Prediction of general medical admission length of stay with natural language processing and deep learning: a pilot study
- PDF / 629,841 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 11 Downloads / 163 Views
IM - ORIGINAL
Prediction of general medical admission length of stay with natural language processing and deep learning: a pilot study Stephen Bacchi1,2 · Samuel Gluck1,2 · Yiran Tan1,2 · Ivana Chim1 · Joy Cheng1 · Toby Gilbert1,2 · David K. Menon3 · Jim Jannes1,2 · Timothy Kleinig1,2 · Simon Koblar1,2 Received: 30 October 2019 / Accepted: 17 December 2019 © Società Italiana di Medicina Interna (SIMI) 2020
Abstract Length of stay (LOS) and discharge destination predictions are key parts of the discharge planning process for general medical hospital inpatients. It is possible that machine learning, using natural language processing, may be able to assist with accurate LOS and discharge destination prediction for this patient group. Emergency department triage and doctor notes were retrospectively collected on consecutive general medical and acute medical unit admissions to a single tertiary hospital from a 2-month period in 2019. These data were used to assess the feasibility of predicting LOS and discharge destination using natural language processing and a variety of machine learning models. 313 patients were included in the study. The artificial neural network achieved the highest accuracy on the primary outcome of predicting whether a patient would remain in hospital for > 2 days (accuracy 0.82, area under the received operator curve 0.75, sensitivity 0.47 and specificity 0.97). When predicting LOS as an exact number of days, the artificial neural network achieved a mean absolute error of 2.9 and a mean squared error of 16.8 on the test set. For the prediction of home as a discharge destination (vs any non-home alternative), all models performed similarly with an accuracy of approximately 0.74. This study supports the feasibility of using natural language processing to predict general medical inpatient LOS and discharge destination. Further research is indicated with larger, more detailed, datasets from multiple centres to optimise and examine the accuracy that may be achieved with such predictions. Keywords Prognostication · Artificial intelligence · Neural network · Natural language processing · Deep learning · Machine learning
Introduction Discharge planning is the process by which an individualized plan is made for a patient to leave hospital and receive ongoing support in the community, preventing readmission [1]. Effective discharge planning can reduce risk of readmission, improve patient satisfaction, and reduce length of stay (LOS) [2]. Discharge planning may involve multiple components including input from allied health staff, discussions
* Stephen Bacchi [email protected] 1
Neurology Department, Royal Adelaide Hospital, Port Road, Adelaide, SA 5000, Australia
2
University of Adelaide, Adelaide, SA 5005, Australia
3
Division of Anaesthesia, University of Cambridge, Cambridge CB2 0QQ, UK
with community healthcare providers, estimating and communicating an estimated discharge date (EDD), and discharge destination. Accurate prediction of EDD, based on predicted LOS, contributes
Data Loading...
