Decision theory and metrics for evaluating predictive models

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:40 - Towards Conversational AI for Disease Management and Towards autonomous medical artificial intelligence agents 10:40 - Physicians and artificial intelligence diverge in evaluating large language models on real clinical cases 15:40 - Evaluating the robustness and readiness of large frontier models in health AI applications Join the conversation on our new LinkedIn page: https://www.linkedin.com/company/medicalattention/ Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:30 - ChatGPT Health performance in a structured test of triage recommendations 11:30 - AI-Guided GDMT Optimization After HFrEF Hospitalization: The ASSIST-HF SIRIO Randomized Pilot Trial 18:25 - AI literacy mediates AI assisted diagnosis participation and critical thinking among medical students under supervision Join the conversation on our new LinkedIn page: https://www.linkedin.com/company/medicalattention/ Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 01:00 - Technical wrap - ChatGPT and Claude for healthcare, AI scribes 07:40 - What is decision theory? 33:20 - Evaluation of performance measures in predictive artificial intelligence models to support medical decisions Join the conversation on our new LinkedIn page: https://www.linkedin.com/company/medicalattention/ Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:30 - LLMs Can Do Medical Harm: Stress-Testing Clinical Decisions Under Social Pressure 09:30 - Measuring provider-level differences in perioperative workflow using computer vision-based artificial intelligence 12:55 - Heterogenous effect of automated alerts on mortality Join the conversation on our new LinkedIn page: https://www.linkedin.com/company/medicalattention/ Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:30 - Ambient AI RCTs A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being Ambient AI Scribes in Clinical Practice: A Randomized Trial AI Scribes Are Not Productivity Tools (Yet) 09:55 - Language models cannot reliably distinguish belief from knowledge and fact 17:20 - Extracting social determinants of health from electronic health records: development and comparison of rule-based and large language models-based methods More details in the show notes on our website. Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:35 - Scaling Large Language Models for Next-Generation Single-Cell Analysis   05:55 - Generative Medical Event Models Improve with Scale   10:50 - When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior More details in the show notes on our website. Episodes | Bluesky | [email protected]

This episode, we discuss some of the challenges in using large language models (LLMs) for the task of summarising inpatient encounters.  00:30 - Technical wrap - new models, MiT’s State of AI in Business 2025 12:40 - Medical summarisation 19:30 - Context Rot: How Increasing Input Tokens Impacts LLM Performance 30:50 - Verifiable Summarization of Electronic Health Records Using Large Language Models to Support Chart Review 40:00 - Evaluating large language models for drafting emergency department encounter summaries 42:25 - Evaluating Hospital Course Summarization by an Electronic Health Record-Based Large Language Model More details in the show notes on our website. Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:30 - Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study   06:05 - Automation Bias in Large Language Model Assisted Diagnostic Reasoning Among AI-Trained Physicians   10:15 - Emerging algorithmic bias: fairness drift as the next dimension of model maintenance and sustainability    15:20 - Evaluating Large Language Model Diagnostic Performance on JAMA Clinical Challenges via a Multi-Agent Conversational Framework More details in the show notes on our website. Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 00:30 - An Electrocardiogram Foundation Model Built on over 10 Million Recordings 07:10 - Zero-shot Large Language Models for Long Clinical Text Summarization with Temporal Reasoning 14:15 - Diagnostic Codes in AI prediction models and Label Leakage of Same-admission Clinical Outcomes 16:50 - Evaluating reasoning LLMs’ potential to perpetuate racial and gender disease stereotypes in healthcare More details in the show notes on our website. Episodes | Bluesky | [email protected]

Here’s a quick wrap of the three papers we found interesting over the last few weeks with some take home points. 1:00 - Clinical knowledge in LLMs does not translate to human interactions 06:45 - From Tool to Teammate: A Randomized Controlled Trial of Clinician-AI Collaborative Workflows for Diagnosis 11:55 - Advancing Real-time Pandemic Forecasting Using Large Language Models: A COVID-19 Case Study More details in the show notes on our website. Episodes | Bluesky | [email protected]