Screening for Depression in Mobile Devices Using Patient Health Questionnaire-9 (PHQ-9) Data: A Diagnostic Meta-Analysis via Machine Learning Methods

Kim, Sunhae; Lee, Kounseok

doi:10.2147/ndt.s339412

Cited by 11 publications

(4 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the current review, two previous systematic reviews showed that AI has a slightly higher performance in detecting patients without depression (specificity) than patients with depression (sensitivity) 14 , 15 . However, the two reviews showed pooled sensitivity (80% 14 and 77% 15 ) and specificity (85% 14 and 78% 15 ) that are slightly lower than those in the current review although they were within the range reported in our review. This may be attributed to the fact that the previous reviews focused on the performance of AI based on only self-reported data collected using mobile-based PHQ-9 14 or neuroimaging data 15 .…”

Section: Discussionsupporting

confidence: 87%

“…However, the two reviews showed pooled sensitivity (80% 14 and 77% 15 ) and specificity (85% 14 and 78% 15 ) that are slightly lower than those in the current review although they were within the range reported in our review. This may be attributed to the fact that the previous reviews focused on the performance of AI based on only self-reported data collected using mobile-based PHQ-9 14 or neuroimaging data 15 .…”

Section: Discussioncontrasting

confidence: 75%

“…Thirdly, they did not search relevant databases such as PsychInfo 10 , 12 , 13 , IEEE Xplore 10 – 12 , and ACM Digital Library 10 – 13 . Fourthly, they focused on a specific type of algorithms (neural networks) and data (e.g., electroencephalogram (EEG) data 13 , self-reported data 14 , and neuroimaging data 15 ). Lastly, and most importantly, they were not systematic reviews and did not assess the performance of the wearable AI in detecting depression via either a narrative approach or statistical approach (e.g., meta-analysis) 7 , 10 – 13 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

et al. 2023

View full text Add to dashboard Cite

Given the limitations of traditional approaches, wearable artificial intelligence (AI) is one of the technologies that have been exploited to detect or predict depression. The current review aimed at examining the performance of wearable AI in detecting and predicting depression. The search sources in this systematic review were 8 electronic databases. Study selection, data extraction, and risk of bias assessment were carried out by two reviewers independently. The extracted results were synthesized narratively and statistically. Of the 1314 citations retrieved from the databases, 54 studies were included in this review. The pooled mean of the highest accuracy, sensitivity, specificity, and root mean square error (RMSE) was 0.89, 0.87, 0.93, and 4.55, respectively. The pooled mean of lowest accuracy, sensitivity, specificity, and RMSE was 0.70, 0.61, 0.73, and 3.76, respectively. Subgroup analyses revealed that there is a statistically significant difference in the highest accuracy, lowest accuracy, highest sensitivity, highest specificity, and lowest specificity between algorithms, and there is a statistically significant difference in the lowest sensitivity and lowest specificity between wearable devices. Wearable AI is a promising tool for depression detection and prediction although it is in its infancy and not ready for use in clinical practice. Until further research improve its performance, wearable AI should be used in conjunction with other methods for diagnosing and predicting depression. Further studies are needed to examine the performance of wearable AI based on a combination of wearable device data and neuroimaging data and to distinguish patients with depression from those with other diseases.

show abstract

Section: Discussionsupporting

confidence: 87%

Section: Discussioncontrasting

confidence: 75%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Both the PHQ-9 and GAD-7 have been validated for use in various formats, including mobile app and remote administration. Studies have shown that these tools retain their reliability and validity when administered electronically [ 31 , 32 ].…”

Section: Methodsmentioning

confidence: 99%

Prevalence and factors associated with antenatal depressive symptoms across trimesters: a study of 110,584 pregnant women covered by a mobile app-based screening programme in Shenzhen, China

Wu,

Chen,

Zhong

et al. 2024

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

Background Antenatal depression is a significant public health issue affecting pregnant women both globally and in China. Using data from a mobile app-based screening programme, this study explored the prevalence and factors associated with antenatal depressive symptoms across different trimesters in Shenzhen. Methods A retrospective cross-sectional study was conducted on pregnant women who gave birth in any hospital in Shenzhen between July 2021 and May 2022 and underwent depression screening using an official maternal and infant health mobile app at least once during pregnancy. Depressive symptoms were evaluated using the 9-item Patient Health Questionnaire (PHQ-9), with cut-off scores of 5 and 10 for mild and high level of symptoms, respectively. The prevalence for each trimester was determined by calculating the proportion of women scoring 5 or higher. A variety of sociodemographic, obstetric, psychological, and lifestyle factors were assessed for their association with depressive symptoms. Chi-square test and multivariate logistic regression were performed to identify significant predictors. Results A total of 110,584 pregnant women were included in the study, with an overall prevalence of depressive symptoms of 18.0% and a prevalence of high-level symptoms of 4.2%. Depressive symptoms were most prevalent in the first trimester (10.9%) and decreased in the second (6.2%) and third trimesters (6.3%). Only a small proportion (0.4%) of women showed persistent depressive symptoms across all trimesters. Anxiety symptoms in early pregnancy emerged as the most significant predictor of depressive symptoms. Other factors linked to an increased risk throughout pregnancy include lower marital satisfaction, living with parents-in-law, experience of negative life events, as well as drinking before and during pregnancy. Factors associated with a reduced risk throughout pregnancy include multiparity and daily physical activity. Conclusions This large-scale study provides valuable insights into the prevalence and factors associated with antenatal depressive symptoms in Shenzhen. The findings underscore the need for targeted interventions for high-risk groups and the integration of mental health care into routine antenatal services. Continuous, dynamic monitoring of depressive symptoms for pregnant women and ensuring at-risk women receive comprehensive follow-up and appropriate psychological or psychiatric care are crucial for effectively addressing antenatal depression and improving maternal and infant health outcomes.

show abstract

Impact assessment of stereotype threat on mobile depression screening using Bayesian estimation

Tlachac

Reisch²,

Lewis³

et al. 2022

Healthcare Analytics

View full text Add to dashboard Cite

Screening for Depression in Mobile Devices Using Patient Health Questionnaire-9 (PHQ-9) Data: A Diagnostic Meta-Analysis via Machine Learning Methods

Cited by 11 publications

References 121 publications

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

Systematic review and meta-analysis of performance of wearable artificial intelligence in detecting and predicting depression

Prevalence and factors associated with antenatal depressive symptoms across trimesters: a study of 110,584 pregnant women covered by a mobile app-based screening programme in Shenzhen, China

Impact assessment of stereotype threat on mobile depression screening using Bayesian estimation

Contact Info

Product

Resources

About