EUVIMEDScopri EUVIMED
Open access

Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis

Darragh Glavin iD, Eoin Martino Grua iD, Carina Akemi Nakamura iD, Marcia Scazufca iD, Edinilza Ribeiro Dos Santos iD, Gloria H Y Wong iD, William Hollingworth iD, Tim J Peters iD, Ricardo Araya iD, Pepijn Van de Ven iD

JMIR Mental Health · 2023-10-19 · 10 · e48444

DOI: 10.2196/48444 ↗

At a glance

Journal article in JMIR Mental Health, published online on 2023-10-19. Written by Darragh Glavin and 9 co-authors. Institution: Department of Electronic and Computer Engineering, University of Limerick, Limerick, Ireland. Cited 15 times so far (Crossref); 32 references. The full text is freely available in PubMed Central. Funded by: Wellcome Trust, Medical Research Council.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

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.

Objective

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.

Methods

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.

Results

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.

Conclusions

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.

Subjects

Author keywords

PHQ-2PHQ-9 itemsPatient Health Questionnaire-2Patient Health Questionnaire-9cardinal symptomsdepressed mooddepressive symptomatologylow energymachine learningprescreeningpsychomotor dysfunctionultrabrief questionnaires

Authors and institutions

  • Department of Electronic and Computer Engineering, University of Limerick, Limerick, Ireland.
  • Health Research Institute, University of Limerick, Limerick, Ireland.
  • Departamento de Psiquiatria, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, Brazil.
  • Instituto de Psiquiatria, Hospital das Clinicas, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, Brazil.
  • Health Sciences School, University of the State of Amazonas, Manaus, Brazil.
  • Department of Social Work and Social Administration, University of Hong Kong, Pok Fu Lam, China (Hong Kong).

ORCID profiles: Darragh Glavin, Eoin Martino Grua, Carina Akemi Nakamura, Marcia Scazufca, Edinilza Ribeiro Dos Santos, Gloria H Y Wong, William Hollingworth, Tim J Peters, Ricardo Araya, Pepijn Van de Ven

Funding

  • Wellcome Trust
  • Medical Research Council

Cite

APA

Glavin, D., Grua, E. M., Nakamura, C. A., Scazufca, M., Ribeiro Dos Santos, E., Wong, G. H. Y., Hollingworth, W., Peters, T. J., Araya, R., & Van de Ven, P. (2023). Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis. JMIR Mental Health, 10, e48444. https://doi.org/10.2196/48444

Vancouver

Glavin D, Grua EM, Nakamura CA, Scazufca M, Ribeiro Dos Santos E, Wong GHY, et al. Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis. JMIR Mental Health. 2023;10:e48444. doi:10.2196/48444

BibTeX
@article{Glavin2023,
  author = {Glavin, Darragh and Grua, Eoin Martino and Nakamura, Carina Akemi and Scazufca, Marcia and Ribeiro Dos Santos, Edinilza and Wong, Gloria H Y and Hollingworth, William and Peters, Tim J and Araya, Ricardo and Van de Ven, Pepijn},
  title = {Patient Health Questionnaire-9 Item Pairing Predictiveness for Prescreening Depressive Symptomatology: Machine Learning Analysis},
  journal = {JMIR Mental Health},
  year = {2023},
  volume = {10},
  pages = {e48444},
  doi = {10.2196/48444}
}
Start for free →