Our paper proposes the first machine learning model to predict long-term mortality in patients with diabetic foot ulcers (DFUs). The study includes 635 patients with DFUs admitted from January 2007 to December 2017, with a follow-up period extending until December 2020. Two multilayer perceptron (MLP) classifiers were developed. The first MLP model was developed to predict whether the patient will die in the next 5 years after the current hospitalization. The second MLP classifier was built to estimate whether the patient will die in the following 10 years. The 5-year and 10-year mortality models were based on the following predictors: age; the University of Texas Staging System for Diabetic Foot Ulcers score; the Wagner–Meggitt classification; the Saint Elian Wound Score System; glomerular filtration rate; topographic aspects and the depth of the lesion; and the presence of foot ischemia, cardiovascular disease, diabetic nephropathy, and hypertension. The accuracy for the 5-year and 10-year models was 0.7717 and 0.7598, respectively (for the training set) and 0.7244 and 0.7087, respectively (for the test set). Our findings indicate that it is possible to predict with good accuracy the risk of death in patients with DFUs using non-invasive and low-cost predictors.

Background and Objectives: Functional capacity (FC) assessed via cardiopulmonary exercise testing (CPET) is a novel, independent prognostic marker for patients with coronary artery disease (CAD). Neutrophil to lymphocyte ratio (NLR) and platelet to lymphocyte ratio (PLR) are two readily available predictors of systemic inflammation and cardiovascular event risk, which could be used as cost-effective predictors of poor FC. The purpose of this study was to evaluate the utility of NLR and PLR in predicting poor FC in patients with CAD and recent elective percutaneous coronary intervention (PCI). Materials and Methods: Our cross-sectional retrospective analysis included 80 patients with stable CAD and recent elective PCI (mean age 55.51 ± 11.83 years, 71.3% male) who were referred to a cardiovascular rehabilitation center from January 2020 to June 2021. All patients underwent clinical examination, cardiopulmonary exercise testing on a cycle ergometer, transthoracic echocardiography and standard blood analysis. Results: Patients were classified according to percent predicted oxygen uptake (% VO2 max) in two groups—poor FC (≤70%, n = 35) and preserved FC (>70%, n = 45). There was no significant difference between groups regarding age, gender ratio, presence of associated comorbidities, left ventricular ejection fraction and NLR. PLR was higher in patients with poor FC (169.8 ± 59.3 vs. 137.4 ± 35.9, p = 0.003). A PLR cut-off point of 139 had 74% sensitivity and 60% specificity in predicting poor FC. After multivariate analysis, PLR remained a significant predictor of poor functional status. Conclusions: Although CPET is the gold standard test for assessing FC prior to cardiovascular rehabilitation, its availability remains limited. PLR, a cheap and simple test, could predict poor FC in patients with stable CAD and recent elective PCI and help prioritize referral for cardiovascular rehabilitation in high-risk patients.

Exercise-based cardiac rehabilitation (ExCR) programs are essential for patients diagnosed with cardiac diseases. Studies have shown that they aid in the rehabilitation process and may even facilitate a return to previous cardiorespiratory fitness. Also, patients who enroll and follow such programs have shown a lower rate of complications and mortality in the long run. The results vary depending on the type of program followed and the degree of debilitation the disease has caused. Therefore, in order to obtain optimal results, it is ideal to tailor each ExCR program to the individual profile of each patient. At the moment, the two most studied and employed training types are medium-intensity continuous training (MICT) and high-intensity interval training (HIIT). For most of the time, MICT was the first-choice program for patients with cardiovascular disease. In recent years, however, more and more studies have pointed towards the benefits of HIIT and how it better aids patients in recovering their cardiovascular fitness. Generally, MICT is more suited for patients with a severe degradation in functional capacity and who require a higher degree of safety (e.g., elderly, with a high number of comorbidities). On the other hand, while HIIT is more demanding, it appears to offer better outcomes. Therefore, this review aimed to summarize information from different publications on both types of training regimens in ExCR and assess their utility in current clinical practice.

