Biosignatures of opioid addiction treatment success

The United States has experienced a four fold increase in medical opioid use over the last twodecadesMedical opioid abuse and addiction have increased and afflictandof US adultsrespectivelyheroin addiction afflictsof US adultsInandgtUS individuals died ofa medical opioidillicit opiate or synthetic opioid overdosean increase offromWhileopioid addiction treatment admissions and treatment capacity have increased many fold over the lasttwo decadespatient needs greatly exceed capacityMedication assisted treatmentMATapproaches for opioid use disorder include three approvedpharmacotherapies combined with psychosocial and supportive therapiesActive investigations areevaluating established and novel therapies for opioid detoxification prior to MATMATs haveestablished but limited efficacy in treating opioid use disorders compared to placebopharmacotherapyPatients treated with MATs have mortality rates during and after treatment thatexceed population mortality ratesImproving efficacy through personalized treatment is essentialto optimize MAT resources and reduce mortalityBiosignatures of opioid addiction treatment successoffers a data science solution that alignswith NIDA priorities and Institute of MedicineIOMguidance to expand use of MATand with HHSpriorities to support cutting edge research on pain and addictionOur overall aim is to decode thepredictors of MAT success and enable health care providers to improve treatment efficacy usingaccurate forecastingIn Aimwe will create a platform for applying learning algorithms to existing and future opioidaddiction treatment dataWe will organize and merge clinicaltreatmentand outcome variablesfrom clinical trials of opioid addiction treatment publicly available through the NIDA Data ShareresourceWe will import these data into a database optimized for high dimensional data analysisWorkflows will be developed to apply multiple Bayesian learning algorithms to the dataIn Aimusing the biosignature learning platformwe will identify sets of variables that together predictopioid addiction treatment successWe will apply this platform to each trial independentlyandthen to multiple trials in an integrative analysisThe learned biosignatures will be ranked by howwell they predict treatment successThe best models will be incorporated into a proof of concept calculatorThe calculator will provide treatment success scores based on thecharacteristics of new patientsWe will present the prototype to multiple stakeholders forassessmentAt the end of Phase Iwe will have created a biosignature learning platform and a proof of conceptopioid addiction treatment success calculatorWe plan to fully develop these components withadditional datasets and variables in Phase IIOur commercial goal is to develop licensable andeasily deployable algorithms for healthcare networks treating opioid addictionThe algorithm willhelp providers understand profiles of patients likely to be successful with MAT and to personalizetreatment strategies to maximize abstinence In this projectwe are using algorithms to learn the predictors of opioid addiction treatmentsuccess from publicly available clinical trial dataHealthcare providers can use these models toimprove their opioid addiction treatment programs