Price George D, Heinz Michael V, Nemesure Matthew D, McFadden Jason, Jacobson Nicholas C
Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States.
Quantitative Biomedical Sciences Program, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States.
Front Psychiatry. 2022 Aug 11;13:807116. doi: 10.3389/fpsyt.2022.807116. eCollection 2022.
Despite existing work examining the effectiveness of smartphone digital interventions for schizophrenia at the group level, response to digital treatments is highly variable and requires more research to determine which persons are most likely to benefit from a digital intervention.
The current work utilized data from an open trial of patients with psychosis ( = 38), primarily schizophrenia spectrum disorders, who were treated with a psychosocial intervention using a smartphone app over a one-month period. Using an ensemble of machine learning models, pre-intervention data, app use data, and semi-structured interview data were utilized to predict response to change in symptom scores, engagement patterns, and qualitative impressions of the app.
Machine learning models were capable of moderately ( = 0.32-0.39, R = 0.10-0.16, MAE = 0.13-0.29) predicting interaction and experience with the app, as well as changes in psychosis-related psychopathology.
The results suggest that individual smartphone digital intervention engagement is heterogeneous, and symptom-specific baseline data may be predictive of increased engagement and positive qualitative impressions of digital intervention in patients with psychosis. Taken together, interrogating individual response to and engagement with digital-based intervention with machine learning provides increased insight to otherwise ignored nuances of treatment response.
尽管已有研究在群体层面考察了智能手机数字干预对精神分裂症的有效性，但对数字治疗的反应差异很大，需要更多研究来确定哪些人最有可能从数字干预中获益。
本研究使用了一项针对精神病患者（n = 38）的开放试验数据，这些患者主要患有精神分裂症谱系障碍，在一个月的时间里接受了使用智能手机应用程序的心理社会干预。利用机器学习模型集合，结合干预前数据、应用程序使用数据和半结构化访谈数据，来预测症状评分变化、参与模式以及对应用程序的定性印象。
机器学习模型能够适度（r = 0.32 - 0.39，R² = 0.10 - 0.16，平均绝对误差 = 0.13 - 0.29）预测与应用程序的交互和体验，以及与精神病相关的精神病理学变化。
结果表明，个体对智能手机数字干预的参与情况存在异质性，特定症状的基线数据可能预示着精神病患者对数字干预的参与度增加和积极的定性印象。总体而言，用机器学习探究个体对基于数字的干预的反应和参与情况，能让我们对原本被忽视的治疗反应细微差别有更多了解。
