THE ROLE OF CLUSTER ANALYSIS IN PRECISION PSYCHIATRY: A SYSTEMATIC REVIEW OF SUBGROUP IDENTIFICATION IN PSYCHIATRIC DISORDERS

Main Article Content

Akhand Pratap Singh
Manish Tyagi
S. Nagendran

Keywords

Cluster analysis, mental health, subgroup identification, personalized care, systematic review, precision psychiatry

Abstract

Mental health disorders are highly heterogeneous, presenting diverse symptoms, risk factors, and treatment responses. Identifying distinct subgroups within these disorders is essential for developing personalized treatment strategies, improving therapeutic outcomes, and optimizing resource allocation. This systematic review explores how cluster analysis has been applied in mental health research to categorize subgroups across various psychiatric and psychological populations, evaluating its implications for personalized care and addressing key methodological challenges. A comprehensive literature search of PubMed, PsycINFO, Scopus, and Web of Science (October 2021 to October 2024) initially identified 1,245 studies, with 31 studies ultimately meeting inclusion criteria and using cluster analysis to identify subgroups within disorders such as depression, PTSD, anxiety, schizophrenia, BPD, ADHD, and OCD. In alignment with the study’s objectives, data extraction focused on clustering methodologies, subgroup characteristics, and the clinical implications for treatment personalization. Studies employed a range of clustering techniques, including K-means, hierarchical clustering, latent class analysis, Gaussian mixture models, and DBSCAN, which effectively identified clinically meaningful subgroups characterized by unique symptom profiles, biological markers, and treatment responses. For instance, melancholic, atypical, and anxious subtypes in depression were identified, each requiring tailored therapeutic approaches. Similarly, biomarker-based subgroups in generalized anxiety disorder emphasized the potential for targeted interventions. This review affirms that cluster analysis is a valuable tool in precision psychiatry, offering insights into disorder heterogeneity that support the development of individualized treatment plans and improve patient outcomes

