LumanLab Inc, R&D Center, Seoul, South Korea.
Department of Psychiatry, Chungnam National University Sejong Hospital, Sejong, South Korea.
JAMA Netw Open. 2023 Mar 1;6(3):e233502. doi: 10.1001/jamanetworkopen.2023.3502.
Early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems is paramount for children's mental health. Interview-based diagnostic approaches have drawbacks, necessitating the development of an evaluation method that uses digital phenotypes in daily life.
To evaluate the predictive performance of machine learning (ML) models by setting the data obtained from personal digital devices comprising training features (ie, wearable data) and diagnostic results of ADHD and sleep problems by the Kiddie Schedule for Affective Disorders and Schizophrenia Present and Lifetime Version for Diagnostic and Statistical Manual of Mental Disorders, 5th edition (K-SADS) as a prediction class from the Adolescent Brain Cognitive Development (ABCD) study.
DESIGN, SETTING, AND PARTICIPANTS: In this diagnostic study, wearable data and K-SADS data were collected at 21 sites in the US in the ABCD study (release 3.0, November 2, 2020, analyzed October 11, 2021). Screening data from 6571 patients and 21 days of wearable data from 5725 patients collected at the 2-year follow-up were used, and circadian rhythm-based features were generated for each participant. A total of 12 348 wearable data for ADHD and 39 160 for sleep problems were merged for developing ML models.
The average performance of the ML models was measured using an area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, the Shapley Additive Explanations value was used to calculate the importance of features.
The final population consisted of 79 children with ADHD problems (mean [SD] age, 144.5 [8.1] months; 55 [69.6%] males) vs 1011 controls and 68 with sleep problems (mean [SD] age, 143.5 [7.5] months; 38 [55.9%] males) vs 3346 controls. The ML models showed reasonable predictive performance for ADHD (AUC, 0.798; sensitivity, 0.756; specificity, 0.716; PPV, 0.159; and NPV, 0.976) and sleep problems (AUC, 0.737; sensitivity, 0.743; specificity, 0.632; PPV, 0.036; and NPV, 0.992).
In this diagnostic study, an ML method for early detection or screening using digital phenotypes in children's daily lives was developed. The results support facilitating early detection in children; however, additional follow-up studies can improve its performance.
早期发现注意力缺陷/多动障碍（ADHD）和睡眠问题对儿童的心理健康至关重要。基于访谈的诊断方法有其缺点，因此需要开发一种评估方法，该方法使用日常生活中的数字表型。
通过设置从个人数字设备获得的数据来评估机器学习 (ML) 模型的预测性能，这些数据包括训练特征（即可穿戴数据）和 ADHD 和睡眠问题的诊断结果，这些结果是通过 Kiddie 情感障碍和精神分裂症的时间表获得的，用于诊断和统计手册，第 5 版（K-SADS）作为来自青少年大脑认知发展 (ABCD) 研究的预测类别。
设计、设置和参与者：在这项诊断研究中，可穿戴数据和 K-SADS 数据在美国 21 个地点的 ABCD 研究（第 3.0 版，2020 年 11 月 2 日，2021 年 10 月 11 日分析）中收集。使用了来自 6571 名患者的筛查数据和来自 5725 名患者的 2 年随访期间的 21 天可穿戴数据，并为每位参与者生成了基于昼夜节律的特征。共合并了 12348 个 ADHD 的可穿戴数据和 39160 个睡眠问题的可穿戴数据用于开发 ML 模型。
使用受试者工作特征曲线下的面积 (AUC)、敏感性、特异性、阳性预测值 (PPV) 和阴性预测值 (NPV) 来衡量 ML 模型的平均性能。此外，还使用 Shapley 加法解释值来计算特征的重要性。
最终人群包括 79 名 ADHD 问题儿童（平均[标准差]年龄，144.5[8.1]个月；55[69.6%]名男性）与 1011 名对照者和 68 名睡眠问题儿童（平均[标准差]年龄，143.5[7.5]个月；38[55.9%]名男性）与 3346 名对照者。ML 模型对 ADHD（AUC，0.798；敏感性，0.756；特异性，0.716；PPV，0.159；NPV，0.976）和睡眠问题（AUC，0.737；敏感性，0.743；特异性，0.632；PPV，0.036；NPV，0.992）具有合理的预测性能。
在这项诊断研究中，开发了一种使用儿童日常生活中的数字表型进行早期检测或筛查的 ML 方法。研究结果支持促进儿童的早期发现；然而，进一步的随访研究可以提高其性能。
