Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques
Outcome prediction studies in healthcare research have gained significant importance, and the application of Artificial Intelligence (AI) in healthcare is rapidly growing. Machine Learning (ML) techniques offer improved detection and prediction of diseases, leading to more objective decision-making...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Informatics in Medicine Unlocked |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352914823002150 |
| _version_ | 1797646572308135936 |
|---|---|
| author | Peter Ifeoluwa Adegbola Abiodun Bukunmi Aborisade Adewale Adetutu |
| author_facet | Peter Ifeoluwa Adegbola Abiodun Bukunmi Aborisade Adewale Adetutu |
| author_sort | Peter Ifeoluwa Adegbola |
| collection | DOAJ |
| description | Outcome prediction studies in healthcare research have gained significant importance, and the application of Artificial Intelligence (AI) in healthcare is rapidly growing. Machine Learning (ML) techniques offer improved detection and prediction of diseases, leading to more objective decision-making processes and reduced diagnosis costs. This manuscript presents a study on the diagnosis of liver diseases using experimental rat data.The study utilized the data obtained from rats-fed environmental concern chemicals. The dataset was pre-processed, standardized, and split into training and testing data. For the rat experimental data, unsupervised data processing and linear regression techniques were employed to extract relevant features and predict the probability of samples being diseased, respectively. Random Forest (RF) classification was applied for predicting disease probability, and the model was evaluated based on accuracy and Mean Squared Error (MSE).The RF analysis achieved higher accuracy with Alanine amino Transferase (ALT) as the root node in the decision tree.The results demonstrated the effectiveness of the RF algorithm in the diagnosis of liver disease using experimental data. The proposed models have the potential to assist healthcare professionals in the prediction of disease onset and diagnosis, thereby contributing to improved patient care and outcomes. |
| first_indexed | 2024-03-11T15:04:33Z |
| format | Article |
| id | doaj.art-355d9715e2da48b5be1d071cfb461cd1 |
| institution | Directory Open Access Journal |
| issn | 2352-9148 |
| language | English |
| last_indexed | 2024-03-11T15:04:33Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Informatics in Medicine Unlocked |
| spelling | doaj.art-355d9715e2da48b5be1d071cfb461cd12023-10-30T06:05:15ZengElsevierInformatics in Medicine Unlocked2352-91482023-01-0142101369Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniquesPeter Ifeoluwa Adegbola0Abiodun Bukunmi Aborisade1Adewale Adetutu2Department of Biochemistry, Ladoke Akintola University of Technology, Ogbomoso, Nigeria; Department of Biochemistry and Forensic Science, First Technical University, Ibadan, NigeriaDepartment of Biochemistry, Ladoke Akintola University of Technology, Ogbomoso, NigeriaDepartment of Biochemistry, Ladoke Akintola University of Technology, Ogbomoso, Nigeria; Corresponding author.Outcome prediction studies in healthcare research have gained significant importance, and the application of Artificial Intelligence (AI) in healthcare is rapidly growing. Machine Learning (ML) techniques offer improved detection and prediction of diseases, leading to more objective decision-making processes and reduced diagnosis costs. This manuscript presents a study on the diagnosis of liver diseases using experimental rat data.The study utilized the data obtained from rats-fed environmental concern chemicals. The dataset was pre-processed, standardized, and split into training and testing data. For the rat experimental data, unsupervised data processing and linear regression techniques were employed to extract relevant features and predict the probability of samples being diseased, respectively. Random Forest (RF) classification was applied for predicting disease probability, and the model was evaluated based on accuracy and Mean Squared Error (MSE).The RF analysis achieved higher accuracy with Alanine amino Transferase (ALT) as the root node in the decision tree.The results demonstrated the effectiveness of the RF algorithm in the diagnosis of liver disease using experimental data. The proposed models have the potential to assist healthcare professionals in the prediction of disease onset and diagnosis, thereby contributing to improved patient care and outcomes.http://www.sciencedirect.com/science/article/pii/S2352914823002150Random forestLiver function markersLiver diseaseMachine learningArtificial intelligence |
| spellingShingle | Peter Ifeoluwa Adegbola Abiodun Bukunmi Aborisade Adewale Adetutu Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques Informatics in Medicine Unlocked Random forest Liver function markers Liver disease Machine learning Artificial intelligence |
| title | Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques |
| title_full | Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques |
| title_fullStr | Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques |
| title_full_unstemmed | Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques |
| title_short | Liver disease prediction in rats exposed to environmental toxicants using Machine-learning techniques |
| title_sort | liver disease prediction in rats exposed to environmental toxicants using machine learning techniques |
| topic | Random forest Liver function markers Liver disease Machine learning Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2352914823002150 |
| work_keys_str_mv | AT peterifeoluwaadegbola liverdiseasepredictioninratsexposedtoenvironmentaltoxicantsusingmachinelearningtechniques AT abiodunbukunmiaborisade liverdiseasepredictioninratsexposedtoenvironmentaltoxicantsusingmachinelearningtechniques AT adewaleadetutu liverdiseasepredictioninratsexposedtoenvironmentaltoxicantsusingmachinelearningtechniques |