Multiple clinical features available at hospital discharge identified a cohort of individuals at substantially increased risk for suicide. Greater positive valence expressed in narrative discharge summaries was associated with substantially diminished risk. Automated tools to aid clinicians in evaluating these risks may assist in identifying high-risk individuals.

Natural language processing tools allow the characterization of sentiment–that is, terms expressing positive and negative emotion–in text. Applying such tools to electronic health records may provide insight into meaningful patient or clinician features not captured in coded data alone. We performed sentiment analysis on 2,484 hospital discharge notes for 2,010 individuals from a psychiatric inpatient unit, as well as 20,859 hospital discharges for 15,011 individuals from general medical units, in a large New England health system between January 2011 and 2014. The primary measures of sentiment captured intensity of subjective positive or negative sentiment expressed in the discharge notes. Mean scores were contrasted between sociodemographic and clinical groups in mixed effects regression models. Discharge note sentiment was then examined for association with risk for readmission in Cox regression models. Discharge notes for individuals with greater medical comorbidity were modestly but significantly lower in positive sentiment among both psychiatric and general medical cohorts (p<0.001 in each). Greater positive sentiment at discharge was associated with significantly decreased risk of hospital readmission in each cohort (~12% decrease per standard deviation above the mean). Automated characterization of discharge notes in terms of sentiment identifies differences between sociodemographic groups, as well as in clinical outcomes, and is not explained by differences in diagnosis. Clinician sentiment merits investigation to understand why and how it reflects or impacts outcomes.

Although lithium preparations remain first-line treatment for bipolar disorder, risk for development of renal insufficiency may discourage their use. Estimating such risk could allow more informed decisions and facilitate development of prevention strategies. We utilized electronic health records from a large New England health-care system between 2006 and 2013 to identify patients aged 18 years or older with a lithium prescription. Renal insufficiency was identified using the presence of renal failure by ICD9 code or laboratory-confirmed glomerular filtration rate below 60 ml/min. Logistic regression was used to build a predictive model in a random two-thirds of the cohort, which was tested in the remaining one-third. Risks associated with aspects of pharmacotherapy were also examined in the full cohort. We identified 1445 adult lithium-treated patients with renal insufficiency, matched by risk set sampling 1 : 3 with 4306 lithium-exposed patients without renal insufficiency. In regression models, features associated with risk included older age, female sex, history of smoking, history of hypertension, overall burden of medical comorbidity, and diagnosis of schizophrenia or schizoaffective disorder (p<0.01 for all contrasts). The model yielded an area under the ROC curve exceeding 0.81 in an independent testing set, with 74% of renal insufficiency cases among the top two risk quintiles. Use of lithium more than once daily, lithium levels greater than 0.6 mEq/l, and use of first-generation antipsychotics were independently associated with risk. These results suggest the possibility of stratifying risk for renal failure among lithium-treated patients. Once-daily lithium dosing and maintaining lower lithium levels where possible may represent strategies for reducing risk.

The cytochrome P450 (CYP450) system of drug-metabolizing enzymes may contribute to individual variation in drug response. We examined prevalence of CYP450 substrates at hospital discharge for patients in two cohorts: insurance claims of Massachusetts residents and the medical records of two academic medical centers. The claims cohort included 47 473 individuals (38.2%) treated with at least one CYP450 2D6, 2C19, 3A4 or 1A2 substrate. The electronic medical records cohort included 45 905 individuals (57.4%) treated with at least one substrate. In adjusted models, substrates of CYP450 2D6 and 2C19 were associated with greater risk for 90-day readmission in both cohorts (odds ratios of 1.104 and 1.128 (P<0.001), respectively). Presence of any CYP450 substrate was associated with increased monthly medical costs (+$397, P<0.003). These analyses of more than 300 000 admissions using two different cohorts and data types indicate that CYP450 substrates are associated with greater readmission rates and greater health-care cost.