Prediction Models for Dialysis Peritonitis Fall Short of Clinical Use, Review Finds
A systematic review of seven prediction models for outcomes after peritoneal dialysis-related peritonitis finds none ready for routine clinical use.
Tag: Clinical decision support
Host Genomics Could Reshape How Doctors Diagnose Immune Disorders and Treat Infections
More than 30 experts outline how patients' germline genomes could improve infectious disease care, from detecting rare immune disorders early ...
AI models learn to read ancient Chinese medicine texts and support clinical reasoning
A new review maps how large language models are being trained on digitized classical texts, billions of clinical records, and ...
Genetic Testing Could Reshape Emergency Prescribing, but the Evidence Is Not There Yet
A new perspective argues that pharmacogenomic testing could improve emergency department prescribing, but no randomized controlled trials have yet tested ...
Fuzzy inference system flags sepsis risk in real time on cloud warehouse
A Mamdani fuzzy inference system built on Google BigQuery and MIMIC-IV data produced well-calibrated sepsis risk scores across 38,888 ICU ...
Anesthesiologists propose risk-based rules for safe use of AI in surgery
An editorial in Anesthesiology and Perioperative Science proposes a risk-based framework for deploying large language models in perioperative anesthesia, reserving ...
AI chatbots show promise and peril in epilepsy care, major review finds
A scoping review of 24 studies finds generative AI models show task-specific promise in epilepsy text processing but are not ...
Machine learning sorts Guillain-Barré syndrome subtypes from nerve conduction data
Interpretable machine-learning models trained on acute-phase nerve conduction data from 99 Korean patients showed preliminary ability to reproduce expert-assigned Guillain-Barré ...
Bayesian Framework Merges Clinical Expertise With Machine Learning Diagnosis
A new Bayesian framework called PIML combines machine learning analysis of electrical impedance signals with clinical prior knowledge, improving diagnostic ...
Machine Learning Models Predict Gangrenous Cholecystitis Before Surgery
A retrospective single-center study of 487 patients developed interpretable machine learning models that predict gangrenous cholecystitis before surgery using five ...
Digital decision support tool shows promise for child respiratory care in Uganda
A three-month implementation study in Uganda found that a digital decision support tool for pediatric respiratory illnesses was used in ...
Web Platform Puts Three Deep Learning Models to Work on Brain Tumor MRI Scans
A new open-access study presents a modular web platform that classifies brain tumor MRI scans in real time using a ...
Interpretable AI Model Predicts 28-Day Mortality in Sepsis-Linked Kidney Injury
An interpretable XGBoost model achieved an AUC of 0.881 for predicting 28-day mortality in critically ill patients with sepsis-associated acute ...
Multimodal AI maps the path to personalized cancer immunotherapy
A Science Bulletin review outlines how multimodal artificial intelligence integrating molecular, cellular, and clinical data could refine immunotherapy decisions while ...
When scans and blood tests disagree, AI could help oncologists decide what to do next
A new narrative review proposes a five-dimensional taxonomy for disagreements between imaging and circulating tumor DNA testing and frames multimodal ...
Hybrid retrieval and verification framework cuts hallucinations in medical AI
A new CARE-Med framework combining dense retrieval, natural language inference verification, and confidence scoring cut unsupported-response rates in medical LLMs ...
Why Almost No Machine Learning Models Ever Reach the Hospital Bedside
An editorial in Frontiers in Medicine argues that the vast majority of clinical machine-learning models never reach patients, with fewer ...
AI pilot reconstructs breast cancer staging logic in low-resource settings
A Nigerian pilot reconstructed AJCC breast cancer staging logic with a lightweight machine-learning tool, achieving perfect retrospective classification without independent ...
Chinese tuberculosis physicians outline explainability needs for clinical AI
A qualitative study of 26 tuberculosis physicians in Hubei Province, China, identified five priorities for explainable AI, including exclusionary and ...
AI drug recommendations converge on the same few brand-name medicines, study finds
A large-scale evaluation of five large language models found that drug recommendations collapse onto a single product in nearly every ...
POPULAR NEWS
-
Study Uncovers Botanical Compounds and Mechanisms Targeting Chronic Bronchitis Inflammation
-
Three Millimolar Caffeine Enhances Cryopreserved Nguni Bull Semen Post-Thaw Motility
-
Higher Brain Iron Levels Are Associated With MRI Alterations in Older Adults
-
Parent B Candida orthopsilosis caused fatal breakthrough candidemia during caspofungin therapy