Clinically Weighted Feature Fusion for Unsupervised Identification of Postpartum Depression and Anxiety Risk Subgroups Among Breastfeeding Mothers
DOI:
https://doi.org/10.62411/jcta.17824Keywords:
Breastfeeding, Clinically weighted feature fusion, Held-out validation, Postpartum anxiety, Postpartum depression, Psychological risk subgroups, Semi-supervised clustering, Spearman correlationAbstract
Postpartum depression and anxiety often go undetected, and breastfeeding experience is among the factors most strongly linked to both. However, previous research has largely been supervised, dependent on biomarkers, and rarely captures the heterogeneity of risk profiles among mothers with similar symptom levels. This study proposes Clinically Weighted Feature Fusion (CWFF), a clustering framework that weights clinical composite features based on their out-of-fold association with EPDS and GAD-7 scores, to map postpartum depression and anxiety risk subgroups among 2,010 breastfeeding mothers in the United Kingdom. As a foundation, 22 composite features representing five clinical domains were compared with 30 raw variables using K-Means (k = 4). The engineered approach with equal weighting (equal-weight) showed better clustering quality, marked by a 28.2% increase in the Silhouette Score, a 21.8% decrease in the Davies–Bouldin Index, and a 26.8% increase in the Calinski–Harabasz Index; all significant based on bootstrap testing (p < 0.0001). Ablation analysis of leave-one-domain-out and leave-one-interaction-term-out (Friedman χ² = 794.15; p < 0.001) shows that this improvement mainly comes from Interaction Features and Mental Health History, not from all domains uniformly. This advantage is also only consistent for K-Means and Agglomerative Clustering, not for Gaussian Mixture Model (GMM) or HDBSCAN. Then, applying CWFF, the results show that CWFF raises Silhouette from 0.1537 to 0.2418 while also raising clinical validity (η²_EPDS from 0.071 to 0.096; η²_GAD-7 from 0.090 to 0.123), with all improvements significant (bootstrap 95% CI does not include zero). These findings indicate that clinically informed weighting improves risk-subgroup identification compared to equal-weight, potentially supporting low-cost postpartum screening in primary healthcare settings.References
S. García-Méndez and F. de Arriba-Pérez, “Detecting and Explaining Postpartum Depression in Real-Time with Generative Artificial Intelligence,” Appl. Artif. Intell., vol. 39, no. 1, pp. 1–27, Dec. 2025, doi: 10.1080/08839514.2025.2515063.
E. M. Nagel et al., “Maternal Psychological Distress and Lactation and Breastfeeding Outcomes: a Narrative Review,” Clin. Ther., vol. 44, no. 2, pp. 215–227, Feb. 2022, doi: 10.1016/j.clinthera.2021.11.007.
H. Lin et al., “A Clinically Practical Postpartum Depression Predictor: Machine Learning Model Based on Simplified Indicators,” Research Square. pp. 1–22, Aug. 01, 2025. doi: 10.21203/rs.3.rs-7079798/v1.
W. A. Fazraningtyas, B. Rahmatullah, H. Naparin, M. Basit, and N. A. Razak, “A predictive model for postpartum depression: ensemble learning strategies in machine learning,” Indones. J. Electr. Eng. Comput. Sci., vol. 37, no. 1, p. 443, Jan. 2025, doi: 10.11591/ijeecs.v37.i1.pp443-451.
Z. Wang et al., “Mapping global prevalence of depression among postpartum women,” Transl. Psychiatry, vol. 11, no. 1, p. 543, Oct. 2021, doi: 10.1038/s41398-021-01663-6.
E. Hellyer et al., “Postnatal Depression Beyond 12 Months: A Systematic Review and Meta‐Analysis,” Int. J. Ment. Health Nurs., vol. 34, no. 2, pp. 1–13, Apr. 2025, doi: 10.1111/inm.70018.
H. Lei, Y. Yang, T. Zhu, X. Zhang, and J. Dang, “Network analysis of the relationship between non-suicidal self-injury, depression, and childhood trauma in adolescents,” BMC Psychol., vol. 12, no. 1, p. 234, Apr. 2024, doi: 10.1186/s40359-024-01729-2.
E. C. Braithwaite, A. Oftedal, A. Kaasen, Z. Ayorech, and M. Bekkhus, “A history of depression and prenatal depression are associated with a lower likelihood of breastfeeding initiation and maintenance, and more breastfeeding problems,” Arch. Womens. Ment. Health, vol. 28, no. 1, pp. 139–146, Feb. 2025, doi: 10.1007/s00737-024-01479-5.
M. L. Gianni et al., “Breastfeeding Difficulties and Risk for Early Breastfeeding Cessation,” Nutrients, vol. 11, no. 10, p. 2266, Sep. 2019, doi: 10.3390/nu11102266.
