Top

BMC Public Health

Published in:

Open Access 01-12-2024 | Mood Disorders | Research

Using machine learning to develop a five-item short form of the children’s depression inventory

Authors: Shumei Lin, Chengwei Wang, Xiuyu Jiang, Qian Zhang, Dan Luo, Jing Li, Junyi Li, Jiajun Xu

Published in: BMC Public Health | Issue 1/2024

Abstract

Background

Many adolescents experience depression that often goes undetected and untreated. Identifying children and adolescents at a high risk of depression in a timely manner is an urgent concern. While the Children’s Depression Inventory (CDI) is widely utilized in China, it lacks a localized revision or simplified version. With its 27 items requiring professional administration, the original CDI proves to be a time-consuming method for predicting children and adolescents with high depression risk. Hence, this study aimed to develop a shortened version of the CDI to predict high depression risk, thereby enhancing the efficiency of prediction and intervention.

Methods

Initially, backward elimination is conducted to identify various version of the short-form scales (e.g., three-item and five-item versions). Subsequently, the performance of five machine learning (ML) algorithms on these versions is evaluated using the area under the ROC curve (AUC) to determine the best algorithm. The chosen algorithm is then utilized to model the short-form scales, facilitating the identification of the optimal short-form scale based on predefined evaluation metrics. Following this, evaluation metrics are computed for all potential decision thresholds of the optimal short-form scale, and the threshold value is determined. Finally, the reliability and validity of the optimal short-form scale are assessed using a new sample.

Results

The study identified a five-item short-form CDI with a decision threshold of 4 as the most appropriate scale considering all assessment indicators. The scale had 81.48% fewer items than the original version, indicating good predictive performance (AUC = 0.81, Accuracy = 0.83, Recall = 0.76, Precision = 0.71). Based on the test of 315 middle school students, the results showed that the five-item CDI had good measurement indexes (Cronbach’s alpha = 0.72, criterion-related validity = 0.77).

Conclusions

This five-item short-form CDI is the first shortened and revised version of the CDI in China based on large local data samples.

Fu X, Zhang K, Chen X. The Report on National Mental Health Development in China (2019–2020). 2021.

Liu F, Song X, Shang X et al. A meta-analysis of detection rate of depression symptoms among middle school students. Chin Mental Health J, 2020.

Liu F, Wu M, Dong Y et al. A meta-analysis of the detection rate of depressive symptoms among primary school students. Chin Mental Health J, 2021.

Cheng D, Liu J, Huang P. The investigation of first diagnosed case and analysis of clinical characteristics of adolescent depression. J Med Theory Pract. 2013. https://doi.org/10.19381/j.issn.1001-7585.2013.15.012.CrossRef

Li J, Sun Y. Summary of global child and adolescent depression screening guidelines. Chin J School Health. 2022. https://doi.org/10.16835/j.cnki.1000-9817.2022.05.027.CrossRef

Kovacs M. Children’s depression inventory. Acta Paedopsychiatrica: International Journal of Child & Adolescent Psychiatry; 1992.

Yu D, Li X. Preliminary use of the children’ s Depression Inventory in China. Chin Mental Health J. 2000;14(4):225–7. https://doi.org/10.3321/j.issn:1000-6729.2000.04.003.CrossRef

Liu Z, Li J, Wang Y, et al. Structural Verification and Measurement Invariance of Chinese Version of Children’s Depression Inventory. Chin J Clin Psychol. 2019. https://doi.org/10.16128/j.cnki.1005-3611.2019.06.019.CrossRef

Olorunju SB, Akpa OM, Afolabi RF. Modelling the factor structure of the child Depression Inventory in a population of apparently healthy adolescents in Nigeria. PLoS ONE. 2018;13(3):e0193699. https://doi.org/10.1371/journal.pone.0193699.CrossRefPubMedPubMedCentral

10.

Ahlen J, Ghaderi A. Evaluation of the children’s Depression Inventory-Short Version (CDI-S). Psychol Assess. 2017;29(9):1157–66. https://doi.org/10.1037/pas0000419.CrossRefPubMed

11.

Preti A, Carta MG, Petretto DR. Factor structure models of the SCL-90-R: replicability across community samples of adolescents. Psychiatry Res. 2019;272:491–8.CrossRefPubMed

12.

Liu J. Simplification and application of symptom self-rating scale based on machine learning. Qingdao University; 2020.

13.

