Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices
Abstract Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, which can progress from simple steatosis to advanced cirrhosis and hepatocellular carcinoma. Clinical diagnosis of NAFLD is crucial in the early stages of the disease. The main aim of this study was to apply...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-32129-y |
| _version_ | 1797853868262948864 |
|---|---|
| author | Farkhondeh Razmpour Reza Daryabeygi-Khotbehsara Davood Soleimani Hamzeh Asgharnezhad Afshar Shamsi Ghasem Sadeghi Bajestani Mohsen Nematy Mahdiyeh Razm Pour Ralph Maddison Sheikh Mohammed Shariful Islam |
| author_facet | Farkhondeh Razmpour Reza Daryabeygi-Khotbehsara Davood Soleimani Hamzeh Asgharnezhad Afshar Shamsi Ghasem Sadeghi Bajestani Mohsen Nematy Mahdiyeh Razm Pour Ralph Maddison Sheikh Mohammed Shariful Islam |
| author_sort | Farkhondeh Razmpour |
| collection | DOAJ |
| description | Abstract Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, which can progress from simple steatosis to advanced cirrhosis and hepatocellular carcinoma. Clinical diagnosis of NAFLD is crucial in the early stages of the disease. The main aim of this study was to apply machine learning (ML) methods to identify significant classifiers of NAFLD using body composition and anthropometric variables. A cross-sectional study was carried out among 513 individuals aged 13 years old or above in Iran. Anthropometric and body composition measurements were performed manually using body composition analyzer InBody 270. Hepatic steatosis and fibrosis were determined using a Fibroscan. ML methods including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Radial Basis Function (RBF) SVM, Gaussian Process (GP), Random Forest (RF), Neural Network (NN), Adaboost and Naïve Bayes were examined for model performance and to identify anthropometric and body composition predictors of fatty liver disease. RF generated the most accurate model for fatty liver (presence of any stage), steatosis stages and fibrosis stages with 82%, 52% and 57% accuracy, respectively. Abdomen circumference, waist circumference, chest circumference, trunk fat and body mass index were among the most important variables contributing to fatty liver disease. ML-based prediction of NAFLD using anthropometric and body composition data can assist clinicians in decision making. ML-based systems provide opportunities for NAFLD screening and early diagnosis, especially in population-level and remote areas. |
| first_indexed | 2024-04-09T19:57:45Z |
| format | Article |
| id | doaj.art-9da650523edf47d9bb8b3ddd7c46827c |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T19:57:45Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9da650523edf47d9bb8b3ddd7c46827c2023-04-03T05:24:44ZengNature PortfolioScientific Reports2045-23222023-03-0113111310.1038/s41598-023-32129-yApplication of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indicesFarkhondeh Razmpour0Reza Daryabeygi-Khotbehsara1Davood Soleimani2Hamzeh Asgharnezhad3Afshar Shamsi4Ghasem Sadeghi Bajestani5Mohsen Nematy6Mahdiyeh Razm Pour7Ralph Maddison8Sheikh Mohammed Shariful Islam9Department of Nutrition, Faculty of Medicine, Hormozgan University of Medical SciencesInstitute for Physical Activity and Nutrition (IPAN), Deakin UniversityDepartment of Nutrition, School of Nutrition Sciences and Food Technology, Kermanshah University of Medical SciencesInstitute for Intelligent Systems Research and Innovation (IISRI)Biomedical Machine Learning Lab, University of New South WhalesDepartment of Biomedical Engineering, Faculty of Engineering, Imam Reza International UniversityMetabolic Syndrome Research Center, Faculty of Medicine, Mashhad University of Medical SciencesDepartment of Electronic Learning, Shiraz UniversityInstitute for Physical Activity and Nutrition (IPAN), Deakin UniversityInstitute for Physical Activity and Nutrition (IPAN), Deakin UniversityAbstract Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, which can progress from simple steatosis to advanced cirrhosis and hepatocellular carcinoma. Clinical diagnosis of NAFLD is crucial in the early stages of the disease. The main aim of this study was to apply machine learning (ML) methods to identify significant classifiers of NAFLD using body composition and anthropometric variables. A cross-sectional study was carried out among 513 individuals aged 13 years old or above in Iran. Anthropometric and body composition measurements were performed manually using body composition analyzer InBody 270. Hepatic steatosis and fibrosis were determined using a Fibroscan. ML methods including k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Radial Basis Function (RBF) SVM, Gaussian Process (GP), Random Forest (RF), Neural Network (NN), Adaboost and Naïve Bayes were examined for model performance and to identify anthropometric and body composition predictors of fatty liver disease. RF generated the most accurate model for fatty liver (presence of any stage), steatosis stages and fibrosis stages with 82%, 52% and 57% accuracy, respectively. Abdomen circumference, waist circumference, chest circumference, trunk fat and body mass index were among the most important variables contributing to fatty liver disease. ML-based prediction of NAFLD using anthropometric and body composition data can assist clinicians in decision making. ML-based systems provide opportunities for NAFLD screening and early diagnosis, especially in population-level and remote areas.https://doi.org/10.1038/s41598-023-32129-y |
| spellingShingle | Farkhondeh Razmpour Reza Daryabeygi-Khotbehsara Davood Soleimani Hamzeh Asgharnezhad Afshar Shamsi Ghasem Sadeghi Bajestani Mohsen Nematy Mahdiyeh Razm Pour Ralph Maddison Sheikh Mohammed Shariful Islam Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices Scientific Reports |
| title | Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices |
| title_full | Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices |
| title_fullStr | Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices |
| title_full_unstemmed | Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices |
| title_short | Application of machine learning in predicting non-alcoholic fatty liver disease using anthropometric and body composition indices |
| title_sort | application of machine learning in predicting non alcoholic fatty liver disease using anthropometric and body composition indices |
| url | https://doi.org/10.1038/s41598-023-32129-y |
| work_keys_str_mv | AT farkhondehrazmpour applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT rezadaryabeygikhotbehsara applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT davoodsoleimani applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT hamzehasgharnezhad applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT afsharshamsi applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT ghasemsadeghibajestani applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT mohsennematy applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT mahdiyehrazmpour applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT ralphmaddison applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices AT sheikhmohammedsharifulislam applicationofmachinelearninginpredictingnonalcoholicfattyliverdiseaseusinganthropometricandbodycompositionindices |