Opioid dependency is devastating for patients and their families. Drug addiction interferes with positive health outcomes for patients being treated for other conditions. Treating addiction is tremendously expensive. This AI solution aims to identify potential drug-seeking behaviour by patients, alert caregivers about patients at risk, improve health outcomes and lower treatment costs.
This tool AI tool helps clinicians identify patients at high risk for opioid use disorder and overdose. The tool uses data from patients’ electronic medical records to guide clinicians in safely and effectively prescribing opioid medications.
One can identify common characteristics of typical drug-seekers by examining three sources of information: the patient’s diseases and conditions as recorded in EMR, the types of drugs that historically had been prescribed to the patient and the behaviours and symptoms exhibited due to each type of drug. The solution not only identifies patient behaviours and symptoms but examines the physician’s notes. It combines phase-based extraction, and advanced text clustering to mine data to identify patients who could become drug-seekers before they turn into addicts, thus improving patient care and lowering healthcare costs and burden.
This solution is powered by the H2O AI Cloud Driverless AI AutoML, H2O-3, and H2O.ai Wave. The data science approaches include genetic algorithm, advanced feature engineering, classification, NLP, GLM, GBM, XGBoost, ensemble stacking, and various machine learning interpretability algorithms.