RESUMEN

BACKGROUND: Coronary artery diseases (CADs) are the most important non­communicable diseases (NCDs), which cause the highest number of deaths around the world. Hypertension (HTN), dyslipidemia (DL), diabetes mellitus (DM), obesity (OB), low physical activity (LPA), smoking, opium consumption (OC) and anxiety are the most important CAD risk factors, which are more dangerously present in combination in some patients. METHODS: A total of 5835 people aged 15 to 75 years were enrolled in the phase 1 (2012) and followed up to the phase 2 (2017) of the population-based Kerman coronary artery diseases risk factors study (KERCADRS). The prevalence and pattern of different combinations of CAD risk factors (double to quintuple) and their 5-year incidence rates were assessed. RESULTS: The prevalence of single CAD risk factors (RFs) in phase 2 was 50.2% (DL), 47.1% (LPA), 28.1% (abdominal obesity), 21.2% (OB), 16.5% (HTN), 9.2% (smoking), 9.1% (OC), and 8.4% (DM). The most frequent combination of risk factors was LPA plus DL (23.9%), metabolic syndrome (19.6%), and DL plus OB (17.8%). The 5-year incidence rates of multiple comorbidities (in persons per 100 person-years) was DL plus LPA (2.80%), HTN plus DL (1.53%), and abdominal obesity (AOB) plus DL (1.47%). The most participants (84.4%) suffered from at least one RF, while 54.9% had at least two and 29.9% had at least three RFs. CONCLUSION: The results showed that a large portion of the study population suffers from multiple CAD RFs. The findings underscore the importance of identifying multiple CAD risk factors to reduce the overall burden of these NCDs.

Asunto(s)

RESUMEN

BACKGROUND: Gene selection from gene expression profiles is the appropriate tool for diagnosing and predicting cancers. The aim of this study is to perform a Precision Lasso regression model on gene expression of diffuse large B cell lymphoma patients and to find marker genes related to DLBCL. METHODS: In the present case-control study, the dataset included 180 gene expressions from 14 healthy individuals and 17 DLBCL patients. The marker genes were selected by fitting Ridge, Lasso, Elastic Net, and Precision Lasso regression models. RESULTS: Based on our findings, the Precision Lasso, the Ridge, the Elastic Net, and the Lasso models choose the most marker genes, respectively. In addition, the top 20 genes are based on models compared with the results of clinical studies. The Precision Lasso and the Ridge models selected the most common genes with the clinical results, respectively. CONCLUSIONS: The performance of the Precision Lasso model in selecting related genes could be considered more acceptable rather than other models.

Asunto(s)

RESUMEN

Background: The rapid prevalence of coronavirus disease 2019 (COVID-19) has caused a pandemic worldwide and affected the lives of millions. The potential fatality of the disease has led to global public health concerns. Apart from clinical practice, artificial intelligence (AI) has provided a new model for the early diagnosis and prediction of disease based on machine learning (ML) algorithms. In this study, we aimed to make a prediction model for the prognosis of COVID-19 patients using data mining techniques. Methods: In this study, a data set was obtained from the intelligent management system repository of 19 hospitals at Shahid Beheshti University of Medical Sciences in Iran. All patients admitted had shown positive polymerase chain reaction (PCR) test results. They were hospitalized between February 19 and May 12 in 2020, which were investigated in this study. The extracted data set has 8621 data instances. The data include demographic information and results of 16 laboratory tests. In the first stage, preprocessing was performed on the data. Then, among 15 laboratory tests, four of them were selected. The models were created based on seven data mining algorithms, and finally, the performances of the models were compared with each other. Results: Based on our results, the Random Forest (RF) and Gradient Boosted Trees models were known as the most efficient methods, with the highest accuracy percentage of 86.45% and 84.80%, respectively. In contrast, the Decision Tree exhibited the least accuracy (75.43%) among the seven models. Conclusion: Data mining methods have the potential to be used for predicting outcomes of COVID-19 patients with the use of lab tests and demographic features. After validating these methods, they could be implemented in clinical decision support systems for better management and providing care to severe COVID-19 patients.