No abstract

Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic analysis of these data has many practical applications in patient monitoring, including the optimization of alarm systems for alerting healthcare personnel. In this paper, explainable machine learning techniques are used for this purpose, with a methodology based on age-stratification, boosting classifiers, and Shapley Additive Explanations (SHAP) proposed. The methodology is evaluated using MIMIC-III, an ICU patient research database. The results show that the proposed model can predict mortality within the ICU with AUROC values of 0.961, 0.936, 0.898, and 0.883 for age groups 18–45, 45–65, 65–85 and 85+, respectively. By using SHAP, the features with the highest impact in predicting mortality for different age groups and the threshold from which the value of a clinical feature has a negative impact on the patient’s health can be identified. This allows ICU alarms to be improved by identifying the most important variables to be sensed and the threshold values at which the health personnel must be warned.

No abstract

Coronary artery disease (CAD) is a common chronic condition in the elderly. However, the earlier CAD begins, the stronger its impact on lifestyle and costs of health and social care. The present study analyzes clinical and angiographic features and the outcome of very young patients undergoing coronary angiography due to suspected CAD, including a nested case-control study of ≤40-year-old patients referred for coronary angiography. Patients were divided into two groups: cases with significant angiographic stenosis, and controls with non-significant stenosis. Of the 19,321 coronary angiographies performed in our center in a period of 10 years, 504 (2.6%) were in patients ≤40 years. The most common cardiovascular risk factors for significant CAD were smoking (OR 2.96; 95% CI 1.65–5.37), dyslipidemia (OR 2.18; 95% CI 1.27–3.82), and family history of CAD (OR 1.95; 95% CI 1.05–3.75). The incidence of major adverse cardiovascular events (MACE) at follow-up was significantly higher in the cases compared to controls (HR 2.71; 95% CI 1.44–5.11). Three conventional coronary risk factors were directly related to the early signs of CAD. MACE in the long-term follow-up is associated to dyslipidaemia and hypertriglyceridemia. Focusing efforts for the adequate control of CAD in young patients is a priority given the high socio-medical cost that this disease entails to society.