Background Automated and data-driven methods for screening using natural language processing (NLP) and machine learning may replace resource-intensive manual approaches in the usual care of patients hospitalized with conditions related to unhealthy substance use. The rigorous evaluation of tools that use artificial intelligence (AI) is necessary to demonstrate effectiveness before system-wide implementation. An NLP tool to use routinely collected data in the electronic health record was previously validated for diagnostic accuracy in a retrospective study for screening unhealthy substance use. Our next step is a noninferiority design incorporated into a research protocol for clinical implementation with prospective evaluation of clinical effectiveness in a large health system. Objective This study aims to provide a study protocol to evaluate health outcomes and the costs and benefits of an AI-driven automated screener compared to manual human screening for unhealthy substance use. Methods A pre-post design is proposed to evaluate 12 months of manual screening followed by 12 months of automated screening across surgical and medical wards at a single medical center. The preintervention period consists of usual care with manual screening by nurses and social workers and referrals to a multidisciplinary Substance Use Intervention Team (SUIT). Facilitated by a NLP pipeline in the postintervention period, clinical notes from the first 24 hours of hospitalization will be processed and scored by a machine learning model, and the SUIT will be similarly alerted to patients who flagged positive for substance misuse. Flowsheets within the electronic health record have been updated to capture rates of interventions for the primary outcome (brief intervention/motivational interviewing, medication-assisted treatment, naloxone dispensing, and referral to outpatient care). Effectiveness in terms of patient outcomes will be determined by noninferior rates of interventions (primary outcome), as well as rates of readmission within 6 months, average time to consult, and discharge rates against medical advice (secondary outcomes) in the postintervention period by a SUIT compared to the preintervention period. A separate analysis will be performed to assess the costs and benefits to the health system by using automated screening. Changes from the pre- to postintervention period will be assessed in covariate-adjusted generalized linear mixed-effects models. Results The study will begin in September 2022. Monthly data monitoring and Data Safety Monitoring Board reporting are scheduled every 6 months throughout the study period. We anticipate reporting final results by June 2025. Conclusions The use of augmented intelligence for clinical decision support is growing with an increasing number of AI tools. We provide a research protocol for prospective evaluation of an automated NLP system for screening unhealthy substance use using a noninferiority design to demonstrate comprehensive screening that may be as effective as manual screening but less costly via automated solutions. Trial Registration ClinicalTrials.gov NCT03833804; https://clinicaltrials.gov/ct2/show/NCT03833804 International Registered Report Identifier (IRRID) DERR1-10.2196/42971
BACKGROUND Automated and data-driven methods for screening using natural language processing (NLP) and machine learning may replace resource-intensive manual approaches in usual care of patients hospitalized with conditions related to unhealthy substance use. Rigorous evaluation of tools that use artificial intelligence (AI) is necessary to demonstrate effectiveness before system-wide implementation. OBJECTIVE To provide a study protocol to evaluate health outcomes and cost-benefit of an AI-driven automated screener compared to manual human screening for unhealthy substance use. METHODS A pre-post design to evaluate 12 months of manual screening followed by 12 months of automated screening across surgical and medical wards in a single medical center. Effectiveness in terms of patient outcomes will be determined by non-inferior rates of interventions (brief intervention/motivational interviewing, medication assisted treatment, naloxone dispensing, referral to outpatient care) in the post-period by a substance use intervention team compared to pre-period. A separate analysis will be performed to assess the cost-benefit to the health system of using automated screening. RESULTS A natural language processing tool to use routinely collected data in the electronic health record was previously validated for diagnostic accuracy in a retrospective study for screening unhealthy substance use. Our next step is a non-inferiority design incorporated into a research protocol for clinical implementation with prospective evaluation of clinical effectiveness in a large health system. The study is approved by the Institutional Review Board and registered at clinicaltrials.gov with a plan for implementation beginning in September 2022. CONCLUSIONS The use of augmented intelligence for clinical decision support is growing with an increasing number of artificial intelligence tools. We provide a research protocol for prospective evaluation of an automated NLP system for screening unhealthy substance use using a non-inferiority design to demonstrate comprehensive screening that may be as effective as manual screening but less costly via automated solutions. CLINICALTRIAL ClinicalTrials.gov NCT03833804
Article Title: Park TW, Saitz R, Ganoczy D, Ilgen MA, Bohnert AS. Benzodiazepine prescribing patterns and deaths from drug overdose among US veterans receiving opioid analgesics: case-cohort study. BMJ. 2015 Jun 10;350:h2698.Background: Deaths from prescription medications, particularly opioids, continue to increase in the USA. In fact, 58 % of all drug-related deaths involved pharmaceuticals, and 75 % of these involved an opioid. There is, however, little data concerning the role that benzodiazepines might play in opiate-related drug deaths.Research Question: The researchers hypothesized that the concurrent use of an opioid and benzodiazepine would be associated with increased deaths from drug-overdose and that this risk would be dose-dependent and vary by type and dosing scheduling of the benzodiazepine.Methods: This was a case-cohort study design where subjects were selected from an established population of veterans receiving opioid prescriptions through the Veterans Health Administration (VHA) between 2004 and 2009. Only those subjects receiving an opioid for acute, chronic, or nonterminal cancer pain were included; those receiving methadone for maintenance purposes, palliative care consultations, or hospice care were excluded. Data were extracted from electronic medical records of VHA patients, prescription data obtained from VHA's Pharmacy Benefits Management Services (PBM; to confirm fulfillment of prescriptions) and the National Death Index (NDI; to establish cause of death). Benzodiazepine and opioid doses were standardized to diazepam and morphine, respectively. Baseline demographic characteristics were compared with χ 2 tests. Death rates were calculated based on history of benzodiazepine use, and the type, dose, and scheduled use of the benzodiazepine. Hazard ratios (HRs) were calculated using Cox proportional hazards model and adjusted for all covariants (e.g., opioid dose).Results: During the study period, 2400 deaths from drug overdose (cases) were identified, and 420,386 subjects (a 5 % random sample of the entire population) served as controls. Among the cases, 1185 (49 %) died during a period when they were prescribed an opioid and benzodiazepine. Among the controls, 112,069 (27 %) were prescribed a benzodiazepine at least once while receiving an opioid. Subjects also receiving a benzodiazepine were more likely to be women (33 % compared to 26 % men), middle aged, white, and living in wealthier zip codes. Additional predictors for a concurrent benzodiazepine prescription included a recent admission for mental health or substance abuse disorder or a diagnosis of psychiatric or substance abuse disorder.Unadjusted rates of death from drug overdose were associated with higher doses of opioids or benzodiazepines and an active prescription for a benzodiazepine.After adjusting for covariants and compared to periods of time when no benzodiazepine was prescribed, the active use of a benzodiazepine (HR 3.96;) and past benzodiazepine prescription (HR 2.33; 95 % CI 2.05-2.64) were both associated with inc...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.