Leveraging observational and prospective data to develop an opioid exposure detection model

Seyed M. Miran, Gregory Boverman, Sara Mariani, Ting Feng, Luoluo Liu, Brian Gross, Daniel McFarlane, Robert Gibson, Anne Marie Kuchinski, Holton Boomer, Dennis Swearingen, Joseph Frassica, Richard B. Schwartz, David P. Noren

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Experimental studies are widely considered as the gold standard for discovering new evidence. However, advances in computational science provide an opportunity to take advantage of large clinical datasets in cases where randomized experiments are not practical. In this study, we used a large clinical database to train a model capable of detecting exposure to opioid medication (AUROC=0.76). We designed and implemented a clinical study to measure the performance of the model against the unseen data from the study. Our results show that the model based on hospital patient data exhibited promising performance against the retrospective clinical study data (AUROC=0.68).

Original languageEnglish (US)
Title of host publication46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350371499
DOIs
StatePublished - 2024
Event46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024 - Orlando, United States
Duration: Jul 15 2024Jul 19 2024

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024
Country/TerritoryUnited States
CityOrlando
Period7/15/247/19/24

Keywords

  • Observational study
  • machine learning model
  • opioid
  • prospective study
  • wearables

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Leveraging observational and prospective data to develop an opioid exposure detection model'. Together they form a unique fingerprint.

Cite this