Towards Reducing Diagnostic Errors with Interpretable Risk Prediction

arXiv:2402.10109v1 Announce Type: cross
Abstract: Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors. In particular, we propose a Neural Additive Model to make predictions backed by evidence with individualized risk …

abstract arxiv clinicians cs.ai cs.cl cs.lg data diagnostic ehr electronic electronic health records errors evidence health identify information llms patient prediction records risk type work