Substance Misuse Algorithm for Referral to Treatment Using Artificial Intelligence (SMART-AI): Multi-Modal Validation with Interpretation and Bias Assessment
Majid AfsharBrihat SharmaDmitriy DligachMadeline OgussRandall BrownNeeraj ChhabraHale M. ThompsonTalar MarkossianCara JoyceMatthew M. ChurpekNiranjan S. Karnik
2
Citation
36
Reference
10
Related Paper
Citation Trend
Abstract:
Background: Substance misuse is a heterogeneous and complex set of behavioral conditions that are highly prevalent in hospital settings and frequently co-occur. Few solutions exist to comprehensively and reliably identify these conditions hospital-wide to prioritize care and guide treatment. The aim is apply natural language processing (NLP) to admission notes in the electronic health record (EHR) to accurately screen for substance misuse.Methods: The reference dataset was derived from a hospital-wide program that used structured diagnostic interviews to manually screen admitted patients over 26 months (n=54,915). Temporal validation was provided over the subsequent 12 months (n=16,917) and external validation at a separate health system (n=1,991). The Alcohol Use Disorder Identification Test and Drug Abuse Screening Tool served as reference standards. The first 24 hours of notes in the EHR were mapped to standardized medical vocabulary and fed into neural network models. The primary outcome was discrimination for alcohol misuse, opioid misuse, or non-opioid drug misuse. Discrimination was assessed by the area under the receiver operating curve (AUROC).Findings: The model was trained on a cohort that had 3.5% (n=1,921) with any type of substance misuse. Nearly 11% of patients with substance misuse had more than one type of misuse. The multi-label convolutional neural network classifier had an average AUROC of 0.97 (95% CI: 0.96, 0.98) during temporal validation for all types of substance misuse. The model was well calibrated and demonstrated good face validity with model features containing explicit mentions of aberrant drug-taking behavior. The false-negative and false-positive rates were similar between non-Hispanic Black and non-Hispanic White groups. In external validation, the AUROC for alcohol and opioid misuse remained above 0.85.Interpretation: We developed a novel and accurate approach to leveraging the first 24 hours of EHR notes for screening multiple types of substance misuse.Funding Information: Research reported in this publication was supported by the National Institute On Drug Abuse of the National Institutes of Health under Award Numbers R01-DA051464 (MA), K23-AA024503 (MA), UL1-TR002389 (NK), KL2-TR002387 (NK), R01-DA041071 (NK), UG1-DA049467 (NK), R01-LM010090 (DD), R01-LM012973 (DD), K12-HS-026385 (HT), and R01-GM123193 (MMC).Declaration of Interests: Dr. Churpek has a patent pending (ARCD. P0535US.P2) for risk stratification algorithms for hospitalized patients, and has received research support from EarlySense (Tel Aviv, Israel). All other authors have nothing to declare. Ethics Approval Statement: This study was approved by the Institutional Review Board at RUMC and LUMC.No abstract available.
Cite
Citations (2)
To describe the general practitioners referral patterns. There is special emphasis in the delay between the referral and the first consultation with the specialist. Also we consider other aspects of the coordination between both levels of care.Cross-sectional study upon 8.095 referrals from 242 spanish doctors.The referral rate was 6.63%, higher in the 15-44 age group and also for men. We find a huge variability in the referral rates among doctors. The referral rates are higher to surgical specialties. The mean delay between referral and specialist appointment was 11 days. The general practitioners didn't receive communication from the specialists in 23.5 of the referrals.A considerable range of referral rates has been identified. There is a poor continuity and coordination in the patient care.
Patient referral
Cite
Citations (12)
Background. In Saudi Arabia, the mortality of diabetes is currently reported at 6%. A well-administered referral system is crucial in aiding the management of this disease. Method. A single reviewer employed a systematic approach to searching the literature databases with regard to the question: what are the attributes of referral systems in Saudi Arabia for patients with type 2 diabetes (T2D)? The results were analysed in order to provide recommendations to improve the Saudi health system. Results. Twelve primary studies were identified from a systematic search. Overall, the 12 studies did not clearly mention any of the factors of a good referral system. The referral problems identified by this study included patients’ unnecessary requests for referral, unstructured referral letters, and unclear dissemination guidelines for referral. Conclusions. This research attempted to identify the efficiency of the referral processes that were implemented for patients with T2D. The majority of the included studies were completely silent on the main referral factors for patients. If this review is representative of the referral system in Saudi Arabia, then, in the context of T2D, current referrals are unsafe. Further research on the quality of the referral system, taking into account at least some of the WHO referral guidelines, is required.
