Xinyu Dong1, Jianyuan Deng2, Sina Rashidian1, Kayley Abell-Hart2, Wei Hou3, Richard N Rosenthal4, Mary Saltz2, Joel H Saltz2, Fusheng Wang1,2. 1. Department of Computer Science, Stony Brook University, Stony Brook, New York, USA. 2. Department of Biomedical Informatics, Renaissance School of Medicine at Stony Brook University, Stony Brook, New York, USA. 3. Department of Family, Population and Preventive Medicine, Renaissance School of Medicine at Stony Brook University, Stony Brook, New York, USA. 4. Department of Psychiatry, Renaissance School of Medicine at Stony Brook University, Stony Brook, New York, USA.
Abstract
OBJECTIVE: The United States is experiencing an opioid epidemic. In recent years, there were more than 10 million opioid misusers aged 12 years or older annually. Identifying patients at high risk of opioid use disorder (OUD) can help to make early clinical interventions to reduce the risk of OUD. Our goal is to develop and evaluate models to predict OUD for patients on opioid medications using electronic health records and deep learning methods. The resulting models help us to better understand OUD, providing new insights on the opioid epidemic. Further, these models provide a foundation for clinical tools to predict OUD before it occurs, permitting early interventions. METHODS: Electronic health records of patients who have been prescribed with medications containing active opioid ingredients were extracted from Cerner's Health Facts database for encounters between January 1, 2008, and December 31, 2017. Long short-term memory models were applied to predict OUD risk based on five recent prior encounters before the target encounter and compared with logistic regression, random forest, decision tree, and dense neural network. Prediction performance was assessed using F1 score, precision, recall, and area under the receiver-operating characteristic curve. RESULTS: The long short-term memory (LSTM) model provided promising prediction results which outperformed other methods, with an F1 score of 0.8023 (about 0.016 higher than dense neural network (DNN)) and an area under the receiver-operating characteristic curve (AUROC) of 0.9369 (about 0.145 higher than DNN). CONCLUSIONS: LSTM-based sequential deep learning models can accurately predict OUD using a patient's history of electronic health records, with minimal prior domain knowledge. This tool has the potential to improve clinical decision support for early intervention and prevention to combat the opioid epidemic.
OBJECTIVE: The United States is experiencing an opioid epidemic. In recent years, there were more than 10 million opioid misusers aged 12 years or older annually. Identifying patients at high risk of opioid use disorder (OUD) can help to make early clinical interventions to reduce the risk of OUD. Our goal is to develop and evaluate models to predict OUD for patients on opioid medications using electronic health records and deep learning methods. The resulting models help us to better understand OUD, providing new insights on the opioid epidemic. Further, these models provide a foundation for clinical tools to predict OUD before it occurs, permitting early interventions. METHODS: Electronic health records of patients who have been prescribed with medications containing active opioid ingredients were extracted from Cerner's Health Facts database for encounters between January 1, 2008, and December 31, 2017. Long short-term memory models were applied to predict OUD risk based on five recent prior encounters before the target encounter and compared with logistic regression, random forest, decision tree, and dense neural network. Prediction performance was assessed using F1 score, precision, recall, and area under the receiver-operating characteristic curve. RESULTS: The long short-term memory (LSTM) model provided promising prediction results which outperformed other methods, with an F1 score of 0.8023 (about 0.016 higher than dense neural network (DNN)) and an area under the receiver-operating characteristic curve (AUROC) of 0.9369 (about 0.145 higher than DNN). CONCLUSIONS: LSTM-based sequential deep learning models can accurately predict OUD using a patient's history of electronic health records, with minimal prior domain knowledge. This tool has the potential to improve clinical decision support for early intervention and prevention to combat the opioid epidemic.
Authors: Jason M Glanz; Komal J Narwaney; Shane R Mueller; Edward M Gardner; Susan L Calcaterra; Stanley Xu; Kristin Breslin; Ingrid A Binswanger Journal: J Gen Intern Med Date: 2018-01-29 Impact factor: 5.128
Authors: Majid Afshar; Brihat Sharma; Dmitriy Dligach; Madeline Oguss; Randall Brown; Neeraj Chhabra; Hale M Thompson; Talar Markossian; Cara Joyce; Matthew M Churpek; Niranjan S Karnik Journal: Lancet Digit Health Date: 2022-06