R. Alimi, E. Azmoude, M. Moradi, and M. Zamani, “The Association of Breastfeeding with a Reduced Risk of Postpartum Depression: A Systematic Review and Meta-Analysis,” Breastfeed. Med., vol. 17, no. 4, pp. 290–296, Apr. 2022, doi: 10.1089/bfm.2021.0183.
S. I. Franklyn, J. Stewart, C. Beaurepaire, E. Thaw, and R. J. McQuaid, “Developing symptom clusters: linking inflammatory biomarkers to depressive symptom profiles,” Transl. Psychiatry, vol. 12, no. 1, p. 133, Mar. 2022, doi: 10.1038/s41398-022-01900-6.
C. Orchard, E. Lin, L. Rosella, and P. M. Smith, “Using unsupervised clustering approaches to identify common mental health profiles and associated mental health-care service-use patterns in Ontario, Canada,” Am. J. Epidemiol., vol. 193, no. 7, pp. 976–986, Jul. 2024, doi: 10.1093/aje/kwae030.
P. Vogazianos, E. Motrico, S. Domínguez-Salas, A. Christoforou, and E. Hadjigeorgiou, “Validation of the generalized anxiety disorder screener (GAD-7) in Cypriot pregnant and postpartum women,” BMC Pregnancy Childbirth, vol. 22, no. 1, p. 841, Nov. 2022, doi: 10.1186/s12884-022-05127-7.
C. Garbazza et al., “A machine learning model to predict the risk of perinatal depression: Psychosocial and sleep-related factors in the Life-ON study cohort,” Psychiatry Res., vol. 337, p. 115957, Jul. 2024, doi: 10.1016/j.psychres.2024.115957.
P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” J. Comput. Appl. Math., vol. 20, pp. 53–65, Nov. 1987, doi: 10.1016/0377-0427(87)90125-7.
M. Nedyalkova, S. Madurga, and V. Simeonov, “Combinatorial K-Means Clustering as a Machine Learning Tool Applied to Diabetes Mellitus Type 2,” Int. J. Environ. Res. Public Health, vol. 18, no. 4, p. 1919, Feb. 2021, doi: 10.3390/ijerph18041919.
E. Prasetyaningrum, A. Z. Fanani, and D. W. Prabowo, “Identification of High-Risk Breastfeeding Mother Subgroups Through K-Means Clustering and Principal Component Analysis (Pca),” Preprints. Jun. 22, 2026. doi: 10.20944/preprints202606.1553.v1.
R. B. GulMohamed et al., “AI Based Early Prediction of Postpartum Depression Using Multidimensional Maternal Health Data with Integrated Secure Data Storage and Privacy Protection Protocols,” J. Internet Serv. Inf. Secur., vol. 16, no. 1, pp. 548–569, Feb. 2026, doi: 10.58346/JISIS.2026.I1.031.
G. Rowles et al., “Investigating the impact of breastfeeding difficulties on maternal mental health,” Sci. Rep., vol. 15, no. 1, p. 13572, Apr. 2025, doi: 10.1038/s41598-025-98357-6.
W. Zhang, K. Mao, and J. Chen, “A Multimodal Approach for Detection and Assessment of Depression Using Text, Audio and Video,” Phenomics, vol. 4, no. 3, pp. 234–249, Jun. 2024, doi: 10.1007/s43657-023-00152-8.
W. A. Fazraningtyas, B. Rahmatullah, D. Dwi Salmarini, S. Arrieya Ariffin, and A. Ismail, “Recent advancements in postpartum depression prediction through machine learning approaches: a systematic review,” Bull. Electr. Eng. Informatics, vol. 13, no. 4, pp. 2729–2737, Aug. 2024, doi: 10.11591/eei.v13i4.7185.
T. L. Galankin, A. Y. Bespalov, and H. Y. Moebius, “Clusterization of Behavioral and Psychological Symptoms of Dementia as Assessed by Neuropsychiatric Inventory: A Case Against the Use of Principal Component Analysis,” J. Alzheimer’s Dis., vol. 98, no. 4, pp. 1483–1491, Apr. 2024, doi: 10.3233/JAD-231008.
D. Usman and I. Bin Mohamad, “Standardization and Its Effects on K-Means Clustering Algorithm,” Res. J. Appl. Sci. Eng. Technol., vol. 6, no. 17, pp. 3299–3303, Sep. 2013, doi: 10.19026/rjaset.6.3638.
D. M. Mathkor, “Explicating the interplay of maternal work stress, breastfeeding, mental health, and infant attachment using machine learning and statistical modeling,” J. King Saud Univ. – Sci., vol. 38, no. 2, p. 15372025, Jan. 2026, doi: 10.25259/JKSUS_1537_2025.
E. Braithwaite et al., “A mixed-methods dataset on maternal reported experiences of breastfeeding difficulties and mental health in the UK,” Data Br., vol. 61, p. 111700, Aug. 2025, doi: 10.1016/j.dib.2025.111700.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Eka Prasetyaningrum, Amiq Fahmi, Purwanto
This work is licensed under a Creative Commons Attribution 4.0 International License.
