Impact of history of mental disorders on short-term mortality among hospitalized patients with sepsis: A population-based cohort study

Abstract

Background: Mental disorders are associated with markedly reduced life expectancy, in part due to an increased risk of death due to infection, likely reflecting sepsis-associated mortality. Patients with mental disorders are at an increased risk of sepsis, but data on the prognostic impact of mental disorders in sepsis are sparse, showing conflicting findings.

Methods: We used statewide data to identify hospitalizations aged ≥18 years with sepsis in Texas during 2014-2017. Mental disorders, including mood, anxiety, psychosis, and personality disorders were identified using Clinical Classification Software codes. Multilevel, multivariable logistic regression with propensity adjustment (primary model), with propensity score matching, and multivariable logistic regression as alternative models, were used to estimate the association between mental disorders and short-term mortality (defined as in-hospital mortality or discharge to hospice). Additional models were fitted for sensitivity analyses and to estimate the prognostic associations of individual categories of mental disorders.

Results: Among 283,025 hospitalizations with sepsis, 56,904 (20.1%) had mental disorders. Hospitalizations with vs without mental disorders were younger (age 18-44 years 12.2% vs 10.6%), more commonly white (61.0% vs 49.8%), with lower burden of comorbidities (mean [SD] Deyo comorbidity index 2.53 [2.27] vs 2.73 [2.47]), and with lower need for organ support (mechanical ventilation 32.8% vs 36.0%); p<0.0001 for all comparisons. Crude short-term mortality among sepsis hospitalizations with and without mental disorders was 25.0% vs 32.8%, respectively. On adjusted analyses, mental disorders remained associated with lower odds of short-term mortality (adjusted odds ratio 0.792 [95% CI 0.772-0.812]). This finding was consistent on the alternative modeling approaches, sensitivity analyses, and examination of individual categories of mental disorders.

Conclusions: Mental disorders were associated, unexpectedly, with markedly lower risk of short-term mortality in sepsis. Further studies to examine the mechanisms underlying these findings may inform future efforts to improve sepsis outcomes.

Fig 1. Subgroup analyses of short-term mortality of septic hospitalizations with and without mental disorders.

Analyses were done using multilevel multivariable logistic regression with propensity adjustment. The odds ratios and 95% confidence intervals have not been adjusted for multiplicity and should not be used to infer definite effects.