Drug-dependent risk of self-harm in patients with bipolar disorder: a comparative effectiveness study using machine learning imputed outcomes.

Background Incomplete suicidality coding in administrative claims data is a known obstacle for observational studies. With most of the negative outcomes missing from the data, it is challenging to assess the evidence on treatment strategies for the prevention of self-harm in bipolar disorder (BD), including pharmacotherapy and psychotherapy. There are conflicting data from studies on the drug-dependent risk of self-harm, and there is major uncertainty regarding the preventive effect of monotherapy and drug combinations. Objective The aim of this study is to compare all commonly used BD pharmacotherapies, as well as psychotherapy for risk of self-harm in a large population of commercially insured individuals, using self-harm imputation to overcome the known limitations of this outcome being under-recorded within US electronic healthcare records. Methods The IBM MarketScan® administrative claims database was used to compare self-harm risk in patients with BD following 65 drug regimens and drug-free periods. Probable but uncoded self-harm events were imputed via machine learning, with different probability thresholds examined in a sensitivity analysis. Comparators included lithium, mood-stabilizing anticonvulsants (MSAs), second-generation antipsychotics (SGAs), first-generation antipsychotics (FGAs), and 5 classes of antidepressants. Cox regression models with time-varying covariates were built for individual treatment regimens, and for any pharmacotherapy with or without psychosocial interventions ("psychotherapy"). Results Out of 529,359 patients 1.66% had imputed and/or coded self-harm following the exposure of interest (N=8,813 events). A higher self-harm risk was observed during adolescence. After multiple testing adjustment (p ≤0.012), six regimens were of higher risk of self-harm than lithium: tri/tetracyclic antidepressant+SGA, FGA+MSA, FGA, serotonin-norepinephrine reuptake inhibitors (SNRI)+SGA, lithium+MSA, and lithium+SGA [hazard ratios (HRs) ranged 1.44-2.29]. Nine were of lower risk: lamotrigine, valproate, risperidone, aripiprazole, SNRI, SSRI, "No drug", bupropion, and bupropion+SSRI (HRs ranged 0.28-0.74). Psychotherapy alone (without medication) had a lower self-harm risk than no treatment (HR=0.56, 95%CI=0.52-0.60, p=8.76×10-58). The sensitivity analysis showed that the direction of drug-outcome associations did not change as a function of self-harm probability threshold. Conclusions Our data support the evidence on the effectiveness of antidepressants, MSAs, and psychotherapy for self-harm prevention in BD. Clinicaltrial ClinicalTrials.gov NCT02893371.