Citations

Abstract Generative artificial intelligence (AI) holds immense potential for medical applications, but the lack of a comprehensive evaluation framework and methodological deficiencies in existing studies hinder its effective implementation. Standardized assessment guidelines are crucial for ensuring reliable and consistent evaluation of generative AI in healthcare. Our objective is to develop robust, standardized guidelines tailored for evaluating generative AI performance in medical contexts. Through a rigorous literature review utilizing the Web of Sciences, Cochrane Library, PubMed, and Google Scholar, we focused on research testing generative AI capabilities in medicine. Our multidisciplinary team of experts conducted discussion sessions to develop a comprehensive 32‐item checklist. This checklist encompasses critical evaluation aspects of generative AI in medical applications, addressing key dimensions such as question collection, querying methodologies, and assessment techniques. The checklist and its broader assessment framework provide a holistic evaluation of AI systems, delineating a clear pathway from question gathering to result assessment. It guides researchers through potential challenges and pitfalls, enhancing research quality and reporting and aiding the evolution of generative AI in medicine and life sciences. Our framework furnishes a standardized, systematic approach for testing generative AI's applicability in medicine. For a concise checklist, please refer to Table S or visit GenAIMed.org .

AbstractTargeting NLRP3 inflammasome has been recognized as a promising therapeutic strategy for the treatment of numerous common diseases. UK5099, a long‐established inhibitor of mitochondrial pyruvate carrier (MPC), is previously found to inhibit macrophage inflammatory responses independent of MPC expression. However, the mechanisms by which UK5099 inhibit inflammatory responses remain unclear. Here, it is shown that UK5099 is a potent inhibitor of the NLRP3 inflammasome in both mouse and human primary macrophages. UK5099 selectively suppresses the activation of the NLRP3 but not the NLRC4 or AIM2 inflammasomes. Of note, UK5099 retains activities on NLRP3 in macrophages devoid of MPC expression, indicating this inhibitory effect is MPC‐independent. Mechanistically, UK5099 abrogates mitochondria‐NLRP3 interaction and in turn inhibits the assembly of the NLRP3 inflammasome. Further, a single dose of UK5099 persistently reduces IL‐1β production in an endotoxemia mouse model. Importantly, structure modification reveals that the inhibitory activities of UK5099 on NLRP3 are unrelated to the existence of the activated double bond within the UK5099 molecule. Thus, this study uncovers a previously unknown molecular target for UK5099, which not only offers a new candidate for the treatment of NLRP3‐driven diseases but also confounds its use as an MPC inhibitor in immunometabolism studies.

Abstract Innovation in medical imaging artificial intelligence (AI)/machine learning (ML) demands extensive data collection, algorithmic advancements, and rigorous performance assessments encompassing aspects such as generalizability, uncertainty, bias, fairness, trustworthiness, and interpretability. Achieving widespread integration of AI/ML algorithms into diverse clinical tasks will demand a steadfast commitment to overcoming issues in model design, development, and performance assessment. The complexities of AI/ML clinical translation present substantial challenges, requiring engagement with relevant stakeholders, assessment of cost-effectiveness for user and patient benefit, timely dissemination of information relevant to robust functioning throughout the AI/ML lifecycle, consideration of regulatory compliance, and feedback loops for real-world performance evidence. This commentary addresses several hurdles for the development and adoption of AI/ML technologies in medical imaging. Comprehensive attention to these underlying and often subtle factors is critical not only for tackling the challenges but also for exploring novel opportunities for the advancement of AI in radiology.

Abstract The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.

Abstract During the 20th century, inflammatory bowel disease (IBD) was considered a disease of early-industrialized regions in North America, Europe, and Oceania. At the turn of the 21st century, incidence of IBD increased in newly-industrialized and emerging regions in Africa, Asia, and Latin America, while prevalence in early-industrialized regions started to grow steadily. Changes in incidence and prevalence denote evolution of IBD across four epidemiologic stages: Stage 1 (Emergence), characterized by low incidence and prevalence; stage 2 (Acceleration in Incidence), characterized by rapidly rising incidence and low prevalence; and stage 3 (Compounding Prevalence), characterized by decelerating, plateauing, or declining incidence and steadily rising prevalence. A fourth stage (Prevalence Equilibrium) has been proposed where the slope of prevalence plateaus due to shifting demographics of an aging IBD population, but it has not yet been evidenced. To date, these stages have been theoretical without specific incidence/prevalence indicators defining transition points. Using real-world data from 490 population-based studies comprising 80 global regions and spanning over a century (1920–2023), we show spatiotemporal transitions across stages 1–3 and model transition towards stage 4. Understanding the evolution of IBD across epidemiologic stages allows healthcare systems to better prepare for the future worldwide burden of IBD.

AbstractCancer and its treatment produce deleterious symptoms across the phases of care. Poorly controlled symptoms negatively affect quality of life and result in increased health-care needs and hospitalization. The Improving the Management of symPtoms during And following Cancer Treatment (IMPACT) Consortium was created to develop 3 large-scale, systematic symptom management systems, deployed through electronic health record platforms, and to test them in pragmatic, randomized, hybrid effectiveness and implementation trials. Here, we describe the IMPACT Consortium’s conceptual framework, its organizational components, and plans for evaluation. The study designs and lessons learned are highlighted in the context of disruptions related to the COVID-19 pandemic.

AbstractBackgroundInaccurate manual organ delineation is one of the high‐risk failure modes in radiation treatment. Numerous automated contour quality assurance (QA) systems have been developed to assess contour acceptability; however, manual inspection of flagged cases is a time‐consuming and challenging process, and can lead to users overlooking the exact error location.PurposeOur aim is to develop and validate a contour QA system that can effectively detect and visualize subregional contour errors, both qualitatively and quantitatively.Methods/MaterialsA novel contour subregion error detection (CSED) system was developed using subregional surface distance discrepancies between manual and deep learning auto‐segmentation (DLAS) contours. A validation study was conducted using a head and neck public dataset containing 339 cases and evaluated according to knowledge‐based pass criteria derived from a clinical training dataset of 60 cases. A blind qualitative evaluation was conducted, comparing the results from the CSED system with manual labels. Subsequently, the CSED‐flagged cases were re‐examined by a radiation oncologist.ResultsThe CSED system could visualize the diverse types of subregional contour errors qualitatively and quantitatively. In the validation dataset, the CSED system resulted in true positive rates (TPR) of 0.814, 0.800, and 0.771; false positive rates (FPR) of 0.310, 0.267, and 0.298; and accuracies of 0.735, 0.759, and 0.730, for brainstem and left and right parotid contours, respectively. The CSED‐assisted manual review caught 13 brainstem, 19 left parotid, and 21 right parotid contour errors missed by conventional human review. The TPR/FPR/accuracy of the CSED‐assisted manual review improved to 0.836/0.253/0.784, 0.831/0.171/0.830, and 0.808/0.193/0.807 for each structure, respectively. Further, the time savings achieved through CSED‐assisted review improved by 75%, with the time for review taking 24.81 ± 12.84, 26.75 ± 10.41, and 28.71 ± 13.72 s for each structure, respectively.ConclusionsThe CSED system enables qualitative and quantitative detection, localization, and visualization of manual segmentation subregional errors utilizing DLAS contours as references. The use of this system has been shown to help reduce the risk of high‐risk failure modes resulting from inaccurate organ segmentation.