Although AAA and PAD have a common atherosclerotic root, lipidomics demonstrates the existence of distinct lipid. Lipidomic research regarding AAA and PAD is still scarce and should be set in motion to increase the knowledge on the lipid changes that occur in these diseases, contributing not only to the discovery of new biomarkers for diagnosis and prognosis assessment but also to tailor precision medicine in the clinical field.

This study aims to develop and validate a machine learning model for identifying individuals within the nursing population experiencing severe subjective cognitive decline (SCD) during the menopause transition, along with their associated factors.

A secondary analysis was performed using cross-sectional data from 1,264 nurses undergoing the menopause transition. The data set was randomly split into training (75%) and validation sets (25%), with the Bortua algorithm employed for feature selection. Seven machine learning models were constructed and optimized. Model performance was assessed using area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, and F1 score. Shapley Additive Explanations analysis was used to elucidate the weights and characteristics of various factors associated with severe SCD.

The average SCD score among nurses in the menopause transition was (5.38 ± 2.43). The Bortua algorithm identified 13 significant feature factors. Among the seven models, the support vector machine exhibited the best overall performance, achieving an area under the receiver operating characteristic curve of 0.846, accuracy of 0.789, sensitivity of 0.753, specificity of 0.802, and an F1 score of 0.658. The two variables most strongly associated with SCD were menopausal symptoms and the stage of menopause.

The machine learning models effectively identify individuals with severe SCD and the related factors associated with severe SCD in nurses during the menopause transition. These findings offer valuable insights for the management of cognitive health in women undergoing the menopause transition.

Artificial Intelligence (AI) is transforming pancreaticobiliary endoscopy by enhancing diagnostic accuracy, procedural efficiency, and clinical outcomes. This narrative review explores AI's applications in endoscopic ultrasound (EUS) and endoscopic retrograde cholangiopancreatography (ERCP), emphasizing its potential to address diagnostic and therapeutic challenges in pancreaticobiliary diseases. In EUS, AI improves pancreatic mass differentiation, malignancy prediction, and landmark recognition, demonstrating high diagnostic accuracy and outperforming traditional guidelines. In ERCP, AI facilitates precise biliary stricture identification, optimizes procedural techniques, and supports decision-making through real-time data integration, improving ampulla recognition and predicting cannulation difficulty. Additionally, predictive analytics help mitigate complications like post-ERCP pancreatitis. The future of AI in pancreaticobiliary endoscopy lies in multimodal data fusion, integrating imaging, genomic, and molecular data to enable personalized medicine. However, challenges such as data quality, external validation, clinician training, and ethical concerns-like data privacy and algorithmic bias-must be addressed to ensure safe implementation. By overcoming these challenges, AI has the potential to redefine pancreaticobiliary healthcare, improving diagnostic accuracy, therapeutic outcomes, and personalized care.

Emerging evidence underscores the potential application of artificial intelligence (AI) in discovering noninvasive blood biomarkers. However, the diagnostic value of AI-derived blood biomarkers for ovarian cancer (OC) remains inconsistent.

We aimed to evaluate the research quality and the validity of AI-based blood biomarkers in OC diagnosis.

A systematic search was performed in the MEDLINE, Embase, IEEE Xplore, PubMed, Web of Science, and the Cochrane Library databases. Studies examining the diagnostic accuracy of AI in discovering OC blood biomarkers were identified. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-AI tool. Pooled sensitivity, specificity, and area under the curve (AUC) were estimated using a bivariate model for the diagnostic meta-analysis.

A total of 40 studies were ultimately included. Most (n=31, 78%) included studies were evaluated as low risk of bias. Overall, the pooled sensitivity, specificity, and AUC were 85% (95% CI 83%-87%), 91% (95% CI 90%-92%), and 0.95 (95% CI 0.92-0.96), respectively. For contingency tables with the highest accuracy, the pooled sensitivity, specificity, and AUC were 95% (95% CI 90%-97%), 97% (95% CI 95%-98%), and 0.99 (95% CI 0.98-1.00), respectively. Stratification by AI algorithms revealed higher sensitivity and specificity in studies using machine learning (sensitivity=85% and specificity=92%) compared to those using deep learning (sensitivity=77% and specificity=85%). In addition, studies using serum reported substantially higher sensitivity (94%) and specificity (96%) than those using plasma (sensitivity=83% and specificity=91%). Stratification by external validation demonstrated significantly higher specificity in studies with external validation (specificity=94%) compared to those without external validation (specificity=89%), while the reverse was observed for sensitivity (74% vs 90%). No publication bias was detected in this meta-analysis.

AI algorithms demonstrate satisfactory performance in the diagnosis of OC using blood biomarkers and are anticipated to become an effective diagnostic modality in the future, potentially avoiding unnecessary surgeries. Future research is warranted to incorporate external validation into AI diagnostic models, as well as to prioritize the adoption of deep learning methodologies.

