Deep learning-based radiomics techniques have the potential to aid specialists and physicians in performing decision-making in COVID-19 scenarios. Specifically, a Deep Learning (DL) ensemble model is employed to classify medical images when addressing the diagnosis during the classification tasks for COVID-19 using chest X-ray images. It also provides feasible and reliable visual explicability concerning the results to support decision-making.

Our DEELE-Rad approach integrates DL and Machine Learning (ML) techniques. We use deep learning models to extract deep radiomics features and evaluate its performance regarding end-to-end classifiers. We avoid successive radiomics approach steps by employing these models with transfer learning techniques from ImageNet, such as VGG16, ResNet50V2, and DenseNet201 architectures. We extract 100 and 500 deep radiomics features from each DL model. We also placed these features into well-established ML classifiers and applied automatic parameter tuning and a cross-validation strategy. Besides, we exploit insights into the decision-making behavior by applying a visual explanation method.

Experimental evaluation on our proposed approach achieved 89.97% AUC when using 500 deep radiomics features from the DenseNet201 end-to-end classifier. Besides, our ensemble DEELE-Rad method improves the results up to 96.19% AUC for the 500 dimensions. To outperform, ML DEELE-Rad reached the best results with an Accuracy of 98.39% and 99.19% AUC for the same setup. Our visual assessment employs additional possibilities for specialists and physicians to decision-making.

The results reflect that the DEELE-Rad approach provides robustness and confidence to the images' analysis. Our approach can benefit healthcare specialists when employed at clinical routines and respective decision-making procedures. For reproducibility, our code is available at https://github.com/usmarcv/deele-rad.

This study aims to identify repeated previous shortcomings in medical imaging data collection, curation, and AI-based analysis during the early phase of respiratory pandemics. Based on the results, it seeks to highlight essential steps for improving future pandemic preparedness.

We searched PubMed/MEDLINE, Scopus, and Cochrane Reviews for articles published from January 1, 2000, to December 31, 2021, using the terms "imaging" or "radiology" or "radiography" or "CT" or "x-ray" combined with "SARS," "MERS," "H1N1," or "COVID-19." WHO and CDC Databases were searched for case definitions.

Over the last 20 years, the world faced several international health emergencies caused by respiratory diseases such as SARS, MERS, H1N1, and COVID-19. During the same period, major technological advances enabled the analysis of vast amounts of imaging data and the continual development of artificial intelligence algorithms to support radiological diagnosis and prognosis. Timely availability of data proved critical, but so far, data collection attempts were initialized only as individual responses to each outbreak, leading to long delays and hampering unified guidelines and data-driven technology to support the management of pandemic outbreaks. Our findings highlight the multifaceted role of imaging in the early stages of SARS, MERS, H1N1, and COVID-19, and outline possible actions for advancing future pandemic preparedness.

Advancing international cooperation and action on these topics is essential to create a functional, effective, and rapid counteraction system to future respiratory pandemics exploiting state of the art imaging and artificial intelligence.

Question What has been the role of radiological data for diagnosis and prognosis in early respiratory pandemics and what challenges were present? Findings International cooperation is essential to developing an effective rapid response system for future respiratory pandemics using advanced imaging and artificial intelligence. Clinical relevance Strengthening global collaboration and leveraging cutting-edge imaging and artificial intelligence are crucial for developing rapid and effective response systems. This approach is essential for improving patient outcomes and managing future respiratory pandemics more effectively.

The rapid advancements of deep learning technology have revolutionized medical imaging diagnosis. However, training these models is often challenged by label imbalance and the scarcity of certain diseases. Most models fail to recognize multiple coexisting diseases, which are common in real-world clinical scenarios. Moreover, most radiological models rely solely on image data, which contrasts with radiologists' comprehensive approach, incorporating both images and other clinical information such as clinical history and laboratory results. In this study, we introduce a Multimodal Chest X-ray Network (MCX-Net) that integrates chest X-ray images and clinical history texts for multi-label disease diagnosis. This integration is achieved by combining a pretrained text encoder, a pretrained image encoder, and a pretrained image-text cross-modal encoder, fine-tuned on the public MIMIC-CXR-JPG dataset, to diagnose 13 diverse lung diseases on chest X-rays. As a result, MCX-Net achieved the highest macro AUROC of 0.816 on the test set, significantly outperforming unimodal baselines such as ViT-base and ResNet152, which scored 0.747 and 0.749, respectively (p < 0.001). This multimodal approach represents a substantial advancement over existing image-based deep-learning diagnostic systems for chest X-rays.

Moves toward integration of Artificial Intelligence (AI), particularly deep learning and generative AI-based technologies, into the domains of healthcare and public health have recently intensified, with a growing body of literature tackling the ethico-political implications of this. This paper considers the interwoven epistemic, sociopolitical and technical ramifications of healthcare-AI entanglements, examining how AI materialities shape emergence of particular modes of healthcare organization, governance and roles, and reflecting on how to embed participatory engagement within these entanglements. We discuss the implications of socio-technical entanglements between AI and Evidence-Based Medicine (EBM) for equitable development and governance of health AI. AI applications invariably center on the domains of medical knowledge and practice that are amenable to computational workings. This, in turn, intensifies the prioritization of these medical domains and furthers the assumptions which support the development of AI, a move which decontextualizes the qualitative nuances and complexities of healthcare while simultaneously advancing infrastructure to support these medical domains. We sketch the material and ideological reconfiguration of healthcare which is being shaped by the move toward embedding health AI assemblages in real-world contexts. We then consider the implications of this, how AI might be best employed in healthcare, and how to tackle the algorithmic injustices which become reproduced within health AI assemblages.

