Sudden cardiac death is, in theory, preventable with defibrillators. But every year, many patients die without defibrillators because doctors fail to predict their risk1. The only predictive biomarker in wide use, cardiac left ventricular ejection fraction (LVEF), misses most sudden cardiac deaths2, and flags many low-risk patients for futile defibrillators that never fire. Here we apply deep learning to a dataset linking all electrocardiograms (ECGs) in a Swedish region to death certificates. The resulting model isolates a high-risk group (2.2% of the sample) with a 7.0% annual rate of sudden cardiac death, higher than those with reduced LVEF (1.9% of the sample; 4.6% annual rate). Notably, 86.1% of the model’s high-risk patients were not flagged by LVEF. High-risk ECG patients with defibrillators implanted were 54.4% less likely to die than expected, suggesting a mortality benefit. We externally validate the model in a US health system, in which it predicts ventricular arrhythmias that cause sudden death; and a Taiwanese hospital registry, in which it specifically predicts future arrhythmic cardiac arrests. To visualize the waveform morphology ‘discovered’ by the predictive model, we pair it with a generative model of the ECG waveform. Together, they reveal a biomarker that is easily visible and robustly predicts sudden cardiac death, but has not to our knowledge been previously described. Tying the biomarker’s shape to electrophysiological first principles, we form and preliminarily test a new hypothesis on the mechanism of sudden cardiac death.
Ziad Obermeyer, Alexander Schubert, James Ross +1 more
Sudden cardiac death is, in theory, preventable with defibrillators. But every year, many patients die without defibrillators because doctors fail to predict their risk1. The only predictive biomarker in wide use, cardiac left ventricular ejection fraction (LVEF), misses most sudden cardiac deaths2, and flags many low-risk patients for futile defibrillators that never fire. Here we apply deep learning to a dataset linking all electrocardiograms (ECGs) in a Swedish region to death certificates. The resulting model isolates a high-risk group (2.2% of the sample) with a 7.0% annual rate of sudden cardiac death, higher than those with reduced LVEF (1.9% of the sample; 4.6% annual rate). Notably, 86.1% of the model’s high-risk patients were not flagged by LVEF. High-risk ECG patients with defibrillators implanted were 54.4% less likely to die than expected, suggesting a mortality benefit. We externally validate the model in a US health system, in which it predicts ventricular arrhythmias that cause sudden death; and a Taiwanese hospital registry, in which it specifically predicts future arrhythmic cardiac arrests. To visualize the waveform morphology ‘discovered’ by the predictive model, we pair it with a generative model of the ECG waveform. Together, they reveal a biomarker that is easily visible and robustly predicts sudden cardiac death, but has not to our knowledge been previously described. Tying the biomarker’s shape to electrophysiological first principles, we form and preliminarily test a new hypothesis on the mechanism of sudden cardiac death.
Ziad Obermeyer, Alexander Schubert, James Ross +1 more
Introduction: Despite advancements in sleep medicine, inadequate sleep habits among young children persist. Establishing appropriate sleep habits in early childhood is essential for supporting physical, emotional, and cognitive development. However, scalable and personalized behavioral interventions for caregivers in community settings remain scarce, particularly AI-enabled systems designed for real-world implementation.Methods: This study evaluated adherence, perceived usefulness, and feasibility of Nenne Navi-AI among 50 caregivers recruited in Hirosaki City, Japan, through community health checkups, childcare facilities, and public advertisements. The culturally tailored application integrates supervised machine-learning models with rule-based algorithms to provide personalized guidance and ongoing support for promoting healthier sleep habits.Results: During the 6-month intervention, only 3 of 50 caregivers (6%) experienced continuous 3-month data-entry lapses, with no withdrawals. Significant pre-post improvements were observed in children's number of awakenings after sleep onset and subjective sleep quality ratings. Subgroup analyses suggested improvements among children with poorer baseline sleep habits (≥0.5 SD worse than the sample mean). Post-intervention assessments confirmed high caregiver acceptability, satisfaction, and reduced parenting stress.
