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 real-world 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.