PROSPERO CRD42023481232; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023481232.

To evaluate the predictive utility of machine learning and nomogram in predicting in-hospital mortality in patients with acute myocardial infarction complicated by cardiogenic shock (AMI-CS), and to visualize the model results in order to analyze the impact of these predictors on the patients' prognosis.

A retrospective analysis was conducted on 332 adult patients who were diagnosed with AMI-CS and admitted to the ICU for the first time within the eICU Collaborative Research Database (eICU-CRD). AdaBoost, XGBoost, LightGBM, Random Forest and logistic regression nomogram were developed utilizing the random forest recursive elimination (RF-RFE) and least absolute shrinkage and selection operator (LASSO) algorithms for feature selection.

Compared to the machine learning models, the nomogram demonstrated superior predictive accuracy for mortality in patients with AMI-CS, with an AUC value of 0.869 (95% CI: 0.803, 0.883) and an F1 score of 0.897 for the internal test set of nomogram, and an AUC of 0.770 (95% CI: 0.702, 0.801) and an F1 score of 0.832 for the external validation set.

Nomogram enhance the interpretability and transparency of the models, leading to more reliable prognostic predictions for AMI-CS patients. This facilitates clinicians in making precise decisions, thereby enhancing patient prognosis.

Weaning from mechanical ventilation (MV) is a key phase in the management of intensive care unit (ICU) patient. According to the WEAN SAFE study, weaning from MV initiation is defined as the first attempt to separate a patient from the ventilator and the success is the absence of reintubation (or death) within 7 days of extubation. Mortality rates increase with the difficulty of weaning, reaching 38% for the most challenging cases. Predicting the success of weaning is difficult, due to the complexity of factors involved. The many biosignals that are measured in patients during ventilation may be considered "weak signals", a concept rarely used in medicine. The aim of this research is to investigate the performance of machine learning (ML) models based on biosignals to predict spontaneous breathing trial success (SBT) using biosignals and to identify the most important variables.

This retrospective study used data from two centers (Nice University Hospital, Archet and Pasteur) collected from 232 intensive care patients who underwent MV (149 successfully and 83 unsuccessfully) between January, 2020 and April, 2023. The study focuses on the development of ML algorithms to predict the success of the spontaneous breathing trial based on a combination of discrete variables and biosignals (time series) recorded during the 24 h prior to the SBT.

For the models tested, the best results were obtained with Support Vector Classifier model: AUC-PR 0.963 (0.936-0.970, p = 0.001), AUROC 0.922 (0.871-0.940, p < 0.001).

We found that ML models are effective in predicting the success of SBT based on biosignals. Predicting weaning from mechanical ventilation thus appears to be a promising area for the application of AI, through the development of multidimensional models to analyze weak signals.

Fungal spores are usually dispersed by wind, water, and animal vectors. Climate change is accelerating the spread of pathogens to new regions. While well-studied vectors like bark beetles and moths contribute to pathogen transmission, other, less-recognized animal species play a crucial role at different scales. Small-scale dispersers, such as mites, rodents, squirrels, and woodpeckers, facilitate fungal spread within trees or entire forest regions. On a larger scale, birds contribute significantly to long-distance fungal dispersal, potentially aiding the establishment of invasive species across continents. These vectors remain underexplored and are often overlooked in fungal disease studies and are therefore called cryptic vectors. Understanding the full range of dispersal mechanisms is critical as climate change drive shifts in species distributions and increases vector activity. Expanding monitoring and detection tools to include these hidden carriers will improve our ability to track the distribution of fungal pathogens. Integrating targeted research, innovative technologies, and collaborative efforts across disciplines and borders is essential for enhancing disease management and mitigating fungal disease's ecological and economic impacts. KEY POINTS: • Cryptic animal vectors play a critical role in fungal spore dispersal across forests and continents. • Climate change accelerates fungal pathogen spread by altering species distributions, increasing vector activity, and facilitating long-distance dispersal. • Innovative monitoring tools, like eDNA sampling and predictive modelling, are essential to uncover cryptic vector contributions and mitigate fungal disease impacts.

Obstructive sleep apnea (OSA) is a prevalent sleep disorder with a high rate of undiagnosed patients, primarily due to the complexity of its diagnosis made by polysomnography (PSG). Considering the severe comorbidities associated with OSA, especially in the cardiovascular system, the development of early screening tools for this disease is imperative. Heart rate variability (HRV) is a simple and non-invasive approach used as a probe to evaluate cardiac autonomic modulation, with a variety of newly developed indices lacking studies with OSA patients.

We aimed to evaluate numerous HRV indices, derived from linear but mainly nonlinear indices, combined or not with oxygen saturation indices, for detecting the presence and severity of OSA using machine learning models.

