Scientific Reports

Rapid risk stratification is essential in the clinic, yet vital signs, laboratory tests, and triage scores may not fully capture risk at presentation. We investigated whether facial photographs taken after emergency admission provide an additional mortality signal. Using 27,660 smartphone facial photographs, we trained deep neural networks to identify mortality risk with a Cox proportional hazards framework. Face-derived risk scores strongly stratified short- and long-term mortality, outperformi...

Respiratory monitoring in daily-life settings is important for health assessment, yet extracting physiologically interpretable information from breathing signals under natural conditions remains challenging, as breathing is inherently dynamic and strongly modulated by behavior. Here, a portable breathing monitoring device based on a flexible lead zirconate titanate sensor is developed to address this challenge. By exploiting polarity-opposed piezoelectric and pyroelectric responses through senso...

Overcrowding of emergency departments (ED) is now a problem of global health care concern due to the increase in patients. Triage systems have been established for a considerable period. However, their reliability in choosing the appropriate patient and the level of service has undergone much scrutiny. In this paper, we describe a comprehensive machine learning framework aimed at predicting critical emergency department outcomes and enabling dynamic routing decisions. Through the MIMIC-IV-ED dat...

Nocturnal glucose regulation is modulated by autonomic and circadian mechanisms, yet their dynamic interplay in apparently healthy, free-living populations remains poorly studied. Here, we assessed 227,860 nights of concurrent sleep data from Ultrahuman AIR ring and M1 continuous glucose monitoring (CGM) system across 5849 adults globally to examine nocturnal cardio-metabolic coupling. We found that higher sleep consistency was inversely associated with glucose variability, and vice versa. Unsup...

The COVID-19 pandemic has presented severe challenges in understanding and predicting the spread of infectious diseases, necessitating innovative approaches beyond traditional epidemiological models. This study introduces an advanced method for automated model discovery using the Sparse Identification of Nonlinear Dynamics (SINDy) algorithm, leveraging a dataset from the COVID-19 outbreak in Thuringia, Germany, encompassing over 400,000 patient records and vaccination data. By analysing this dat...

Sudden cardiac death risk is 2-3-fold higher in athletes than in non-athletes. We classify sports-related cardiac arrhythmias using a novel explainability framework comprising data analysis, model interpretability, post-hoc visualisation, and systematic assessment. Two neural networks--one with interpretable sinc convolution and one with standard convolution--were trained on general-population ECGs (PhysioNet, n=88,253, 30 arrhythmias, three continents) and tested on professional footballers (PF...

Osteoporosis is a silent yet debilitating disease that often remains undetected until fractures occur. While early prediction is crucial, most studies combine male and female datasets to train a single model, introducing bias since osteoporosis risk and progression differ by gender. This study aims to develop gender-specific machine learning models that leverage longitudinal data to predict osteoporosis risk, providing tailored insights for men and women. Data were obtained from two large longit...

Current standard of care imaging practices cannot reliably differentiate among certain renal tumors such as benign oncocytoma and clear cell renal cell carcinoma (RCC), and between low and high grade RCCs. Previous work has explored using deep learning, radiomics, and texture analysis to predict renal tumor subtypes and differentiate between low and high grade RCCs with mixed success. To further this work, large diverse datasets are needed to improve model performance and provide strong evaluati...

Handheld ultrasound devices have revolutionized point-of-care diagnostics, but their effectiveness remains limited by operator dependency and the need for specialized training. This paper presents an intelligent guidance and diagnostic assistance system for the handheld wireless ultrasound device, enabling automated carotid artery and thyroid examinations through handheld operation. Drawing inspiration from the Actor-Critic framework, we implement a simulation-based reinforcement learning approa...

Radiogenomics enables the non-invasive characterisation of the genomic and molecular properties of tumours, with epidermal growth factor receptor (EGFR) mutations in non-small cell lung cancer (NSCLC) being one of the most investigated applications. In this study, we evaluate radiomics, contrastive learning, and convolutional deep learning approaches to predict the EGFR mutation status from chest Computed Tomography (CT) images using the TCIA Radiogenomics dataset (n=115). Our results, using 10-...