Radiology images are one of the most commonly used in daily clinical diagnosis. Typically, clinical diagnosis using radiology images involves disease reporting and classification, where the former is a multimodal task whereby textual reports are generated to describe clinical findings in images, as are common in various domains, e.g., chest X-ray or computed tomography. Existing approaches are mainly supervised, the quality of which heavily depends on the volume and quality of available labeled data. However, for rarer or more novel diseases, enrolling patients to collect data is both time-consuming and expensive. For non-English languages, sufficient quantities of labeled data are typically not available. We propose the Multimodal Multidomain Multilingual Foundation Model. It is useful for rare diseases and non-English languages, where the labeled data are frequently much more scarce, and may even be absent. Our approach achieves encouraging performances on nine datasets, including 2 infectious and 14 non-infectious diseases.

In oncology, medical imaging is crucial for diagnosis, treatment planning and therapy execution. Treatment responses can be complex and varied and are known to involve factors of treatment, patient characteristics and tumor microenvironment. Longitudinal image analysis is able to track temporal changes, aiding in disease monitoring, treatment evaluation, and outcome prediction. This allows for the enhancement of personalized medicine. However, analyzing longitudinal 2D and 3D images presents unique challenges, including image registration, reliable segmentation, dealing with variable imaging intervals, and sparse data. This review presents an overview of techniques and methodologies in longitudinal image analysis, with a primary focus on outcome modeling in radiation oncology.

Deep learning shows promise for medical image segmentation but suffers performance declines when applied to diverse healthcare sites due to data discrepancies among the different sites. Translating deep learning models to new clinical environments is challenging, especially when the original source data used for training is unavailable due to privacy restrictions. Source-free domain adaptation (SFDA) aims to adapt models to new unlabeled target domains without requiring access to the original source data. However, existing SFDA methods face challenges such as error propagation, misalignment of visual and structural features, and inability to preserve source knowledge. This paper introduces Continual Learning Multi-Scale domain adaptation (CLMS), an end-to-end SFDA framework integrating multi-scale reconstruction, continual learning, and style alignment to bridge domain gaps across medical sites using only unlabeled target data or publicly available data. Compared to the current state-of-the-art methods, CLMS consistently and significantly achieved top performance for different tasks, including prostate MRI segmentation (improved Dice of 10.87 %), colonoscopy polyp segmentation (improved Dice of 17.73 %), and plus disease classification from retinal images (improved AUC of 11.19 %). Crucially, CLMS preserved source knowledge for all the tasks, avoiding catastrophic forgetting. CLMS demonstrates a promising solution for translating deep learning models to new clinical imaging domains towards safe, reliable deployment across diverse healthcare settings.

Artificial intelligence (AI) has made significant advances in radiology. Nonetheless, challenges in AI development, validation, and reproducibility persist, primarily due to the lack of high-quality, large-scale, standardized data across the world. Addressing these challenges requires comprehensive standardization of medical imaging data and seamless integration with structured medical data.Developed by the Observational Health Data Sciences and Informatics community, the OMOP Common Data Model enables large-scale international collaborations with structured medical data. It ensures syntactic and semantic interoperability, while supporting the privacy-protected distribution of research across borders. The recently proposed Medical Imaging Common Data Model is designed to encompass all DICOM-formatted medical imaging data and integrate imaging-derived features with clinical data, ensuring their provenance.The harmonization of medical imaging data and its seamless integration with structured clinical data at a global scale will pave the way for advanced AI research in radiology. This standardization will enable federated learning, ensuring privacy-preserving collaboration across institutions and promoting equitable AI through the inclusion of diverse patient populations. Moreover, it will facilitate the development of foundation models trained on large-scale, multimodal datasets, serving as powerful starting points for specialized AI applications. Objective and transparent algorithm validation on a standardized data infrastructure will enhance reproducibility and interoperability of AI systems, driving innovation and reliability in clinical applications.

Retinal optical coherence tomography (OCT) biomarkers have the potential to serve as early, noninvasive, and cost-effective markers for identifying individuals at risk for cognitive impairments and neurodegenerative diseases. They may also aid in monitoring disease progression and evaluating the effectiveness of interventions targeting cognitive decline. The association between retinal OCT biomarkers and cognitive performance has been demonstrated in several studies, and their importance in cognitive assessment is increasingly being recognized. Machine learning (ML) is a branch of artificial intelligence (AI) with an exponential number of applications in the medical field, particularly its deep learning (DL) subset, which is widely used for the analysis of medical images. These techniques efficiently deal with novel biomarkers when their outcome for the applications of interest is unclear, e.g., for diagnosis, prognosis prediction, disease staging, or any other relevance to clinical practice. However, using AI-based tools for medical purposes must be approached with caution, despite the many efforts to address the black-box nature of such approaches, especially due to the general underperformance in datasets other than those used for their development. Retinal OCT biomarkers are promising as potential indicators for decline in cognitive function. The underlying mechanisms are currently being explored to gain deeper insights into this relationship linking retinal health and cognitive function. Insights from neurovascular coupling and retinal microvascular changes play an important role. Further research is needed to establish the validity and utility of retinal OCT biomarkers as early indicators of cognitive decline and neurodegenerative diseases in routine clinical practice. Retinal OCT biomarkers could then provide a new avenue for early detection, monitoring and intervention in cognitive impairment with the potential to improve patient care and outcomes.

