Heart failure (HF) is one of the leading causes of mortality and hospitalization worldwide. The accurate prediction of mortality and readmission risk provides crucial information for guiding decision making. Unfortunately, traditional predictive models reached modest accuracy in HF populations. We therefore aimed to present predictive models based on machine learning (ML) techniques in HF patients that were externally validated. We searched four databases and the reference lists of the included papers to identify studies in which HF patient data were used to create a predictive model. Literature screening was conducted in Academic Search Ultimate, ERIC, Health Source Nursing/Academic Edition and MEDLINE. The protocol of the current systematic review was registered in the PROSPERO database with the registration number CRD42022344855. We considered all types of outcomes: mortality, rehospitalization, response to treatment and medication adherence. The area under the receiver operating characteristic curve (AUC) was used as the comparator parameter. The literature search yielded 1649 studies, of which 9 were included in the final analysis. The AUCs for the machine learning models ranged from 0.6494 to 0.913 in independent datasets, whereas the AUCs for statistical predictive scores ranged from 0.622 to 0.806. Our study showed an increasing number of ML predictive models concerning HF populations, although external validation remains infrequent. However, our findings revealed that ML approaches can outperform conventional risk scores and may play important role in HF management.

Background: Dietary sodium restriction remains a guidelines-approved lifestyle recommendation for chronic heart failure (CHF) patients. However, its efficacy in clinical outcome improvement is dubious. Objective: The study evaluated whether dietary sodium restriction in CHF reduces clinical events. Methods: We performed a systematic review of the following databases: Academic Search Ultimate, ERIC, Health Source Nursing/Academic Edition, MEDLINE, Embase, Clinicaltrials.gov and Cochrane Library (trials) to find studies analysing the impact of sodium restriction in the adult CHF population. Both observational and interventional studies were included. Exclusion criteria included i.e.: sodium consumption assessment based only on natriuresis, in-hospital interventions or mixed interventions—e.g. sodium and fluid restriction in one arm only. The review was conducted following PRISMA guidelines. Meta-analysis was performed for the endpoints reported in at least 3 papers. Analyses were conducted in Review Manager (RevMan) Version 5.4.1. Results: Initially, we screened 9175 articles. Backward snowballing revealed 1050 additional articles. Eventually, 9 papers were evaluated in the meta-analysis. All-cause mortality, HF-related hospitalizations and the composite of mortality and hospitalisation were reported in 8, 6 and 3 articles, respectively. Sodium restriction was associated with a higher risk of the composite endpoint (OR 4.12 [95% CI 1.23–13.82]) and did not significantly affect the all-cause mortality (OR 1.38 [95% CI 0.76–2.49]) or HF hospitalisation (OR 1.63 [95% CI 0.69–3.88]). Conclusions: In a meta-analysis, sodium restriction in CHF patients worsened the prognosis in terms of a composite of mortality and hospitalizations and did not influence all-cause mortality and HF hospitalisation rate. Graphical

Despite the progress of its management, COVID-19 maintains an ominous condition which constitutes a threat, especially for the susceptible population. The cardiac injury occurs in approximately 30% of COVID-19 infections and is associated with a worse prognosis. The clinical presentation of cardiac involvement can be COVID-19-related myocarditis. Our review aims to summarise current evidence about that complication. The research was registered at PROSPERO (CRD42022338397). We performed a systematic analysis using five different databases, including i.a. MEDLINE. Further, the backward snowballing technique was applied to identify additional papers. Inclusion criteria were: full-text articles in English presenting cases of COVID-19-related myocarditis diagnosed by the ESC criteria and patients over 18 years old. The myocarditis had to occur after the COVID-19 infection, not vaccination. Initially, 1588 papers were screened from the database search, and 1037 papers were revealed in the backward snowballing process. Eventually, 59 articles were included. Data about patients’ sex, age, ethnicity, COVID-19 confirmation technique and vaccination status, reported symptoms, physical condition, laboratory and radiological findings, applied treatment and patient outcome were investigated and summarised. COVID-19-related myocarditis is associated with the risk of sudden worsening of patients’ clinical status, thus, knowledge about its clinical presentation is essential for healthcare workers.

Acute heart failure (AHF) is a life-threatening, heterogeneous disease requiring urgent diagnosis and treatment. The clinical severity and medical procedures differ according to a complex interplay between the deterioration cause, underlying cardiac substrate, and comorbidities. This study aimed to analyze the natural phenotypic heterogeneity of the AHF population and evaluate the possibilities offered by clustering (unsupervised machine-learning technique) in a medical data assessment. We evaluated data from 381 AHF patients. Sixty-three clinical and biochemical features were assessed at the admission of the patients and were included in the analysis after the preprocessing. The K-medoids algorithm was implemented to create the clusters, and optimization, based on the Davies-Bouldin index, was used. The clustering was performed while blinded to the outcome. The outcome associations were evaluated using the Kaplan-Meier curves and Cox proportional-hazards regressions. The algorithm distinguished six clusters that differed significantly in 58 variables concerning i.e., etiology, clinical status, comorbidities, laboratory parameters and lifestyle factors. The clusters differed in terms of the one-year mortality (p = 0.002). Using the clustering techniques, we extracted six phenotypes from AHF patients with distinct clinical characteristics and outcomes. Our results can be valuable for future trial constructions and customized treatment.

Heart failure is one of the leading causes of death in developed countries and remains a significant burden to the healthcare system. Fluid overload is a process responsible for the majority of the heart failure symptoms. Pharmacotherapy is a first-line treatment for this condition; however, due to the phenomenon of diuretic resistance, drug therapy can frequently be insufficient. Ultrafiltration is a promising but still understudied procedure that effectively targets the underlying pathophysiological mechanisms of congestion. The increased availability of simplified ultrafiltration devices, especially in intensive care units, prompted us to perform a current literature review on this treatment. In the present paper, we provide a concise review of the published trials on ultrafiltration, with a brief commentary on their conclusions and shortcomings. We also discuss the practical aspects of this treatment that remain unclear, such as the accurate selection of patients, choosing a suitable protocol for ultrafiltration, the proper time of initiation, monitoring of the therapy, and its desirable effects on renal function with further restoration of diuretic agent responsiveness.

Acute heart failure (AHF) is a common and severe condition with a poor prognosis. Its course is often complicated by worsening renal function (WRF), exacerbating the outcome. The population of AHF patients experiencing WRF is heterogenous, and some novel possibilities for its analysis have recently emerged. Clustering is a machine learning (ML) technique that divides the population into distinct subgroups based on the similarity of cases (patients). Given that, we decided to use clustering to find subgroups inside the AHF population that differ in terms of WRF occurrence. We evaluated data from the three hundred and twelve AHF patients hospitalized in our institution who had creatinine assessed four times during hospitalization. Eighty-six variables evaluated at admission were included in the analysis. The k-medoids algorithm was used for clustering, and the quality of the procedure was judged by the Davies–Bouldin index. Three clinically and prognostically different clusters were distinguished. The groups had significantly (p = 0.004) different incidences of WRF. Inside the AHF population, we successfully discovered that three groups varied in renal prognosis. Our results provide novel insight into the AHF and WRF interplay and can be valuable for future trial construction and more tailored treatment.