Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM
Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide, emphasizing the urgent need for accurate and efficient predictive models. This study proposes a dual-output deep learning model based on a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model, optim...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier B.V.
2025
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/44971/ http://umpir.ump.edu.my/id/eprint/44971/1/1-s2.0-S2215016125003115-main.pdf |
| _version_ | 1848827226409140224 |
|---|---|
| author | Ahmed Alsarori, Ahmed Mohammed Mohd Herwan, Sulaiman |
| author_facet | Ahmed Alsarori, Ahmed Mohammed Mohd Herwan, Sulaiman |
| author_sort | Ahmed Alsarori, Ahmed Mohammed |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide, emphasizing the urgent need for accurate and efficient predictive models. This study proposes a dual-output deep learning model based on a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model, optimized using the Evolutionary Mating Algorithm (EMA). The model predicts both a continuous risk score and a binary diagnostic outcome, supporting both quantitative assessment and early clinical decision-making. EMA was applied for hyperparameter optimization, demonstrating improved convergence and generalization over conventional methods. Performance was benchmarked against CNN-LSTM models optimized using Particle Swarm Optimization (PSO) and Barnacle Mating Optimization (BMO). The EMA-based model achieved superior results, with a Mean Absolute Error (MAE) of 0.018, Mean Squared Error (MSE) of 0.0006, Root Mean Squared Error (RMSE) of 0.024, and a coefficient of determination (R²) of 0.98 for risk prediction. For the diagnostic task, the model attained 70 % accuracy and 80 % precision. These findings validate EMA’s effectiveness in tuning dual-output deep learning models and highlight its potential in enhancing cardiovascular risk stratification and early diagnosis in clinical settings. |
| first_indexed | 2025-11-15T03:57:21Z |
| format | Article |
| id | ump-44971 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:57:21Z |
| publishDate | 2025 |
| publisher | Elsevier B.V. |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-449712025-07-09T00:50:33Z http://umpir.ump.edu.my/id/eprint/44971/ Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM Ahmed Alsarori, Ahmed Mohammed Mohd Herwan, Sulaiman RC Internal medicine RD Surgery TK Electrical engineering. Electronics Nuclear engineering Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide, emphasizing the urgent need for accurate and efficient predictive models. This study proposes a dual-output deep learning model based on a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model, optimized using the Evolutionary Mating Algorithm (EMA). The model predicts both a continuous risk score and a binary diagnostic outcome, supporting both quantitative assessment and early clinical decision-making. EMA was applied for hyperparameter optimization, demonstrating improved convergence and generalization over conventional methods. Performance was benchmarked against CNN-LSTM models optimized using Particle Swarm Optimization (PSO) and Barnacle Mating Optimization (BMO). The EMA-based model achieved superior results, with a Mean Absolute Error (MAE) of 0.018, Mean Squared Error (MSE) of 0.0006, Root Mean Squared Error (RMSE) of 0.024, and a coefficient of determination (R²) of 0.98 for risk prediction. For the diagnostic task, the model attained 70 % accuracy and 80 % precision. These findings validate EMA’s effectiveness in tuning dual-output deep learning models and highlight its potential in enhancing cardiovascular risk stratification and early diagnosis in clinical settings. Elsevier B.V. 2025 Article PeerReviewed pdf en cc_by_4 http://umpir.ump.edu.my/id/eprint/44971/1/1-s2.0-S2215016125003115-main.pdf Ahmed Alsarori, Ahmed Mohammed and Mohd Herwan, Sulaiman (2025) Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM. MethodsX, 15 (103466). pp. 1-12. ISSN 2215-0161. (Published) https://doi.org/10.1016/j.mex.2025.103466 https://doi.org/10.1016/j.mex.2025.103466 |
| spellingShingle | RC Internal medicine RD Surgery TK Electrical engineering. Electronics Nuclear engineering Ahmed Alsarori, Ahmed Mohammed Mohd Herwan, Sulaiman Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title | Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title_full | Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title_fullStr | Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title_full_unstemmed | Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title_short | Integrated deep learning for cardiovascular risk assessment and diagnosis: An evolutionary mating algorithm-enhanced CNN-LSTM |
| title_sort | integrated deep learning for cardiovascular risk assessment and diagnosis: an evolutionary mating algorithm-enhanced cnn-lstm |
| topic | RC Internal medicine RD Surgery TK Electrical engineering. Electronics Nuclear engineering |
| url | http://umpir.ump.edu.my/id/eprint/44971/ http://umpir.ump.edu.my/id/eprint/44971/ http://umpir.ump.edu.my/id/eprint/44971/ http://umpir.ump.edu.my/id/eprint/44971/1/1-s2.0-S2215016125003115-main.pdf |