Medical datasets are vital for advancing Artificial Intelligence (AI) in healthcare. Yet biases in these datasets on which deep-learning models are trained can compromise reliability. This study investigates biases stemming from dataset-creation practices. Drawing on existing guidelines, we first developed a BEAMRAD tool to assess the documentation of public Magnetic Resonance Imaging (MRI); Color Fundus Photography (CFP), and Electrocardiogram (ECG) datasets. In doing so, we provide an overview of the biases that may emerge due to inadequate dataset documentation. Second, we examine the current state of documentation for public medical images and signal data. Our research reveals that there is substantial variance in the documentation of image and signal datasets, even though guidelines have been developed in medical imaging. This indicates that dataset documentation is subject to individual discretionary decisions. Furthermore, we find that aspects such as hardware and data acquisition details are commonly documented, while information regarding data annotation practices, annotation error quantification, or data limitations are not consistently reported. This risks having considerable implications for the abilities of data users to detect potential sources of bias through these respective aspects and develop reliable and robust models that can be adapted for clinical practice.

Facilitating large-scale, cross-institutional collaboration in biomedical machine learning (ML) projects requires a trustworthy and resilient federated learning (FL) environment to ensure that sensitive information such as protected health information is kept confidential. Specifically designed for this purpose, this work introduces APPFLx - a low-code, easy-to-use FL framework that enables easy setup, configuration, and running of FL experiments. APPFLx removes administrative boundaries of research organizations and healthcare systems while providing secure end-to-end communication, privacy-preserving functionality, and identity management. Furthermore, it is completely agnostic to the underlying computational infrastructure of participating clients, allowing an instantaneous deployment of this framework into existing computing infrastructures. Experimentally, the utility of APPFLx is demonstrated in two case studies: (1) predicting participant age from electrocardiogram (ECG) waveforms, and (2) detecting COVID-19 disease from chest radiographs. Here, ML models were securely trained across heterogeneous computing resources, including a combination of on-premise high-performance computing and cloud computing facilities. By securely unlocking data from multiple sources for training without directly sharing it, these FL models enhance generalizability and performance compared to centralized training models while ensuring data remains protected. In conclusion, APPFLx demonstrated itself as an easy-to-use framework for accelerating biomedical studies across organizations and healthcare systems on large datasets while maintaining the protection of private medical data.

In response to the increasing significance of artificial intelligence (AI) in healthcare, there has been increased attention - including a Presidential executive order to create an AI Safety Institute - to the potential threats posed by AI. While much attention has been given to the conventional risks AI poses to cybersecurity, and critical infrastructure, here we provide an overview of some unique challenges of AI for the medical community. Above and beyond obvious concerns about vetting algorithms that impact patient care, there are additional subtle yet equally important things to consider: the potential harm AI poses to its own integrity and the broader medical information ecosystem. Recognizing the role of healthcare professionals as both consumers and contributors to AI training data, this article advocates for a proactive approach in understanding and shaping the data that underpins AI systems, emphasizing the need for informed engagement to maximize the benefits of AI while mitigating the risks.

Passive acoustic monitoring (PAM) is an increasingly popular tool to study vocalising species. The amount of data generated by PAM studies calls for robust automatic classifiers. Deep learning (DL) techniques have been proven effective in identifying acoustic signals in challenging datasets, but due to their black-box nature their underlying biases are hard to quantify. This study compares human analyst annotations, a multi-hypothesis tracking (MHT) click train classifier and a DL-based acoustic classifier to classify acoustic recordings based on the presence or absence of sperm whale (Physeter macrocephalus) click trains and study the temporal and spatial distributions of the Mediterranean sperm whale subpopulation around the Balearic Islands. The MHT and DL classifiers showed agreements with human labels of 85.7% and 85.0%, respectively, on data from sites they were trained on, but both saw a drop in performance when deployed on a new site. Agreement rates between classifiers surpassed those between human experts. Modeled seasonal and diel variations in sperm whale detections for both classifiers showed compatible results, revealing an increase in occurrence and diurnal activity during the summer and autumn months. This study highlights the strengths and limitations of two automatic classification algorithms to extract biologically useful information from large acoustic datasets.

