Tag
A secondary analysis of the EMERGE trial reveals that Random Survival Forest models utilizing early glycemic data can accurately predict the time to insulin initiation in women with gestational diabetes, offering a roadmap for personalized
Researchers have developed a machine learning model using real-world and clinical trial data to predict distant recurrence risk and ribociclib’s therapeutic effect in HR+/HER2- early breast cancer, offering a potential tool for person
A nationwide target trial emulation study reveals that SGLT2 inhibitors provide cardiovascular benefits across a broader range of patients than previously recognized, with benefit more closely tied to individual metabolic traits than tradit
A large-scale UK Biobank study reveals that while visceral and liver fat accelerate cardiovascular ageing in both sexes, subcutaneous and android fat specifically impact males, whereas gynoid fat may offer protective benefits.
The novel PILOT machine learning architecture integrates time-phased perioperative data and regeneration-associated biomarkers to predict post-hepatectomy liver failure within six hours of surgery, significantly outperforming traditional cl
A secondary analysis of the TEAM trial using machine learning demonstrates that enhanced early mobilization in mechanically ventilated patients has highly individualized effects, ranging from a 34% mortality reduction to a 39% increase in r
This review synthesizes evidence on a novel hybrid machine learning model leveraging US lung transplant registry data to predict mortality or retransplant risk at 1, 5, and 10 years, highlighting its clinical utility and balanced interpreta
A multicentre deep‑learning model reliably classified biopsy focus score and ACR‑EULAR–defined Sjögren’s disease (AUROC ≈0.88–0.89) and identified a novel CD8+ T‑cell peri‑acinar pattern associated with disease; prospective validation is ne
Comprehensive proteogenomic profiling in resected extrahepatic cholangiocarcinoma reveals predictive biomarkers for tailoring adjuvant chemotherapy, offering a precision medicine approach to improve patient outcomes.
This study applies machine learning and explainable AI to identify factors associated with chronic pain, psychological distress, and their co-occurrence in Norwegian young adults, highlighting the importance of integrated approaches for ear
This study developed and validated machine learning models with high accuracy to predict early pediatric sepsis and septic shock within 48 hours using multisite electronic health record data in emergency departments.
Integrated radiomic-clinical machine learning models outperform traditional clinical biomarkers in predicting survival and treatment response in unresectable hepatocellular carcinoma patients undergoing atezolizumab plus bevacizumab therapy
A machine learning model accurately stratifies patients with hepatocellular carcinoma to guide individualized selection between liver transplantation and surgical resection, improving survival outcomes while addressing donor scarcity and pa
Machine learning models trained on clinical data improve prediction of coronary artery disease on CT scans compared to traditional risk scores, potentially guiding better resource utilization in cardiovascular care.
A new cell-free DNA fragmentomics model combined with machine learning achieves high accuracy for early pancreatic cancer detection, potentially improving patient outcomes through timely intervention.
A prospective study shows that machine learning models trained on 12-lead ECG features outperform HEART score in predicting mortality among chest pain patients, improving risk-based care precision.
A machine learning model using nationwide registry data accurately predicts long-term remission in refractory ulcerative colitis and identifies key prognostic factors such as pseudopolyps.
