Assessment of Thoracic Pain Using Machine Learning

Thoracic pain is a shared symptom among gastrointestinal diseases, muscle pain, emotional disorders, and the most deadly: Cardiovascular diseases. Due to the limited space in the emergency department, it is important to identify when thoracic pain is of cardiac origin, since being a symptom of CVD (Cardiovascular Disease), the attention to the patient must be immediate to prevent irreversible injuries or even death. Artificial intelligence contributes to the early detection of pathologies, such as chest pain. In this study, the machine learning techniques were used, performing an analysis of 27 variables provided by a database with information from 258 geriatric patients with 60 years old average age from Medical Norte Hospital in Tijuana, Baja California, Mexico. The objective of this analysis is to determine which variables are correlated with thoracic pain of cardiac origin and use the results as secondary parameters to evaluate the thoracic pain in the emergency rooms, and determine if its origin comes from a CVD or not. For this, two machine learning techniques were used: Tree classification and cross-validation. As a result, the Logistic Regression model, using the characteristics proposed as second factors to consider as variables, obtained an average accuracy (μ) of 96.4% with a standard deviation (σ) of 2.4924, while for F1 a mean (μ) of 91.2% and a standard deviation (σ) of 6.5640. This analysis suggests that among the main factors related to cardiac thoracic pain are: Dyslipidemia, diabetes, chronic kidney failure, hypertension, smoking habits, and troponin levels at the time of admission, which is when the pain occurs. Considering dyslipidemia and diabetes as the main variables due to similar results with machine learning techniques and statistical methods, where 61.95% of the patients who suffer an Acute Myocardial Infarction (AMI) have diabetes, and the 71.73% have dyslipidemia

Chest pain · Disease · Dyslipidemia · Emergency department · Logistic regression · Physical therapy · Cardiac Health and Mental Health · Chronic Obstructive Pulmonary Disease (COPD) Research · Medicine · Phonocardiography and Auscultation Techniques · Emergency Medicine · Internal Medicine

• The pathophysiology of cigarette smoking and cardiovascular disease

  Open Access•John A Ambrose, Rajat S Barua•Journal of the American College…•2004

  Add to list

• Global burden of blood-pressure-related disease, 2001

  Open Access•Carlene MM Lawes, Carlene M M Lawes et al.•The Lancet•2008

  Add to list

• Estimation of ten-year risk of fatal cardiovascular disease in Europe

  Richard Conroy•European Heart Journal•2003

  Add to list