TY - JOUR AU - Kuleindiren, Narayan AU - Rifkin-Zybutz, Raphael Paul AU - Johal, Monika AU - Selim, Hamzah AU - Palmon, Itai AU - Lin, Aaron AU - Yu, yzhou AU - alimi - marvasti, Ali AU - Mahmud, Mohammad PY - 2022 DA - 2022/3/22 TI -优化现有心理健康筛查方法在痴呆筛查和风险因素应用程序中的应用;观察性机器学习研究JO - JMIR Form Res SP - e31209 VL - 6 IS - 3 KW -抑郁KW -焦虑KW -筛选KW -研究方法KW -问卷KW -精度KW -痴呆KW -认知KW -危险因素KW -机器学习KW -预测AB -背景:Mindstep是一款旨在通过评估认知和危险因素来改善痴呆筛查的应用程序。它考虑了重要的临床危险因素，包括前驱症状、精神健康障碍和痴呆症的鉴别诊断。9项抑郁患者健康问卷(PHQ-9)和7项广泛性焦虑障碍量表(GAD-7)分别被广泛验证并被广泛用于筛查抑郁和焦虑障碍。两者的缩短版本(PHQ-2/GAD-2)已经生产出来。目的:我们寻求一种方法，既保持这些较短的问卷的简洁性，又保持原始问卷的更好的准确性。方法:设计单个问题以涵盖原始问卷所涵盖的症状。这些问题的答案与PHQ-2/GAD-2相结合，Mindset4Dementia收集了2235名用户的匿名风险因素。机器学习模型经过训练，可以将这些单一问题与应用程序已经收集的数据(年龄、对笑话的反应、功能障碍报告)结合起来，预测使用PHQ-9/GAD-7测量的二进制和连续结果。我们的模型是通过使用10倍交叉验证和holdout测试数据集开发的训练数据集，并与单独使用较短问卷(PHQ-2/GAD-2)的结果进行比较，以基准性能。 Results: We were able to achieve superior performance in predicting PHQ-9/GAD-7 screening cutoffs compared to PHQ-2 (difference in area under the curve 0.04, 95% CI 0.00-0.08, P=.02) but not GAD-2 (difference in area under the curve 0.00, 95% CI –0.02 to 0.03, P=.42). Regression models were able to accurately predict total questionnaire scores in PHQ-9 (R2=0.655, mean absolute error=2.267) and GAD-7 (R2=0.837, mean absolute error=1.780). Conclusions: We app-adapted PHQ-4 by adding brief summary questions about factors normally covered in the longer questionnaires. We additionally trained machine learning models that used the wide range of additional information already collected in Mindstep to make a short app-based screening tool for affective disorders, which appears to have superior or equivalent performance to well-established methods. SN - 2561-326X UR - https://formative.www.mybigtv.com/2022/3/e31209 UR - https://doi.org/10.2196/31209 UR - http://www.ncbi.nlm.nih.gov/pubmed/35315786 DO - 10.2196/31209 ID - info:doi/10.2196/31209 ER -