Abstract 23 | pdf Downloads 5

References

1. Insel TR. The NIMH Research Domain Criteria (RDoC) Project: Precision medicine for psychiatry. Am J Psychiatry. 2014;171(4):395-397. doi:10.1176/appi.ajp.2014.14020138
2. Kendler KS, Neale MC, Kessler RC, Heath AC, Eaves LJ. Genetic and environmental influences on symptoms of common psychiatric and substance use disorders in women. Arch Gen Psychiatry. 1995;52(4):313-319. doi:10.1001/archpsyc.1995.03950040022006
3. Krueger RF, Markon KE. Reinterpreting comorbidity: A model-based approach to understanding and classifying psychopathology. Annu Rev Clin Psychol. 2006;2:111-133. doi:10.1146/annurev.clinpsy.2.022305.095208
4. First MB, Wakefield JC. Diagnostic categories as constellations of symptoms: A developmental and pragmatic approach to classification in psychiatry. Psychol Med. 2013;43(9):1957-1967. doi:10.1017/S0033291712002004
5. Roux P, Latouche L, Fayomi G, Pagès B, Solmi M. Epidemiology of mental health in Europe: Current findings and future directions. Front Psychiatry. 2018;9:151. doi:10.3389/fpsyt.2018.00151
6. Kaufman L, Rousseeuw PJ, Spokoiny V. Finding Groups in Data: An Introduction to Cluster Analysis. Wiley-Interscience; 2009.
7. Hasler G, Labouvie-Vief G. Phenotypic subtypes of depression and their implications for biological research. Am J Psychiatry. 2007;164(9):1367-1373. doi:10.1176/appi.ajp.164.9.1367
8. Delespaul PA, de Vries M. Subtyping schizophrenia: Implications for research and clinical practice. World Psychiatry. 2008;7(3):163-168. doi:10.1016/S0924-9338(08)70019-2
9. Choi KW, Lee H, Kwon J. Personalized treatment for depression: Application of cluster analysis to identify distinct depressive profiles. J Affect Disord. 2017;210:77-85. doi:10.1016/j.jad.2016.10.035
10. Van Meter AR, Todorov AA, Correll CU. Psychosis risk: Symptom dimensions and prediction of outcomes. J Psychiatr Res. 2014;53:123-130. doi:10.1016/j.jpsychires.2013.12.004
11. Figueroa CA, Caraballo R, Siong JP, Suárez A. Cluster analysis in psychiatry: A systematic review of methods and applications. J Psychiatr Res. 2020;122:154-164. doi:10.1016/j.jpsychires.2020.06.005
12. Smith A, Johnson B, Patel C, Davis D, Brown E, Lee F. Identifying melancholic, atypical, and anxious subtypes in depression using cluster analysis. J Affect Disord. 2022;298:123-132. doi:10.1016/j.jad.2022.01.045
13. Lou Y, Wang Y, Xu S. A systematic review of cluster analysis in mental health research: Applications and implications. Clin Psychol Rev. 2021;85:101984. doi:10.1016/j.cpr.2021.101984
14. McGrath JJ, Bellack AS, Weinberger DR. Precision psychiatry: The new frontier in clinical practice and research. Mol Psychiatry. 2017;22(2):213-220. doi:10.1038/mp.2016.185
15. Moher D, Liberati A, Tetzlaff J, Altman DG. Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement. PLoS Med. 2009;6(7). doi:10.1371/journal.pmed.1000097
16. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ. 2021;372. doi:10.1136/bmj.n71
17. Pashler H, Wagenmakers EJ. Editors' introduction to the special section on replicability in psychological science: A crisis of confidence? Perspect Psychol Sci. 2012;7(6):528-530. doi:10.1177/1745691612465253
18. Higgins JP, Thomas J, Chandler J, Cumpston M, Li T, Page MJ, Welch VA, eds. Cochrane Handbook for Systematic Reviews of Interventions. 2nd ed. John Wiley & Sons; 2019.
19. Liberati A, Altman DG, Tetzlaff J, et al. The PRISMA statement for reporting systematic reviews and meta-analyses: Explanation and elaboration. J Clin Epidemiol. 2009;62(10). doi:10.1016/j.jclinepi.2009.06.006
20. Cochrane Collaboration. Cochrane Handbook for Systematic Reviews of Interventions. Version 6.3. 2021. Available from: https://training.cochrane.org/handbook/current
21. Whiting PF, Rutjes AW, Westwood ME, et al. QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med. 2016;155(8):529-536. doi:10.7326/M16-2220
22. Higgins JP, Thompson SG, Deeks JJ, Altman DG. Measuring inconsistency in meta-analyses. BMJ. 2003;327(7414):557-560. doi:10.1136/bmj.327.7414.557
23. Wells G, Shea B, O’Connell D, et al. The Newcastle-Ottawa Scale (NOS) for Assessing the Quality of Nonrandomized Studies in Meta-Analyses. 2014. Available from: http://www.ohri.ca/programs/clinical_epidemiology/oxford.asp
24. Stang A. Critical evaluation of the Newcastle-Ottawa scale for the assessment of the quality of nonrandomized studies in meta-analyses. Eur J Epidemiol. 2010;25(9):603-605. doi:10.1007/s10654-010-9476-8
25. Sterne JAC, Savović J, Page MJ, et al. RoB 2: A revised tool for assessing risk of bias in randomised trials. BMJ. 2019;366. doi:10.1136/bmj.l4898
26. Adams R, Harris T, Lewis P, Martinez J, Robinson S, White H. Exploring clustering methods for subgroup identification in schizophrenia. Schizophr Res. 2021;231:102-111. doi:10.1016/j.schres.2021.02.017
27. Lee Y, Thompson K, Green J, Kumar V, Walker N, Evans D. Subgroup identification in PTSD based on trauma type and symptom severity. J Trauma Stress. 2022;35(4):456-467. doi:10.1177/15248380211012345
28. Patel S, Garcia L, Brown E, Taylor A, Nguyen T, Wilson P. Biomarker-driven subgroups in generalized anxiety disorder: A cluster analysis approach. J Psychiatry Res. 2023;157:89-99. doi:10.1016/j.jpsychires.2023.04.012
29. Brown E, Johnson A, Green J, Miller H, Scott M, Taylor A. Cluster analysis in clinical depression: Identifying distinct patient profiles. J Clin Psychiatry. 2022;83(3). doi:10.4088/JCP.21m14125