Mccrae RR, Costa PT. Jr. Brief versions of the NEO-PI-3. J Individual Differences. 2007;28(3):116–28. https://doi.org/10.1027/1614-0001.28.3.116.CrossRef

14.

Zhang P, Liang Z, Chen H, et al. The stability and gender difference of children’s self-control from 2 to 11 years old. Psychol Dev Educ. 2012;5:463–70. https://doi.org/10.16187/j.cnki.issn1001-4918.2012.05.001.CrossRef

15.

Zhang H. The identification and intervention of depression in children and adolescents. Educator. 2020;48:52–3.

16.

Li A, Zhang Y, Li K. Recent developments in assessment tools for depression in children and adolescents in China. Chin Gen Pract. 2017;20(35):4464–9. https://doi.org/10.3969/j.issn.1007-9572.2017.00.094.

17.

Kim MH, Mazenga AC, Devandra A et al. Prevalence of depression and validation of the Beck Depression Inventory-II and the Children’s Depression Inventory‐Short amongst HIV‐positive adolescents in Malawi. J Int AIDS Soc, 2014;17(1).

18.

Gomez R, Vance A, Gomez A. Children’s Depression Inventory: invariance across children and adolescents with and without depressive disorders. Psychol Assess. 2012;24(1):1–10. https://doi.org/10.1037/a0024966.CrossRefPubMed

19.

Liu F. The structure of the Childhood Depression Scale and the characteristics of depression development in children and adolescents. Psychol Dev Educ. 1997;13(2):57–61. https://doi.org/10.16187/j.cnki.issn1001-4918.1997.02.011.CrossRef

20.

Lu X. The application of confirmatory factor analysis in the preparation of questionnaires. Educational Meas Evaluation. 2008. https://doi.org/10.16518/j.cnki.emae.2008.04.001.CrossRef

21.

Dong J, Wei W, Wu K, et al. The application of machine learning in depression. Advances in Psychological Science; 2020.

22.

Chen EE, Wojcik SP. A practical guide to big data research in psychology. Psychol Methods. 2016;21(4):458–74. https://doi.org/10.1037/met0000111.CrossRefPubMed

23.

Wall DP, Dally R, Luyster R, et al. Use of Artificial Intelligence to shorten the behavioral diagnosis of Autism. PLoS ONE. 2012;7(8). https://doi.org/10.1371/journal.pone.0043855.

24.

Sun Q, Dong W, Wang K et al. Research on the validity of simplified MMPI scale based on machine learning. J Qingdao Univ 2021.

25.

Haque UM, Kabir E, Khanam R. Detection of child depression using machine learning methods. PLoS ONE. 2021;16(12). https://doi.org/10.1371/journal.pone.0261131.

26.

Shatte ABR, Hutchinson DM, Teague SJ. Machine learning in mental health: a scoping review of methods and applications. Psychol Med. 2019;49(9):1426–48. https://doi.org/10.1017/S0033291719000151.CrossRefPubMed

27.

Saqib K, Khan AF, Butt ZA. Machine learning methods for Predicting Postpartum Depression: scoping review. JMIR Ment Health. 2021;8(11):e29838. https://doi.org/10.2196/29838.CrossRefPubMedPubMedCentral

28.

Bickman L. Improving Mental Health Services: a 50-Year journey from Randomized experiments to Artificial Intelligence and Precision Mental Health. Adm Policy Ment Health. 2020;47(5):795–843. https://doi.org/10.1007/s10488-020-01065-8.CrossRefPubMedPubMedCentral

29.

Graham S, Depp C, Lee EE, et al. Artificial Intelligence for Mental Health and Mental illnesses: an overview. Curr Psychiatry Rep. 2019;21(11):116. https://doi.org/10.1007/s11920-019-1094-0.CrossRefPubMedPubMedCentral

30.

Chen Y, Xu X. Research progress on application of machine learning in liquid biopsy of lung cancer. J Air Force Med Univ. 2022;43(03):235–239243. https://doi.org/10.13276/j.issn.2097-1656.2022.02.022.CrossRef

31.

Zhang J, Zhang Y, Yin Y, et al. A review of machine learning in tumor radiotherapy. J Biomed Eng. 2019;36:879–84.

32.

Wang Y, Chen R. Comparison of application of different machine learning algorithms in classification problems. Heilongjiang Sci. 2021;12:16–8.

33.

Kosinski M, Wang Y, Lakkaraju H, et al. Mining big data to extract patterns and predict real-life outcomes. Psychol Methods. 2016;21(4):493–506. https://doi.org/10.1037/met0000105.CrossRefPubMed

34.

