Nutritional Status and Recurrent Major Cardiovascular Events Following Acute Myocardial Infarction-A Follow-Up Study in a Primary Percutaneous Coronary Intervention Center.

BACKGROUND: Acute myocardial infarction is often accompanied by malnutrition, which is associated with an imbalance between catabolic and anabolic processes. This ultimately leads to cardiac cachexia, which worsens the patient's prognosis. We aimed to assess the correlation between nutritional status, assessed using the controlling nutritional status (CONUT) score, and the rate of major cardiovascular adverse events (MACE). METHODS: The present investigation was a non-randomized, prospective, observational study in which 108 patients with acute myocardial infarction were included. Nutritional status was assessed using the CONUT score. Based on the CONUT score, the patients were divided as follows: Group 1-normal or mild nutritional status (CONUT < 3 points, n = 76), and Group 2-moderate to severe nutritional deficiency (CONUT ≥ 3 points, n = 32). Demographic, echocardiographic, and laboratory parameters were obtained for all patients, as well as the MACE rate at 1 and 3 months of follow-up. RESULTS: The MACE occurred more frequently in patients with impaired nutritional status at both 1-month follow-up (46.9% versus 9.2%; p < 0.0001) and 3-month follow-up (68.8% versus 10.5%; p < 0.0001). In terms of cardiovascular events, patients with poor nutritional status, with a CONUT score ≥ 3, presented more frequent non-fatal myocardial infarction, stroke, revascularization procedure, and ventricular arrhythmia. Also, the number of cardiovascular deaths was higher in the undernourished group. CONCLUSIONS: This study found that patients with poor nutritional status experienced inflammatory status, frailty, and cardiovascular events more often than those with normal nutritional status at 1-month and 3-month follow-up after an acute myocardial infarction.

Machine learning based assessment of preclinical health questionnaires.

BACKGROUND: Within modern health systems, the possibility of accessing a large amount and a variety of data related to patients' health has increased significantly over the years. The source of this data could be mobile and wearable electronic systems used in everyday life, and specialized medical devices. In this study we aim to investigate the use of modern Machine Learning (ML) techniques for preclinical health assessment based on data collected from questionnaires filled out by patients. METHOD: To identify the health conditions of pregnant women, we developed a questionnaire that was distributed in three maternity hospitals in the Mureș County, Romania. In this work we proposed and developed an ML model for pattern detection in common risk assessment based on data extracted from questionnaires. RESULTS: Out of the 1278 women who answered the questionnaire, 381 smoked before pregnancy and only 216 quit smoking during the period in which they became pregnant. The performance of the model indicates the feasibility of the solution, with an accuracy of 98 % confirmed for the considered case study. CONCLUSION: The proposed solution offers a simple and efficient way to digitize questionnaire data and to analyze the data through a reduced computational effort, both in terms of memory and computing power used.