Clinical Phenotyping for Prediction of Retention in HIV Care

用于预测 HIV 护理保留的临床表型

• 批准号: 10762595
• 负责人: Anoop Mayampurath
• 金额: $ 45.24万
• 依托单位: UNIVERSITY OF CHICAGO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-05 至 2025-09-04
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10762595
• 关键词: Address; Calibration; Caring; Characteristics; Child Care; Clinic; Clinical; Compensation; Complex; Computerized Medical Record; Data; Diagnosis; Drops; Early Diagnosis; Early Intervention; Epidemic; Face; Future; Grant; HIV; Individual; Injecting drug user; Intervention; Intuition; Laboratories; Life; Logistic Regressions; Machine Learning; Measures; Medical; Modeling; Natural Language Processing; Patient Care; Patient risk; Patients; Pattern; Performance; Persons; Phenotype; Physicians; Population Heterogeneity; Predictive Factor; Predictive Value; Prevalence; Prevention; Provider; Psychosocial Factor; Resolution; Resources; Risk; Site; Social support; Specificity; Subgroup; Substance abuse problem; Techniques; Testing; Text; Time; United States; Work; analytical method; antiretroviral therapy; black men who have sex with men; cis-female; clinical phenotype; cohort; electronic health data; electronic structure; follow-up; housing instability; improved; machine learning model; mortality; patient subsets; predictive modeling; prospective; random forest; risk prediction; social stigma; social structure; stressor; transmission process

Retention in care is essential to HIV treatment and prevention, yet only half of people with HIV in the U.S. are retained in medical care. Improving retention is critical for ending the HIV epidemic in the U.S., but effective retention interventions are highly resource intensive. With diminishing resources for HIV care and increasing prevalence of HIV, better approaches are needed to assist HIV care teams to identify patients most vulnerable to loss to follow-up (LTFU) who would most benefit from retention resources before LTFU occurs. A predictive model of LTFU based on electronic health data has the potential to address this need, as it quantifies a specific patient’s risk of future disengagement from care based on his/her unique characteristics and can be automated to generate risk prediction in real time. Using data from an urban HIV clinic, we have developed a machine learning model to predict LTFU from HIV care using natural language processing (NLP) of unstructured text of provider notes in the electronic medical record (EMR). The NLP model demonstrated good performance in detecting patients at risk for LTFU with a positive predictive value (PPV) of 0.86, and identified word patterns associated with LTFU, such as “substance abuse” and “stigma,” thereby demonstrating good face validity. While our preliminary data reveal the potential of NLP-based machine learning models to predict future retention in care, several key issues need to be addressed before the model can be deployed for patient care. First, PWH are a markedly heterogeneous population, and it is possible that there may exist sub-groups of patients (e.g., young Black men who have sex with men, cisgender women with childcare responsibilities, people who inject drugs and are unstably housed, etc) that differ drastically in the factors that are predictive of LTFU. Clinical phenotyping is an analytic method that can cluster patients within a heterogeneous population into different sub-groups based on profile similarities. Before a single model is deployed with a “one-size-fits- all” manner, it is crucial to better understand the performance of our NLP model on different clinical phenotypes of patients with HIV. Second, it is not known how the model would perform in a prospective, real-life setting. Finally, it is also unclear how a machine learning model would perform compared to provider intuition regarding patients’ risk for disengagement from care. This proposal seeks to address these issues through 2 specific aims. In Aim 1, we will determine the performance of the NLP predictive model of LTFU for different clinical phenotypes of people with HIV. In Aim 2, we will prospectively validate the model and compare results with care team intuition regarding risk for LTFU among people with HIV. As we move toward ending the HIV epidemic, results from this project will provide crucial information regarding the use of NLP and clinical phenotyping to predict loss to follow-up from HIV care and will enable a future R01 application for a multi-site implementation of the model paired with individually tailored retention interventions.

保留护理对于艾滋病毒治疗和预防至关重要，但美国只有一半的艾滋病毒感染者接受护理 保留在医疗护理中。提高保留率对于结束美国艾滋病毒流行至关重要，但也很有效 保留干预措施是高度资源密集型的。随着艾滋病毒护理资源的减少和增加 由于艾滋病毒的流行，需要更好的方法来协助艾滋病毒护理团队识别最脆弱的患者 失访 (LTFU) 在 LTFU 发生之前最能从保留资源中受益。一个预测性的 基于电子健康数据的 LTFU 模型有可能满足这一需求，因为它量化了特定的 根据患者的独特特征，确定患者未来脱离护理的风险，并且可以自动化 实时生成风险预测。 利用城市 HIV 诊所的数据，我们开发了一种机器学习模型来预测 HIV 的 LTFU 使用自然语言处理（NLP）对电子医疗中提供者注释的非结构化文本进行护理 记录（EMR）。 NLP 模型在检测有 LTFU 风险的患者方面表现出良好的性能 阳性预测值 (PPV) 为 0.86，并识别出与 LTFU 相关的词模式，例如“物质” 虐待”和“耻辱”，从而表现出良好的表面效度。 虽然我们的初步数据揭示了基于 NLP 的机器学习模型预测未来的潜力 为了保留护理，在将该模型应用于患者护理之前需要解决几个关键问题。 首先，艾滋病毒感染者是一个明显异质的人群，可能存在以下亚组： 患者（例如，与男性发生性关系的年轻黑人男性、有育儿责任的顺性别女性、 注射吸毒者和居住不稳定的人等）在预测因素方面存在巨大差异 LTFU。临床表型分析是一种可以对异质人群中的患者进行聚类的分析方法 根据个人资料的相似性分为不同的子组。在使用“一刀切”部署单个模型之前 所有”方式，更好地了解我们的 NLP 模型在不同临床表型上的表现至关重要 艾滋病毒感染者。其次，尚不清楚该模型在预期的现实环境中的表现如何。 最后，与提供者的直觉相比，机器学习模型的表现也不清楚 患者脱离护理的风险。该提案旨在通过 2 个具体措施解决这些问题 目标。在目标 1 中，我们将确定 LTFU 的 NLP 预测模型对于不同临床的表现 HIV 感染者的表型。在目标 2 中，我们将前瞻性地验证模型并将结果与 护理团队对 HIV 感染者 LTFU 风险的直觉。 当我们努力结束艾滋病毒流行时，该项目的结果将提供以下方面的重要信息： 使用 NLP 和临床表型来预测 HIV 护理的随访损失，并将使未来的 R01 成为可能 模型的多站点实施的应用程序与单独定制的保留干预措施相结合。