Dr. Chekroud, Dr. Gerhard, Dr. Gueorguieva, and Dr. Krystal are with the Department of Psychiatry and Dr. Roy is with the Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut. Dr. Chekroud is also with Spring Health, New York, where Mr. Chandra and Dr. Subramanyan are affiliated. Dr. Gueorguieva is also with the Department of Biostatistics, Yale University, New Haven, Connecticut. Mr. Foster is with Applied Data Science Partners, London. Dr. Zheutlin is with the Center for Genomic Medicine, Massachusetts General Hospital, Boston. Dr. Koutsouleris is with the Department of Psychiatry and Psychotherapy, Ludwig Maximilian University, Munich. Ms. Degli Esposti is with the Department of Experimental Psychology, University of Oxford, Oxford, United Kingdom. Dr. Paulus is with the Laureate Institute for Brain Research, Tulsa, Oklahoma.
Psychiatr Serv. 2018 Aug 1;69(8):927-934. doi: 10.1176/appi.ps.201800094. Epub 2018 Jul 2.
Even though safe and effective treatments for depression are available, many individuals with a diagnosis of depression do not obtain treatment. This study aimed to develop a tool to identify persons who might not initiate treatment among those who acknowledge a need.
Data were aggregated from the 2008-2014 U.S. National Survey on Drug Use and Health (N=391,753), including 20,785 adults given a diagnosis of depression by a health care provider in the 12 months before the survey. Machine learning was applied to self-report survey items to develop strategies for identifying individuals who might not get needed treatment.
A derivation cohort aggregated between 2008 and 2013 was used to develop a model that identified the 30.6% of individuals with depression who reported needing but not getting treatment. When applied to independent responses from the 2014 cohort, the model identified 72% of those who did not initiate treatment (p<.01), with a balanced accuracy that was also significantly above chance (71%, p<.01). For individuals who did not get treatment, the model predicted 10 (out of 15) reasons that they endorsed as barriers to treatment, with balanced accuracies between 53% and 65% (p<.05 for all).
Considerable work is needed to improve follow-up and retention rates after the critical initial meeting in which a patient is given a diagnosis of depression. Routinely collected information about patients with depression could identify those at risk of not obtaining needed treatment, which may inform the development and implementation of interventions to reduce the prevalence of untreated depression.
尽管有安全有效的抑郁症治疗方法，但许多被诊断为抑郁症的患者并未接受治疗。本研究旨在开发一种工具，以识别那些承认有治疗需求但可能不会开始治疗的患者。
数据来自 2008-2014 年美国全国药物使用与健康调查（N=391753），包括在调查前 12 个月内被医疗保健提供者诊断为抑郁症的 20785 名成年人。应用机器学习对自我报告的调查项目进行分析，以制定识别可能无法获得所需治疗的个体的策略。
使用 2008 年至 2013 年聚合的推导队列来开发一种模型，该模型确定了 30.6%报告需要但未获得治疗的抑郁症患者。当应用于 2014 年队列的独立回复时，该模型识别出 72%未开始治疗的患者（p<.01），其均衡准确性也明显高于机会水平（71%，p<.01）。对于未接受治疗的个体，该模型预测了他们认可的 10 个（共 15 个）治疗障碍原因，其均衡准确性在 53%至 65%之间（所有原因均为 p<.05）。
在患者被诊断为抑郁症的关键初始会议之后，需要做大量工作来提高随访和保留率。常规收集有关抑郁症患者的信息可以识别出那些可能无法获得所需治疗的患者，这可能有助于制定和实施干预措施，以降低未治疗抑郁症的患病率。
