Search Articles

View query in Help articles search

Search Results (1 to 3 of 3 Results)

Download search results: CSV END BibTex RIS


Clinical Utility and Functionality of an Artificial Intelligence–Based App to Predict Mortality in COVID-19: Mixed Methods Analysis

Clinical Utility and Functionality of an Artificial Intelligence–Based App to Predict Mortality in COVID-19: Mixed Methods Analysis

Data were anonymized at the point of extraction and encoded from patient electronic health records by 3 health care practitioners (EC, AP, and A Abdulaal). The model weights were initialized with Xavier normal initialization, and a dropout of 20% and 40% were used on the 2 hidden layers. Euclidean (L2) regularization was further added to the hidden layers to further prevent overfitting.

Ahmed Abdulaal, Aatish Patel, Ahmed Al-Hindawi, Esmita Charani, Saleh A Alqahtani, Gary W Davies, Nabeela Mughal, Luke Stephen Prockter Moore

JMIR Form Res 2021;5(7):e27992