Implementation of support vector machines to classify abnormal neuronal response during emotion regulation at an individual level in patients with newly diagnosed bipolar disorder – and its association with subsequent functional changes and mood episodes

Psychol Med. 2025 Nov 11;55:e338. doi: 10.1017/S0033291725101876.

ABSTRACT

BACKGROUND: In this study, a classifier (hyperplane) is determined to distinguish the neural responses during emotion regulation versus viewing images in healthy adults and then applied to determine (i) the effectiveness of the emotion regulation response (defined as emotion regulation distance from the hyperplane [DFH_ER]) in independent samples of healthy adults, patients with BD, and the patients’ unaffected relatives (URs) and (ii) the association of DFH_ER with the duration of future (hypo)manic and depressive episodes for patients with BD over a 16-month follow-up period.

METHODS: Study participants (N = 226) included 65 healthy adults (35 used for support vector machine [SVM] learning [HC_Train] and 30 kept as an independent test sample [HC_Test]), 87 patients with newly diagnosed BD (67% BD type 2) and 74 URs. BOLD response data came from an emotion regulation task. Clinical symptoms were assessed at baseline fMRI and after 16 months of specialized treatment.

RESULTS: The SVM ML analysis identified a hyperplane with 75.7% accuracy. Patients with BD showed reduced DFH_ER relative to the HC_Test and UR groups. Reduced DFH_ER was associated with reduced improvement in psychosocial functioning during the 16-month follow-up time (B = -1.663, p = 0.02).

CONCLUSIONS: The neural response during emotion regulation can be relatively well distinguished in healthy adults via ML. Patients with newly diagnosed BD show significant disruption in the recruitment of this emotion regulation response. Disrupted may indicate a reduced capacity for functional improvement during specialized treatment in a mood disorder clinic.

PMID:41216716 | DOI:10.1017/S0033291725101876