Literature DB >> 33930132

Identifying risk of opioid use disorder for patients taking opioid medications with deep learning.

Xinyu Dong1, Jianyuan Deng2, Sina Rashidian1, Kayley Abell-Hart2, Wei Hou3, Richard N Rosenthal4, Mary Saltz2, Joel H Saltz2, Fusheng Wang1,2.   

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.
© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  deep learning; electronic health records; machine learning; opioid use disorder

Mesh:

Substances:

Year:  2021        PMID: 33930132      PMCID: PMC8324214          DOI: 10.1093/jamia/ocab043

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  28 in total

Review 1.  Major increases in opioid analgesic abuse in the United States: concerns and strategies.

Authors:  Wilson M Compton; Nora D Volkow
Journal:  Drug Alcohol Depend       Date:  2005-07-14       Impact factor: 4.492

2.  Prediction of Future Chronic Opioid Use Among Hospitalized Patients.

Authors:  S L Calcaterra; S Scarbro; M L Hull; A D Forber; I A Binswanger; K L Colborn
Journal:  J Gen Intern Med       Date:  2018-02-05       Impact factor: 5.128

3.  Long short-term memory.

Authors:  S Hochreiter; J Schmidhuber
Journal:  Neural Comput       Date:  1997-11-15       Impact factor: 2.026

Review 4.  Deep learning for healthcare: review, opportunities and challenges.

Authors:  Riccardo Miotto; Fei Wang; Shuang Wang; Xiaoqian Jiang; Joel T Dudley
Journal:  Brief Bioinform       Date:  2018-11-27       Impact factor: 11.622

5.  Prediction Model for Two-Year Risk of Opioid Overdose Among Patients Prescribed Chronic Opioid Therapy.

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

6.  Chronic use of opioid analgesics in non-malignant pain: report of 38 cases.

Authors:  Russell K Portenoy; Kathleen M Foley
Journal:  Pain       Date:  1986-05       Impact factor: 6.961

7.  The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.

Authors:  Takaya Saito; Marc Rehmsmeier
Journal:  PLoS One       Date:  2015-03-04       Impact factor: 3.240

8.  A comparison of a multistate inpatient EHR database to the HCUP Nationwide Inpatient Sample.

Authors:  Jonathan P DeShazo; Mark A Hoffman
Journal:  BMC Health Serv Res       Date:  2015-09-15       Impact factor: 2.655

9.  BEHRT: Transformer for Electronic Health Records.

Authors:  Yikuan Li; Shishir Rao; José Roberto Ayala Solares; Abdelaali Hassaine; Rema Ramakrishnan; Dexter Canoy; Yajie Zhu; Kazem Rahimi; Gholamreza Salimi-Khorshidi
Journal:  Sci Rep       Date:  2020-04-28       Impact factor: 4.379

Review 10.  CDC Guideline for Prescribing Opioids for Chronic Pain--United States, 2016.

Authors:  Deborah Dowell; Tamara M Haegerich; Roger Chou
Journal:  JAMA       Date:  2016-04-19       Impact factor: 56.272

View more
  1 in total

1.  Development and multimodal validation of a substance misuse algorithm for referral to treatment using artificial intelligence (SMART-AI): a retrospective deep learning study.

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
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.