ECG waveforms were collected from 291 PSG recordings to calculate 34 HRV indices. Minimum oxygen saturation value during sleep (SatMin), the percentage of total sleep time the patient spent with oxygen saturation below 90% (T90), and patient anthropometric data were also considered as inputs to the models. The Apnea-Hypopnea Index (AHI) was used to categorize into severity classes of OSA (normal, mild, moderate, severe) to train multiclass or binary (normal-to-mild and moderate-to-severe) classification models, using the Random Forest (RF) algorithm. Since the OSA severity groups were unbalanced, we used the Synthetic Minority Over-sampling Technique (SMOTE) to oversample the minority classes.

Multiclass models achieved a mean area under the ROC curve (AUROC) of 0.92 and 0.86 in classifying normal individuals and severe OSA patients, respectively, when using all attributes. When the groups were dichotomized into normal-to-mild OSA vs. moderate-to-severe OSA, an AUROC of 0.83 was obtained. As revealed by RF, the importance of features indicates that all feature modalities (HRV, SpO2, and anthropometric variables) contribute to the top 10 ranks.

The present study demonstrates the feasibility of using classification models to detect the presence and severity of OSA using these indices. Our findings have the potential to contribute to the development of rapid screening tools aimed at assisting individuals affected by this condition, to expedite diagnosis and initiate timely treatment.

Glycolysis is recognized as a central metabolic pathway in the neoplastic evolution of gastric cancer, exerting profound effects on the tumor microenvironment and the neoplastic growth trajectory. However, the identification of key glycolytic genes that significantly affect gastric cancer prognosis remains underexplored. In this work, five machine-learning algorithms were used to elucidate the intimate association between the glycolysis-associated gene phosphofructokinase fructose-bisphosphate 3 (PFKFB3) and the prognosis of gastric cancer patients. Validation across multiple independent datasets confirmed the prognostic significance of PFKFB3. Further, we delved into the functional implications of PFKFB3 in modulating immune responses and biological processes within gastric cancer patients, as well as its broader relevance across multiple cancer types. Results underscore the potential of PFKFB3 as a prognostic biomarker and therapeutic target in gastric cancer. Our project can be found at https://github.com/PiPiNam/ML-GCP .

Programmed death ligand 1 (PD-L1) expression status, closely related to immunotherapy outcomes, is a reliable biomarker for screening patients who may benefit from immunotherapy. Here, we developed and validated an interpretable machine learning (ML) model based on contrast-enhanced computed tomography (CECT) radiomics for preoperatively predicting PD-L1 expression status in patients with gastric cancer (GC).

We retrospectively recruited 285 GC patients who underwent CECT and PD-L1 detection from two medical centers. A PD-L1 combined positive score (CPS) of ≥ 5 was considered to indicate a high PD-L1 expression status. Patients from center 1 were divided into training (n = 143) and validation sets (n = 62), and patients from center 2 were considered a test set (n = 80). Radiomics features were extracted from venous-phase CT images. After feature reduction and selection, 11 ML algorithms were employed to develop predictive models, and their performance in predicting PD-L1 expression status was evaluated using areas under receiver operating characteristic curves (AUCs). SHapley Additive exPlanations (SHAP) were used to interpret the optimal model and visualize the decision-making process for a single individual.

Nine features significantly associated with PD-L1 expression status were ultimately selected to construct the predictive model. The light gradient-boosting machine (LGBM) model demonstrated the best performance for PD-L1 high expression status prediction in the training, validation, and test sets, with AUCs of 0.841(95% CI: 0.773, 0.908), 0.834 (95% CI:0.729, 0.939), and 0.822 (95% CI: 0.718, 0.926), respectively. The SHAP summary and bar plots illustrated that a feature's value affected the feature's impact attributed to the model. The SHAP waterfall plots were used to visualize the decision-making process for a single individual.

Our CT radiomics-based LGBM model may aid in preoperatively predicting PD-L1 expression status in GC patients, and the SHAP method may improve the interpretability of this model.

To develop a machine learning (ML) model utilizing transfer learning (TL) techniques to predict hypertension in children and adolescents across South America.

Data from two cohorts (children and adolescents) in seven South American cities were analyzed. A TL strategy was implemented by transferring knowledge from a CatBoost model trained on the children's sample and adapting it to the adolescent sample. Model performance was evaluated using standard metrics.

Among children, the prevalence of normal blood pressure was 88.9% (301 participants), while 14.1% (50 participants) had elevated blood pressure (EBP). In the adolescent group, the prevalence of normal blood pressure was 92.5% (284 participants), with 7.5% (23 participants) presenting with EBP. Random Forest, XGBoost, and LightGBM achieved high accuracy (0.90) for children, with XGBoost and LightGBM demonstrating superior recall (0.50) and AUC-ROC (0.74). For adolescents, models without TL showed poor performance, with accuracy and recall values remaining low and AUC-ROC ranging from 0.46 to 0.56. After applying TL, model performance improved significantly, with CatBoost achieving an AUC-ROC of 0.82, accuracy of 1.0, and recall of 0.18.