This narrative review explores the ethical, legal, and regulatory landscape of AI integration in Australian healthcare, focusing on radiography. It examines the current legislative framework, assesses the trust and reliability of AI tools, and proposes future directions for ethical AI integration in radiography. AI systems significantly enhance diagnostic radiography by improving diagnostic accuracy and efficiency in stroke detection, brain imaging, and chest reporting. However, AI raises substantial ethical concerns due to its 'black-box' nature and potential biases in training data. The Therapeutic Goods Administration's reforms in Australia, though comprehensive, fall short of fully addressing issues related to the trustworthiness and legal liabilities of AI tools. Adopting a comprehensive research strategy that includes doctrinal, comparative, and public policy analyses will facilitate an understanding of international practices, particularly from countries with similar legal systems, and help guide Australia in refining its regulatory framework. For an ethical future in radiography, a robust, multi-disciplinary approach is required to prioritize patient safety, data privacy, and equitable AI use. A framework that balances technological innovation with ethical and legal integrity is essential for advancing healthcare while preserving trust and transparency. Healthcare professionals, policymakers, and AI developers must collaborate to establish a resilient, equitable, and transparent healthcare system. Future research should focus on multi-disciplinary methodologies, combining doctrinal, comparative, and public policy research to provide comprehensive insights. This approach will guide Australia in creating a more inclusive and ethically sound legal framework for AI in healthcare, ensuring its ethical and beneficial integration into radiography.

This work aims to assess standard evaluation practices used by the research community for evaluating medical imaging classifiers, with a specific focus on the implications of class imbalance. The analysis is performed on chest X-rays as a case study and encompasses a comprehensive model performance definition, considering both discriminative capabilities and model calibration.

We conduct a concise literature review to examine prevailing scientific practices used when evaluating X-ray classifiers. Then, we perform a systematic experiment on two major chest X-ray datasets to showcase a didactic example of the behavior of several performance metrics under different class ratios and highlight how widely adopted metrics can conceal performance in the minority class.

Our literature study confirms that: (1) even when dealing with highly imbalanced datasets, the community tends to use metrics that are dominated by the majority class; and (2) it is still uncommon to include calibration studies for chest X-ray classifiers, albeit its importance in the context of healthcare. Moreover, our systematic experiments confirm that current evaluation practices may not reflect model performance in real clinical scenarios and suggest complementary metrics to better reflect the performance of the system in such scenarios.

Our analysis underscores the need for enhanced evaluation practices, particularly in the context of class-imbalanced chest X-ray classifiers. We recommend the inclusion of complementary metrics such as the area under the precision-recall curve (AUC-PR), adjusted AUC-PR, and balanced Brier score, to offer a more accurate depiction of system performance in real clinical scenarios, considering metrics that reflect both, discrimination and calibration performance.

This study underscores the critical need for refined evaluation metrics in medical imaging classifiers, emphasizing that prevalent metrics may mask poor performance in minority classes, potentially impacting clinical diagnoses and healthcare outcomes.

Common scientific practices in papers dealing with X-ray computer-assisted diagnosis (CAD) systems may be misleading. We highlight limitations in reporting of evaluation metrics for X-ray CAD systems in highly imbalanced scenarios. We propose adopting alternative metrics based on experimental evaluation on large-scale datasets.

The COVID-19 outbreak caused saturations of hospitals, highlighting the importance of early patient triage to optimize resource prioritization. Herein, our objective was to test if high definition metabolomics, combined with ML, can improve prognostication and triage performance over standard clinical parameters using COVID infection as an example. Using high resolution mass spectrometry, we obtained metabolomics profiles of patients and combined them with clinical parameters to design machine learning (ML) algorithms predicting severity (herein determined as the need for mechanical ventilation during patient care). A total of 64 PCR-positive COVID patients at the Poitiers CHU were recruited. Clinical and metabolomics investigations were conducted 8 days after the onset of symptoms. We show that standard clinical parameters could predict severity with good performance (AUC of the ROC curve: 0.85), using SpO2, first respiratory rate, Horowitz quotient and age as the most important variables. However, the performance of the prediction was substantially improved by the use of metabolomics (AUC = 0.92). Our small-scale study demonstrates that metabolomics can improve the performance of diagnosis and prognosis algorithms, and thus be a key player in the future discovery of new biological signals. This technique is easily deployable in the clinic, and combined with machine learning, it can help design the mathematical models needed to advance towards personalized medicine.

Deep learning and artificial intelligence offer promising tools for improving the accuracy and efficiency of diagnosing various lung conditions using portable chest x-rays (CXRs). This study explores this potential by leveraging a large dataset containing over 6,000 CXR images from publicly available sources. These images encompass COVID-19 cases, normal cases, and patients with viral or bacterial pneumonia. The research proposes a novel approach called "Enhancing COVID Prediction with ESN-MDFS" that utilizes a combination of an Extreme Smart Network (ESN) and a Mean Dropout Feature Selection Technique (MDFS). This study aimed to enhance multi-class lung condition detection in portable chest X-rays by combining static texture features with dynamic deep learning features extracted from a pre-trained VGG-16 model. To optimize performance, preprocessing, data imbalance, and hyperparameter tuning were meticulously addressed. The proposed ESN-MDFS model achieved a peak accuracy of 96.18% with an AUC of 1.00 in a six-fold cross-validation. Our findings demonstrate the model's superior ability to differentiate between COVID-19, bacterial pneumonia, viral pneumonia, and normal conditions, promising significant advancements in diagnostic accuracy and efficiency.

