Leveraging Social Media Data and Machine Learning to Optimize Treatment Paradigms for Youth with Schizophrenia

利用社交媒体数据和机器学习优化青少年精神分裂症的治疗模式

基本信息

批准号：
9914128
负责人：
Munmun De Choudhury
金额：
$ 64万
依托单位：
GEORGIA INSTITUTE OF TECHNOLOGY
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-04-15 至 2023-02-28
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9914128
关键词：
Address Adolescent and Young Adult Adopted Adoption Affect Aftercare Behavior Behavioral Big Data Biometry Caring Chronic Circadian Rhythms Clinical Clinical Data Clinical Psychology Clinical Research Clinical Trials Cognition Cognitive Computational Technique Computers Computing Methodologies Data Data Collection Deterioration Development Disorientation Doctor of Philosophy Early Diagnosis Early Intervention Emerging Technologies Emotional Evaluation Evidence based treatment Family Feedback Foundations Goals Health Hospitalization Improve Access Individual Intervention Investigation Knowledge Lead Learning Linguistics Machine Learning Mental Depression Mental Health Mental disorders Methods Monitor Moods National Institute of Mental Health Outcome Patient-Focused Outcomes Patients Phase Phenotype Population Privacy Psychiatric therapeutic procedure Psychiatry Psychology Psychotic Disorders Relapse Reporting Research Research Ethics Research Methodology Risk Role Sampling Schizophrenia Scientist Severities Site Social Functioning Social Psychology Source Stigmatization Strategic Planning Suicide Surface Symptoms Techniques Testing Texas Theoretical model Time Universities Validation Violence Work Youth base biological research biomarker development clinical decision support clinical efficacy clinical heterogeneity cohort computational basis deep learning digital digital media digital models disability disease classification disorder later incidence prevention evidence base experience family burden first episode schizophrenia high risk improved innovative technologies intervention program lens machine learning method medical complication multidisciplinary natural language novel novel strategies peer personalized intervention prevent prospective psychosocial psychotic symptoms recruit relapse patients relapse prediction relapse risk response social social media social observations stem support tools treatment optimization treatment response treatment strategy volunteer willingness young adult

项目摘要

Abstract Schizophrenia constitutes a chronic and disabling illness. While patients show high rates of response to treatment after a ﬁrst-episode of schizophrenia, the long-term course of the illness is typically characterized by frequent re- lapses, persistence of symptoms, and enduring cognitive and functional deﬁcits. Despite the prioritization of relapse prevention as a treatment goal, about four out of ﬁve patients experience a relapse within the ﬁrst ﬁve years of treatment. Relapses are known to have serious psychosocial, educational, or vocational implications in young adults—a population at high risk of psychosis. However, current psychiatric ability to recognize indicators of relapse in order to prevent escalation of psychotic symptoms is markedly limited. Challenges stem from a lack of availability of comprehensive information about early warning signs, and reliance on ﬁxed time point sampling of cross-sectional data as well as patient or family reported observations, that is subject to recall bias, or on clin- ician sought information, that needs frequent and timely contact. The present proposal seeks to address these gaps in early psychosis treatment, by leveraging patient-generated and patient-volunteered social media data, and developing and validating machine learning approaches for “digital phenotyping” and relapse prediction. Our proposed work is founded on the observation that social media sites have emerged as prominent platforms of emotional and linguistic expression—young adults are among the heaviest users of social media. The work signif- icantly advances the research agenda and extensive pilot investigations of the team, who a) have demonstrated that social media data of individuals can serve as a powerful “lens” toward understanding and inferring mental health state, illness course, and likelihood of relapse, including among young adults with early psychosis; and b) have been involved in examining the role of emergent technologies, like social media, in improving access to and delivery of psychiatric care. Aim 1 will provide theoretically-grounded and clinically meaningful methods for extracting and modeling digital phenotypes and symptoms from social media data of young adult early psychosis patients. Then in Aim 2, we will develop and evaluate machine learning methods that will utilize the extracted social media digital phenotypes to infer patient-speciﬁc personalized risk of relapse, and identify its antecedents. Finally, Aim 3 will develop a two-faceted validation framework, to assess the statistical and clinical efﬁcacy and utility of the social media derived inferences of psychosis and relapse in inﬂuencing clinical outcomes and in facilitating evidence-based treatment. To accomplish these aims, the project brings together a strong multidisci- plinary team, combining expertise in social media analytics, psychiatry, psychology, natural language analysis, machine learning, information privacy, and research ethics. Our novel approach offers unprecedented opportuni- ties to initiate the adoption of personalized, responsive, and preemptive evidence-based strategies in treatment of psychosis. The knowledge will set the stage for future research on launching large-scale trials aimed to develop interventions that diminish the severity of relapses, or prevent their occurrence altogether.

抽象的精神分裂症构成了一种慢性致残的疾病。虽然患者对治疗的反应率很高在精神分裂症的第一集之后，疾病的长期病程通常以经常重复为特征失误，症状的持久性以及持久的认知和功能降低。尽管优先考虑预防复发作为治疗目标，大约有四名患者在第一个五个患者中得到了缓解多年治疗。众所周知，复发具有严重的社会心理，教育或发布的意义年轻人 - 患有精神病的高风险人群。但是，当前识别指标的精神病能力为了防止精神病符号升级而被显着限制。挑战源于缺乏提供有关预警信号的全面信息以及固定时间点采样的救济横截面数据以及患者或家庭报告的观察结果，可能会召回偏见，或 ICIAN感知的信息经常需要及时接触。本提案旨在解决这些问题通过利用患者生成和患者志愿的社交媒体数据来进行早期精神病治疗的差距，以及开发和验证“数字表型”和浮雕预测的机器学习方法。我们的拟议的工作是建立在社交媒体网站已成为重要平台的观察基础上的情感和语言表达 - 年轻的成年人是社交媒体中最重的使用者之一。工作意义重大 - 明显地提高了研究议程和对团队的广泛试点调查，A）已证明个人的社交媒体数据可以作为理解和推断精神的强大“镜头” 健康状态，疾病课程和退休的可能性，包括早期精神病的年轻人；和 b）参与了研究新兴技术（如社交媒体）在改善访问访问访问方面的作用和精神病护理的提供。 AIM 1将为理论上且临床上有意义的方法从年轻成人早期精神病的社交媒体数据中提取和建模数字表型和符号患者。然后在AIM 2中，我们将开发和评估将利用提取的机器学习方法社交媒体数字表型，以推断患者特定的个性化继电器风险，并确定其前因。最后，AIM 3将开发一个两方面的验证框架，以评估统计和临床效率和社交媒体的实用性在影响临床结果和中的精神病和缓解的推论中促进基于证据的治疗。为了实现这些目标，该项目汇集了一个强大的多阶段三级团队，结合社交媒体分析，精神病学，心理学，自然语言分析的专业知识，机器学习，信息隐私和研究道德。我们的新颖方法提供了前所未有的机会启动采用个性化，响应式和先发制的基于证据的策略的关系精神病。知识将为未来的研究奠定舞台，以启动旨在开发的大规模试验干预措施会减少继电器的严重程度，或完全阻止其发生。