Popis: |
BACKGROUND Opioid Use Disorder (OUD) is an addiction crisis in the United States. As recent as 2019, more than 10 million people have misused or abused prescription opioids making OUD one of the leading causes of accidental death in the U.S. Workforces that are physically demanding and laborious such as transportation, construction, and extraction, and health care workers, are prime targets for OUD. The results of opioid misuse in the U.S. have been elevated workers' compensation and health insurance costs, absenteeism, and lost productivity. OBJECTIVE With the emergence of new smartphone technologies, health interventions can be widely utilized outside the clinical settings via mobile health (mHealth) tools. We developed a smartphone application (App) to track work-related risk factors and assess an individual's OUD risk. METHODS Traditionally, the assessment of OUD solely depends on patients' and caregivers' physical presence. However, to make it more convenient and motivate potential OUD patients, a smartphone-based App was developed. An extensive literature survey listed some critical questionaries vital for assessing possible interventions used in the App. The user will provide responses to the questionaries, and based on their responses, an artificial intelligence algorithm Naïve Bayes will determine the risk of OUD. The algorithm will get trained with the response from the user and then predict the risk of OUD. RESULTS The smartphone App we have developed is functioning and deployed. Each patient's response is recorded in a secure database in the cloud. All responses are used as training data for the Naïve Bayes algorithm. After completing the training, the Naïve Bayes algorithm is able to predict the risk of OUD successfully. CONCLUSIONS The current trend indicates that utilization of mHhealth techniques, such as a mobile App, is favorable in predicting and offering mitigation plans for disease detection and prevention. Amidst the ever-increasing opioid epidemic, utilizing such tools can offer tailored mitigation strategies to communities that OUD most impacts. |