Studies linking mental health with brain function in cross-sectional population-based association studies have historically relied on small, underpowered samples. Given the small effect sizes typical of such brain-wide associations, studies require samples into the thousands to achieve the statistical power necessary for replicability. Here, we detail how small sample sizes have hampered replicability and provide sample size targets given established association strength benchmarks. Critically, while replicability will improve with larger samples, it is not guaranteed that observed effects will meaningfully apply to target populations of interest (i.e., be generalizable). We discuss important considerations related to generalizability in psychiatric neuroimaging and provide an example of generalizability failure due to "shortcut learning" in brain-based predictions of mental health phenotypes. Shortcut learning is a phenomenon whereby machine learning models learn an association between the brain and an unmeasured construct (the shortcut), rather than the intended target of mental health. Given the complex nature of brain-behavior interactions, the future of epidemiological approaches to brain-based studies of mental health will require large, diverse samples with comprehensive assessment.

Deep learning models have achieved high performance in a wide range of applications. Recently, however, there have been increasing concerns about the fragility of many of those models to adversarial approaches and out-of-distribution inputs. A way to investigate and potentially address model fragility is to develop the ability to provide interpretability to model predictions. To this end, input attribution approaches such as Grad-CAM and integrated gradients have been introduced to address model interpretability. Here, we combine adversarial and input attribution approaches in order to achieve two goals. The first is to investigate the impact of adversarial approaches on input attribution. The second is to benchmark competing input attribution approaches. In the context of the image classification task, we find that models trained with adversarial approaches yield dramatically different input attribution matrices from those obtained using standard techniques for all considered input attribution approaches. Additionally, by evaluating the signal-(typical input attribution of the foreground)-to-noise (typical input attribution of the background) ratio and correlating it to model confidence, we are able to identify the most reliable input attribution approaches and demonstrate that adversarial training does increase prediction robustness. Our approach can be easily extended to contexts other than the image classification task and enables users to increase their confidence in the reliability of deep learning models.

The ethics of artificial intelligence (AI) are increasingly recognized due to concerns such as algorithmic bias, opacity, trust issues, data security, and fairness. Specifically, machine learning algorithms, central to AI technologies, are essential in striving for ethically sound systems that mimic human intelligence. These technologies rely heavily on data, which often remain obscured within complex systems and must be prioritized for ethical collection, processing, and usage. The significance of data ethics in achieving responsible AI was first highlighted in the broader context of health care and subsequently in nursing. This viewpoint explores the principles of data ethics, drawing on relevant frameworks and strategies identified through a formal literature review. These principles apply to real-world and synthetic data in AI and machine-learning contexts. Additionally, the data-centric AI paradigm is briefly examined, emphasizing its focus on data quality and the ethical development of AI solutions that integrate human-centered domain expertise. The ethical considerations specific to nursing are addressed, including 4 recommendations for future directions in nursing practice, research, and education and 2 hypothetical nurse-focused ethical case studies. The primary objectives are to position nurses to actively participate in AI and data ethics, thereby contributing to creating high-quality and relevant data for machine learning applications.

Mistakes in machine learning practice are commonplace and can result in loss of confidence in the findings and products of machine learning. This tutorial outlines common mistakes that occur when using machine learning and what can be done to avoid them. While it should be accessible to anyone with a basic understanding of machine learning techniques, it focuses on issues that are of particular concern within academic research, such as the need to make rigorous comparisons and reach valid conclusions. It covers five stages of the machine learning process: what to do before model building, how to reliably build models, how to robustly evaluate models, how to compare models fairly, and how to report results.

Fetal brain MRI is becoming an increasingly relevant complement to neurosonography for perinatal diagnosis, allowing fundamental insights into fetal brain development throughout gestation. However, uncontrolled fetal motion and heterogeneity in acquisition protocols lead to data of variable quality, potentially biasing the outcome of subsequent studies. We present FetMRQC, an open-source machine-learning framework for automated image quality assessment and quality control that is robust to domain shifts induced by the heterogeneity of clinical data. FetMRQC extracts an ensemble of quality metrics from unprocessed anatomical MRI and combines them to predict experts' ratings using random forests. We validate our framework on a pioneeringly large and diverse dataset of more than 1600 manually rated fetal brain T2-weighted images from four clinical centers and 13 different scanners. Our study shows that FetMRQC's predictions generalize well to unseen data while being interpretable. FetMRQC is a step towards more robust fetal brain neuroimaging, which has the potential to shed new insights on the developing human brain.

This narrative review focuses on the role of clinical prediction models in supporting informed decision-making in critical care, emphasizing their 2 forms: traditional scores and artificial intelligence (AI)-based models. Acknowledging the potential for both types to embed biases, the authors underscore the importance of critical appraisal to increase our trust in models. The authors outline recommendations and critical care examples to manage risk of bias in AI models. The authors advocate for enhanced interdisciplinary training for clinicians, who are encouraged to explore various resources (books, journals, news Web sites, and social media) and events (Datathons) to deepen their understanding of risk of bias.

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area for its technological advancements and clinical application. In this review we explore the complex issue of data bias, specifically addressing those encountered during the development and implementation of AI tools in cardiology. We dissect the origins and effects of these biases, which challenge their reliability and widespread applicability in health care. Using a case study, we highlight the complexities involved in addressing these biases from a clinical viewpoint. The goal of this review is to equip researchers and clinicians with the practical knowledge needed to identify, understand, and mitigate these biases, advocating for the creation of AI solutions that are not just technologically sound, but also fair and effective for all patients.

