Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations

IF 45.5 1区生物学 Q1 BIOCHEMISTRY & MOLECULAR BIOLOGY

Cell Pub Date : 2024-12-19 DOI:10.1016/j.cell.2024.11.012

Jason J. Liu, Beatrice Borsari, Yunyang Li, Susanna X. Liu, Yuan Gao, Xin Xin, Shaoke Lou, Matthew Jensen, Diego Garrido-Martín, Terril L. Verplaetse, Garrett Ash, Jing Zhang, Matthew J. Girgenti, Walter Roberts, Mark Gerstein

{"title":"Digital phenotyping from wearables using AI characterizes psychiatric disorders and identifies genetic associations","authors":"Jason J. Liu, Beatrice Borsari, Yunyang Li, Susanna X. Liu, Yuan Gao, Xin Xin, Shaoke Lou, Matthew Jensen, Diego Garrido-Martín, Terril L. Verplaetse, Garrett Ash, Jing Zhang, Matthew J. Girgenti, Walter Roberts, Mark Gerstein","doi":"10.1016/j.cell.2024.11.012","DOIUrl":null,"url":null,"abstract":"Psychiatric disorders are influenced by genetic and environmental factors. However, their study is hindered by limitations on precisely characterizing human behavior. New technologies such as wearable sensors show promise in surmounting these limitations in that they measure heterogeneous behavior in a quantitative and unbiased fashion. Here, we analyze wearable and genetic data from the Adolescent Brain Cognitive Development (ABCD) study. Leveraging >250 wearable-derived features as digital phenotypes, we show that an interpretable AI framework can objectively classify adolescents with psychiatric disorders more accurately than previously possible. To relate digital phenotypes to the underlying genetics, we show how they can be employed in univariate and multivariate genome-wide association studies (GWASs). Doing so, we identify 16 significant genetic loci and 37 psychiatric-associated genes, including <em>ELFN1</em> and <em>ADORA3</em>, demonstrating that continuous, wearable-derived features give greater detection power than traditional case-control GWASs. Overall, we show how wearable technology can help uncover new linkages between behavior and genetics.","PeriodicalId":9656,"journal":{"name":"Cell","volume":"31 1","pages":""},"PeriodicalIF":45.5000,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cell","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1016/j.cell.2024.11.012","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Psychiatric disorders are influenced by genetic and environmental factors. However, their study is hindered by limitations on precisely characterizing human behavior. New technologies such as wearable sensors show promise in surmounting these limitations in that they measure heterogeneous behavior in a quantitative and unbiased fashion. Here, we analyze wearable and genetic data from the Adolescent Brain Cognitive Development (ABCD) study. Leveraging >250 wearable-derived features as digital phenotypes, we show that an interpretable AI framework can objectively classify adolescents with psychiatric disorders more accurately than previously possible. To relate digital phenotypes to the underlying genetics, we show how they can be employed in univariate and multivariate genome-wide association studies (GWASs). Doing so, we identify 16 significant genetic loci and 37 psychiatric-associated genes, including ELFN1 and ADORA3, demonstrating that continuous, wearable-derived features give greater detection power than traditional case-control GWASs. Overall, we show how wearable technology can help uncover new linkages between behavior and genetics.

Abstract Image

查看原文本刊更多论文

使用人工智能的可穿戴设备的数字表型可以表征精神疾病并识别遗传关联

精神疾病受遗传和环境因素的影响。然而，精确描述人类行为的局限性阻碍了他们的研究。可穿戴传感器等新技术有望克服这些限制，因为它们可以以定量和公正的方式测量异质行为。在这里，我们分析了来自青少年大脑认知发展（ABCD）研究的可穿戴设备和遗传数据。利用250个可穿戴设备衍生的特征作为数字表型，我们展示了一个可解释的人工智能框架，可以比以前更准确地客观地对患有精神疾病的青少年进行分类。为了将数字表型与潜在遗传学联系起来，我们展示了如何将它们用于单变量和多变量全基因组关联研究（GWASs）。通过这样做，我们确定了16个重要的遗传位点和37个精神病学相关基因，包括ELFN1和ADORA3，这表明连续的、可穿戴的特征比传统的病例对照GWASs具有更高的检测能力。总的来说，我们展示了可穿戴技术如何帮助发现行为和基因之间的新联系。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Cell 生物-生化与分子生物学

CiteScore

110.00

自引率

0.80%

发文量

396

审稿时长

2 months

期刊介绍： Cells is an international, peer-reviewed, open access journal that focuses on cell biology, molecular biology, and biophysics. It is affiliated with several societies, including the Spanish Society for Biochemistry and Molecular Biology (SEBBM), Nordic Autophagy Society (NAS), Spanish Society of Hematology and Hemotherapy (SEHH), and Society for Regenerative Medicine (Russian Federation) (RPO). The journal publishes research findings of significant importance in various areas of experimental biology, such as cell biology, molecular biology, neuroscience, immunology, virology, microbiology, cancer, human genetics, systems biology, signaling, and disease mechanisms and therapeutics. The primary criterion for considering papers is whether the results contribute to significant conceptual advances or raise thought-provoking questions and hypotheses related to interesting and important biological inquiries. In addition to primary research articles presented in four formats, Cells also features review and opinion articles in its "leading edge" section, discussing recent research advancements and topics of interest to its wide readership.