Predicting Mortality of patients admitted to the Internal Medicine Ward
Talya Sassoon is an M.Sc.

department of Industrial Engineering in Tel Aviv University
 

Tuesday, May 11, 2021, at 14:00

Via Zoom
https://us02web.zoom.us/j/83642216097?pwd=Nk91ZFJzUjZFcU1aR2s2cTBkMmdVQT09

Abstract:

One of the paths to better medicine, is better triage. When patients are hospitalized in an internal medicine department, which ones need closer attention to help them survive or counseling about end-of-life care?
Our research applied machine learning tools to help clinicians augment current traditional scoring and intuition to better predict endangered patients. The research used state-of-the-art techniques e.g. CatBoost model using features that were selected based on both statistical methods and clinicians’ inputs. The research achieved 0.9 AUC with 0.9 recall and 0.18 precision on a highly imbalanced data set where the mortality rate is six percent. To ease the use of the model as a decision support tool, we applied the SHAP method on the results for local explainability.

Bio:

Talya Sassoon is an M.Sc. student at the department of Industrial Engineering in Tel Aviv University, specializing in Business Analytics. Talya holds a B.Sc. degree in Industrial Engineering from Tel Aviv University. Her research focuses on predicting mortality in the Internal Medicine Ward. The research is being supervised by Prof. Irad Ben Gal in collaboration with ARC, the Digital Innovation Center at Sheba Medical Center