Forecasting the spread of SARS-CoV-2 in the campania region using genetic programming

Increased prevalence of cardiovascular-kidney-metabolic syndrome during COVID-19: A propensity score-matched study

A recent presidential advisory from the American Heart Association (AHA) has introduced the term cardiovascular-kidney-metabolic (CKM) syndrome to describe the complex interplay among health conditions linking heart, kidney, and metabolism. The aim of our study was to compare the prevalence of concurrent CKM syndrome components before and during the COVID-19 pandemic and identify associated risk factors. We conducted a study utilizing data from a real-world population obtained from a primary care database. The study cohort comprised a closed group followed over a 6-year period (2017-2022). A total of 81,051 individuals were included: 32,650 in the pre-pandemic period and 48,401 in the 2020-2022 triennium. After propensity-score matching for sex, age, and BMI, the study included 30,511 participants for each period. 3554 individuals were diagnosed with type 2 diabetes in the pre-pandemic period, compared to 7430 during the pandemic. Hypertension, dyslipidemia, and obesity displayed significant increases in prevalence during the pandemic, and prediabetes had a particularly sharp rise of 170%. Age-stratified analyses revealed a higher burden of CKM conditions with advancing age. Our findings indicate a substantial increase in the prevalence of CKM syndrome during the COVID-19 pandemic, with nearly half of the patients exhibiting one or more CKM syndrome components.

An explainable model for predicting Worsening Heart Failure based on genetic programming

Heart Failure (HF) poses a challenge for our health systems, and early detection of Worsening HF (WHF), defined as a deterioration in symptoms and clinical and instrumental signs of HF, is vital to improving prognosis. Predicting WHF in a phase that is currently undiagnosable by physicians would enable prompt treatment of such events in patients at a higher risk of WHF. Although the role of Artificial Intelligence in cardiovascular diseases is becoming part of clinical practice, especially for diagnostic and prognostic purposes, its usage is often considered not completely reliable due to the incapacity of these models to provide a valid explanation about their output results. Physicians are often reluctant to make decisions based on unjustified results and see these models as black boxes. This study aims to develop a novel diagnostic model capable of predicting WHF while also providing an easy interpretation of the outcomes. We propose a threshold-based binary classifier built on a mathematical model derived from the Genetic Programming approach. This model clearly indicates that WHF is closely linked to creatinine, sPAP, and CAD, even though the relationship of these variables and WHF is almost complex. However, the proposed mathematical model allows for providing a 3D graphical representation, which medical staff can use to better understand the clinical situation of patients. Experiments conducted using retrospectively collected data from 519 patients treated at the HF Clinic of the University Hospital of Salerno have demonstrated the effectiveness of our model, surpassing the most commonly used machine learning algorithms. Indeed, the proposed GP-based classifier achieved a 96% average score for all considered evaluation metrics and fully supported the controls of medical staff. Our solution has the potential to impact clinical practice for HF by identifying patients at high risk of WHF and facilitating more rapid diagnosis, targeted treatment, and a reduction in hospitalizations.

Incidence of new-onset hypertension before, during, and after the COVID-19 pandemic: a 7-year longitudinal cohort study in a large population

BACKGROUND

While the augmented incidence of diabetes after COVID-19 has been widely confirmed, controversial results are available on the risk of developing hypertension during the COVID-19 pandemic.

METHODS

We designed a longitudinal cohort study to analyze a closed cohort followed up over a 7-year period, i.e., 3 years before and 3 years during the COVID-19 pandemic, and during 2023, when the pandemic was declared to be over. We analyzed medical records of more than 200,000 adults obtained from a cooperative of primary physicians from January 1, 2017, to December 31, 2023. The main outcome was the new diagnosis of hypertension.

RESULTS

We evaluated 202,163 individuals in the pre-pandemic years and 190,743 in the pandemic years, totaling 206,857 when including 2023 data. The incidence rate of new hypertension was 2.11 (95% C.I. 2.08-2.15) per 100 person-years in the years 2017-2019, increasing to 5.20 (95% C.I. 5.14-5.26) in the period 2020-2022 (RR = 2.46), and to 6.76 (95% C.I. 6.64-6.88) in 2023. The marked difference in trends between the first and the two successive observation periods was substantiated by the fitted regression lines of two Poisson models conducted on the monthly log-incidence of hypertension.

CONCLUSIONS

We detected a significant increase in new-onset hypertension during the COVID-19 pandemic, which at the end of the observation period affected ~ 20% of the studied cohort, a percentage higher than the diagnosis of COVID-19 infection within the same time frame. This observation suggests that increased attention to hypertension screening should not be limited to individuals who are aware of having contracted the infection but should be extended to the entire population.