Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers
Objective: This study aimed to classify open-access gene expression data of patients with hepatitis B virus-related hepatocellular carcinoma (HBV + HCC) and chronic HBV without HCC (HBV alone) using the XGBoost method, one of the machine learning methods, and reveal important genes that may cause HC...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Galenos Publishing House
2022-09-01
|
| Series: | Medeniyet Medical Journal |
| Subjects: | |
| Online Access: | https://jag.journalagent.com/z4/download_fulltext.asp?pdir=medeniyet&un=MEDJ-39049 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832581941408301056 |
|---|---|
| author | Zeynep KUCUKAKCALI Sami AKBULUT Cemil COLAK |
| author_facet | Zeynep KUCUKAKCALI Sami AKBULUT Cemil COLAK |
| author_sort | Zeynep KUCUKAKCALI |
| collection | DOAJ |
| description | Objective: This study aimed to classify open-access gene expression data of patients with hepatitis B virus-related hepatocellular carcinoma (HBV + HCC) and chronic HBV without HCC (HBV alone) using the XGBoost method, one of the machine learning methods, and reveal important genes that may cause HCC.
Methods: This case-control study used the open-access gene expression data of patients with HBV + HCC and HBV alone. Data from 17 patients with HBV + HCC and 36 patients with HBV were included. XGBoost was constructed for the classification via 10-fold cross-validation. Accuracy, balanced accuracy, sensitivity, selectivity, positive-predictive value, and negative-predictive value performance metrics were evaluated for model performance.
Results: According to the feature-selection method, 18 genes were selected, and modeling was performed with these input variables. Accuracy, balanced accuracy, sensitivity, specificity, positive-predictive value, negative-predictive value, and F1 score obtained from XGBoost model were 98.1%, 98.6%, 100%, 97.2%, 94.4%, 100%, and 97.1%, respectively. Based on the predictor importance findings acquired from XGBoost, the RNF26, FLJ10233, ACBD6, RBM12, PFAS, H3C11, and GKP5 can be employed as potential biomarkers of HBV-related HCC.
Conclusions: In this study, genes that may be possible biomarkers of HBV-related HCC were determined using a machine learning-based prediction approach. After the reliability of the obtained genes are clinically verified in subsequent research, therapeutic procedures can be established based on these genes, and their usefulness in clinical practice may be documented. |
| format | Article |
| id | doaj-art-2eaa45b46653474a87b92976b1bd86df |
| institution | Kabale University |
| issn | 2149-2042 2149-4606 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | Galenos Publishing House |
| record_format | Article |
| series | Medeniyet Medical Journal |
| spelling | doaj-art-2eaa45b46653474a87b92976b1bd86df2025-01-30T07:10:56ZengGalenos Publishing HouseMedeniyet Medical Journal2149-20422149-46062022-09-0137325526310.4274/MMJ.galenos.2022.39049MEDJ-39049Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate BiomarkersZeynep KUCUKAKCALI0Sami AKBULUT1Cemil COLAK2Inonu University Faculty of Medicine, Department of Biostatistics and Medical Informatics, Malatya, TurkeyInonu University Faculty of Medicine, Department of Biostatistics and Medical Informatics, Malatya, Turkey, Inonu University Faculty of Medicine, Department of General Surgery, Malatya, Turkey, Inonu University Faculty of Medicine, Department of Public Health, Malatya, TurkeyInonu University Faculty of Medicine, Department of Biostatistics and Medical Informatics, Malatya, TurkeyObjective: This study aimed to classify open-access gene expression data of patients with hepatitis B virus-related hepatocellular carcinoma (HBV + HCC) and chronic HBV without HCC (HBV alone) using the XGBoost method, one of the machine learning methods, and reveal important genes that may cause HCC. Methods: This case-control study used the open-access gene expression data of patients with HBV + HCC and HBV alone. Data from 17 patients with HBV + HCC and 36 patients with HBV were included. XGBoost was constructed for the classification via 10-fold cross-validation. Accuracy, balanced accuracy, sensitivity, selectivity, positive-predictive value, and negative-predictive value performance metrics were evaluated for model performance. Results: According to the feature-selection method, 18 genes were selected, and modeling was performed with these input variables. Accuracy, balanced accuracy, sensitivity, specificity, positive-predictive value, negative-predictive value, and F1 score obtained from XGBoost model were 98.1%, 98.6%, 100%, 97.2%, 94.4%, 100%, and 97.1%, respectively. Based on the predictor importance findings acquired from XGBoost, the RNF26, FLJ10233, ACBD6, RBM12, PFAS, H3C11, and GKP5 can be employed as potential biomarkers of HBV-related HCC. Conclusions: In this study, genes that may be possible biomarkers of HBV-related HCC were determined using a machine learning-based prediction approach. After the reliability of the obtained genes are clinically verified in subsequent research, therapeutic procedures can be established based on these genes, and their usefulness in clinical practice may be documented.https://jag.journalagent.com/z4/download_fulltext.asp?pdir=medeniyet&un=MEDJ-39049hepatocellular carcinomahepatitis b infectionchronic liver diseasegene expression |
| spellingShingle | Zeynep KUCUKAKCALI Sami AKBULUT Cemil COLAK Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers Medeniyet Medical Journal hepatocellular carcinoma hepatitis b infection chronic liver disease gene expression |
| title | Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers |
| title_full | Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers |
| title_fullStr | Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers |
| title_full_unstemmed | Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers |
| title_short | Machine Learning-based Prediction of HBV-related Hepatocellular Carcinoma and Detection of Key Candidate Biomarkers |
| title_sort | machine learning based prediction of hbv related hepatocellular carcinoma and detection of key candidate biomarkers |
| topic | hepatocellular carcinoma hepatitis b infection chronic liver disease gene expression |
| url | https://jag.journalagent.com/z4/download_fulltext.asp?pdir=medeniyet&un=MEDJ-39049 |
| work_keys_str_mv | AT zeynepkucukakcali machinelearningbasedpredictionofhbvrelatedhepatocellularcarcinomaanddetectionofkeycandidatebiomarkers AT samiakbulut machinelearningbasedpredictionofhbvrelatedhepatocellularcarcinomaanddetectionofkeycandidatebiomarkers AT cemilcolak machinelearningbasedpredictionofhbvrelatedhepatocellularcarcinomaanddetectionofkeycandidatebiomarkers |