Identifying Risk of Opioid Use Disorder for Patients Taking Opioid Medications with Deep Learning

The United States is experiencing an opioid epidemic, and there were more than 10 million opioid misusers aged 12 or older each year. 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 predict OUD patients among opioid prescription users through analyzing electronic health records with machine learning and deep learning methods. This will help us to better understand the diagnoses of OUD, providing new insights on opioid epidemic. Electronic health records of patients who have been prescribed with medications containing active opioid ingredients were extracted from Cerner Health Facts database between January 1, 2008 and December 31, 2017. Long Short-Term Memory (LSTM) models were applied to predict opioid use disorder risk in the future based on recent five encounters, and compared to Logistic Regression, Random Forest, Decision Tree and Dense Neural Network. Prediction performance was assessed using F-1 score, precision, recall, and AUROC. Our temporal deep learning model provided promising prediction results which outperformed other methods, with a F1 score of 0.8023 and AUCROC of 0.9369. The model can identify OUD related medications and vital signs as important features for the prediction. LSTM based temporal deep learning model is effective on predicting opioid use disorder using a patient past history of electronic health records, with minimal domain knowledge. It has potential to improve clinical decision support for early intervention and prevention to combat the opioid epidemic.

[1]  Grant T. Harris,et al.  Comparing Effect Sizes in Follow-Up Studies: ROC Area, Cohen's d, and r , 2005, Law and human behavior.

[2]  Zachariah Zhang,et al.  Deep EHR: Chronic Disease Prediction Using Medical Notes , 2018, MLHC.

[3]  Jeremy C. Weiss,et al.  Using machine learning to predict risk of incident opioid use disorder among fee-for-service Medicare beneficiaries: A prognostic study , 2020, PloS one.

[4]  Rajarsi R. Gupta,et al.  Deep Learning on Electronic Health Records to Improve Disease Coding Accuracy. , 2019, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[5]  Ping Zhang,et al.  Risk Prediction with Electronic Health Records: A Deep Learning Approach , 2016, SDM.

[6]  Yu Wang,et al.  Machine Learning Based Opioid Overdose Prediction Using Electronic Health Records , 2019, AMIA.

[7]  Joel H. Saltz,et al.  Disease phenotyping using deep learning: A diabetes case study , 2018, ArXiv.

[8]  Fei Wang,et al.  Deep Learning in Medicine-Promise, Progress, and Challenges. , 2019, JAMA internal medicine.

[9]  Yan Liu,et al.  Deep Learning Solutions for Classifying Patients on Opioid Use , 2017, AMIA.

[10]  Kazem Rahimi,et al.  BEHRT: Transformer for Electronic Health Records , 2019, Scientific Reports.

[11]  Jeremy C. Weiss,et al.  Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries With Opioid Prescriptions , 2019, JAMA network open.

[12]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  John Van Hoewyk,et al.  A multivariate technique for multiply imputing missing values using a sequence of regression models , 2001 .

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[17]  Sungroh Yoon,et al.  Security and Privacy Issues in Deep Learning , 2018, ArXiv.

[18]  Jeffrey Dean,et al.  Scalable and accurate deep learning with electronic health records , 2018, npj Digital Medicine.

[19]  Jonathan P. DeShazo,et al.  A comparison of a multistate inpatient EHR database to the HCUP Nationwide Inpatient Sample , 2015, BMC Health Services Research.

[20]  Avi Ma'ayan,et al.  Predicting opioid dependence from electronic health records with machine learning , 2019, BioData Mining.

[21]  Wes McKinney,et al.  pandas: a Foundational Python Library for Data Analysis and Statistics , 2011 .

[22]  M. Otto,et al.  Does anxiety sensitivity predict addiction severity in opioid use disorder? , 2020, Addictive behaviors.

[23]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[24]  Parisa Rashidi,et al.  Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis , 2017, IEEE Journal of Biomedical and Health Informatics.

[25]  Stef van Buuren,et al.  MICE: Multivariate Imputation by Chained Equations in R , 2011 .

[26]  J. L. Dahl,et al.  A reassessment of trends in the medical use and abuse of opioid analgesics and implications for diversion control: 1997-2002. , 2004, Journal of pain and symptom management.

[27]  H Britt,et al.  A new drug classification for computer systems: the ATC extension code. , 1995, International journal of bio-medical computing.

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  J. Henry,et al.  Adoption of Electronic Health Record Systems among U . S . Non-Federal Acute Care Hospitals : 2008-2015 , 2013 .

[30]  Evan Wood,et al.  Management of opioid use disorders: a national clinical practice guideline , 2018, Canadian Medical Association Journal.

[31]  Fei Wang,et al.  Deep learning for healthcare: review, opportunities and challenges , 2018, Briefings Bioinform..

[32]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[33]  David S. Wishart,et al.  DrugBank 5.0: a major update to the DrugBank database for 2018 , 2017, Nucleic Acids Res..

[34]  Andrew Y. Ng,et al.  Improving palliative care with deep learning , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[35]  Jason Weston,et al.  ELI5: Long Form Question Answering , 2019, ACL.

[36]  R. Chou,et al.  CDC Guideline for Prescribing Opioids for Chronic Pain--United States, 2016. , 2016, JAMA.

[37]  Komal J. Narwaney,et al.  Prediction Model for Two-Year Risk of Opioid Overdose Among Patients Prescribed Chronic Opioid Therapy , 2018, Journal of General Internal Medicine.

[38]  Adway S. Wadekar,et al.  Understanding Opioid Use Disorder (OUD) using tree-based classifiers. , 2020, Drug and alcohol dependence.

[39]  Christopher M. Jones,et al.  Prescription Opioid Use, Misuse, and Use Disorders in U.S. Adults: 2015 National Survey on Drug Use and Health , 2017, Annals of Internal Medicine.

[40]  Roger Chou,et al.  CDC Guideline for Prescribing Opioids for Chronic Pain - United States, 2016. , 2016, MMWR. Recommendations and reports : Morbidity and mortality weekly report. Recommendations and reports.

[41]  Russell K. Portenoy,et al.  Chronic use of opioid analgesics in non-malignant pain: Report of 38 cases , 1986, Pain.

[42]  Nora D Volkow,et al.  Major increases in opioid analgesic abuse in the United States: concerns and strategies. , 2006, Drug and alcohol dependence.

[43]  S. Calcaterra,et al.  Prediction of Future Chronic Opioid Use Among Hospitalized Patients , 2018, Journal of General Internal Medicine.