A proposed approach for diabetes diagnosis using neuro-fuzzy technique
Diabetes is a chronic disease characterized by a decrease in pancreatic insulin production. The immune system will be harmed due to this condition, which will raise blood sugar levels. However, early detection of diabetes enables patients to begin treatment on time, therefore reducing or eliminating...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Advanced Engineering and Science (IAES)
2022
|
| _version_ | 1825938352723984384 |
|---|---|
| author | Alasaady, Maher Talal Mohd Aris, Teh Noranis Mohd Sharef, Nurfadhlina Hamdan, Hazlina |
| author_facet | Alasaady, Maher Talal Mohd Aris, Teh Noranis Mohd Sharef, Nurfadhlina Hamdan, Hazlina |
| author_sort | Alasaady, Maher Talal |
| collection | UPM |
| description | Diabetes is a chronic disease characterized by a decrease in pancreatic insulin production. The immune system will be harmed due to this condition, which will raise blood sugar levels. However, early detection of diabetes enables patients to begin treatment on time, therefore reducing or eliminating the risk of severe consequences. One of the most significant challenges in the healthcare unit is disease diagnosis. Traditional techniques of disease diagnosis are manual and prone to inaccuracy. This paper proposed an approach for diagnosing diabetes using the adaptive neuro-fuzzy inference system (ANFIS) based on Pima Indians diabetes dataset (PIDD). The three stages of the proposed approach are pre-processing classification and evaluation. Normalization, imputation, and anomaly detection are part of the pre-processing stage. The pre-processing was done by normalizing the data, replacing the missing values, and using the local outlier factor (LOF) technique. In the classification stage, ANFIS classifiers were trained using the hybrid learning algorithm of the neural network. Finally, the evaluation procedures use the last stage’s sensitivity, specificity, and accuracy metrics. The obtained classification accuracy was 92.77%, and it seemed rather promising compared to the other classification applications for this topic found in the literature. |
| first_indexed | 2024-03-06T11:12:27Z |
| format | Article |
| id | upm.eprints-100339 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T11:12:27Z |
| publishDate | 2022 |
| publisher | Institute of Advanced Engineering and Science (IAES) |
| record_format | dspace |
| spelling | upm.eprints-1003392023-12-26T07:29:19Z http://psasir.upm.edu.my/id/eprint/100339/ A proposed approach for diabetes diagnosis using neuro-fuzzy technique Alasaady, Maher Talal Mohd Aris, Teh Noranis Mohd Sharef, Nurfadhlina Hamdan, Hazlina Diabetes is a chronic disease characterized by a decrease in pancreatic insulin production. The immune system will be harmed due to this condition, which will raise blood sugar levels. However, early detection of diabetes enables patients to begin treatment on time, therefore reducing or eliminating the risk of severe consequences. One of the most significant challenges in the healthcare unit is disease diagnosis. Traditional techniques of disease diagnosis are manual and prone to inaccuracy. This paper proposed an approach for diagnosing diabetes using the adaptive neuro-fuzzy inference system (ANFIS) based on Pima Indians diabetes dataset (PIDD). The three stages of the proposed approach are pre-processing classification and evaluation. Normalization, imputation, and anomaly detection are part of the pre-processing stage. The pre-processing was done by normalizing the data, replacing the missing values, and using the local outlier factor (LOF) technique. In the classification stage, ANFIS classifiers were trained using the hybrid learning algorithm of the neural network. Finally, the evaluation procedures use the last stage’s sensitivity, specificity, and accuracy metrics. The obtained classification accuracy was 92.77%, and it seemed rather promising compared to the other classification applications for this topic found in the literature. Institute of Advanced Engineering and Science (IAES) 2022-12 Article PeerReviewed Alasaady, Maher Talal and Mohd Aris, Teh Noranis and Mohd Sharef, Nurfadhlina and Hamdan, Hazlina (2022) A proposed approach for diabetes diagnosis using neuro-fuzzy technique. Bulletin of Electrical Engineering and Informatics (BEEI), 11 (6). 3590 - 3597. ISSN 2089-3191; ESSN: 2302-9285 https://beei.org/index.php/EEI/article/view/4269 10.11591/eei.v11i6.4269 |
| spellingShingle | Alasaady, Maher Talal Mohd Aris, Teh Noranis Mohd Sharef, Nurfadhlina Hamdan, Hazlina A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title | A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title_full | A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title_fullStr | A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title_full_unstemmed | A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title_short | A proposed approach for diabetes diagnosis using neuro-fuzzy technique |
| title_sort | proposed approach for diabetes diagnosis using neuro fuzzy technique |
| work_keys_str_mv | AT alasaadymahertalal aproposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT mohdaristehnoranis aproposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT mohdsharefnurfadhlina aproposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT hamdanhazlina aproposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT alasaadymahertalal proposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT mohdaristehnoranis proposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT mohdsharefnurfadhlina proposedapproachfordiabetesdiagnosisusingneurofuzzytechnique AT hamdanhazlina proposedapproachfordiabetesdiagnosisusingneurofuzzytechnique |