Background: Cognitive impairment is an important health issue in middle-aged and older adults, and insomnia may be associated with increased cognitive vulnerability. However, models specifically designed to identify cognitive impairment in individuals with different severities of sleep-duration-defined insomnia remain limited. This study aimed to develop and validate interpretable machine learning models for current cognitive impairment identification in mild and severe insomnia subgroups.Methods: Data from CHARLS 2015 were used as the development cohort, CHARLS 2011 as the cross-wave temporal validation cohort, and clinical data from Gansu Provincial People’s Hospital as the clinical external validation cohort. Participants with insomnia were stratified into mild and severe subgroups according to self-reported nighttime sleep duration. LASSO regression was used for feature selection, and candidate machine learning algorithms were compared for model selection. The selected LightGBM model was further evaluated using Bayesian optimization and optimized-threshold analysis. Model performance was assessed using AUROC, Brier score, calibration curves, decision curve analysis, and SHAP-based interpretability analysis.Results: The development, cross-wave temporal validation, and clinical external validation cohorts included 5,500, 4,231, and 500 participants, respectively. LightGBM showed the most balanced overall performance. In the mild insomnia subgroup, LightGBM achieved AUROCs of 0.772, 0.749, and 0.748 across the three cohorts; in the severe insomnia subgroup, the corresponding AUROCs were 0.763, 0.757, and 0.750. Bayesian optimization produced comparable external validation discrimination, while optimized-threshold analysis improved threshold-dependent classification performance. SHAP analysis suggested different feature contribution patterns across insomnia severity.
Sleep apnea is a common but frequently underdiagnosed respiratory disorder that poses serious health risks, including cardiovascular diseases and cognitive impairments. Despite recent advances in deep learning-based detection approaches, most methods heavily rely on large-scale, high-quality labeled data, which are costly and labor-intensive to acquire due to the need for expert annotation. To overcome this limitation, we propose a self-supervised learning framework with hierarchical residual cross fusion network (SSL-HRCNet) for sleep apnea detection using single-lead ECG signals. The framework operates through a two-stage pipeline: self-supervised pre-training followed by supervised fine-tuning. During pre-training, we apply a contrastive learning strategy that treats two physiologically meaningful transformed views, R-R intervals (RRIs) and R-peak amplitudes (R-peaks), extracted from the same ECG segment as positive pairs to learn cardiopulmonary representations from unlabeled signals. The feature encoder is further enhanced by hierarchical learnable residual blocks, which employ stacked depthwise–pointwise convolutional layers with progressively expanding receptive fields and learnable residual connections, facilitating multi-scale temporal modeling. During fine-tuning, an attention-based cross fusion module adaptively integrates the complementary representations of RRIs and R-peaks, improving the model’s ability to discriminate apnea events. Extensive evaluations on the Apnea-ECG dataset demonstrate that SSL-HRCNet achieves competitive accuracy using only 10% labeled data, and outperforms existing approaches under full supervision with an accuracy of 91.91% and sensitivity of 89.97%. Moreover, the representations learned during pre-training on Apnea-ECG transfer well to the UCDDB dataset, demonstrating robustness to domain shifts and adaptability to clinical applications.
The appendix is involved in a diverse spectrum of inflammatory, infectious, benign, and malignant conditions that extend far beyond acute appendicitis. Although acute appendicitis remains the most common appendiceal emergency, numerous entities—including reactive appendiceal inflammation, inflammatory bowel disease, appendiceal endometriosis, mucinous and non-mucinous neoplasms, lymphoma, post-transplant lymphoproliferative disorder, and rare mesenchymal tumors—may present with similar clinical symptoms and overlapping imaging findings. Accurate distinction among these conditions is essential because management ranges from conservative medical therapy to appendectomy, right hemicolectomy, cytoreductive surgery or systemic oncologic treatment. Furthermore, several common mimics of appendiceal disease, including mesenteric adenitis, terminal ileitis, epiploic appendagitis, cecal diverticulitis, gynecologic disorders, and ureteric calculi, can closely resemble appendiceal pathology and may lead to inappropriate treatment if not correctly recognized. This narrative imaging review provides a comprehensive multimodality imaging approach to appendiceal diseases using ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), and molecular imaging techniques. Emphasis is placed on imaging features that facilitate differential diagnosis, clinicopathologic and surgical correlation, recognition of disease mimics, assessment of complications, and determination of disease extent. The review highlights how radiologists contribute not only to diagnosis but also to treatment planning, surgical decision-making, staging, surveillance, and multidisciplinary patient management. Emerging applications of dual-energy CT, radiomics, artificial intelligence, and advanced molecular imaging are also discussed. By integrating imaging findings with clinical and pathologic considerations, this review aims to improve diagnostic accuracy, guide appropriate management, and strengthen the radiologist's role in the comprehensive evaluation of appendiceal pathology.
