Development of a predictive model of hospitalization in primary care patients with heart failure

Abstract

Background Heart failure (HF) is the leading cause of hospitalization in people over age 65. Predictive hospital admission models have been developed to help reduce the number of these patients. Aim To develop and internally validate a model to predict hospital admission in one-year for any non-programmed cause in heart failure patients receiving primary care treatment. Design and setting Cohort study, prospective. Patients treated in family medicine clinics. Methods Logistic regression analysis was used to estimate the association between the predictors and the outcome, i.e. unplanned hospitalization over a 12-month period. The predictive model was built in several steps. The initial examination included a set of 31 predictors. Bootstrapping was used for internal validation. Results The study included 251 patients, 64 (25.5%) of whom were admitted to hospital for some unplanned cause over the 12 months following their date of inclusion in the study. Four predictive variables of hospitalization were identified: NYHA class III-IV, OR (95% CI) 2.46 (1.23–4.91); diabetes OR (95% CI) 1.94 (1.05–3.58); COPD OR (95% CI) 3.17 (1.45–6.94); MLHFQ Emotional OR (95% CI) 1.07 (1.02–1.12). AUC 0.723; R2N 0.17; Hosmer-Lemeshow 0.815. Internal validation AUC 0.706.; R2N 0.134 Conclusion This is a simple model to predict hospitalization over a 12-month period based on four variables: NYHA functional class, diabetes, COPD and the emotional dimension of the MLHFQ scale. It has an acceptable discriminative capacity enabling the identification of patients at risk of hospitalization.

Man vs. Machine: Comparing Physician vs. Electronic Health Record–Based Model Predictions for 30-Day Hospital Readmissions

“…[11][12][13][14][15][16][17][18] A growing body of evidence suggests that social, functional, and behavioral factors are associated with increased risk of readmission, and that incorporating this information into prediction models improves readmission risk prediction across a variety of conditions. [19][20][21][22][23][24][25][26][27][28][29][30] However, at present, this information is not uniformly available in EHRs. 31 Clinician perceptions of readmission risk are readily ascertainable and may incorporate valuable information on severity and complexity of patient illness, as well as information on social, functional, and behavioral factors unavailable in the EHR, but the comparative accuracy of physician predictions for 30-day readmissions is not well established.…”