Conference proceeding
Drug Overdose Vital-Signs Evaluator Using Machine Learning
PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, pp 7358-7366
01 Jan 2024
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Opioid overdose is an escalating global epidemic, affecting 16 million individuals. Lack of overdose detection and slower response times are the leading causes of overdose deaths. During a fatal opioid overdose, the user exhibits motionlessness, lack of breathing, and hypoxemia (oxygen saturation drops). In this paper, we discuss the development of a shoulder-based wearable overdose detection device that monitors hypoxemia, motion, and respiration. The device's design considers the underserved socio-economic population and their psychological contexts. However, conventional approaches to detecting an overdose typically focus on a single biomarker. To address this, we have developed a robust capsule networks based machine learning (ML) model, OxyCaps that integrates oxygen saturation, respiration rate, and motion to classify different levels of hypoxemia. This also helps improve patient adherence by decreasing the chances of false positive alerts. To determine a hypoxemic state, the model considers various features like skin tone, body physiology, motion, and photoplethysmography (PPG) signals. In the absence of realworld opioid overdose data, our research leverages data collected by our device from 19 patients experiencing sleep apnea, exploiting the parallels between overdose and apnea biomarkers. Our dataset provides a novel compilation of raw PPG and motion signals detected from the shoulder. Our model classifies 3 stages of hypoxemia with an average accuracy of 92%, specifically achieving a high recall of 0.98 for the critical hypoxemic state that is crucial in determining an overdose.
Metrics
13 Record Views
Details
- Title
- Drug Overdose Vital-Signs Evaluator Using Machine Learning
- Creators
- Anush Niranjan Lingamoorthy - Drexel UniversityAbhishek Kumar Mishra - Drexel UniversitySuman Kumar - Drexel Univ, Philadelphia, PA 19104 USADavid Gordon - Thomas Jefferson UniversityJacob Brenner - Univ Penn, Philadelphia, PA 19104 USANagarajan Kandasamy - Drexel UniversityAmanda Watson - University of Virginia
- Contributors
- K Larson (Editor)
- Publication Details
- PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, pp 7358-7366
- Publisher
- Association for Computing Machinery
- Number of pages
- 9
- Grant note
- R41DA056276 / NIH/NIDA; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA; NIH National Institute on Drug Abuse (NIDA) Drexel University Coulter Translational Research Partnership Program
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; College of Engineering
- Web of Science ID
- WOS:001347142807056
- Other Identifier
- 991022035263704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Theory & Methods
- Mathematics, Applied