Existing evidence indicates that children and adolescents experiencing bullying victimization (BV) exhibit mental health deterioration, and such effects can persist into adulthood. As current decision-making tools are scarce, we aim to develop a tool to predict subsequent BV risk among Chinese youth. Data were retrieved from a three-wave prospective study which incorporated into the Mental Health Survey for Children and Adolescents in Yunnan (MHSCAY). Six common machine learning (ML) algorithms were used. We internally validated the models using 500 times bootstrap approach to assess discrimination, calibration, and utility. A total of 5345 participants aged 10–17 years completed the survey. The internal validation showed the logistic regression (LR) model slightly outperformed other ML algorithms and exhibited more evenly distributed individual-level prediction uncertainty. It was therefore selected as the final model, achieving an AUROC of 0.800 (95% CI: 0.785, 0.815), AUPRC of 0.519 (95% CI: 0.483, 0.553), calibration intercept of -0.001 (95% CI: -0.076, 0.069), calibration slope of 0.990 (95% CI: 0.930, 1.059), and Brier score of 0.122 (95% CI: 0.117, 0.128). Furthermore, the calibration plot indicated excellent precision, and positive net benefits were observed across broad threshold ranges. Fairness analysis revealed no predictive bias in key subpopulations. This novel predictive tool utilizes seven baseline predictors that are readily accessible to generate accurate, individualized predictions of subsequent BV risk in children and adolescents. Upon further validation, the model may facilitate risk stratification, thereby guiding resource allocation and informing targeted interventions for potential BV crises among Chinese children and adolescents.
Immune checkpoint blockade therapy has revolutionized cancer treatment and demonstrated significant clinical efficacy. However, conventional monoclonal antibody therapeutics still face numerous limitations. Peptide inhibitors, with their low molecular weight, ease of synthesis, cost-effectiveness, and minimal immunogenicity, offer a promising alternative by combining the high specificity of antibodies with the favorable tissue penetration of small molecules. As such, they represent a key direction for overcoming existing therapeutic bottlenecks and developing next-generation immunotherapies. Despite facing key challenges in clinical translation, particularly regarding metabolic stability and oral bioavailability, peptide-based inhibitors hold considerable potential to bridge the gap between antibodies and small-molecule drugs, positioning them as an important component of next-generation cancer immunotherapy. Currently, research in this field is increasingly shifting from traditional empirical screening to intelligent precision design, employing strategies such as rational design based on hotspot amino acids, AI-assisted drug discovery, and advanced delivery systems to optimize the activity, stability, and targeting properties of peptides. This review systematically outlines recent advances in immune checkpoint peptide-based inhibitors, aiming to provide a theoretical foundation for the rational design and clinical translation of this emerging class of therapeutics.
Non-pedunculated colonic neoplasia (NPCN) is increasingly encountered due to expanded bowel cancer screening and improvements in high-definition endoscopy. Flat and sessile lesions carry higher risks of incomplete resection, recurrence and submucosal invasion than pedunculated polyps, making accurate optical diagnosis and appropriate technique selection essential for high-quality care. This review synthesises evidence from 2016 to 2026 providing a contemporary practice-focused update for clinicians delivering endoscopic resection services.
Advances in optical characterisation, including Narrow-band imaging International Colorectal Endoscopic classification, Japan NBI Expert Team classification and Kudo pit pattern classifications, have improved real-time prediction of histology and invasion depth, supporting decision-making between cold resection, endomucosal resection (EMR), endoscopic submucosal dissection (ESD) and surgical referral. Cold snare polypectomy and cold EMR have become preferred techniques for small and intermediate lesions due to excellent safety profiles and high complete resection rates. For larger lesions (≥20 mm), piecemeal EMR with systematic margin ablation using snare-tip soft coagulation now represents the standard of care, reducing recurrence to below 10%.
Emerging techniques such as underwater EMR, cap-assisted EMR and endoscopic full-thickness resection expand therapeutic options for fibrotic or non-lifting lesions. ESD remains crucial for en bloc resection when superficial submucosal invasion is suspected, though its use varies across the UK and international practice due to differences in training pathways and service configuration.
OBJECTIVE
To develop an artificial intelligence system to assist intraoperative decision-making during diagnostic laparoscopy in patients with advanced ovarian cancer. Fagotti score assessment at diagnostic laparoscopy guides treatment planning by estimating surgical resectability, but its subjective and operator-dependent nature limits reproducibility and widespread use.
METHODS
Videos of patients undergoing diagnostic laparoscopy with concomitant Fagotti score assessments at a referral center were retrospectively collected and divided into a development dataset, for artificial intelligence training and evaluation, and an independent test dataset, for validation. Frames extracted from the region of interest of diagnostic laparoscopy videos were manually segmented with anatomical structures and peritoneal carcinomatosis masks by experienced gynecologists. Deep learning models were trained to automatically identify Fagotti score-relevant frames, segment anatomical structures and peritoneal carcinomatosis, and predict video-level Fagotti score and indication to surgery. Artificial intelligence performance was evaluated using Dice score for segmentation, F1-scores for anatomical stations and indication to surgery prediction, and root mean square error for final Fagotti score assessment.
