PROGNOSTICATING CLINICAL INCIDENTS VIA RECURRENT NEURAL NETWORKS BY USING CLINICAL DOCTOR AI
European Journal of Molecular & Clinical Medicine,
2021, Volume 8, Issue 3, Pages 2374-2386
AbstractDoctor AI imitates human doctor’s forecasting potential and gives diagnostic results that are clinically significant. Prognosticating Clinical Incidents is a timeseries based RNN model. It is implemented and employed to longitudinal time stamped electronic health record data from a twenty thousand patients over a decade. Encounter medical logs of patients data such as diagnosis codes, medication codes and procedure codes are input data to RNN to predict the diagnosis and medication types for a future visit of patients in a hospital. Doctor AI evaluates the history of patient’s to prepare one label for each diagnosis predictions and medication types i.e.,multi-label forecasting/prediction. Leveraging huge historical patient details in electronic health records (EHR), a collective generic and comprehensive predictive model that covers perceived health state and medication uses for EHR, is new approach in disease progress identification.
- Article View: 48
- PDF Download: 80