Relevant Features in Nonalcoholic Steatohepatitis Determined Using Machine Learning for Feature Selection
| Autor: | Oscar Barquero-Perez, Luis Vigil-Medina, Rafael Garcia-Carretero, Javier Ramos-Lopez |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Adult
Liver Cirrhosis Male Cirrhosis Endocrinology Diabetes and Metabolism medicine.medical_treatment Decision Making 030209 endocrinology & metabolism Type 2 diabetes 030204 cardiovascular system & hematology Machine learning computer.software_genre Sensitivity and Specificity Severity of Illness Index Machine Learning 03 medical and health sciences 0302 clinical medicine Insulin resistance Non-alcoholic Fatty Liver Disease Nonalcoholic fatty liver disease Internal Medicine medicine Prevalence Humans Aged Retrospective Studies Metabolic Syndrome Univariate analysis business.industry Insulin nutritional and metabolic diseases Middle Aged medicine.disease Prognosis digestive system diseases Cross-Sectional Studies Diabetes Mellitus Type 2 Hypertension Disease Progression Female Artificial intelligence Metabolic syndrome business computer Dyslipidemia Algorithms |
| Zdroj: | Metabolic syndrome and related disorders. 17(9) |
| ISSN: | 1557-8518 |
| Popis: | Aim: We investigated the prevalence and the most relevant features of nonalcoholic steatohepatitis (NASH), a stage of nonalcoholic fatty liver disease, (NAFLD) in which the inflammation of hepatocytes can lead to increased cardiovascular risk, liver fibrosis, cirrhosis, and the need for liver transplant. Methods: We analyzed data from 2239 hypertensive patients using descriptive statistics and supervised machine learning algorithms, including the least absolute shrinkage and selection operator and random forest classifier, to select the most relevant features of NASH. Results: The prevalence of NASH among our hypertensive patients was 11.3%. In univariate analyses, it was associated with metabolic syndrome, type 2 diabetes, insulin resistance, and dyslipidemia. Ferritin and serum insulin were the most relevant features in the final model, with a sensitivity of 70%, specificity of 79%, and area under the curve of 0.79. Conclusion: Ferritin and insulin are significant predictors of NASH. Clinicians may use these to better assess cardiovascular risk and provide better management to hypertensive patients with NASH. Machine-learning algorithms may help health care providers make decisions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|