Over the past 2 decades, exponential growth in data availability, computational power, and newly available modeling techniques has led to an expansion in interest, investment, and research in Artificial Intelligence (AI) applications. Ophthalmology is one of many fields that seek to benefit from AI given the advent of telemedicine screening programs and the use of ancillary imaging. However, before AI can be widely deployed, further work must be done to avoid the pitfalls within the AI lifecycle. This review article breaks down the AI lifecycle into seven steps-data collection; defining the model task; data preprocessing and labeling; model development; model evaluation and validation; deployment; and finally, post-deployment evaluation, monitoring, and system recalibration-and delves into the risks for harm at each step and strategies for mitigating them.

To fuel artificial intelligence (AI) potential in clinical practice in otolaryngology, researchers must understand its epistemic limitations, which are tightly linked to ethical dilemmas requiring careful consideration. AI tools are fundamentally opaque systems, though there are methods to increase explainability and transparency. Reproducibility and replicability limitations can be overcomed by sharing computing code, raw data, and data processing methodology. The risk of bias can be mitigated via algorithmic auditing, careful consideration of the training data, and advocating for a diverse AI workforce to promote algorithmic pluralism, reflecting our population's diverse values and preferences.

Machine Learning (ML) has emerged as a promising approach in healthcare, outperforming traditional statistical techniques. However, to establish ML as a reliable tool in clinical practice, adherence to best practices in data handling, and modeling design and assessment is crucial. In this work, we summarize and strictly adhere to such practices to ensure reproducible and reliable ML. Specifically, we focus on Alzheimer's Disease (AD) detection, a challenging problem in healthcare. Additionally, we investigate the impact of modeling choices, including different data augmentation techniques and model complexity, on overall performance.

We utilize Magnetic Resonance Imaging (MRI) data from the ADNI corpus to address a binary classification problem using 3D Convolutional Neural Networks (CNNs). Data processing and modeling are specifically tailored to address data scarcity and minimize computational overhead. Within this framework, we train 15 predictive models, considering three different data augmentation strategies and five distinct 3D CNN architectures with varying convolutional layers counts. The augmentation strategies involve affine transformations, such as zoom, shift, and rotation, applied either concurrently or separately.

The combined effect of data augmentation and model complexity results in up to 10% variation in prediction accuracy. Notably, when affine transformation are applied separately, the model achieves higher accuracy, regardless the chosen architecture. Across all strategies, the model accuracy exhibits a concave behavior as the number of convolutional layers increases, peaking at an intermediate value. The best model reaches excellent performance both on the internal and additional external testing set.

Our work underscores the critical importance of adhering to rigorous experimental practices in the field of ML applied to healthcare. The results clearly demonstrate how data augmentation and model depth-often overlooked factors- can dramatically impact final performance if not thoroughly investigated. This highlights both the necessity of exploring neglected modeling aspects and the need to comprehensively report all modeling choices to ensure reproducibility and facilitate meaningful comparisons across studies.

We challenge the dominant technology-centric narrative around clinical AI. To realise the true potential of the technology, clinicians must be empowered to take a whole-system perspective and assess the suitability of AI-supported tasks for their specific complex clinical setting. Key factors include the AI's capacity to augment human capabilities, evidence of clinical safety beyond general performance metrics and equitable clinical decision-making by the human-AI team. Proactively addressing these issues could pave the way for an accountable clinical buy-in and a trustworthy deployment of the technology.

Artificial Intelligence (AI) and Machine Learning (ML) models are increasingly deployed on biomedical and health data to shed insights on biological mechanism, predict disease outcomes, and support clinical decision-making. However, ensuring model validity is challenging. The 10 quick tips described here discuss useful practices on how to check AI/ML models from 2 perspectives-the user and the developer.

Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population-based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVID-negative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.

The rapidly evolving field of machine learning (ML), along with artificial intelligence in a broad sense, is revolutionising many areas of healthcare, including laboratory medicine. The amalgamation of the fields of ML and patient-based real-time quality control (PBRTQC) processes could improve the traditional PBRTQC and error detection algorithms in the laboratory. This narrative review discusses published studies on using ML for the detection of systematic errors, non-systematic errors, and combinations of different types of errors in clinical laboratories. The studies discussed used ML for detecting bias, the requirement for re-calibration, samples contaminated with intravenous fluid or EDTA, delayed sample analysis, wrong-blood-in-tube errors, interference or a combination of different types of errors, by comparing the performance of ML models with human validators or traditional PBRTQC algorithms. Advantages, limitations, the creation of standardised ML models, ethical and regulatory aspects and potential future developments have also been discussed in brief.

Artificial intelligence (AI) algorithms hold the potential to revolutionize radiology. However, a significant portion of the published literature lacks transparency and reproducibility, which hampers sustained progress toward clinical translation. Although several reporting guidelines have been proposed, identifying practical means to address these issues remains challenging. Here, we show the potential of cloud-based infrastructure for implementing and sharing transparent and reproducible AI-based radiology pipelines. We demonstrate end-to-end reproducibility from retrieving cloud-hosted data, through data pre-processing, deep learning inference, and post-processing, to the analysis and reporting of the final results. We successfully implement two distinct use cases, starting from recent literature on AI-based biomarkers for cancer imaging. Using cloud-hosted data and computing, we confirm the findings of these studies and extend the validation to previously unseen data for one of the use cases. Furthermore, we provide the community with transparent and easy-to-extend examples of pipelines impactful for the broader oncology field. Our approach demonstrates the potential of cloud resources for implementing, sharing, and using reproducible and transparent AI pipelines, which can accelerate the translation into clinical solutions.

