Your browser doesn't support javascript.
loading
Deep Learning vs Traditional Models for Predicting Hospital Readmission among Patients with Diabetes.
Hai, Ameen A; Weiner, Mark G; Paranjape, Anuradha; Livshits, Alice; Brown, Jeremiah R; Obradovic, Zoran; Rubin, Daniel J.
Afiliação
  • Hai AA; Center for Data Analytics and Biomedical Informatics, Philadelphia, PA.
  • Weiner MG; Weill Cornell Medicine, New York, NY.
  • Paranjape A; Lewis Katz School of Medicine at Temple University, Philadelphia, PA.
  • Livshits A; Lewis Katz School of Medicine at Temple University, Philadelphia, PA.
  • Brown JR; Departments of Epidemiology and Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, NH.
  • Obradovic Z; Center for Data Analytics and Biomedical Informatics, Philadelphia, PA.
  • Rubin DJ; Lewis Katz School of Medicine at Temple University, Philadelphia, PA.
AMIA Annu Symp Proc ; 2022: 512-521, 2022.
Article em En | MEDLINE | ID: mdl-37128461
A hospital readmission risk prediction tool for patients with diabetes based on electronic health record (EHR) data is needed. The optimal modeling approach, however, is unclear. In 2,836,569 encounters of 36,641 diabetes patients, deep learning (DL) long short-term memory (LSTM) models predicting unplanned, all-cause, 30-day readmission were developed and compared to several traditional models. Models used EHR data defined by a Common Data Model. The LSTM model Area Under the Receiver Operating Characteristic Curve (AUROC) was significantly greater than that of the next best traditional model [LSTM 0.79 vs Random Forest (RF) 0.72, p<0.0001]. Experiments showed that performance of the LSTM models increased as prior encounter number increased up to 30 encounters. An LSTM model with 16 selected laboratory tests yielded equivalent performance to a model with all 981 laboratory tests. This new DL model may provide the basis for a more useful readmission risk prediction tool for diabetes patients.
Assuntos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Diabetes Mellitus / Aprendizado Profundo Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Revista: AMIA Annu Symp Proc Assunto da revista: INFORMATICA MEDICA Ano de publicação: 2022 Tipo de documento: Article País de publicação: Estados Unidos

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Diabetes Mellitus / Aprendizado Profundo Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Revista: AMIA Annu Symp Proc Assunto da revista: INFORMATICA MEDICA Ano de publicação: 2022 Tipo de documento: Article País de publicação: Estados Unidos