Logo image
Drug Overdose Vital-Signs Evaluator Using Machine Learning
Conference proceeding

Drug Overdose Vital-Signs Evaluator Using Machine Learning

Anush Niranjan Lingamoorthy, Abhishek Kumar Mishra, Suman Kumar, David Gordon, Jacob Brenner, Nagarajan Kandasamy and Amanda Watson
PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, pp 7358-7366
01 Jan 2024
url
https://doi.org/10.24963/ijcai.2024/814View
Published, Version of Record (VoR) Open

Abstract

Computer Science, Artificial Intelligence Computer Science, Theory & Methods Mathematics, Applied Science & Technology Computer Science Mathematics Physical Sciences Technology
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

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

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
Logo image