Soft drinks, filled cookies, and chips were key dietary predictors of elevated blood pressure, with higher intake in adolescents. Machine learning with transfer learning effectively identified these risks, emphasizing the need for early dietary interventions to prevent hypertension and support cardiovascular health in pediatric populations.

This study aims to construct a prediction model for the demand for medical and daily care services of the elderly and to explore the factors that affect the demand for medical and daily care services of the elderly. In this study, a questionnaire survey on the demand for medical and daily care services of 1291 elderly was conducted using multi-stage stratified whole cluster random sampling. SPSS21.0 statistical analysis software was used to describe the basic data of the elderly statistically, and univariate analysis was used to screen variables for model construction and binary logistic regression analysis. The acquired dataset has class imbalance, and to handle this issue, Synthetic Minority Over Sampling Technique with TomekLink (SMOTE-TomekLink) was adopted to resample the dataset for class-balancing. To improve computational efficiency, we used three algorithms to develop prediction models, including Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Light Gradient Boosting Machine (LightGBM) algorithms. The performance of each model was measured, and the performance of the prediction model was obtained using the following performance metrics: accuracy (ACC), recall (R), precision (P), F1-score, and area under the receiver operating characteristic (AUC). The prediction models for the medical and daily care services demand of the elderly were developed and validated using 12 and 13 key features, respectively. The LightGBM algorithm emerged as the superior prediction model for estimating the service needs of the elderly. For the medical service demand prediction model, LightGBM achieved an AUC of 0.910 and F1-score of 0.841. In the daily care services demand prediction model, LightGBM demonstrated an AUC of 0.906 and an F1-score of 0.819. In the LightGBM model, the analysis of feature importance indicates that the number of chronic diseases, education level, and financial sources emerge as the most significant predictors for the demand of healthcare services, encompassing both medical and daily care services. Based on questionnaire information combined with feature selection, unbalanced data processing and machine learning methods, this study constructed a machine learning model for predicting the demand for medical and daily care services for the elderly, and analyzed the influencing factors of the demand for medical and daily care services for the elderly, providing a reference for the construction and verification of future prediction models for the demand for medical and daily care services for the elderly.

The importance of drug toxicity assessment lies in ensuring the safety and efficacy of the pharmaceutical compounds. Predicting toxicity is crucial in drug development and risk assessment. This study compares the performance of GPT-4 and GPT-4o with traditional deep-learning and machine-learning models, WeaveGNN, MorganFP-MLP, SVC, and KNN, in predicting molecular toxicity, focusing on bone, neuro, and reproductive toxicity. The results indicate that GPT-4 is comparable to deep-learning and machine-learning models in certain areas. We utilized GPT-4 combined with molecular docking techniques to study the cardiotoxicity of three specific targets, examining traditional Chinese medicinal materials listed as both food and medicine. This approach aimed to explore the potential cardiotoxicity and mechanisms of action. The study found that components in Black Sesame, Ginger, Perilla, Sichuan Pagoda Tree Fruit, Galangal, Turmeric, Licorice, Chinese Yam, Amla, and Nutmeg exhibit toxic effects on cardiac target Cav1.2. The docking results indicated significant binding affinities, supporting the hypothesis of potential cardiotoxic effects.This research highlights the potential of ChatGPT in predicting molecular properties and its significance in medicinal chemistry, demonstrating its facilitation of a new research paradigm: with a data set, high-accuracy learning models can be generated without requiring computational knowledge or coding skills, making it accessible and easy to use.

Neonatal infections pose a significant threat to the health of newborns. Associated morbidity and mortality risks underscore the urgency of prompt diagnosis and treatment with appropriate empiric antibiotics. Delay in treatment can be fatal; thus, early detection improves outcomes. However, diagnosing early is a challenge as signs and symptoms of neonatal infection are non-specific and overlap with non-infectious conditions. Machine learning (ML) offers promise in early detection, utilizing various data sources and methodologies. However, ML models require rigorous validation and consideration of various challenges, including false alarms and user acceptance requiring careful integration and ongoing evaluation for successful implementation.

