The Lancet Digital Health

The Updated Sydney System (USS) provides a standardized framework for grading gastritis and stratifying gastric cancer risk. However, subjective observer variability and labor-intensive workflows impede its routine clinical use. To address these challenges, we developed SydneyMTL, a multi-task deep learning framework that uses Multiple Instance Learning (MIL) with task-specific attention pooling to predict severity grades across all five USS attributes simultaneously. Trained on an unprecedented...

BackgroundSepsis remains a leading cause of preventable hospital mortality in England, with NHS England reporting over 48,000 sepsis-related deaths annually. Natural language processing (NLP)-driven clinical decision support systems (CDSS) have been deployed in several NHS Trusts to enable automated early detection of sepsis from unstructured clinical notes, yet causal evidence of their effectiveness at the hospital level remains limited. ObjectiveTo estimate the causal effect of implementing N...

IntroductionKidney biopsy reports contain rich information that is clinically actionable and useful for research. However, the narrative format hinders scalable reuse. We here investigated whether open-source large language models (LLMs) can extract relevant, standardized readouts from native kidney biopsy pathology reports. MethodsGerman free-text native kidney biopsy reports were parsed with three open-source LLMs (Llama3 70B, Llama3 8B, MedGemma) to generate structured JSON outputs covering ...

BackgroundRecent global outbreaks of Mpox have posed significant diagnostic challenges, particularly in resource-limited settings. Conventional diagnostic methods are often inaccessible due to cost, logistical constraints, or lack of trained personnel. These limitations highlight the urgent need for alternative, scalable diagnostic strategies. This study explored the application of machine learning (ML) classifiers trained on clinical symptom data as a rapid, cost-effective tool for Mpox detecti...

Pathology faces persistent challenges including a global shortage of specialists, uneven access to expertise, increasing diagnostic complexity, and a growing need for second-opinion consultations. While digital and telepathology platforms address parts of this problem, existing solutions often trade accessibility for structured, workflow-aware clinical integration. At the same time, multimodal medical AI shows promise for diagnostic support but raises concerns regarding transparency, automation ...

BackgroundArtificial intelligence chatbots (AICs) are increasingly being integrated into scholarly publishing, with the potential to automate routine editorial tasks and streamline workflows. In traditional, complementary, and integrative medicine (TCIM) publishing, editorial and peer review processes can be particularly complex due to diverse methodologies and culturally embedded knowledge systems, presenting unique opportunities and challenges for AIC adoption. MethodsAn anonymous, online cro...

Background & AimsLiver cancer primarily develops in patients with chronic liver disease (CLD), yet most cases are diagnosed at an advanced stage with poor prognosis. While clinical surveillance of patients with CLD generates extensive longitudinal data, its unstructured free-text nature hinders large-scale research. To unlock this real-world evidence, we developed a scalable framework using open-source Large Language Models (LLMs) to transform unstructured clinical text into structured data. Me...

BackgroundDelivering timely, high-quality feedback on resident scholarly projects is labour-intensive, especially in large programmes. We developed an AI-assisted evaluation system, powered by the open-weight LLaMA-3.1 large-language model (LLM), to generate formative feedback on Family Medicine residents scholarly projects and compared its performance with expert human evaluators. MethodsWe evaluated whether the AI-generated feedback achieves comparable quality to expert feedback. The tool ing...

BackgroundHypertension is a major modifiable risk factor for cardiovascular disease, yet blood pressure (BP) control remain suboptimal, particularly in socially disadvantaged communities. Guidelines recommend initiating single-pill combination (SPC) therapy to improve adherence and BP control, but uptake in primary care is limited. ObjectivesTo evaluate the SOLO care improvement project, promoting SPC initiation among general practitioners (GPs) in Amsterdam Zuidoost, a disadvantaged, multi-eth...

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 ...