Priya A, Garg S, Tigga NP. Predicting anxiety, depression and stress in Modern Life using machine learning algorithms. Procedia Comput Sci. 2020;167:1258–67. https://doi.org/10.1016/j.procs.2020.03.442.CrossRef

35.

Silverman WK, Ollendick TH. Evidence-based assessment of anxiety and its disorders in children and adolescents. J Clin Child Adolesc Psychol. 2005;34(3):380–411. https://doi.org/10.1207/s15374424jccp3403_2.CrossRefPubMed

36.

Zuromski KL, Ustun B, Hwang I, et al. Developing an optimal short-form of the PTSD Checklist for DSM-5 (PCL-5). Depress Anxiety. 2019;36(9):790–800. https://doi.org/10.1002/da.22942.CrossRefPubMedPubMedCentral

37.

Chen Z, Yang X, Li X. Psychometric features of CES-D in Chinese adolescents. Chin J Clin Psychol. 2009;17(4):443–5.

38.

Ren F, Liu J, Fang Y, et al. Measurement invariance of the CES-D in adult sample. Chin J Clin Psychol. 2019;27(9):973–7. https://doi.org/10.16128/j.cnki.1005-3611.2019.05.025.CrossRef

39.

Liao J, Zheng Y, Huang M, et al. Study of PHQ-2-C,CES-D and BDI-II-C in the application of screening of adolescents with depressive disorder. J Int Psychiatry. 2017;44(1):23–5. https://doi.org/10.13479/j.cnki.jip.2017.01.003.CrossRef

40.

Yang W, Xiong G. Screening for adolescent depression: validity and cut-off scores for Depression scales. Chin J Clin Psychol. 2016;24(6):1010–5. https://doi.org/10.16128/j.cnki.1005-3611.2016.06.011.CrossRef

41.

Zhang J, Wu Z, Fang G, et al. Development of the Chinese age norms of CES-D in urban area. Chin Mental Health J. 2010;5(24):139–43.

42.

Allgaier A-K, Frühe B, Pietsch K, et al. Is the children’s Depression Inventory Short version a valid screening tool in pediatric care? A comparison to its full-length version. J Psychosom Res. 2012;73(5):369–74. https://doi.org/10.1016/j.jpsychores.2012.08.016.CrossRefPubMed

43.

Reyes AL, Langer DA. Assessment and the Journal of Clinical Child and adolescent psychology’s evidence base updates Series: evaluating the tools for gathering evidence. J Clin Child Adolesc Psychol. 2018;47(3):357–65. https://doi.org/10.1080/15374416.2018.1458314.CrossRefPubMed

44.

Stevanovic D. Childhood depression and anxiety disorders in Serbia: a psychometric study of four screening questionnaires. Epidemiol Psychiatr Sci. 2012;21(1):111–6. https://doi.org/10.1017/s2045796011000655.CrossRefPubMed

45.

Zhang Q, Wang Y, Yuan C, et al. The gender effect on the relationshiop between internet addiction and emotional and behavioral problems in adolescents. Chin J Clin Psychol. 2014;22(06):1004–9. https://doi.org/10.16128/j.cnki.1005-3611.2014.06.011.CrossRef

Title: Using machine learning to develop a five-item short form of the children’s depression inventory
Authors: Shumei Lin
Chengwei Wang
Xiuyu Jiang
Qian Zhang
Dan Luo
Jing Li
Junyi Li
Jiajun Xu
Publication date: 01-12-2024
Publisher: BioMed Central
Keywords: Mood Disorders
Affective Disorder
Published in: BMC Public Health / Issue 1/2024
Electronic ISSN: 1471-2458
DOI: https://doi.org/10.1186/s12889-024-18657-w

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Using machine learning to develop a five-item short form of the children’s depression inventory

Abstract

Background

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2024

Mortality and disability risk among older adults unable to complete grip strength and physical performance tests: a population-based cohort study from China

Comparing PrEP initiation rates by service delivery models among high risk adolescent boys and young men in KwaZulu-Natal, South Africa: findings from a population-based prospective study

Health effects of holistic housing renovation in a disadvantaged neighbourhood in the Netherlands: a qualitative exploration among residents and professionals

Impact of COVID-19 on women living with HIV who are survivors of intimate partner violence

Association between blood volatile organic aromatic compound concentrations and hearing loss in US adults

Impact of psychosocial work factors on risk of medically certified sick leave due to common mental disorders: a nationwide prospective cohort study of Norwegian home care workers