We develop a predictive prognosis model to support medical experts in their clinical decision-making process in Intensive Care Units (ICUs) (a) to enhance early mortality prediction, (b) to make more efficient medical decisions about patients at higher risk, and (c) to evaluate the effectiveness of new treatments or detect changes in clinical practice. It is a machine learning hierarchical model based on Bayesian classifiers built from some recorded features of a real-world ICU cohort, to bring about the assessment of the risk of mortality, also predicting destination at ICU discharge if the patient survives, or the cause of death otherwise, constructed as an ensemble of five base Bayesian classifiers by using the average ensemble criterion with weights, and we name it the Ensemble Weighted Average (EWA). We compare EWA against other state-of-the-art machine learning predictive models. Our results show that EWA outperforms its competitors, presenting in addition the advantage over the ensemble using the majority vote criterion of allowing to associate a confidence level to the provided predictions. We also prove the convenience of locally recalibrate from data the standard model used to predict the mortality risk based on the APACHE II score, although as a predictive model it is weaker than the other.

Background: Clinical guidelines recommend frailty screening for the aged population, given that frailty is frequently reversible. However, little is known about frailty and prefrailty reversal rates in the general population if no specific interventions have been implemented.Aim: To assess real-world frailty and prefrailty reversal rates in the general population aged ≥65 years, the main contributing clinical conditions and the main risk factors for reversing frailty and prefrailty.Methods: Observational longitudinal 12-month study (2019) of all 1·5 million persons aged ≥65 years in Catalonia. Data were retrospectively collected from various health databases through the Catalan Public Data Analysis for Health Research and Innovation (PADRIS) V.2022 programme. Frailty status according to the electronic Screening Index for Frailty (e-SIF) was determined for 31 December 2018 and for 31 December 2019.Results: The study included 1 465 312 Catalan inhabitants (mean age 75.8 years, 57.0% women). The annual frailty and pre-frailty reversal rates were 7.1% and 4.6%, respectively. Both rates were higher in men and decreased with age. The e-SIF components with the greatest impact on frailty reversal were non-planned hospitalisations, polypharmacy, orthostatic hypotension or syncope, anaemia and visual impairment. Female sex, age, dependency, ≥2 comorbidities and polypharmacy had an independent protective effect on 12-month frailty and pre-frailty reversals.Conclusions: Prefrailty and frailty are reversible, but reversal is unlikely in cases of multimorbidity, polypharmacy and functional dependency in older and severely frail individuals. Interventions that mainly target the avoidance of non-planned hospitalisations, polypharmacy and falls would have the greatest impact on reversing frailty and pre-frailty.

Aim: The aim was to assess the effectiveness of 23-valent pneumococcal polysaccharide vaccine (PPV23) in preventing CAP in adults. Methods: This was a population-based cohort study, followed up over 5 years (2015–2019), that included 47,768 persons aged ≥18 years assigned to three primary care centres. Data were retrospectively obtained from electronic medical records and databases. The vaccination effect was adjusted for potential confounders. Analyses were performed for the entire study population and for the ≥65 age subgroup. Results: The annual incidence of CAP (per 10³ adult inhabitants) was 3.29 overall, and 8.08 and 2.93 for vaccinated and non-vaccinated persons, respectively. The non-adjusted effect of PPV23 on CAP was evidenced by HR = 2.80 (95% CI: 2.32–3.37), and after adjusting for possible confounders, PPV23 showed no significant independent effect on CAP in the overall population (HR = 1.14; p = 0.277) or in persons aged ≥65 years (HR = 1.30; p = 0.051). No protective effect was observed in persons vaccinated <2 years previously (HR = 1.17; p = 0.514). Conclusions: PPV23 showed no effect in preventing CAP in adults aged ≥18 years or in the subgroup aged ≥65 years, even if vaccinated <2 years previously.