Chronic hepatitis B (CHB) infection represents a significant global public health issue, often leading to hepatitis B virus (HBV)-related liver cirrhosis (HBV-LC) with poor prognoses. Early identification of HBV-LC risk is essential for timely intervention. This study develops and compares nine machine learning (ML) models to predict HBV-LC risk in CHB patients using routine clinical and laboratory data. A retrospective analysis was conducted involving 777 CHB patients, with 50.45% (392/777) progressing to HBV-LC. Admission data consisted of 52 clinical and laboratory variables, with missing values addressed using multiple imputation. Feature selection utilized Least Absolute Shrinkage and Selection Operator (LASSO) regression and the Boruta algorithm, identifying 24 key variables. The evaluated ML models included XGBoost, logistic regression (LR), LightGBM, random forest (RF), AdaBoost, Gaussian naive Bayes (GNB), multilayer perceptron (MLP), support vector machine (SVM), and k-nearest neighbors (KNN). The data set was partitioned into an 80% training set (n = 621) and a 20% independent testing set (n = 156). Cross-validation (CV) facilitated hyperparameter tuning and internal validation of the optimal model. Performance metrics included the area under the receiver operating characteristic curve (AUC), Brier score, accuracy, sensitivity, specificity, and F1 score. The RF model demonstrated superior performance, with AUCs of 0.992 (training) and 0.907 (validation), while the reconstructed model achieved AUCs of 0.944 (training) and 0.945 (validation), maintaining an AUC of 0.863 in the testing set. Calibration curves confirmed a strong alignment between observed and predicted probabilities. Decision curve analysis indicated that the RF model provided the highest net benefit across threshold probabilities. The SHAP algorithm identified RPR, PLT, HBV DNA, ALT, and TBA as critical predictors. This interpretable ML model enhances early HBV-LC prediction and supports clinical decision-making in resource-limited settings.

Acute lung injury (ALI)/acute respiratory distress syndrome (ARDS) is an inflammatory response arising from lung and systemic injury with diverse causes and associated with high rates of morbidity and mortality. To date, no fully effective pharmacological therapies have been established and the relevant underlying mechanisms warrant elucidation, which may be facilitated by multi‑omics technology. The present review summarizes the application of multi‑omics technology in identifying novel diagnostic markers and therapeutic strategies of ALI/ARDS as well as its pathogenesis.

Diabetic kidney disease (DKD) is the primary reason of chronic kidney disease. Our objective was to discover potential autophagy-related biomarkers of tubulointerstitial injury in DKD and assess their clinical value.

We retrieved four datasets (GSE104954, GSE30122, GSE30529, and GSE99340) of renal tubule samples from Gene Expression Omnibus (GEO) and used two algorithms (LASSO and SVM-RFE) to screen for autophagy-related differentially expressed genes (ARDEGs) in DKD. Tripartite motif containing 22 (TRIM22) was identified for subsequent validation. Validation of TRIM22 and autophagic indicators expression in clinical samples and HK-2 cells stimulated by high glucose using immunohistochemistry, immunofluorescence, and western blot.

We identified four ARDEGs (TRIM22, PLK2, HTR2B, and FAS) using a diagnostic gene model. ROC curves further confirmed that TRIM22 had the best diagnostic efficacy for DKD. Both clinical samples and HK-2 cells stimulated by high glucose showed high protein expression of TRIM22. The correlation analysis revealed that TRIM22 correlates with SQSTM1, NGAL, and some clinical and pathological indicators in patients with DKD.

We identified TRIM22 as a potential diagnostic biomarker for DKD, revealing its high diagnostic value in patients with DKD with moderate-to-severe interstitial fibrosis and tubular atrophy (IFTA). TRIM22 is involved in tubulointerstitial injury and autophagy dysregulation in DKD.

This study aimed to develop a predictive model using a random forest algorithm to determine the likelihood of postoperative adhesive small bowel obstruction (ASBO) in infants under 3 months with intestinal malrotation.

A machine learning model was used to predict postoperative adhesive small bowel obstruction using comprehensive clinical data extracted from 107 patients with a follow-up of at least 24 months. The Boruta algorithm was used for selecting clinical features, and nested cross-validation tuned and selected hyper-parameters for the random forest model. The model's performance was validated with 1000 bootstrap samples and assessed using receiver operating characteristic (ROC) analysis, the area under the ROC curve (AUC), sensitivity, specificity, precision, and F1 score.

The random forest model demonstrated high diagnostic accuracy with an AUC of 0.960. Significant predictors of ASBO included pre-operative white blood cell count (pre-WBC), mechanical ventilation (MV) duration, surgery duration, and post-operative albumin levels (post-ALB). Partial dependence plots showed non-linear relationships and threshold effects for these variables. The model achieved high sensitivity (0.805) and specificity (0.952), along with excellent precision (0.809) and a robust F1 score (0.799), indicating balanced recall and precision performance.

This study presents a machine learning model to accurately predict postoperative ASBO in infants with intestinal malrotation. Demonstrating high accuracy and robustness, this model shows great promise for enhancing clinical decision-making and patient outcomes in pediatric surgery.

The atherogenic index of plasma (AIP) is considered an important marker of atherosclerosis and cardiovascular risk. However, its potential role in predicting length of stay (LOS), especially in patients with atherosclerotic cardiovascular disease (ASCVD), remains to be explored. We investigated the effect of AIP on hospital LOS in critically ill ASCVD patients and explored the risk factors affecting LOS in conjunction with machine learning.

