Registered report protocol: A scoping review to identify potential predictors as features for developing automated estimation of the probability of being frail in secondary care.

INTRODUCTION: The impact of frailty surges, as the prevalence increases with age and the population age is rising. Frailty is associated with adverse health outcomes and increased healthcare costs. Many validated instruments to detect frailty have been developed. Using these in clinical practice takes time. Automated estimation of the probability of being frail using routinely collected data from hospital electronic health records (EHRs) would circumvent that. We aim to identify potential predictors that could be used as features for modeling algorithms on the basis of routine hospital EHR data to incorporate in an automated tool for estimating the probability of being frail. METHODS: PubMed (MEDLINE), CINAHL Plus, Embase, and Web of Science will be searched. The studied population consists of older people (≥65 years). The first step is searching articles published ≥2018. Second, we add two published literature reviews (and the articles included therein) [Bery 2020; Bouillon, 2013] to our search results. In these reviews, articles on potential predictor variables in frailty screening tools were included from inception until March 2018. The goal is to identify and extract all potential predictors of being frail. Domain experts will be consulted to evaluate the results. DISCUSSION: The results of the intended study will increase the quality of the developed algorithms to be used for automated estimation of the probability of being frail in secondary care. This is a promising perspective, being less labor-intensive compared to screening each individual patient by hand. Also, such an automated tool may raise awareness of frailty, especially in those patients who would not be screened for frailty by hand because they seem robust. CONCLUSION: The identified potential predictors of being frail can be used as evidence-based input for machine learning based automated estimation of the probability of being frail using routine EHR data in the near future.

Acute heart failure and iron deficiency: a prospective, multicentre, observational study.

AIMS: The prevalence and the natural course of iron deficiency (ID) in acute heart failure (AHF) are still unclear. We investigated the prevalence of ID in unselected patients admitted with AHF on admission, at discharge and up to 3 months thereafter. METHODS AND RESULTS: In this prospective, multicentre, observational study, 742 patients admitted with AHF were enrolled. The main study outcome was the percentage of patients with ID (ferritin <100 µg/L = absolute ID or ferritin 100-299 µg/L and transferrin saturation <20% = functional ID) at admission (T0), after clinical stabilization prior to discharge (T1), and 10 ± 6 weeks after discharge (T2). At T0, ID was present in 71.8% of the patients (44.1% absolute and 27.7% functional ID). At T1 and T2, ID was present in 56.4% (32.4% absolute and 24% functional ID) and 50.3% (36.8% absolute and 13.5% functional ID), respectively. Absolute ID persisted from T0 to T2 in 66% of the patients, while functional ID resolved in 56% of the patients. Ferritin (median [interquartile range] 124 µg/L [56-247] to 150 µg/L [73-277]), transferrin saturation (15% [10-20] to 18% [12-27]), and iron levels (9 µmol/L [6-13] to 11 µmol/L [8-16]) increased significantly (all P < 0.001) from T0 to T1. Transferrin saturation (to 21% [15-29]) and iron levels (to 13 µmol/L [9-17]) also increased significantly (both P < 0.01) from T1 to T2 without iron supplementation. CONCLUSIONS: Iron deficiency is highly prevalent in patients with AHF, but resolves during treatment in some patients, even without iron supplementation. Absolute ID is more likely to persist over time, whereas functional ID often resolves during treatment of AHF, representing probably a reduced iron availability rather than a true deficiency.