Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/28265
Title: | Deep Learning Classification and Model Explainability for Prediction of Mental Health Patients Emergency Department Visit |
Other Titles: | Emergency Department Resource Prediction Using Explainable Deep Learning |
Authors: | Rashidiani, Sajjad |
Advisor: | Doyle, Thomas E. |
Department: | Electrical and Computer Engineering |
Keywords: | Deep Learning;Transfer Learning;Natural Language Processing;Readmission Prediction;Emergency Department Visit;Questionnaire;Patient Reported Outcome Measure;PROM;NLP;Explainability;Artificial Intelligence;Machine Learning |
Publication Date: | 2022 |
Abstract: | The rate of Emergency Department (ED) visits due to mental health and drug abuse among children and youth has been increasing for more than a decade and is projected to become the leading cause of ED visits. Identifying high-risk patients well before an ED visit will enable mental health care providers to better predict ED resource utilization, improve their service, and ultimately reduce the risk of a future ED visit. Many studies in the literature utilized medical history to predict future hospitalization. However, in mental health care, the medical history of new patients is not always available from the first visit and it is crucial to identify high risk patients from the beginning as the rate of drop-out is very high in mental health treatment. In this study, a new approach of creating a text representation of questionnaire data for deep learning analysis is proposed. Employing this new text representation has enabled us to use transfer learning and develop a deep Natural Language Processing (NLP) model that estimates the possibility of 6-month ED visit among children and youth using mental health patient reported outcome measures (PROM). The proposed method achieved an Area Under Receiver Operating Characteristic Curve of 0.75 for classification of 6-month ED visit. In addition, a novel method was proposed to identify the words that carry the highest amount of information related to the outcome of the deep NLP models. This measurement of word information using Entropy Gain increases the explainability of the model by providing insight to the model attention. Finally, the results of this method were analyzed to explain how the deep NLP model achieved a high classification performance. |
URI: | http://hdl.handle.net/11375/28265 |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Rashidiani_Sajjad_2022December_MASc.pdf | 4.46 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.