Fluid overload is common after neonatal congenital #cardiac surgery (CCS) and is frequently managed with continuous furosemide infusions requiring iterative dose titration. An interpretable prediction model could support more consistent early postoperative dosing decisions. We hypothesized that a novel, interpretable machine learning approach could accurately predict furosemide dosing decisions in neonates following CCS. We identified… Continue reading A Novel, Interpretable Machine Learning Model Predicts Furosemide Dosing After Congenital Cardiac Surgery
Category: Tech
Optimizing temporal windows for wearable-augmented post-discharge risk prediction: a methods study
Objective: Traditional #readmission risk models relying on static discharge data have limited predictive performance and fail to capture patients' recovery trajectories after hospitalization. We sought to identify optimal modeling parameters for dynamically predicting readmission risk using post-discharge step-count data from remote monitoring devices.Methods: We combined data for adults aged 55+ from 2 studies that collected… Continue reading Optimizing temporal windows for wearable-augmented post-discharge risk prediction: a methods study
Comprehensive validation of machine learning models predicting chemotherapy related electrolyte disorders in a multicenter study
Background: Electrolyte abnormalities following #chemotherapy are common and clinically significant complications in cancer patients and are often associated with treatment delays and adverse outcomes. This study aims to develop and validate machine learning models to predict eight electrolyte abnormalities in cancer patients receiving chemotherapy.Methods: We retrospectively analyze medical records of cancer patients from two tertiary… Continue reading Comprehensive validation of machine learning models predicting chemotherapy related electrolyte disorders in a multicenter study
From Advice to Action — Real-World Behavior of Patients Using an Integrated Diagnostic Decision Support System for Navigating the Health Care System
Artificial intelligence (#AI )–powered digital front door tools are increasingly being used to guide patients to appropriate care and alleviate health care system pressure. However, most evaluations offer limited insight into stated care intent, real-world behavior, or care appropriateness.MethodsThe E-Health Self–Symptom Assessment as a Front Door and Facilitator of Care (ESSENCE) study was a prospective… Continue reading From Advice to Action — Real-World Behavior of Patients Using an Integrated Diagnostic Decision Support System for Navigating the Health Care System
Vulnerability of Large Language Models to Prompt Injection When Providing Medical Advice
Importance Large language models (#LLMs ) are increasingly integrated into health care applications; however, their vulnerability to prompt-injection attacks (ie, maliciously crafted inputs that manipulate an LLM’s behavior) capable of altering medical recommendations has not been systematically evaluated.Objective To evaluate the susceptibility of commercial LLMs to prompt-injection attacks that may induce unsafe clinical advice and… Continue reading Vulnerability of Large Language Models to Prompt Injection When Providing Medical Advice
Artificial intelligence assisted colorectal lesion detection in private practices a randomized controlled study
Computer-aided #colonoscopy (CAC) may improve polyp detection and characterization compared to traditional colonoscopy (TC). However, recent studies also reported no relevant effect on #adenoma detection rate (ADR). This study evaluates the real-time #polyp detection system EndoMind during screening and surveillance colonoscopy in a multicenter randomized controlled trial. From November 2021 to November 2022, 933 individuals… Continue reading Artificial intelligence assisted colorectal lesion detection in private practices a randomized controlled study
Immersive Virtual Reality Training to Improve Novice Physicians’ Emergency Response Skills: Randomized Controlled Trial
Background:Simulation-based training is essential for preparing medical interns to manage high-stakes emergencies. Although virtual reality (VR)-based simulation has been rapidly integrated into medical education, there remains limited evidence directly assessing its effectiveness relative to established high-fidelity simulation (HFS) methodologies.Objective:This study aimed to assess the perceived educational effectiveness of #VR and HFS in enhancing novice physicians’… Continue reading Immersive Virtual Reality Training to Improve Novice Physicians’ Emergency Response Skills: Randomized Controlled Trial
Consumer wearables, cardiology and clinical practice
Consumer wearables enable continuous cardiac monitoring through photoplethysmography and electrocardiography. Twenty per cent of Danes now share wearable data with physicians. Evidence shows high accuracy for atrial #fibrillation (AF) detection, but anticoagulation for device-detected AF remains controversial. Ethical challenges include data quality, interoperability, health equity, fairness and privacy. While patients increasingly use wearables, clinical integration… Continue reading Consumer wearables, cardiology and clinical practice
Predicting adverse outcomes in dilated cardiomyopathy using 3D echocardiography: penalised Cox regression versus machine learning
Background: Risk prediction in dilated cardiomyopathy ( #DCM ) remains suboptimal, and there is uncertainty about how newer machine-learning (ML) methods compare with conventional regression for clinically useful prognostic modelling. Advanced three-dimensional (3D) echocardiographic measures, particularly of right ventricular function, may improve model performance when combined with routinely collected clinical data. We aimed to compare… Continue reading Predicting adverse outcomes in dilated cardiomyopathy using 3D echocardiography: penalised Cox regression versus machine learning
2 Medical News 