Machine Learning for Precision Treatments in Schizophrenia

机器学习用于精神分裂症的精准治疗

• 批准号: 10591784
• 负责人: Natalie Bareis
• 金额: $ 19.55万
• 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: 2022
• 资助国家: 美国
• 起止时间: 2022-09-05 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10591784
• 关键词: Address; Age; Antipsychotic Agents; Anxiety; Characteristics; Clinical; Clinical Data; Clinical Research; Clinical Treatment; Clinical Trials; Code; Cognition; Combined Modality Therapy; Community Practice; Complex; Consensus; Data; Data Science; Data Set; Databases; Demographic Factors; Diabetes Mellitus; Diagnosis; Diagnostic; Diagnostic tests; Dose; Early treatment; Effectiveness; Electronic Health Record; Emergency department visit; Equilibrium; Evidence based practice; Goals; Hospitals; Impairment; Incidence; Individual; Informatics; International; K-Series Research Career Programs; Knowledge; Laboratories; Machine Learning; Medicaid; Medical; Mental Depression; Mental disorders; Methods; Modeling; New York; Outcome; Patient-Focused Outcomes; Patients; Pattern; Pharmaceutical Preparations; Pharmacoepidemiology; Population; Precision therapeutics; Presbyterian Church; Procedures; Psychiatry; Randomized; Randomized Clinical Trials; Records; Regimen; Relapse; Research; Research Design; Research Training; Sampling; Schizophrenia; Scoring Method; Services; Standardization; Symptoms; Techniques; Testing; Time; To specify; Training; Translating; Treatment Effectiveness; Treatment Protocols; adjudicate; adverse outcome; affective disturbance; associated symptom; base; burden of illness; clinical practice; clinically relevant; comorbidity; comparative effectiveness; comparative effectiveness study; compare effectiveness; data quality; disability; effective therapy; effectiveness testing; first episode psychosis; functional disability; health data; hospital readmission; improved; individualized medicine; information model; innovation; machine learning algorithm; machine learning method; network informatics; novel; outcome prediction; patient oriented; person centered; personalized medicine; predict clinical outcome; psychiatric emergency; psychosocial; psychotic symptoms; residence; response; sex; social; societal costs; supervised learning; tool; treatment effect; treatment guidelines; unsupervised learning

Project Summary/Abstract Schizophrenia is associated with psychotic symptoms, mood disturbances, deficits in cognition, comorbidities, significant social and functional impairment and is a leading cause of disability in the U.S. and worldwide. Although antipsychotic medications and psychosocial treatments are effective for some symptoms of schizophrenia, effective regimens for all symptoms are not established. The primary limitation of treatment guidelines is reliance on RCTs that test limited treatments and their effects on few symptoms and comorbidities. Trials of treatments administered to address all aspects of impairment is prohibitively complex. Data driven machine learning (ML) can address this gap using large observational datasets with information about complex and effective regimens used in real-world practice. ML can cluster individuals with shared characteristics and identify unique regimens administered for their psychiatric and clinical comorbidities. These new treatment regimens are possible precision treatments. ML algorithms can then predict critical patient-centered outcomes for these different clusters (or classes) administered these treatment regimens. Examining the comparative effectiveness of these treatment regimens that predict critical outcomes is an essential next step. Unique pharmacoepidemiologic methods with observational data can simulate clinical trials. Propensity score methods address confounding, mimicking balance achieved by randomization in RCTs. These tools will determine which precision treatment regimens are the most effective for the classes in these datasets. Relevance of ML findings depends on data quality. Claims have the largest, most nationally representative samples reflecting real-world community practice patterns but use billing codes not originally designed for research. Electronic health records (EHR) are extensive but limited due to bias from incomplete records with uncertain accuracy and complexity due to their granular level of detail. This proposal will establish the strengths and limitations of these dataset types by conducting ML analyses on exemplar datasets, a Medicaid Analytic eXtract (MAX) national sample, and the Observational Health Data Sciences and Informatics (OHDSI) network New York-Presbyterian Hospital (iNYP) EHR. An enhancement to this project will compare more traditional multivariate and regression techniques to the ML findings identifying whether ML provides additional information. To address the “research-practice” gap the ML results will be translated into personalized treatment rules to inform clinical practice for schizophrenia treatment. After training in unsupervised and supervised learning in Training Aims A and B, Research Aim 1 will identify classes and their administered treatments in the datasets and Research Aim 2 will predict outcomes of those treatments: time to emergency department visit, time to re-admission and incidence of comorbidities. Research Aim 3 will use pharmacoepidemiologic methods learned in Training Aim C to compare effectiveness of the treatments, supporting an R01 submitted at the end of this K-award to test effectiveness in an international EHR dataset.

项目摘要/摘要精神分裂症与精神病症状、情绪障碍、 认知缺陷、合并症、严重的社交和功能障碍，是导致 在美国和世界范围内的残疾。虽然抗精神病药物和心理社会治疗是 对精神分裂症的某些症状有效，但对所有症状都有效的治疗方案尚未建立。的 治疗指南的主要局限性是依赖于RCT，这些RCT测试了有限的治疗方法及其对 很少有症状和合并症。针对损伤各方面的治疗试验是 过于复杂数据驱动的机器学习（ML）可以使用大规模的观测数据来解决这一差距。 数据集，其中包含有关实际实践中使用的复杂和有效方案的信息。ML可以集群 具有共同特征的个体，并确定针对其精神病和 临床合并症。这些新的治疗方案是可能的精确治疗。ML算法可以 然后预测这些不同的集群（或类）管理这些关键的以患者为中心的结果， 治疗方案。检查这些治疗方案的比较有效性， 成果是下一个重要步骤。具有观察数据的独特药物流行病学方法可以 模拟临床试验。倾向评分方法解决了混淆问题，模拟了通过以下方式实现的平衡： 随机对照试验。这些工具将决定哪种精准治疗方案最有效 这些数据集中的类。ML结果的相关性取决于数据质量。索赔额最大， 大多数具有全国代表性的样本反映了真实世界的社区实践模式，但使用计费代码 不是为研究而设计的电子健康记录（EHR）是广泛的，但由于偏见而受到限制。 不完整的记录，由于其粒度级别的细节而具有不确定的准确性和复杂性。这项建议 我将通过对样本进行ML分析来确定这些数据集类型的优势和局限性 数据集，Medicaid Analytic eXtract（MAX）国家样本，以及观察性健康数据科学， 信息学（OHDSI）网络纽约长老会医院（iNYP）EHR。对该项目的增强将 将更传统的多变量和回归技术与ML结果进行比较，以确定ML是否 提供了其他信息。为了解决“研究-实践”的差距，ML结果将被转化为 个性化治疗规则，为精神分裂症治疗的临床实践提供信息。训练后 训练目标A和B中的无监督和监督学习，研究目标1将识别类及其 研究目标2将预测这些治疗的结果： 急诊就诊、再入院时间和合并症发生率。研究目标3将使用 在培训目标C中学习的药物流行病学方法，以比较治疗的有效性， 支持在K奖结束时提交的R 01，以测试国际EHR数据集的有效性。