A Machine Learning Model Using Clinical Notes to Identify Physician Fatigue

A machine learning model using clinical notes to identify physician fatigue

Clinical notes should capture important information from a physician-patient encounter, but they may also contain signals indicative of physician fatigue. Using data from 129,228 emergency department (ED) visits, we train a model to identify notes written by physicians who are likely to be tired: those who worked ED shifts on at least 5 of the prior 7 days. In a hold-out set, the model accurately identifies notes written by such high-workload ph…

AI model converts hospital records into text for better emergency care decisions

UCLA researchers have developed an AI system that turns fragmented electronic health records (EHR) normally in tables into readable narratives, allowing artificial intelligence to make sense of complex patient histories and use these narratives to perform clinical decision support with high accuracy. The Multimodal Embedding Model for EHR (MEME) transforms tabular health data into "pseudonotes" that mirror clinical documentation, allowing AI mod…

Struggling with Medical Reports? How AI Can Cut Through the Noise and Save Lives

The News God Struggling with Medical Reports? How AI Can Cut Through the Noise and Save Lives An intensive care unit generates over 1,000 data points—per patient, per day. Multiply that by hundreds of patients and you begin to see the problem: doctors are drowning in documentation. Missed diagnoses, delayed decisions, exhausted staff. The information is there—it just can’t be processed fast enough. So the question becomes: how do you extract lif…

AI Model Converts Hospital Records Into Text for Better Emergency Care Decisions

UCLA researchers have developed an AI system that turns fragmented electronic health records (EHR) normally in tables into readable narratives, allowing artificial intelligence to make sense of complex patient histories and use these narratives to perform clinical decision support with high accuracy.