Using data from the Medical Information Mart for Intensive Care (MIMIC)-IV. AIP was calculated as the logarithmic ratio of TG to HDL-C, and patients were stratified into four groups based on AIP values. We investigated the association between AIP and two key clinical outcomes: ICU LOS and total hospital LOS. Multivariate logistic regression models were used to evaluate these associations, while restricted cubic spline (RCS) regressions assessed potential nonlinear relationships. Additionally, machine learning (ML) techniques, including logistic regression (LR), decision tree (DT), random forest (RF), extreme gradient boosting (XGB), and light gradient boosting machine (LGB), were applied, with the Shapley additive explanation (SHAP) method used to determine feature importance.

The study enrolled a total of 2423 patients with critically ill ASCVD, predominantly male (54.91%), and revealed that higher AIP values were independently associated with longer ICU and hospital stays. Specifically, for each unit increase in AIP, the odds of prolonged ICU and hospital stays were significantly higher, with adjusted odds ratios (OR) of 1.42 (95% CI, 1.11-1.81; P = 0.006) and 1.73 (95% CI, 1.34-2.24; P < 0.001), respectively. The RCS regression demonstrated a linear relationship between increasing AIP and both ICU LOS and hospital LOS. ML models, specifically LGB (ROC:0.740) and LR (ROC:0.832) demonstrated superior predictive accuracy for these endpoints, identifying AIP as a vital component of hospitalization duration.

AIP is a significant predictor of ICU and hospital LOS in patients with critically ill ASCVD. AIP could serve as an early prognostic tool for guiding clinical decision-making and managing patient outcomes.

Differentiating idiopathic Parkinson's disease (IPD) from multiple system atrophy-parkinsonian type (MSA-P) is essential for optimizing patient care and prognosis, given the differences in disease progression and treatment response.

This study aimed to develop and evaluate a radiomics-based model using magnetic resonance imaging (MRI)-derived features to distinguish IPD from MSA-P.

A multicenter retrospective study.

A multicenter retrospective study was conducted with 287 patients (186 IPD and 101 MSA-P) who underwent brain MRI. Radiomic features were extracted from T1-weighted imaging and T2-weighted imaging sequences, and various machine learning classifiers were applied, including logistic regression, support vector machine (SVM), ExtraTrees, extreme gradient boosting, and Light Gradient Boosting Machine. Model performance was assessed using area under the curve (AUC), accuracy, sensitivity, and specificity. A nomogram combining clinical and radiomic features was also evaluated.

The SVM model, selected as the base for the Rad-signature, achieved the best diagnostic performance, with AUCs of 0.885 and 0.900 in the training and testing cohorts, respectively. The Rad-signature significantly outperformed clinical-only models in distinguishing IPD from MSA-P. The nomogram incorporating radiomic and clinical features yielded the highest diagnostic accuracy (AUC = 0.973 and 0.963 for training and testing cohorts, respectively) and balanced sensitivity and specificity. Decision curve analysis confirmed the nomogram's clinical utility.

Radiomics-based MRI analysis offers a powerful tool for distinguishing IPD from MSA-P, enhancing diagnostic accuracy, and aiding personalized treatment planning. Integrating radiomic and clinical data may improve diagnostic workflows in clinical practice.

Staphylococcus aureus bacteremia (SAB) remains a significant contributor to both community-acquired and healthcare-associated bloodstream infections. SAB exhibits a high recurrence rate and mortality rate, leading to numerous clinical treatment challenges. Particularly, since the outbreak of COVID-19, there has been a gradual increase in SAB patients, with a growing proportion of (Methicillin-resistant Staphylococcus aureus) MRSA infections. Therefore, we have constructed and validated a pediction model for recurrent SAB using machine learning. This model aids physicians in promptly assessing the condition and intervening proactively.

The patients data is sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database version 2.2. The patients were divided into training and testing datasets using a 7:3 random sampling ratio. The process of feature selection employed two methods: Recursive Feature Elimination (RFE) and Least Absolute Shrinkage and Selection Operator (LASSO). Prediction models were built using Extreme Gradient Boosting (XGBoost), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Model validation included Receiver Operating Characteristic (ROC) analysis, Decision Curve Analysis (DCA), and Precision-Recall Curve (PRC). We utilized SHAP (SHapley Additive exPlanations) values to demonstrate the significance of each feature and explain the XGBoost model.

After screening, MRSA, PTT, RBC, RDW, Neutrophils_abs, Sodium, Calcium, Vancomycin concentration, MCHC, MCV, and Prognostic Nutritional Index(PNI) were selected as features for constructing the model. Through combined evaluation using ROC、 DCA and PRC, XGBoost demonstrated the best predictive performance, achieving an AUC value of 0.76 (95% CI: 0.66-0.85) in ROC and 0.56 (95% CI: 0.37-0.75) in PRC. Building a website based on the Xgboost model. SHAP illustrated the feature importance ranking in the XGBoost model and provided examples to explain the XGBoost model.

The adoption of XGBoost for model development holds widespread acceptance in the medical domain. The prediction model for recurrent SAB, developed by our team, aids physicians in timely diagnosis and treatment of patients.

