Increasingly, Artificial Intelligence (AI) is used in health care. Chatbot systems based on AI can act as automated conversational agents capable of promoting health, providing education, and potentially promoting behavioral change, particularly in the case of opioid use during pregnancy. To forecast take-up, exploring the incentive to use health chatbots is necessary; however, few studies to date have explored their acceptability. The experiences, inspiration and skills of patients must be taken into account in the creation and assessment of health chatbots ‘ efficacy1)
The integration of all kinds of information and high-level simulation of structures are important topics for specific AI in medicine study. In addition, it is also very important to make good use of expertise in developing decision-making tools and extracting details from the results. In this respect, the area of intelligent data analysis appears important. Because AI in medical applications today varies from molecular medicine to organizational modeling2).
Different platforms use the AI approaches in this regard, like, Q2i offers services to support Opioid Use Disorder (OUD) and Drug Use Disorder treatment professionals. Q2i devices, which include a platform for clinical professionals and a mobile app for patients, promote patient care progress by assisting patients with their treatment plans by improved communication and exchange of information with their healthcare teams3).
SABLE SPEAR is a mass data processing platform primarily designed to collect knowledge on foreign sources and people associated with the synthetic opioid industry, utilizing machine learning to absorb large datasets of publicly available information to identify signs of criminal or suspicious activity4).
Already there are companies seeking to use artificial intelligence (AI), some using machine learning (ML), hoping to help solve opioid use disorder problem or mitigate its effect at least5). Machine learning tools could offer effective risk stratification capabilities for providers attempting to prevent opioid overdoses. A machine learning tool developed by researchers at the University of Florida, University of Pittsburgh, Carnegie Mellon University, and the University of Utah was able to use administrative data to stratify Medicare patients into risk-based subgroups, allowing providers to focus their resources on higher-risk individuals6).
AI applications in this space appear to be focused on prevention of new overdoses or incidences of misuse by identifying patterns in opioid users both in and outside of addiction treatment7). To better understand the biomedical profile of opioid-dependent patients, it is analyzed information from electronic health records (EHR) including lab tests, vital signs, medical procedures, prescriptions, and other data from millions of patients to predict opioid substance dependence8).
Another way of using AI and machine learning is the retail store Target created a predictive model for pregnancy to determine if their customers were pregnant based on their buying background. Nevertheless, the complexity and implementation of AI technology enables the extrapolation of confidential medical or psychological knowledge utilizing out – of-domain evidence such as actions in social media. Knowing how AI systems work requires a significant level of education and familiarity with the application of analytics and AI. Such problems include the processing, storage and distribution of data as well as the use of data by computer or analytics and how a specific AI system communicates with the environment. Due to the human-focused design of many AI systems, the ethical principles built in medical and biological research provide good reference points for ethical appraisal in AI9).
We are sorry that this post was not useful for you!
Let us improve this post!
Tell us how we can improve this post?
References [ + ]
|1.||↑||Patel, V. L. et al. The coming of age of artificial intelligence in medicine. Artif. Intell. Med. 46, 5–17 (2009).|
|3.||↑||Defense Intelligence Agency uses artificial intelligence to confront o. Defense Intelligence Agency https://www.dia.mil/News/Articles/Article-View/Article/1942872/defense-intelligence-agency-uses-artificial-intelligence-to-confront-opioid-cri/.|
|4.||↑||Artificial Intelligence Can be Leveraged to Minimize Casualties of the Opioid Epidemic. Pharmacy Times https://www.pharmacytimes.com/news/artificial-intelligence-can-be-leveraged-to-minimize-casualties-of-the-opioid-epidemic.|
|5.||↑||HealthITAnalytics. Machine Learning Proves Effective for Opioid Risk Stratification. HealthITAnalytics https://healthitanalytics.com/news/machine-learning-proves-effective-for-opioid-risk-stratification (2019).|
|6.||↑||Sennaar, K. Artificial Intelligence and the Opioid Epidemic – Applications for Relapse Treatment, Abuse Prevention, and More. Emerj https://emerj.com/ai-sector-overviews/artificial-intelligence-opioid-epidemic/.|
|7.||↑||Ellis, R. J., Wang, Z., Genes, N. & Ma’ayan, A. Predicting opioid dependence from electronic health records with machine learning. BioData Min. 12, 3 (2019).|
|8.||↑||Mohan, D. et al. Use of Big Data and Machine Learning Methods in the Monitoring and Evaluation of Digital Health Programs in India: An Exploratory Protocol. JMIR Res. Protoc. 8, e11456 (2019).|
|9.||↑||Guiding the Ethics of Artificial Intelligence. RTI https://www.rti.org/insights/guiding-ethics-artificial-intelligence (2019).|