To evaluate the use of reporting checklists and quality scoring tools for self-reporting purposes in radiomics literature.

Literature search was conducted in PubMed (date, April 23, 2023). The radiomics literature was sampled at random after a sample size calculation with a priori power analysis. A systematic assessment for self-reporting, including the use of documentation such as completed checklists or quality scoring tools, was conducted in original research papers. These eligible papers underwent independent evaluation by a panel of nine readers, with three readers assigned to each paper. Automatic annotation was used to assist in this process. Then, a detailed item-by-item confirmation analysis was carried out on papers with checklist documentation, with independent evaluation of two readers.

The sample size calculation yielded 117 papers. Most of the included papers were retrospective (94%; 110/117), single-center (68%; 80/117), based on their private data (89%; 104/117), and lacked external validation (79%; 93/117). Only seven papers (6%) had at least one self-reported document (Radiomics Quality Score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD), or Checklist for Artificial Intelligence in Medical Imaging (CLAIM)), with a statistically significant binomial test (p < 0.001). Median rate of confirmed items for all three documents was 81% (interquartile range, 6). For quality scoring tools, documented scores were higher than suggested scores, with a mean difference of - 7.2 (standard deviation, 6.8).

Radiomic publications often lack self-reported checklists or quality scoring tools. Even when such documents are provided, it is essential to be cautious, as the accuracy of the reported items or scores may be questionable.

Current state of radiomic literature reveals a notable absence of self-reporting with documentation and inaccurate reporting practices. This critical observation may serve as a catalyst for motivating the radiomics community to adopt and utilize such tools appropriately, thereby fostering rigor, transparency, and reproducibility of their research, moving the field forward.

• In radiomics literature, there has been a notable absence of self-reporting with documentation. • Even if such documents are provided, it is critical to exercise caution because the accuracy of the reported items or scores may be questionable. • Radiomics community needs to be motivated to adopt and appropriately utilize the reporting checklists and quality scoring tools.

A significant challenge in machine learning-based medical image analysis is the scarcity of medical images. Obtaining a large number of labeled medical images is difficult because annotating medical images is a time-consuming process that requires specialized knowledge. In addition, inappropriate annotation processes can increase model bias. Self-supervised learning (SSL) is a type of unsupervised learning method that extracts image representations. Thus, SSL can be an effective method to reduce the number of labeled images. In this study, we investigated the feasibility of reducing the number of labeled images in a limited set of unlabeled medical images. The unlabeled chest X-ray (CXR) images were pretrained using the SimCLR framework, and then the representations were fine-tuned as supervised learning for the target task. A total of 2000 task-specific CXR images were used to perform binary classification of coronavirus disease 2019 (COVID-19) and normal cases. The results demonstrate that the performance of pretraining on task-specific unlabeled CXR images can be maintained when the number of labeled CXR images is reduced by approximately 40%. In addition, the performance was significantly better than that obtained without pretraining. In contrast, a large number of pretrained unlabeled images are required to maintain performance regardless of task specificity among a small number of labeled CXR images. In summary, to reduce the number of labeled images using SimCLR, we must consider both the number of images and the task-specific characteristics of the target images.

Aspirations for artificial intelligence (AI) as a catalyst for scientific discovery are growing. High-profile successes deploying AI in domains such as protein folding have highlighted AI's potential to unlock new frontiers of scientific knowledge. However, the pathway from AI innovation to deployment in research is not linear. Those seeking to drive a new wave of scientific progress through the application of AI require a diffusion engine that can enhance AI adoption across disciplines. Lessons from previous waves of technology change, experiences of deploying AI in real-world contexts and an emerging research agenda from the AI for science community suggest a framework for accelerating AI adoption. This framework requires action to build supply chains of ideas between disciplines; rapidly transfer technological capabilities through open research; create AI tools that empower researchers; and embed effective data stewardship. Together, these interventions can cultivate an environment of open data science that deliver the benefits of AI across the sciences.

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Machine Learning (ML) and Artificial Intelligence (AI) have become an integral part of the drug discovery and development value chain. Many teams in the pharmaceutical industry nevertheless report the challenges associated with the timely, cost effective and meaningful delivery of ML and AI powered solutions for their scientists. We sought to better understand what these challenges were and how to overcome them by performing an industry wide assessment of the practices in AI and Machine Learning. Here we report results of the systematic business analysis of the personas in the modern pharmaceutical discovery enterprise in relation to their work with the AI and ML technologies. We identify 23 common business problems that individuals in these roles face when they encounter AI and ML technologies at work, and describe best practices (Good Machine Learning Practices) that address these issues.

Artificial intelligence (AI) is increasingly being used in the medical field, specifically for brain cancer imaging. In this review, we explore how AI-powered medical imaging can impact the diagnosis, prognosis, and treatment of brain cancer. We discuss various AI techniques, including deep learning and causality learning, and their relevance. Additionally, we examine current applications that provide practical solutions for detecting, classifying, segmenting, and registering brain tumors. Although challenges such as data quality, availability, interpretability, transparency, and ethics persist, we emphasise the enormous potential of intelligent applications in standardising procedures and enhancing personalised treatment, leading to improved patient outcomes. Innovative AI solutions have the power to revolutionise neuro-oncology by enhancing the quality of routine clinical practice.