Accurate polyp segmentation from colonoscopy images is critical for colorectal cancer prevention, yet the generalization of deep learning models under domain shift remains insufficiently explored. We propose Boundary-Explicit Guided Attention U-Net (BEGA-UNet), a boundary-aware segmentation architecture that introduces explicit edge modeling as a structural inductive bias to enhance both segmentation accuracy and cross-domain robustness. The framework integrates three components: an Edge-Guided ...

Machine learning adoption in clinical decision support systems remains limited by concerns about transparency and robustness. Causal structure learning (CSL) combined with expert knowledge may address these concerns by identifying potentially causal predictors, enabling more interpretable and clinically aligned models. In this study, we show that by integrating clinician expertise with CSL algorithms we can identify plausible causal drivers of acquired acute brain dysfunction (ABD) in the pediat...

Frequent blood testing is a routine but burdensome reality for many children, particularly those with chronic, rare, or medically complex conditions. Repeated clinic, hospital, and laboratory visits can disrupt family life, increase stress for children and caregivers, and limit access to timely monitoring and research participation. Despite advances in pediatric care, blood collection has remained largely tethered to in-person clinical settings. This study validates a new model: safe, effective,...

BackgroundHistologic descriptors such as lymphovascular invasion (LVI), visceral pleural invasion (VPI), spread through air spaces (STAS), and grading system have each been associated with adverse outcomes in lung adenocarcinoma (LUAD). However, with the exception of VPI, these features are not formally incorporated into the TNM staging system. We evaluated the prognostic value and incremental contribution of these histologic descriptors within the framework of the 9th edition TNM staging system...

POLE sequencing for somatic mutations (POLEmut) guides adjuvant therapy in endometrial cancer (EC), but cost and infrastructural considerations lead to limited uptake. Omission of POLE testing leads to unnecessary exposure to radiotherapy and/or chemotherapy. We developed POLARIX, a multiple instance deep learning model with attention pooling, which predicts POLE mutation status from routine hematoxylin and eosin whole-slide images (WSIs). Trained on 2,238 cases from eleven EC cohorts, POLARIX s...

BackgroundPancreatic cancer is a leading cause of cancer mortality, and early recognition is challenging. To achieve early diagnosis using symptoms alone, we examined patterns across different stages using network analysis to derive clinically useful insights. MethodsSymptom variables from a de-identified dataset of 50,000 pancreatic cancer patients were analyzed. Stratification by stage was done, followed by bootstrap resampling to address imbalances across strata. Symptom networks were then c...

BackgroundThe 2024 blood culture bottle shortage brought diagnostic resource allocation to the forefront, reflecting persistent, foundational challenges with low-value testing and empiric treatment approaches under clinical uncertainty. ObjectiveTo determine whether a machine learning approach using electronic medical record data can predict bacteremia more effectively than existing systems and practices to guide diagnostic testing and empiric treatment strategies. MethodsIn a retrospective co...

Background and AimsThe glucagon-like peptide-1 receptor agonist (GLP-1 RA) semaglutide has demonstrated efficacy for the secondary prevention of cardiovascular disease among patients with overweight/obesity without diabetes mellitus. However, the comparative effectiveness of GLP-1 RA versus other antiobesity medications (e.g. phentermine-topiramate) not been evaluated. MethodsThis was a retrospective, observational, cohort study using target trial emulation methodology using the Truveta electro...

BackgroundPlacental growth and function are imperative for healthy fetal growth; data on placentas can inform research and clinical care. Measuring placental size after delivery should be easy, but current methods are hard to standardize and error prone. We developed PlacentaVision using artificial intelligence (AI)-based models, to automatically, accurately, and precisely measure placentas from digital photographs. ObjectiveWe aimed to compare placental disc morphology between gross pathology ...

BackgroundTyphoid fever incidence estimates are central to policy decisions on vaccine introduction and investments in non-vaccine prevention and control but are often unavailable. We explored whether prevalence metrics from sentinel studies of community-onset bloodstream infections could accurately predict local Salmonella Typhi (S. Typhi) incidence. MethodsUsing a previous systematic review (January 2018-December 2024), we identified studies reporting both typhoid incidence and prevalence of ...