Towards Reducing Diagnostic Errors with Interpretable Risk Prediction.

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 estimates at time-points where clinicians are still uncertain, aiming to specifically mitigate delays in diagnosis and errors stemming from an incomplete differential.

Does the Timed-Up-and-Go Test Predict Length of Stay After Total Hip Arthroplasty? A Retrospective Study.

Background: The prevalence of ambulatory total hip arthroplasty (THA) is rising, but it is not appropriate for all patients. Preoperative patient selection considers medical and social factors but overlooks patients' prior level of physical function.

Purpose: The aim of this study was to evaluate if preoperative physical function, measured by the Timed-Up-and-Go (TUG) test, is associated with length of stay (LOS) in patients who underwent primary THA.

Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges.

Unstructured data in Electronic Health Records (EHRs) often contains critical information-complementary to imaging-that could inform radiologists' diagnoses. But the large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. In this work we propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR relevant to a given query.

Preoperative Education Prior to Hip or Knee Arthroplasty Is Associated With Home Discharge but Not Reduced Length of Stay.

Background: Increasing numbers of patients are undergoing total joint arthroplasty as a treatment for osteoarthritis, which can be an anxiety-provoking experience. Setting expectations through a preoperative physical therapy (pre-op PT) session can alleviate some of these stressors, potentially decrease hospital length of stay (LOS), and promote home discharge.

Purpose: We sought to determine whether attending a pre-op PT session is associated with decreased hospital LOS and home discharge in total hip arthroplasty (THA) and total knee arthroplasty (TKA) patients.