Real time relapse risk scoring for Opioid Use Disorder (OUD) from clinical trial datasets

根据临床试验数据集对阿片类药物使用障碍 (OUD) 进行实时复发风险评分

• 批准号: 10585452
• 负责人: Ying Liu
• 金额: $ 68.34万
• 依托单位: NEW YORK STATE PSYCHIATRIC INSTITUTE DBA RESEARCH FOUNDATION FOR MENTAL HYGIENE, INC
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-01 至 2028-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10585452
• 关键词: Address; Administrator; Alcohols; Algorithms; Back; Behavior; Behavioral; Big Data Methods; Clinic; Clinical; Clinical Data; Clinical Trials; Clinical Trials Network; Complex; Computer software; Conduct Clinical Trials; Data; Data Science; Data Set; Data Sources; Development; Dimensions; Disease model; Dose; Drug Screening; Drug abuse; Drug usage; Enrollment; Evaluation; Foundations; Frequencies; Future; Goals; Individual; Intervention; Intuition; Learning; Length; Linear Models; Measures; Methodology; Methods; Modeling; Nicotine; Online Systems; Outcome; Outpatients; Participant; Patient Self-Report; Patients; Pattern; Pharmaceutical Preparations; Pharmacotherapy; Play; Pragmatic clinical trial; Principal Component Analysis; Procedures; Questionnaires; Records; Relapse; Reporting; Research; Research Personnel; Risk; Risk Assessment; Risk Estimate; Role; Sampling; Scoring Method; Series; Shapes; Site; Standardization; Stream; Substance Use Disorder; Substance of Abuse; Surveys; System; Testing; Time; Toxicology; Urine; Validation; Visualization; Work; adaptive intervention; addiction; algorithmic bias; autoencoder; automated analysis; behavioral outcome; care delivery; clinical application; clinical decision support; clinical decision-making; computer framework; data harmonization; data standards; data streams; data structure; disorder risk; generative adversarial network; high dimensionality; improved; individualized medicine; interest; learning strategy; longitudinal dataset; machine learning classification; machine learning method; opioid use disorder; polysubstance use; predictive modeling; prototype; relapse risk; statistical and machine learning; substance use; supervised learning; timeline; usability; user friendly software; web portal

Real time relapse risk scoring for Opioid Use Disorder (OUD) from clinical trial datasets Project Summary Any clinician treating a patient with Opioid Use Disorder (OUD) would like to know whether this patient would relapse in the next week or month. Such a score, analogous to a credit score in consumer finance, may be similarly obtained from longitudinal data streams derived from patient behavior during SUD treatment. There are several common data sources that every OUD patient in treatment produces: a binary, longitudinal data survey of use patterns for a set of pre-determined substances of abuse, treatment session attendance records, and medication records. In particular, urine drug screens (UDS) or alcohol and nicotine breathalyzers and standard Timeline Follow Back (TLFB) questionnaires are universal surveys in every treatment delivery context, including large pragmatic clinical trials. While these data streams are incomplete, of different lengths and sampling frequencies, and correlate in complex ways, contemporary machine learning methods allow us to overcome these challenges. We aim to build a toolbox that would allow for the following: 1) standardized methods for risk scoring and visualization from UDS and TLFB datasets in existing large clinical trials; 2) standard methods for inferences of risk scores: procedure for hypothesis testing whether an intervention made a difference in the risk scores and their trajectories. 3) user-friendly software modules aimed toward researchers and administrators for quality improvement projects and customized predictive modeling pipelines, and interpretable web portal for clinicians, analogous to a credit report. This proposal will also incorporate usability survey and evaluation for algorithmic bias. These applications will provide a computational framework for future real time predictive modeling work for many other different substance use disorders.

来自临床试验数据集的阿片类药物使用障碍（OUD）的真实的复发风险评分 项目摘要 任何治疗阿片类药物使用障碍（OUD）患者的临床医生都想知道该患者是否会 在接下来的一周或一个月内复发。类似于消费者金融中的信用评分，这样的评分可以是 类似地从从SUD治疗期间患者行为导出的纵向数据流获得。那里 是每个OUD患者在治疗中产生的几个常见数据源： 一套预先确定的滥用物质的使用模式调查，治疗会议出席记录， 和用药记录特别是，尿液药物筛查（UDS）或酒精和尼古丁呼气测醉器， 标准时间轴随访（TLFB）问卷是每次治疗实施中的通用调查 背景，包括大型实用临床试验。虽然这些数据流是不完整的，长度不同， 和采样频率，并以复杂的方式相互关联，当代机器学习方法使我们能够 克服这些挑战。我们的目标是建立一个工具箱，将允许：1）标准化 现有大型临床试验中UDS和TLFB数据集的风险评分和可视化方法; 2） 风险评分推断的标准方法：假设检验是否进行干预的程序 风险分数和轨迹的差异。3)用户友好的软件模块， 质量改进项目和定制预测建模管道的研究人员和管理人员， 和临床医生的可解释的网络门户，类似于信用报告。该提案还将纳入 算法偏差的可用性调查和评估。这些应用程序将提供一个计算框架 用于未来真实的时间预测建模工作，用于许多其他不同的物质使用障碍。