Multimodal monitoring and high-dimensional data for episode prediction in bipolar disorder

用于双相情感障碍发作预测的多模态监测和高维数据

• 批准号: 10383774
• 负责人: Abigail Ortiz
• 金额: $ 12.55万
• 依托单位: CENTRE FOR ADDICTION AND MENTAL HEALTH
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-05 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10383774
• 关键词: Address; Adult; Anxiety; Arrhythmia; Artificial Intelligence; Award; Behavior; Bipolar Disorder; Brain; Classification; Clinical; Collection; Complex; Data; Detection; Disease; Economic Burden; Entropy; Event; Exploratory/Developmental Grant; First Degree Relative; Future; General Population; Goals; Health Care Costs; Health Technology; Heart Diseases; Individual; International; Life; Machine Learning; Manic; Mathematics; Measures; Mental Health; Mental disorders; Metabolic Diseases; Methods; Modeling; Monitor; Mood Disorders; Moods; National Institute of Mental Health; Paper; Participant; Patients; Pattern; Performance; Physics; Physiological; Population; Property; Recommendation; Recurrence; Relapse; Research; Research Priority; Sampling; Series; Signal Transduction; Sleep; Societies; Suicide; System; Techniques; Time; Time Series Analysis; Visual; Work; analog; analytical method; base; biological systems; clinically relevant; data modeling; depressive symptoms; digital; digital health; disability; efficacious treatment; heart rate variability; high dimensionality; high risk; individual variation; mHealth; mood regulation; multidimensional data; multimodal data; multimodality; new technology; novel; novel strategies; prediction algorithm; predictive modeling; predictive signature; prevent; simulation; suicidal risk; telemonitoring; tool

SUMMARY Bipolar disorder (BD) is a mood disorder with high recurrence and disability rates, high economic burden, and an estimated suicide risk 20 times higher than the general population. While efficacious treatment is available, BD patients spend a large proportion of their life symptomatic. Predicting the onset of episodes is a valuable strategy to decrease suicide and disability rates and to optimize healthcare costs. The overall objective of this (R21) Exploratory/Developmental study is to obtain pilot data to support the feasibility and potential value of a new approach to predict mood episodes in stable adult patients with BD. This proposal aims to develop new data modeling and inference techniques that will enable more tailored clinical signal detection: examining changes within each individual, over time. To do so, we propose integrating multimodal, high-dimensional telemonitoring data, nonlinear techniques and artificial intelligence classification systems. This approach builds on our preliminary work on: (i) nonlinear techniques for the study of mood regulation in BD; (ii) an award-winning simulation using a machine learning technique (Markov Brains) for episode prediction in BD. AIMS: Aim 1 (feasibility): To obtain and integrate multimodal data to perform time-series analysis and to calculate entropy levels in 90 euthymic BD adults. Exploratory Aim 2 (potential value): To use machine learning techniques (Markov Brains) to distinguish participants at higher risk for a depressive or manic relapse based on their time-series and entropy levels (from Aim 1). HYPOTHESES: H1: We will be able to collect enough data in 80% of our participants and to integrate multimodal data to perform time-series analysis and to calculate entropy levels. H2: Markov Brains will identify participants at higher risk for a mood episode based on high (vs. low) auto-correlated time-series and low (vs. high) entropy levels. SIGNIFICANCE: This R21 application challenges more traditional prediction models by conceptualizing inter- and intra-individual variability as a dynamic property of biological systems. By leveraging densely-sampled objective and subjective data, autonomic, clinical and demographic data, this proposal aims to develop inference techniques that will examine changes within each individual, over time, in order to enhance the estimation performance. Ultimately, if we develop the capacity to predict mood episodes, we should be able to prevent them.

概括 躁郁症（BD）是一种情绪障碍，具有高复发和残疾率，高经济负担， 估计的自杀风险是普通人群的20倍。虽然有效的治疗是 可用的BD患者在症状上花费很大一部分。预测情节的发作 是降低自杀和残疾率并优化医疗保健成本的宝贵策略。 该（R21）探索性/发展研究的总体目的是获取试点数据以支持 一种新方法的可行性和潜在价值，以预测稳定的成年患者的情绪发作 BD。该建议旨在开发新的数据建模和推理技术，以启用更多 量身定制的临床信号检测：随着时间的流逝，检查每个个体内部的变化。为此，我们 建议整合多模式，高维远程监控数据，非线性技术和人工 情报分类系统。这种方法基于我们的初步工作：（i）非线性 BD中情绪调节的研究技术； （ii）使用机器的屡获殊荣的模拟 BD中的情节预测的学习技术（Markov Brains）。 目的：目标1（可行性）：获取和整合多模式数据以执行时间序列分析和 计算90个整体BD成年人的熵水平。探索目标2（潜在价值）：使用 机器学习技术（Markov Brains）以区分抑郁症或较高风险的参与者 基于其时间序列和熵水平（来自AIM 1）的躁狂复发。 假设：H1：我们将能够在80％的参与者中收集足够的数据并整合 多模式数据以执行时间序列分析并计算熵水平。 H2：马尔可夫·脑子将 确定基于高（低）自动相关的时间序列的情绪发作风险较高的参与者 和低（与高）熵水平。 意义：此R21应用程序挑战了更传统的预测模型 将个体内和个体内变异性概念化为生物系统的动态特性。经过 利用密集采样的客观和主观数据，自主神经，临床和人口统计数据， 建议旨在开发推理技术，以检查每个人的变化， 时间，以增强估计性能。最终，如果我们发展了预测的能力 情绪发作，我们应该能够防止它们。

项目成果

Predictors of adherence to electronic self-monitoring in patients with bipolar disorder: a contactless study using Growth Mixture Models.

• DOI: 10.1186/s40345-023-00297-5
• 发表时间: 2023-05-17
• 期刊: International journal of bipolar disorders
• 影响因子: 4

Identifying patient-specific behaviors to understand illness trajectories and predict relapses in bipolar disorder using passive sensing and deep anomaly detection: protocol for a contactless cohort study.

• DOI: 10.1186/s12888-022-03923-1
• 发表时间: 2022-04-22
• 期刊: BMC PSYCHIATRY
• 影响因子: 4.4
• 作者: Ortiz, Abigail;Hintze, Arend;Burnett, Rachael;Gonzalez-Torres, Christina;Unger, Samantha;Yang, Dandan;Miao, Jingshan;Alda, Martin;Mulsant, Benoit H.
• 通讯作者: Mulsant, Benoit H.