RESULTS
In the development dataset, the segmentation model trained on 7,311 frames achieved Dice scores of 70 ± 3% for anatomical structures and 56 ± 3% for peritoneal carcinomatosis. Video-level anatomical stations classification achieved F1-scores of 74 ± 3% and 73 ± 4%, Fagotti score prediction showed normalized root mean square error values of 1.39 ± 0.18 and 1.15 ± 0.08, and indication to surgery reached F1-scores of 80 ± 8% and 80 ± 2% in the development (n=101) and independent test datasets (n=50), respectively.
Spinal cord injury (SCI) is a highly disabling central nervous system disease with complex pathology, and targeted neuroprotective drugs remain clinically lacking. However, traditional molecular target screening and drug prediction methods are inefficient, costly, and poorly targeted, failing to meet clinical precision treatment needs. To address this, we introduced machine learning to construct a multi-dimensional data integration framework. First, we established normal, acute- and subacute-phase SCI mouse complete transection models, and RNA-seq combined with single-cell sequencing revealed acute-phase may occur extensive neuronal PANoptosis. Using WGCNA and MCC algorithms, 25 candidate genes for extensive neuronal PANoptosis in the acute phase were screened out. Then, we comprehensively applied machine learning algorithms including Elastic Net-GLM, Random Forest, Support Vector Machine, and LASSO to predict and prioritize potential molecular targets, identifying 13 possible core genes for extensive neuronal PANoptosis, including Tacc3, Aurka, Mcm6, Mcm5, Ripk1, etc. With the help of the Connectivity Map, drug prediction was performed on these 13 genes, and the 8 candidate drugs with neuroprotective effects were screened out. Through protein domain screening, it was verified via proof-by-contradiction assays that the drug Xaliproden can establish robust interactions with the 7XMK, 7FCZ and 7FD0 domains of Ripk1, a core molecule of the PANoptosome, via a network of multiple hydrogen bonds. This finding provides a novel screening strategy for neuroprotective drugs for spinal cord injury and is of great significance for promoting the establishment of a precision treatment system for the acute phase of injury.
Background Clinicians frequently face questions that require rapid, evidence-based answers. Artificial intelligence (AI) tools are increasingly used for this purpose, yet their reliability for clinical decision-making remains uncertain. This study compared two generative large language model (LLM) systems (ChatGPT and Gemini) and a retrieval-supported clinical platform (OpenEvidence) to determine which provides the most reliable, clear, and clinically applicable information in obstetrics, gynecology, and urogynecology. Methods A cross-sectional comparative design was used to evaluate ChatGPT (GPT-5), Gemini (Gemini 2.5), and the retrieval-supported platform OpenEvidence. Twenty-four clinical questions across three subspecialties were independently assessed by two blinded specialists using the Expert-Adapted DISCERN (EA-DISCERN) tool, which rates 12 quality domains on a five-point scale. Mean ± SD scores were compared across systems and clinical domains using repeated-measures analysis. Results OpenEvidence achieved the highest mean total score (54.0 ± 2.3), outperforming Gemini (50.3 ± 2.4) and ChatGPT (48.7 ± 2.4) (p < 0.001). OpenEvidence scored significantly higher in evidence-based domains; clinical accuracy, guideline consistency, completeness, transparency, and reliability across all fields. As of this writing, Gemini ranked between the two, showing a modest advantage over ChatGPT in rationale explanation and evidence transparency, while both generative models scored higher in language fluency and readability. Overall, total EA-DISCERN scores ranked OpenEvidence highest, followed by Gemini, then ChatGPT. Inter-rater reliability for the total score was ICC[2,1] (absolute agreement = 0.391). Conclusions OpenEvidence provided more guideline-aligned and transparent responses, whereas ChatGPT and Gemini were generally more fluent and readable. For OB/GYN clinicians, retrieval-supported platforms may be more suitable for point-of-care verification, while generative models should be used more cautiously and with clinician oversight.
Aging populations face growing multimorbidity, while episodic clinical assessments fail to capture gradual physiological changes unfolding during daily life. Although wearable technologies enable continuous monitoring, single-modality systems provide incomplete and context-limited insight. This Perspective focuses on hybrid wearable sensors that integrate physical and chemical sensing for geriatric healthcare. Hybrid wearable sensing provides a pathway toward continuous, predictive, and personalized geriatric health management. By monitoring continuously multiple health parameters, such multimodal systems have distinct advantages for real-time monitoring, including early risk detection and more personalized health assessment through the integration of complementary physical and biochemical signals. We discuss recent advances in wearable physical sensors, alongside with emerging wearable chemical sensors, then argue that chem-phys hybrid integration enables more interpretable and clinically actionable assessment of aging trajectories than single-modality wearable systems. Finally, we discuss translational requirements and future prospects, including robust real-world operation, AI-driven inference, and integration with telemedicine and home-based care.
