Predicting Risk of Heroin Overdose, Remission, Use, and Mortality Using Ensemble Learning Methods in a Cohort of People with Heroin Dependence

IF 3.2 3区医学 Q2 PSYCHIATRY International Journal of Mental Health and Addiction Pub Date : 2024-02-26 DOI:10.1007/s11469-024-01257-5

{"title":"Predicting Risk of Heroin Overdose, Remission, Use, and Mortality Using Ensemble Learning Methods in a Cohort of People with Heroin Dependence","authors":"","doi":"10.1007/s11469-024-01257-5","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> Despite decades of research demonstrating the effectiveness of treatments for heroin dependence, rates of heroin use, dependence, and death have dramatically increased over the past decade. While evidence has highlighted a range of risk and protective factors for relapse, remission, and other outcomes, this presents clinicians with the challenge as to how to synthesise and integrate the evolving evidence-base to guide clinical decision-making and facilitate the provision of personalised healthcare. Using data from the 11-year follow-up of the Australian Treatment Outcome Study (ATOS), we aimed to develop a clinical risk prediction model to assist clinicians calculate the risk of a range of heroin-related outcomes at varying follow-up intervals for their clients based on known risk factors. Between 2001 and 2002, 615 people with heroin dependence were recruited as part of a prospective longitudinal cohort study. An ensemble machine learning approach was applied to predict risk of heroin use, remission, overdose, and mortality at 1-, 5-, and 10 + year post-study entry. Variables most consistently ranked in the top 10 in terms of their level of importance across outcomes included age; age first got high, used heroin, or injected; sexual trauma; years of school completed; prison history; severe mental health disability; past month criminal involvement; and past month benzodiazepine use. This study provides clinically relevant information on key risk factors associated with heroin use, remission, non-fatal overdose, and mortality among people with heroin dependence, to help guide clinical decision-making in the selection and tailoring of interventions to ensure that the ‘right treatment’ is delivered to the ‘right person’ at the ‘right time’.","PeriodicalId":14083,"journal":{"name":"International Journal of Mental Health and Addiction","volume":"16 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Mental Health and Addiction","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11469-024-01257-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

Abstract

Despite decades of research demonstrating the effectiveness of treatments for heroin dependence, rates of heroin use, dependence, and death have dramatically increased over the past decade. While evidence has highlighted a range of risk and protective factors for relapse, remission, and other outcomes, this presents clinicians with the challenge as to how to synthesise and integrate the evolving evidence-base to guide clinical decision-making and facilitate the provision of personalised healthcare. Using data from the 11-year follow-up of the Australian Treatment Outcome Study (ATOS), we aimed to develop a clinical risk prediction model to assist clinicians calculate the risk of a range of heroin-related outcomes at varying follow-up intervals for their clients based on known risk factors. Between 2001 and 2002, 615 people with heroin dependence were recruited as part of a prospective longitudinal cohort study. An ensemble machine learning approach was applied to predict risk of heroin use, remission, overdose, and mortality at 1-, 5-, and 10 + year post-study entry. Variables most consistently ranked in the top 10 in terms of their level of importance across outcomes included age; age first got high, used heroin, or injected; sexual trauma; years of school completed; prison history; severe mental health disability; past month criminal involvement; and past month benzodiazepine use. This study provides clinically relevant information on key risk factors associated with heroin use, remission, non-fatal overdose, and mortality among people with heroin dependence, to help guide clinical decision-making in the selection and tailoring of interventions to ensure that the ‘right treatment’ is delivered to the ‘right person’ at the ‘right time’.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

在海洛因依赖者队列中使用集合学习方法预测海洛因过量、缓解、使用和死亡风险

摘要尽管数十年来的研究证明了治疗海洛因依赖的有效性，但在过去十年中，海洛因的使用率、依赖率和死亡率却急剧上升。虽然有证据强调了复吸、缓解和其他结果的一系列风险和保护因素，但这给临床医生带来了挑战，即如何综合和整合不断发展的证据基础，以指导临床决策并促进提供个性化的医疗保健服务。利用澳大利亚治疗结果研究（ATOS）11 年的随访数据，我们旨在开发一个临床风险预测模型，以帮助临床医生根据已知的风险因素，计算客户在不同随访间隔期内出现一系列海洛因相关结果的风险。在 2001 年至 2002 年期间，作为前瞻性纵向队列研究的一部分，我们招募了 615 名海洛因依赖者。研究采用了一种集合机器学习方法来预测海洛因使用、缓解、用药过量的风险，以及进入研究后 1 年、5 年和 10 年以上的死亡率。在各种结果中，最重要的变量一直排在前 10 位，包括年龄；首次嗑药、使用海洛因或注射的年龄；性创伤；完成学业的年数；监狱服刑史；严重精神残疾；过去一个月的犯罪记录；以及过去一个月苯二氮卓的使用情况。这项研究提供了与海洛因依赖者使用海洛因、病情缓解、非致命性用药过量和死亡率相关的关键风险因素的临床相关信息，有助于指导临床决策，选择和调整干预措施，确保在 "正确的时间 "向 "正确的人 "提供 "正确的治疗"。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

International Journal of Mental Health and Addiction SUBSTANCE ABUSE-PSYCHIATRY

CiteScore

15.90

自引率

2.50%

发文量

245

审稿时长

6-12 weeks

期刊介绍： The International Journal of Mental Health and Addictions (IJMH) is a publication that specializes in presenting the latest research, policies, causes, literature reviews, prevention, and treatment of mental health and addiction-related topics. It focuses on mental health, substance addictions, behavioral addictions, as well as concurrent mental health and addictive disorders. By publishing peer-reviewed articles of high quality, the journal aims to spark an international discussion on issues related to mental health and addiction and to offer valuable insights into how these conditions impact individuals, families, and societies. The journal covers a wide range of fields, including psychology, sociology, anthropology, criminology, public health, psychiatry, history, and law. It publishes various types of articles, including feature articles, review articles, clinical notes, research notes, letters to the editor, and commentaries. The journal is published six times a year.