Atherosclerosis is a significant health concern with a growing incidence worldwide. It is directly linked to an increased cardiovascular risk and to major adverse cardiovascular events, such as acute coronary syndromes. In this review, we try to assess the potential diagnostic role of biomarkers in the early identification of patients susceptible to the development of atherosclerosis and other adverse cardiovascular events. We have collected publications concerning already established parameters, such as low-density lipoprotein cholesterol (LDL-C), as well as newer markers, e.g., apolipoprotein B (apoB) and the ratio between apoB and apoA. Additionally, given the inflammatory nature of the development of atherosclerosis, high-sensitivity c-reactive protein (hs-CRP) or interleukin-6 (IL-6) are also discussed. Additionally, newer publications on other emerging components linked to atherosclerosis were considered in the context of patient evaluation. Apart from the already in-use markers (e.g., LDL-C), emerging research highlights the potential of newer molecules in optimizing the diagnosis of atherosclerotic disease in earlier stages. After further studies, they might be fully implemented in the screening protocols.

Background and Objectives: Non-alcoholic fatty liver disease is a worldwide significant public health problem, particularly in patients with type 2 diabetes mellitus. Identifying possible risk factors for the disease is mandatory for a better understandingand management of this condition. Patatin-like phospholipase domain-containing protein 3 (PNPLA3) has been linked to the development and evolution of fatty liver but not to insulin resistance. The aim of this study isto evaluate the relationships between PNPLA3 and fatty liver, metabolic syndrome and subclinical atherosclerosis. Materials and Methods: The study group consisted of patients with type 2 diabetes mellitus without insulin treatment. The degree of liver fat loading was assessed by ultrasonography, and subclinical atherosclerosis was assessed using carotid intima-media thickness (CIMT). PNPLA3 rs738409 genotype determination was performed by high-resolution melting analysis that allowed three standard genotypes: CC, CG, and GG. Results: Among the 92 patients, more than 90% showed various degrees of hepatic steatosis, almost 62% presented values over the normal limit for the CIMT. The majority of the included subjects met the criteria for metabolic syndrome. Genotyping of PNPLA3 in 68 patients showed that the difference between subjects without steatosis and subjects with hepatic steatosis was due to the higher frequency of genotype GG. The CC genotype was the most common in the group we studied and was significantly more frequent in the group of subjects with severe steatosis; the GG genotype was significantly more frequent in subjects with moderate steatosis; the frequency of the CG genotype was not significantly different among the groups.When we divided the group of subjects into two groups: those with no or mild steatosis and those with moderate or severe steatosis it was shown that the frequency of the GG genotype was significantly higher in the group of subjects with moderate or severe steatosis. PNPLA3 genotypes were not associated with metabolic syndrome, subclinical atherosclerosis, or insulin resistance. Conclusions: Our results suggest that PNPLA3 does not independently influence cardiovascular risk in patients with type 2 diabetes mellitus. The hypothesis that PNPLA3 may have a cardioprotective effect requires future confirmation.

Introduction. Chronic inflammation plays an essential role in the pathophysiology of both arterial hypertension (HTN) and coronary artery disease (CAD), and is more pronounced in individuals with a non-dipper circadian blood pressure (BP) pattern. A non-dipping BP pattern is in turn is associated with increased cardiovascular morbi-mortality, and a higher risk of atherosclerotic events. Neutrophil to lymphocyte ratio (NLR), monocyte to lymphocyte ratio (MLR) and platelet to lymphocyte ratio (PLR) are readily available predictors of systemic inflammation and cardiovascular risk. The purpose of our study is to evaluate whether NLR, MLR and PLR can be used as cost-effective predictors of a non-dipping blood pressure pattern in hypertensive patients with stable CAD. Materials and Methods: We performed a cross-sectional retrospective analysis that included 80 patients with hypertension and stable CAD (mean age 55.51 ± 11.83 years, 71.3% male) referred to a cardiovascular rehabilitation center. All patients underwent clinical examination, 24 h ambulatory blood pressure monitoring (ABPM) and standard blood analysis. Results: Baseline demographic characteristics were similar in both groups. Patients with non-dipper pattern had significantly higher NLR (median = 2, IR (2–3), p < 0.001), MLR (median = 0.31, IR (0.23–0.39), p < 0.001) and PLR (median = 175, IR (144–215), p < 0.001) compared to dippers. Conclusion: Our results suggest that MLR and PLR are inexpensive and easily accessible biomarkers that predict a non-dipping pattern in hypertensive patients with stable CAD.