Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis.
Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis.
复制标题
DOI：
10.2196/48444
复制
发表时间：
2023-10-19
影响因子：
5.2
通讯作者：
Van de Ven P
中科院分区：
文献类型：
--
作者：
Glavin D;Grua EM;Nakamura CA;Scazufca M;Ribeiro Dos Santos E;Wong GHY;Hollingworth W;Peters TJ;Araya R;Van de Ven P
快感缺乏和抑郁情绪被认为是重性抑郁症的主要症状。这些是患者健康问卷（PHQ）-9的前2项，包括用于预筛选抑郁症的超简短PHQ-2。替代PHQ-9项目配对的预筛选性能很少与PHQ-2进行比较。本研究的目的是使用机器学习（ML）与PHQ-9项目来识别和验证最具预测性的2项抑郁症诊断超简问卷，并测试主要数据集上发现的最佳配对的普遍性，使用来自不同人群的6个外部数据集来验证其作为预筛选工具的用途。所有36个可能的PHQ-9项目配对（每个产生0-6分）进行了调查，使用基于ML的方法与逻辑回归模型。他们的表现是根据抑郁症的分类，定义为PHQ-9评分≥10。这给每个配对一个平等的机会，并避免任何偏见，在项目配对选择。基于ML的PHQ-9项目2和4（phq2&4），抑郁情绪和低能量项目配对，以及PHQ-9项目2和8（phq2&8），抑郁情绪和精神发育迟滞或激动项目配对，被认为是主要数据集训练分割的最佳选择。它们在主要数据集测试中的推广效果良好，曲线下面积（AUC）分别为0.954和0.946，而PHQ-2的AUC为0.942。在所有6个外部数据集上，phq2&4的AUC高于PHQ-2，在3个数据集上，phq2&8的AUC高于PHQ-2。phq2&4在2个外部数据集上具有最高的约登指数（灵敏度和特异性的未加权平均值），而phq2&8在另2个数据集上具有最高的约登指数。PHQ-2≥2临界值在2个外部数据集上也具有最高的Youden指数，与phq 2&4在1上联合最高，但其性能波动最大。PHQ-2≥3临界值在1个外部数据集上具有最高的Youden指数。phq2&4和phq2&8达到的灵敏度和特异性比PHQ-2≥2和≥3临界值更均衡。与其他PHQ-9项目配对相比，PHQ-2并没有被证明是一个更有效的预筛选工具。评估所有项目配对显示，与替代伙伴项目相比，快感缺乏项目与抑郁情绪项目一起表现不佳。这表明，将快感缺失作为抑郁症的核心症状，并将其存在于超简短问卷中，可能与经验证据不一致。使用PHQ-2对抑郁症患者进行预筛选可能会导致比替代项目配对更多的错误分类。
Anhedonia and depressed mood are considered the cardinal symptoms of major depressive disorder. These are the first 2 items of the Patient Health Questionnaire (PHQ)–9 and comprise the ultrabrief PHQ-2 used for prescreening depressive symptomatology. The prescreening performance of alternative PHQ-9 item pairings is rarely compared with that of the PHQ-2. This study aims to use machine learning (ML) with the PHQ-9 items to identify and validate the most predictive 2-item depressive symptomatology ultrabrief questionnaire and to test the generalizability of the best pairings found on the primary data set, with 6 external data sets from different populations to validate their use as prescreening instruments. All 36 possible PHQ-9 item pairings (each yielding scores of 0-6) were investigated using ML-based methods with logistic regression models. Their performances were evaluated based on the classification of depressive symptomatology, defined as PHQ-9 scores ≥10. This gave each pairing an equal opportunity and avoided any bias in item pairing selection. The ML-based PHQ-9 items 2 and 4 (phq2&4), the depressed mood and low-energy item pairing, and PHQ-9 items 2 and 8 (phq2&8), the depressed mood and psychomotor retardation or agitation item pairing, were found to be the best on the primary data set training split. They generalized well on the primary data set test split with area under the curves (AUCs) of 0.954 and 0.946, respectively, compared with an AUC of 0.942 for the PHQ-2. The phq2&4 had a higher AUC than the PHQ-2 on all 6 external data sets, and the phq2&8 had a higher AUC than the PHQ-2 on 3 data sets. The phq2&4 had the highest Youden index (an unweighted average of sensitivity and specificity) on 2 external data sets, and the phq2&8 had the highest Youden index on another 2. The PHQ-2≥2 cutoff also had the highest Youden index on 2 external data sets, joint highest with the phq2&4 on 1, but its performance fluctuated the most. The PHQ-2≥3 cutoff had the highest Youden index on 1 external data set. The sensitivity and specificity achieved by the phq2&4 and phq2&8 were more evenly balanced than the PHQ-2≥2 and ≥3 cutoffs. The PHQ-2 did not prove to be a more effective prescreening instrument when compared with other PHQ-9 item pairings. Evaluating all item pairings showed that, compared with alternative partner items, the anhedonia item underperformed alongside the depressed mood item. This suggests that the inclusion of anhedonia as a core symptom of depression and its presence in ultrabrief questionnaires may be incompatible with the empirical evidence. The use of the PHQ-2 to prescreen for depressive symptomatology could result in a greater number of misclassifications than alternative item pairings.
登录
查看更多内容
患者健康问卷（PHQ）-2和PHQ-9的有效性和实用性用于筛查和诊断墨西哥农村奇亚帕斯的抑郁症：一项横断面研究。
影响因子：
3
作者：
Arrieta J;Aguerrebere M;Raviola G;Flores H;Elliott P;Espinosa A;Reyes A;Ortiz-Panozo E;Rodriguez-Gutierrez EG;Mukherjee J;Palazuelos D;Franke MF
通讯作者：
Franke MF
影响因子：
3
作者：
Feng L;Hancock R;Watson C;Bogley R;Miller ZA;Gorno-Tempini ML;Briggs-Gowan MJ;Hoeft F
通讯作者：
Hoeft F
影响因子：
3.1
作者：
Rosenstrom, Tom;Elovainio, Marko;Keltikangas-Jarvinen, Liisa
通讯作者：
Keltikangas-Jarvinen, Liisa
DOI：
10.1590/0102-311x00123421
发表时间：
2022-01-01
期刊：
Cadernos de Saúde Pública
影响因子：
--
作者：
Lopes, Claudia de Souza;Gomes, Nayara Lopes;Menezes, Paulo Rossi
通讯作者：
Menezes, Paulo Rossi
影响因子：
7.6
作者：
Johnson, JG;Harris, ES;Williams, JBW
通讯作者：
Williams, JBW