 |
For the study, Juliet Edgcomb, M.D., Ph.D., of the University of California, Los Angeles, and colleagues analyzed electronic health record data of patients seen in the emergency department within the University of California Health Care System between 2006 and 2016. Specifically, the researchers focused on patients aged 18 and older with bipolar disorder, a comorbid medical illness, and at least one hospitalization during the study period.
In total, 552 patients with bipolar disorder and serious comorbid medical illness with 1,250 hospital admissions were included in the analysis. The researchers used a machine learning model to identify potential predictors of 30-day psychiatric readmission across these 1,250 hospital admissions.
The model predicted 30-day readmission with high accuracy, the authors reported. Predictors of readmission included the initial hospitalization length of stay, transfers between medical and psychiatric services, circumstances of discharge, and use of health services in the year prior to the index hospitalization.
“[I]ndividuals with short length of stay and rapid transfer may be more vulnerable to gaps in care and subsequent decompensation,” Edgcomb and colleagues wrote. “For these patients, interventions such as early consultation with psychiatry, involvement of interdisciplinary teams to address psychosocial needs, ongoing medical care during psychiatric hospitalization, and coordination of robust psychiatric and medical aftercare services may be particularly important to mitigate this vulnerability.”
For related information, see the Psychiatric Services article “Outpatient Follow-Up Care and Risk of Hospital Readmission in Schizophrenia and Bipolar Disorder.”
(Image: hxdbzxy/Shutterstock)