Preeclampsia (PE) is a severe pregnancy complication with limited early diagnostic and therapeutic options. Ferroptosis, an iron-dependent cell death pathway, has emerged as a potential mechanism in PE pathogenesis. This study investigated ferroptosis-related genes (FRGs) in PE to identify diagnostic biomarkers and therapeutic targets.

Differentially expressed genes were identified from GEO databases and intersected with FRGs. Hub genes were selected using RandomForest and LASSO algorithms. Their diagnostic potential was evaluated through ROC analysis. Regulatory networks were constructed using transcription factors, microRNAs and potential drug targets. Hub gene expression was validated through immunohistochemistry, Western blot, and RT-qPCR in placental tissues and hypoxic trophoblasts.

We identified 25 ferroptosis-related differentially expressed genes enriched in ferroptosis and HIF-1 pathways. Four hub genes (NDRG1, P4HA1, LDHA, and IDO1) showed high diagnostic efficiency (AUC=0.9182). Immune cell analysis revealed altered levels of plasma cells, CD8+ T cells, Tregs, monocytes, and M2 macrophages in PE, correlating significantly with hub gene expression. We identified 84 mRNA-miRNA and 119 mRNA-TF interactions. Among 19 potential drugs, Tetrahydro-NAD showed promising targeting potential. Experimental validation confirmed elevated expression of NDRG1, P4HA1, and LDHA, and decreased IDO1 in PE tissues and hypoxic conditions.

This study identified four FRGs as potential PE biomarkers and therapeutic targets, providing new insights into PE pathogenesis through integrated bioinformatics and experimental validation. These findings may facilitate early PE diagnosis and treatment development.

Nucleus pulposus (NP) deterioration plays a significant role in the development of intervertebral disc degeneration (IVDD) and low back pain (LBP). This paper aims to identify potential genes within degenerated NP tissue and elucidate the pathogenesis of IVDD through bioinformatics analysis.

We conducted a transcriptomic analysis of patient's degenerative NP tissue employing advanced bioinformatics techniques and machine learning algorithms. Utilizing hdWGCNA, we successfully acquired WGCNA single-cell sequencing data and pinpointed crucial genes implicated in IVDD. Subsequently, we employed the Monocle3 package to perform pseudotime sequence analysis, enabling the identification of genes associated with the differentiation and developmental processes of NP tissue. Following this, normalized and logarithmically transformed the bulk sequencing data. Subsequently, we conducted preliminary screening using single-factor logistic regression on the genes derived from single-cell sequencing. Next, we applied two machine learning techniques, namely, SVM-RFE and random forest, to discern pivotal pathogenic genes. Finally, we used validation sets to verify trends and qualitativeness and performed in vitro and in vivo validation analyses of normal and degenerative NP tissues.

909 genes associated with IVDD were identified through hdWGCNA, while pseudotime sequence analysis uncovered 1964 genes related to differentiation and developmental processes. The two had 208 genes in common. Subsequently, we conducted an initial screening of single-cell genes by integrating the bulk database with single logistic regression. Next, we utilized machine learning techniques to identify the IVDD genes CDH, DPH5, and SELENOF. PCR analysis confirmed that the expression of CDH and DPH5 in degraded nucleus pulposus cells (NPCs) was decreased by 31% and 28% in vivo, and 36% and 29% in vitro, respectively, while SELENOF showed the opposite trend. Furthermore, IVDD was validated through imaging and histological staining.

As pathogenic genes in IVDD, our findings indicate that CTH, DPH5, and SELENOF are important players and might be promising therapeutic targets for IVDD treatment.

Early treatment and prevention are the keys to reducing the mortality of VTE in patients with thoracic trauma. This study aimed to develop and validate an automatic prediction model based on machine learning for VTE risk screening in patients with thoracic trauma.

In this national multicenter retrospective study, the clinical data of chest trauma patients hospitalized in 33 hospitals in China from October 2020 to September 2021 were collected for model training and testing. The data of patients with thoracic trauma at Shanghai Sixth People's Hospital from October 2021 to September 2022 were included for further verification. The performance of the model was measured mainly by the area under the receiver operating characteristic curve (AUROC) and the mean accuracy (mAP), and the sensitivity, specificity, positive predictive value, and negative predictive value were also measured.

A total of 3116 patients were included in the training and validation of the model. External validation was performed in 408 patients. The random forest (RF) model was selected as the final model, with an AUROC of 0·879 (95% CI 0·856-0·902) in the test dataset. In the external validation, the AUROC was 0.83 (95% CI 0.794-0.866), the specificity was 0.756 (95% CI 0.713-0.799), the sensitivity was 0.821 (95% CI 0.692-0.923), the negative predictive value was 0.976 (95% CI 0.958-0.993), and the positive likelihood ratio was 3.364.

