A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients
Diabetes is a major chronic health problem affecting millions globally. Effective diabetes management can reduce the risk of hospital readmission and the associated financial losses for both the healthcare system and insurance companies. Hospital readmission is a high-priority healthcare quality mea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10122939/ |
| _version_ | 1797823410464620544 |
|---|---|
| author | Avishek Anishkar Ram Zain Ali Vandana Krishna Nandita Nishika Anuraganand Sharma |
| author_facet | Avishek Anishkar Ram Zain Ali Vandana Krishna Nandita Nishika Anuraganand Sharma |
| author_sort | Avishek Anishkar Ram |
| collection | DOAJ |
| description | Diabetes is a major chronic health problem affecting millions globally. Effective diabetes management can reduce the risk of hospital readmission and the associated financial losses for both the healthcare system and insurance companies. Hospital readmission is a high-priority healthcare quality measure that reflects the inadequacies in the healthcare system that also increase healthcare costs and negatively influence hospitals’ reputation. Predicting readmissions in the early stages prompts great attention to patients with a high risk of readmission. There has been some attempt in applying machine learning predictive models such as ensemble learning with Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM) and Artificial Neural Networks (ANN) to correctly identify if the readmission can happen within 30 days (< 30 days) or it may never happen or happens after 30 days (<inline-formula> <tex-math notation="LaTeX">$\ge 30$ </tex-math></inline-formula> days). We are proposing a new method that is applied to ANN to guide it through its gradient descent optimizers by realizing consistent vs inconsistent data in every batch. Our results show that there are up to 1.5% improvement in classification accuracies in both 2-class and 3-class variations of the experimented benchmark dataset when using the guided optimizer to train the ANN as opposed to the standard optimizer. Guided ANN is also able to achieve better error convergence than standard ANN. |
| first_indexed | 2024-03-13T10:23:37Z |
| format | Article |
| id | doaj.art-3049b3b2956c489e92b96fbaadcb0883 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T10:23:37Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3049b3b2956c489e92b96fbaadcb08832023-05-19T23:01:06ZengIEEEIEEE Access2169-35362023-01-0111475274753810.1109/ACCESS.2023.327508610122939A Guided Neural Network Approach to Predict Early Readmission of Diabetic PatientsAvishek Anishkar Ram0https://orcid.org/0009-0008-5061-2386Zain Ali1https://orcid.org/0009-0001-0547-3806Vandana Krishna2Nandita Nishika3Anuraganand Sharma4https://orcid.org/0000-0002-2572-7922School of Information Technology, Engineering, Mathematics and Physics (STEMP), The University of the South Pacific, Suva, FijiSchool of Information Technology, Engineering, Mathematics and Physics (STEMP), The University of the South Pacific, Suva, FijiDepartment of Medicine, Fiji National University, Suva, FijiSchool of Information Technology, Engineering, Mathematics and Physics (STEMP), The University of the South Pacific, Suva, FijiSchool of Information Technology, Engineering, Mathematics and Physics (STEMP), The University of the South Pacific, Suva, FijiDiabetes is a major chronic health problem affecting millions globally. Effective diabetes management can reduce the risk of hospital readmission and the associated financial losses for both the healthcare system and insurance companies. Hospital readmission is a high-priority healthcare quality measure that reflects the inadequacies in the healthcare system that also increase healthcare costs and negatively influence hospitals’ reputation. Predicting readmissions in the early stages prompts great attention to patients with a high risk of readmission. There has been some attempt in applying machine learning predictive models such as ensemble learning with Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM) and Artificial Neural Networks (ANN) to correctly identify if the readmission can happen within 30 days (< 30 days) or it may never happen or happens after 30 days (<inline-formula> <tex-math notation="LaTeX">$\ge 30$ </tex-math></inline-formula> days). We are proposing a new method that is applied to ANN to guide it through its gradient descent optimizers by realizing consistent vs inconsistent data in every batch. Our results show that there are up to 1.5% improvement in classification accuracies in both 2-class and 3-class variations of the experimented benchmark dataset when using the guided optimizer to train the ANN as opposed to the standard optimizer. Guided ANN is also able to achieve better error convergence than standard ANN.https://ieeexplore.ieee.org/document/10122939/Artificial neural network (ANN)hospital readmissionmachine learningerror convergencesupport vector machinegradient descent |
| spellingShingle | Avishek Anishkar Ram Zain Ali Vandana Krishna Nandita Nishika Anuraganand Sharma A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients IEEE Access Artificial neural network (ANN) hospital readmission machine learning error convergence support vector machine gradient descent |
| title | A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients |
| title_full | A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients |
| title_fullStr | A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients |
| title_full_unstemmed | A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients |
| title_short | A Guided Neural Network Approach to Predict Early Readmission of Diabetic Patients |
| title_sort | guided neural network approach to predict early readmission of diabetic patients |
| topic | Artificial neural network (ANN) hospital readmission machine learning error convergence support vector machine gradient descent |
| url | https://ieeexplore.ieee.org/document/10122939/ |
| work_keys_str_mv | AT avishekanishkarram aguidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT zainali aguidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT vandanakrishna aguidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT nanditanishika aguidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT anuraganandsharma aguidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT avishekanishkarram guidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT zainali guidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT vandanakrishna guidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT nanditanishika guidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients AT anuraganandsharma guidedneuralnetworkapproachtopredictearlyreadmissionofdiabeticpatients |