Congenital anomalies of the kidney and urinary tract (CAKUT) are the leading cause of pediatric kidney failure, but predicting individual progression remains challenging. This multicenter study developed and validated POCC, a machine learning model for predicting kidney failure risk at 1, 3, and 5 years post-diagnosis in CAKUT patients. Two versions were created using data from 2,249 children. The general model achieved internal AUCs of 0.93-0.99 and external AUCs of 0.90-0.98 and 0.81- 0.90 in ...

BackgroundAI-based radiomics has demonstrated promising diagnostic performance for pancreatic cystic neoplasms, yet clinical translation remains limited. Whether this reflects insufficient model performance or structural limitations of the evidence base remains unclear. MethodsWe performed a systematic review and diagnostic test accuracy meta-analysis of AI-based radiomics in pancreatic cyst (2015-2025), addressing two clinically relevant tasks (Q1: cyst type differentiation/Q2: malignancy or h...

In previous work, we achieved state-of-the-art performance on ChestX-ray14 (ROC-AUC 0.940, F1 0.821) using pretraining diversity and clinical metric optimization. Applying the same methodology to CheXpert, we received similar results when using NLP valuation and test data--but when evaluated against expert radiologist labels, performance was only 0.75-0.87 ROC-AUC. The models had learned to match the automated NLP labeling system, not to diagnose disease. This paper documents our investigation ...

Widespread screening for Adolescent Idiopathic Scoliosis (AIS) is critical for timely intervention but is currently constrained by the radiation risks of X-rays and the subjectivity of physical examinations. Here, we present PointScol, a radiation-free triage system leveraging 3D back surface point clouds. To reconcile the conflicting clinical demands for "zero-miss" screening and "fine-grained" severity assessment, we developed a two-stage deep learning framework. First, an automated segmentati...

Brain tumors are one of the most life-threatening diseases, requiring precise and timely detection for effective treatment. Traditional methods for brain tumor detection rely heavily on manual analysis of MRI scans, which is time-consuming, subjective, and prone to human error. With advancements in deep learning, Convolutional Neural Networks (CNNs) have become popular for medical image analysis. However, CNNs are limited in their ability to capture spatial hierarchies and pose variations, which...

Chronic constipation is highly prevalent, and cases refractory to treatment are particularly challenging to manage. High-resolution colonic manometry (HRM) is used to further evaluate these patients to identify cases of intrinsic motor dysfunction (underlying myopathy or neuropathy). However, HRM is invasive and resource-intensive, limiting uptake and clinical utility. This study presents Body Surface Colonic Mapping (BSCM), a non-invasive cutaneous electrical recording technique, as a clinical ...

Sleep arousals trigger rapid autonomic shifts, yet their specific sympathetic signatures remain poorly characterized due to the mixed sympathetic-parasympathetic nature of traditional cardiovascular markers. Electrodermal activity (EDA), driven exclusively by sympathetic sudomotor pathways, offers a more direct opportunity to characterize arousal-related autonomic responses during sleep. This study quantifies the evolution of EDA-based features associated with arousal events in 100 adults using ...

Quantifying muscle health at scale has been limited by the difficulty of segmenting individual muscles on MRI. We developed an automated 3D deep-learning framework that segments 20 bilateral hip and thigh muscles from Dixon MRI, enabling muscle level quantification of volume and relative fat fraction (rFF). Applied to 10,840 baseline and 2,766 longitudinal UK Biobank scans, this framework supports population-scale phenotyping across demographic, metabolic and treatment exposures. Segmentation ac...

Computational growth and remodeling (G&R) models have been extentively used to investigate abdominal aortic aneurysm (AAA) progression and to support clinical decision-making. However, the development of robust predictive models is often limited by the scarcity of large-scale longitudinal imaging datasets. In this study, we propose a physics-based G&R framework to simulate AAA shape evolution and generate a virtual cohort of aneurysms, thereby addressing data limitations and enabling integration...

We propose a lesion-centric phenotype learning pipeline for interpretable breast ultrasound (BUS). Predicted lesion masks are used for mask-weighted pooling of segmentation-encoder latents, producing compact embeddings that suppress background influence; a lightweight calibration step improves cross-dataset consistency. We cluster embeddings to discover latent phenotypes and relate phenotype structure to morphology descriptors (compactness, boundary sharpness). On BUSI and BUS-UCLM with external...