Cite
Citations (18)
Objective To explore and discuss contradictions and problems existing in the two-way referral system through analyzing the situation of patients' referral between Sichuan Provincial People's Hospital and 21 community health service centers in Chengdu,and propose measures and methods to further improve the two-way referral system.Methods Totally 3652 patients required referral from April 2010 to March 2011(2 635 patients from the hospital to community medical service centers and 1017 in a opposite direction) were selected.The reasons for referral and the factors for successful and unsuccessful referral were analyzed.The on-site interviews were conducted among doctors,department directors,and medical administrators from both the hospital and the centers.The talking topics included the design of bi-directional referral system,policy support from the government,current status of two-way referral and the main factors restricting the implementation of bi-directional referral system.Results Among the 2635 patients needed to have a referral from the hospital to centers(downward referral) for rehabilitation only 50 were successfully transferred,with a successful referral ratio of 52.7∶ 1.However,concurrently 1017 patients were transferred from the 21 centers to the hospital(upward referral).The ratio of upward referral to downward referral was 20.3∶ 1.There are a total of 1623 beds in all the 21 centers,however,the average utilization rate of beds was only 70.65%,as contrasted with that of 112.35% in the hospital.Majority of the interviewers believed that the factors impacting the implementation of two-way referral included un-smooth communication of medical information,no criteria and process of referral so far,shortage of mutual trust between the two referral parties,and non-full consideration of the two-way referral factors by the medical authorities in formulating the local health plan.Conclusion Although the two-way referral system has been implemented in Chengdu area,the rate of successful transfer is still lower,especially for the patients needing downward referral.
Cite
Citations (2)
article Free Access Share on Remarks on Algorithm 332: Jacobi polynomials: Algorithm 344: student's t-distribution: Algorithm 351: modified Romberg quadrature: Algorithm 359: factoral analysis of variance Author: Arthur H. J. Sale Univ. of Sydney, Sydney, Australia Univ. of Sydney, Sydney, AustraliaView Profile Authors Info & Claims Communications of the ACMVolume 13Issue 7July 1970 https://doi.org/10.1145/362686.362700Published:01 July 1970Publication History 0citation275DownloadsMetricsTotal Citations0Total Downloads275Last 12 Months10Last 6 weeks3 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF
Quadrature (astronomy)
Cite
Citations (0)
Referral rates and urgency of referral to hospital by six pairs of trainers and trainees were compared over one month in 1986. From 5846 consultations, 327 resulted in referral to hospital. Overall, the referral rates was low at 5.6 per 100 consultations; however, there was considerable variation in individual referral rates with trainees tending to follow their trainer's referral patterns, despite statistical adjustment for sharing the same practice. This paper critically examines the wisdom of using general practitioner referral rates for the purpose of resource allocation and education.
Trainer
Cite
Citations (14)
OBJECTIVES--To determine the extent to which variation in rates of referral among general practitioners may be explained by inappropriate referrals and to estimate the effect of implementing referral guidelines. SETTING--Practices within Cambridge Health Authority and Addenbrooke9s Hospital, Cambridge. MAIN OUTCOME MEASURES--Data on practice referral rates from hospital computers, inappropriate referrals as judged by hospital consultants, and inappropriate referrals as judged against referral guidelines which had been developed locally between general practitioners and specialists. Effect of referral guidelines on referral patterns as judged by general practitioners using the guidelines in clinical practice. RESULTS--There was 2.5-fold variation in referral rates among general practices. According to the specialists, 9.6% (95% confidence interval 6.4% to 12.9%) of referrals by general practitioners and 8.9% (2.6% to 15.2%) of referrals from other specialists were judged possibly or definitely inappropriate. Against locally determined referral guidelines 15.9% of referrals by general practitioners were judged possibly inappropriate (11.8% to 20.0%). Elimination of all possibly inappropriate referrals could reduce variation in practice referral rates only from 2.5-fold to 2.1-fold. An estimate of the effect of using referral guidelines for 60 common conditions in routine general practice suggested that application of guidelines would have been unlikely to reduce rates of referral in hospital (95% confidence interval -4.5% to 8.6% of consultations resulting in referral). CONCLUSION--The variation in referral rates among general practitioners in Cambridge could not be explained by inappropriate referrals. Application of referral guidelines would be unlikely to reduce the number of patients referred to hospital.
Variation (astronomy)
Cite
Citations (106)
Objective To understand the present situation of medical referral in community health service (CHS) institutions of Beijing and the demands for referral criteria.Methods A questionnaire survey was conduced among trainees of training program for key general practitioners form CHS institutions in Beijing.Results The present situation of referral was unsatisfactory;with a lower referral rate.The major problems were unsmooth referral channel between the higher level hospital and CHS institutions,more up-referral from CHS institutions to higher-level hospital,and no unified referral criteria.General practitioners had an urgent demand for referral criteria.Conclusion In order to improve the two-way referral system,the referral guidelines and referral indicators or main symptoms of diseases for CHS institutions should be made as soon as possible.
Cite
Citations (0)
Objective: To explore the implementation and nursing experience of community two-way referral system.Methods: The referral rate and readmission rates of 240 cases patients were analyzed and discussed before and after the community two-way referral system,then gave the advice according to the results.Results: The referral rate of the patients after the community two-way referral system was 68.3%(82/120),which was higher than the rate before 30.8%(37/120),there was a significant difference between them(P0.01).The readmission rate also reduced after the community two-way referral system with it was from 63.7% to 22.1%.Conclusion: The performance of community two-way referral system is in favor of utilizing the medical resources reasonably.Meanwhile,it is benefit for the development of community hospital.
Community hospital
Cite
Citations (0)
Maqasidi interpretation discourse as a form of response methodology of interpretation to the current situation faced. This response is considered as one of the efforts to synchronize religious teachings to the development and interpretation as well as social society. The explanation in this paper is descriptive as an effort to understand the existence as a maqasidi interpretation in the modern era. This means that maqasidi interpretation as a modern interpretation performs the construction of works of past or classical interpretation using interpretive methods that have developed in contemporary times.
Cite
Citations (4)