Sustainability in Internal Medicine: A Year-Long Ward-Wide Observational Study

Abstract

Population aging and multimorbidity challenge health system sustainability, but the role of assistance-related variables rather than individual pathophysiological factors in determining patient outcomes is unclear. To identify assistance-related determinants of sustainable hospital healthcare, all patients hospitalised in an Internal Medicine Unit (n = 1073) were enrolled in a prospective year-long observational study and split 2:1 into a training (n = 726) and a validation subset (n = 347). Demographics, comorbidities, provenance setting, estimates of complexity (cumulative illness rating scale, CIRS: total, comorbidity, CIRS-CI, and severity, CIRS-SI subscores) and intensity of care (nine equivalents of manpower score, NEMS) were analysed at individual and Unit levels along with variations in healthcare personnel as determinants of in-hospital mortality, length of stay and nosocomial infections. Advanced age, higher CIRS-SI, end-stage cancer, and the absence of immune-mediated diseases were correlated with higher mortality. Admission from nursing homes or intensive care units, dependency on activity of daily living, community- or hospital-acquired infections, oxygen support and the number of exits from the Unit along with patient/physician ratios were associated with prolonged hospitalisations. Upper gastrointestinal tract disorders, advanced age and higher CIRS-SI were associated with nosocomial infections. In addition to demographic variables and multimorbidity, physician number and assistance context affect hospitalisation outcomes and healthcare sustainability.

Keywords: general internal medicine; healthcare resources; hospital-acquired infections; in-hospital mortality; length of stay; sustainability.

Figure 1

Multivariate derivation and validation of factors associated with in-hospital mortality. (A) depicts the classification and regression tree analysis for in-hospital mortality in the training subset. The model included age, ADL/IADL dependency, cardiovascular disorders, immune–mediated disorders, end-stage cancer, admission from nursing homes or ICUs, average cumulative illness rating scale severity index (CIRS-SI), average nine equivalents of manpower score (NEMS), circulation support with at least one vasoactive drug. Only age, CIRS-SI, end-stage cancer and (absence of) immunological disorders were identified as significant strata for patient risk classification. Based on derived, log-transformed hazard ratios (HR), four risk groups were defined (very low risk, blue; low risk, red; intermediate risk, green; high risk, orange). This classification was then applied to patients in the validation subset (B) to assess its performance in identifying patients at higher vs. lower risk of in-hospital death. Cox’s regression analysis in this subset confirmed the significant correlation between the derived risk classification and the actual risk of in-hospital mortality (Log rank = 24.91; p < 0.001).

Figure 2

Multivariate derivation and validation of factors associated with nosocomial infections. (A) depicts the classification and regression tree analysis for the development of nosocomial infections in the training subset. The model included age, cardiovascular disorders, upper gastrointestinal (GI) disorders, average cumulative illness rating scale severity index (CIRS–SI), average nine equivalents of manpower score (NEMS), use of any form of oxygen support, circulation support with at least one vasoactive drug and total number of in-ward non-standard procedures. Only age, CIRS–SI and upper GI disorders were identified as significant strata for patient risk classification. Based on derived, log-transformed hazard ratios (HR), three risk groups were defined (low risk, blue; intermediate risk, red; high risk, green). This classification was then applied to patients in the validation subset (B) to assess its performance in identifying patients at higher vs. lower risk of nosocomial infection. Cox’s regression analysis in this subset confirmed the significant correlation between the derived risk classification and the actual risk of nosocomial infection (Log rank = 5.38; p = 0.020).