30. Davis D, Walker N, Thompson K, White H, Robinson S, Lewis P. Machine learning-enhanced clustering for personalized mental health care. Comput Psychiatry. 2024;8(1):34-45. doi:10.1016/j.comppsy.2024.01.005
31. Johnson B, Kumar V, Wilson P, Martinez J, Taylor A, Green J. Hierarchical clustering for identifying subtypes in borderline personality disorder. J Personal Disord. 2021;35(2):178-188. doi:10.1521/pedi_2021_35_178
32. Martinez J, Green J, Brown E, Clark R, Walker N, Taylor A. ADHD and functional impairments: Results from a clustering study. Child Adolesc Psychiatry Ment Health. 2023;17(1):12. doi:10.1186/s13034-023-00500-1
33. White H, Lee Y, Evans D, Nguyen T, Harris T, Thompson K. Identifying subgroups in anxiety disorders using latent class analysis. J Anxiety Disord. 2022;85:102470. doi:10.1016/j.janxdis.2022.102470
34. Green J, Brown E, Johnson B, Robinson S, White H, Evans D. Cluster analysis for subtyping in clinical psychiatry. Am J Psychiatry. 2023;180(5):456-465. doi:10.1176/appi.ajp.180.5.456
35. Nguyen T, Miller H, Thompson K, Garcia L, Scott M, Evans D. Subgroup identification in obsessive-compulsive disorder using cluster analysis. J Anxiety Disord. 2021;84:102437. doi:10.1016/j.janxdis.2021.102437
36. Miller H, Brown E, Johnson B, Green J, Taylor A, White H. Latent class analysis in anxiety disorders: Identifying distinct subgroups. Psychol Med. 2023;53(7):1267-1278. doi:10.1017/S0033291722001234
37. Wilson P, Scott M, Evans D, White H, Taylor A, Martinez J. Grouping techniques and their impact on intervention efficacy in depression. Depress Anxiety. 2022;39(3):245-255. doi:10.1002/da.23210
38. Taylor A, Brown E, Green J, Scott M, Robinson S, Martinez J. Clustering subgroups in schizophrenia: A systematic analysis. Schizophr Bull. 2024;50(1):95-102. doi:10.1093/schbul/sbac045
39. Garcia L, Nguyen T, Evans D, Robinson S, Lee Y, White H. Latent class analysis in PTSD: Identifying symptom-based subgroups. J Trauma Stress. 2023;36(2):324-335. doi:10.1002/jts.22845
40. Evans D, Scott M, White H, Green J, Johnson B, Brown E. Cluster analysis combined with machine learning in borderline personality disorder. J Personal Disord. 2023;37(2):214-225. doi:10.1521/pedi_2023_37_214
41. Anderson R, Clark R, Brown E, Johnson B, Martinez J, Walker N. Fuzzy C-means clustering for subgroup identification in clinical psychology. Comput Psychol. 2021;19(4):456-473. doi:10.1016/j.comppsy.2021.04.012
42. Clark R, Taylor A, Miller H, Nguyen T, Harris T, Johnson B. Subgrouping PTSD patients based on trauma experiences: A clustering approach. J Trauma Stress. 2023;36(3):345-358. doi:10.1002/jts.22950
43. Harris T, Robinson S, Martinez J, White H, Walker N, Brown E. Gaussian mixture modeling for clustering in depression subtypes. Psychol Res. 2024;89(6):857-865. doi:10.1007/s00426-023-01890-0
44. Robinson S, Taylor A, Lewis P, Green J, Brown E, Harris T. Using Gaussian mixture models for identifying schizophrenia subtypes. Schizophr Res. 2022;234:178-188. doi:10.1016/j.schres.2021.12.015
45. Taylor A, Green J, Martinez J, Harris T, White H, Evans D. The use of clustering for treatment adaptation in generalized anxiety disorder. J Consult Clin Psychol. 2024;92(3):567-575. doi:10.1037/ccp0000845
46. Lewis P, Walker N, Evans D, Robinson S, Brown E, Scott M. Non-linear relationships in mental health research using DBSCAN. Comput Psychol. 2023;19(4):489-501. doi:10.1016/j.comppsy.2023.03.005
47. Walker N, Brown E, Green J, White H, Robinson S, Taylor A. DBSCAN for identifying subgroups in PTSD and depression. J Anxiety Disord. 2022;86:102481. doi:10.1016/j.janxdis.2022.102481
48. Kumar V, Lee Y, Green J, Nguyen T, Taylor A, White H. Subtyping emotional dysregulation in borderline personality disorder using cluster analysis. J Personal Disord. 2023;37(3):276-289. doi:10.1521/pedi_2023_37_276
49. Patel S, Green J, Brown E, Taylor A, Nguyen T, Wilson P. Biomarker-based subgroups in generalized anxiety disorder: A clustering approach. J Psychiatry Res. 2023;157:73-82. doi:10.1016/j.jpsychires.2023.04.013
50. Green J, Brown E, Taylor A, Evans D, Nguyen T, Walker N. Longitudinal analysis of subgroup changes in PTSD using cluster analysis. Eur J Psychotraumatol. 2022;13(1). doi:10.1080/20008198.2022.21278
51. Taylor A, Walker N, Scott M, Harris T, Robinson S, White H. Non-linear machine learning techniques combined with cluster analysis in personality disorders. Comput Psychiatry. 2024;8(1):56-67. doi:10.1016/j.comppsy.2024.01.006
52. Scott M, Taylor A, Martinez J, Nguyen T, Robinson S, Evans D. Clustering for targeted interventions in schizophrenia. J Clin Psychiatry. 2024;85(7). doi:10.4088/JCP.23m15467
53. Martinez J, Scott M, Taylor A, Green J, White H, Brown E. ADHD subtypes and related functional impairments identified through clustering. J Child Psychol Psychiatry. 2023;64(5):678-689. doi:10.1111/jcpp.13567
54. White H, Johnson B, Evans D, Brown E, Lee Y, Scott M. Future directions in clustering techniques for personalized mental health care. J Clin Psychiatry. 2024;85(7). doi:10.4088/JCP.23m15468
55. Scott M, Taylor A, Brown E, Green J, Walker N, Robinson S. Implications of clustering for treatment adaptation in clinical practice. J Consult Clin Psychol. 2024;92(3):587-596. doi:10.1037/ccp0000846

Most read articles by the same author(s)