This model can be used to quickly screen for the risk of VTE in patients with thoracic trauma. More than 90% of unnecessary VTE tests can be avoided, which can help clinicians target interventions to high-risk groups and ensure resource optimization. Although further validation and improvement are needed, this study has considerable clinical value.

Artificial intelligence (AI) algorithms for the detection of retinoblastoma (RB) by fundus image analysis have been proposed as a potentially effective technique to facilitate diagnosis and screening programs. However, doubts remain about the accuracy of the technique, the best type of AI for this situation, and its feasibility for everyday use. Therefore, we performed a systematic review and meta-analysis to evaluate this issue.

Following PRISMA 2020 guidelines, a comprehensive search of MEDLINE, Embase, ClinicalTrials.gov and IEEEX databases identified 494 studies whose titles and abstracts were screened for eligibility. We included diagnostic studies that evaluated the accuracy of AI in identifying retinoblastoma based on fundus imaging. Univariate and bivariate analysis was performed using the random effects model. The study protocol was registered in PROSPERO under CRD42024499221.

Six studies with 9902 fundus images were included, of which 5944 (60%) had confirmed RB. Only one dataset used a semi-supervised machine learning (ML) based method, all other studies used supervised ML, three using architectures requiring high computational power and two using more economical models. The pooled analysis of all models showed a sensitivity of 98.2% (95% CI: 0.947-0.994), a specificity of 98.5% (95% CI: 0.916-0.998) and an AUC of 0.986 (95% CI: 0.970-0.989). Subgroup analyses comparing models with high and low computational power showed no significant difference (p=0.824).

AI methods showed a high precision in the diagnosis of RB based on fundus images with no significant difference when comparing high and low computational power models, suggesting a viability of their use. Validation and cost-effectiveness studies are needed in different income countries. Subpopulations should also be analyzed, as AI may be useful as an initial screening tool in populations at high risk for RB, serving as a bridge to the pediatric ophthalmologist or ocular oncologist, who are scarce globally.

What is known Retinoblastoma is the most common intraocular cancer in childhood and diagnostic delay is the main factor leading to a poor prognosis. The application of machine learning techniques proposes reliable methods for screening and diagnosis of retinal diseases. What is new The meta-analysis of the diagnostic accuracy of artificial intelligence methods for diagnosing retinoblastoma based on fundus images showed a sensitivity of 98.2% (95% CI: 0.947-0.994) and a specificity of 98.5% (95% CI: 0.916-0.998). There was no statistically significant difference in the diagnostic accuracy of high and low computational power models. The overall performance of supervised machine learning was best than unsupervised, although few studies were available on the second type.

Intracranial solitary fibrous tumor is a rare central nervous system tumor that lacks a reliable prognostic clinical model. Uncertainty persists regarding the treatment outcomes of surgery and adjuvant radiotherapy (ART). To address this, we investigated the efficacy of ART and applied machine learning (ML) to develop accurate prognostic models.

The Surveillance, Epidemiology, and End Results database was used for this study's analysis. To identify the prognostic variables, we conducted Cox regression analysis and constructed prognostic models using 5 ML algorithms to predict 5-year survival. A validation method incorporating the area under the curve of the receiver operating characteristic curve was used to validate the accuracy and reliability of the models. We investigated the role of ART and surgery using Kaplan-Meier survival analysis, competing risk analysis, and Bias Reduction through Analysis of Competing Events method.

The study population comprised 747 patients. Among them are 316 patients with "surgery" and 431 patients with "surgery + ART." The therapeutic groups showed significant differences in overall survival. Multivariate Cox regression analysis revealed that older age and surgery alone were poor prognostic factors. The most significant prognostic factors were the local tumor excision, followed by lobectomy and age.

Although ART did not lead to a substantial decrease in cancer-specific deaths, it did improve overall survival. This underscores the broader health benefits of ART, including effective management of comorbid conditions. Caution is advised when interpreting these survival benefits because of potential confounding factors in patient health and treatment management. Our web tool and ML models aid in clinical decision-making.

Acute coronary syndrome (ACS) is a leading cause of death worldwide. Prompt and accurate diagnosis of acute myocardial infarction (AMI) or ACS is crucial for improved management and prognosis of patients. The rapid growth of machine learning (ML) research has significantly enhanced our understanding of ACS. Most studies have focused on applying ML to detect ACS, predict prognosis, manage treatment, identify risk factors, and discover potential biomarkers, particularly using data from electrocardiograms (ECGs), electronic medical records (EMRs), imaging, and omics as the main data modality. Additionally, integrating ML with smart devices such as wearables, smartphones, and sensor technology enables real-time dynamic assessments, enhancing clinical care for patients with ACS. This review provided an overview of the workflow and key concepts of ML as they relate to ACS. It then provides an overview of current ML algorithms used for ACS diagnosis, prognosis, identification of potential risk biomarkers, and management. Furthermore, we discuss the current challenges faced by ML algorithms in this field and how they might be addressed in the future, especially in the context of medicine.