Science is in the midst of a reproducibility crisis and the integration of artificial intelligence into scientific research has only compounded the problem; yet could the technology hold the solution to its own problems?[Formula: see text].

For healthcare datasets, it is often impossible to combine data samples from multiple sites due to ethical, privacy, or logistical concerns. Federated learning allows for the utilization of powerful machine learning algorithms without requiring the pooling of data. Healthcare data have many simultaneous challenges, such as highly siloed data, class imbalance, missing data, distribution shifts, and non-standardized variables, that require new methodologies to address. Federated learning adds significant methodological complexity to conventional centralized machine learning, requiring distributed optimization, communication between nodes, aggregation of models, and redistribution of models. In this systematic review, we consider all papers on Scopus published between January 2015 and February 2023 that describe new federated learning methodologies for addressing challenges with healthcare data. We reviewed 89 papers meeting these criteria. Significant systemic issues were identified throughout the literature, compromising many methodologies reviewed. We give detailed recommendations to help improve methodology development for federated learning in healthcare.

Artificial intelligence (AI) technologies are expected to "revolutionise" healthcare. However, despite their promises, their integration within healthcare organisations and systems remains limited. The objective of this study is to explore and understand the systemic challenges and implications of their integration in a leading Canadian academic hospital.

Semi-structured interviews were conducted with 29 stakeholders concerned by the integration of a large set of AI technologies within the organisation (e.g., managers, clinicians, researchers, patients, technology providers). Data were collected and analysed using the Non-Adoption, Abandonment, Scale-up, Spread, Sustainability (NASSS) framework.

Among enabling factors and conditions, our findings highlight: a supportive organisational culture and leadership leading to a coherent organisational innovation narrative; mutual trust and transparent communication between senior management and frontline teams; the presence of champions, translators, and boundary spanners for AI able to build bridges and trust; and the capacity to attract technical and clinical talents and expertise. Constraints and barriers include: contrasting definitions of the value of AI technologies and ways to measure such value; lack of real-life and context-based evidence; varying patients' digital and health literacy capacities; misalignments between organisational dynamics, clinical and administrative processes, infrastructures, and AI technologies; lack of funding mechanisms covering the implementation, adaptation, and expertise required; challenges arising from practice change, new expertise development, and professional identities; lack of official professional, reimbursement, and insurance guidelines; lack of pre- and post-market approval legal and governance frameworks; diversity of the business and financing models for AI technologies; and misalignments between investors' priorities and the needs and expectations of healthcare organisations and systems.

Thanks to the multidimensional NASSS framework, this study provides original insights and a detailed learning base for analysing AI technologies in healthcare from a thorough socio-technical perspective. Our findings highlight the importance of considering the complexity characterising healthcare organisations and systems in current efforts to introduce AI technologies within clinical routines. This study adds to the existing literature and can inform decision-making towards a judicious, responsible, and sustainable integration of these technologies in healthcare organisations and systems.

Artificial intelligence (AI) has emerged as a transformative force in medical research and is garnering increased attention in the public consciousness. This represents a critical time period in which medical researchers, healthcare providers, insurers, regulatory agencies, and patients are all developing and shaping their beliefs and policies regarding the use of AI in the healthcare sector. The successful deployment of AI will require support from all these groups. This commentary proposes that widespread support for medical AI must be driven by clear and transparent scientific reporting, beginning at the earliest stages of scientific research.

A review of relevant guidelines and literature describing how scientific reporting plays a central role at key stages in the life cycle of an AI software product was conducted. To contextualize this principle within a specific medical domain, we discuss the current state of predictive tissue outcome modeling in acute ischemic stroke and the unique challenges presented therein.

Translating AI methods from the research to the clinical domain is complicated by challenges related to model design and validation studies, medical product regulations, and healthcare providers' reservations regarding AI's efficacy and affordability. However, each of these limitations is also an opportunity for high-impact research that will help to accelerate the clinical adoption of state-of-the-art medical AI. In all cases, establishing and adhering to appropriate reporting standards is an important responsibility that is shared by all of the parties involved in the life cycle of a prospective AI software product.

This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools.

Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction.

Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases.

This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

Classical statistical analysis of data can be complemented or replaced with data analysis based on machine learning. However, in certain disciplines, such as education research, studies are frequently limited to small datasets, which raises several questions regarding biases and coincidentally positive results. In this study, we present a refined approach for evaluating the performance of a binary classification based on machine learning for small datasets. The approach includes a non-parametric permutation test as a method to quantify the probability of the results generalising to new data. Furthermore, we found that a repeated nested cross-validation is almost free of biases and yields reliable results that are only slightly dependent on chance. Considering the advantages of several evaluation metrics, we suggest a combination of more than one metric to train and evaluate machine learning classifiers. In the specific case that both classes are equally important, the Matthews correlation coefficient exhibits the lowest bias and chance for coincidentally good results. The results indicate that it is essential to avoid several biases when analysing small datasets using machine learning.