Predicting clinical outcome to specialist multimodal inpatient treatment in patients with treatment resistant depression.

Abstract

BACKGROUND\nTreatment resistant depression (TRD) poses a significant clinical challenge, despite a range of efficacious specialist treatments. Accurately predicting response a priori may help to alleviate the burden of TRD. This study sought to determine whether outcome prediction can be achieved in a specialist inpatient setting.\n\n\nMETHODS\nPatients at the Affective Disorders Unit of the Bethlam Royal Hospital, with current depression and established TRD were included (N\xa0=\xa0174). Patients were treated with an individualised combination of pharmacotherapy and specialist psychological therapies. Predictors included clinical and sociodemographic characteristics, and polygenic risk scores for depression and related traits. Logistic regression models examined associations with outcome, and predictive potential was assessed using elastic net regularised logistic regressions with 10-fold nested cross-validation.\n\n\nRESULTS\n47% of patients responded (50% reduction in HAMD-21 score at discharge). Age at onset and number of depressive episodes were positively associated with response, while degree of resistance was negatively associated. All elastic net models had poor performance (AUC<0.6). Illness history characteristics were commonly retained, and the addition of genetic risk scores did not improve performance.\n\n\nLIMITATIONS\nThe patient sample was heterogeneous and received a variety of treatments. Some variable associations may be non-linear and therefore not captured.\n\n\nCONCLUSIONS\nThis treatment may be most effective for recurrent patients and those with a later age of onset, while patients more severely treatment resistant at admission remain amongst the most difficult to treat. Individual level prediction remains elusive for this complex group. The assessment of homogenous subgroups should be one focus of future investigations.