Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics
<b>Introduction:</b> Accurate prediction of tumor dynamics following Gamma Knife radiosurgery (GKRS) is critical for optimizing treatment strategies for patients with brain metastases (BMs). Traditional machine learning (ML) algorithms have been widely used for this purpose; however, rec...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/18/2091 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850261476003020800 |
|---|---|
| author | Simona Ruxandra Volovăț Tudor Ovidiu Popa Dragoș Rusu Lăcrămioara Ochiuz Decebal Vasincu Maricel Agop Călin Gheorghe Buzea Cristian Constantin Volovăț |
| author_facet | Simona Ruxandra Volovăț Tudor Ovidiu Popa Dragoș Rusu Lăcrămioara Ochiuz Decebal Vasincu Maricel Agop Călin Gheorghe Buzea Cristian Constantin Volovăț |
| author_sort | Simona Ruxandra Volovăț |
| collection | DOAJ |
| description | <b>Introduction:</b> Accurate prediction of tumor dynamics following Gamma Knife radiosurgery (GKRS) is critical for optimizing treatment strategies for patients with brain metastases (BMs). Traditional machine learning (ML) algorithms have been widely used for this purpose; however, recent advancements in deep learning, such as autoencoders, offer the potential to enhance predictive accuracy. This study aims to evaluate the efficacy of autoencoders compared to traditional ML models in predicting tumor progression or regression after GKRS. <b>Objectives:</b> The primary objective of this study is to assess whether integrating autoencoder-derived features into traditional ML models can improve their performance in predicting tumor dynamics three months post-GKRS in patients with brain metastases. <b>Methods:</b> This retrospective analysis utilized clinical data from 77 patients treated at the “Prof. Dr. Nicolae Oblu” Emergency Clinic Hospital-Iasi. Twelve variables, including socio-demographic, clinical, treatment, and radiosurgery-related factors, were considered. Tumor progression or regression within three months post-GKRS was the primary outcome, with 71 cases of regression and 6 cases of progression. Traditional ML models, such as Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Extra Trees, Random Forest, and XGBoost, were trained and evaluated. The study further explored the impact of incorporating features derived from autoencoders, particularly focusing on the effect of compression in the bottleneck layer on model performance. <b>Results:</b> Traditional ML models achieved accuracy rates ranging from 0.91 (KNN) to 1.00 (Extra Trees). Integrating autoencoder-derived features generally enhanced model performance. Logistic Regression saw an accuracy increase from 0.91 to 0.94, and SVM improved from 0.85 to 0.96. XGBoost maintained consistent performance with an accuracy of 0.94 and an AUC of 0.98, regardless of the feature set used. These results demonstrate that hybrid models combining deep learning and traditional ML techniques can improve predictive accuracy. <b>Conclusion:</b> The study highlights the potential of hybrid models incorporating autoencoder-derived features to enhance the predictive accuracy and robustness of traditional ML models in forecasting tumor dynamics post-GKRS. These advancements could significantly contribute to personalized medicine, enabling more precise and individualized treatment planning based on refined predictive insights, ultimately improving patient outcomes. |
| format | Article |
| id | doaj-art-9652aef99e62435982f5ad994dc7fb20 |
| institution | OA Journals |
| issn | 2075-4418 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-9652aef99e62435982f5ad994dc7fb202025-08-20T01:55:22ZengMDPI AGDiagnostics2075-44182024-09-011418209110.3390/diagnostics14182091Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor DynamicsSimona Ruxandra Volovăț0Tudor Ovidiu Popa1Dragoș Rusu2Lăcrămioara Ochiuz3Decebal Vasincu4Maricel Agop5Călin Gheorghe Buzea6Cristian Constantin Volovăț7University of Medicine and Pharmacy “Grigore T. Popa” Iași, 700115 Iași, RomaniaUniversity of Medicine and Pharmacy “Grigore T. Popa” Iași, 700115 Iași, RomaniaFaculty of Engineering, “Vasile Alecsandri” University of Bacău, 600115 Bacău, RomaniaUniversity of Medicine and Pharmacy “Grigore T. Popa” Iași, 700115 Iași, RomaniaUniversity of Medicine and Pharmacy “Grigore T. Popa” Iași, 700115 Iași, RomaniaPhysics Department, Technical University “Gheorghe Asachi” Iași, 700050 Iași, RomaniaClinical Emergency Hospital “Prof. Dr. Nicolae Oblu” Iași, 700309 Iași, RomaniaUniversity of Medicine and Pharmacy “Grigore T. Popa” Iași, 700115 Iași, Romania<b>Introduction:</b> Accurate prediction of tumor dynamics following Gamma Knife radiosurgery (GKRS) is critical for optimizing treatment strategies for patients with brain metastases (BMs). Traditional machine learning (ML) algorithms have been widely used for this purpose; however, recent advancements in deep learning, such as autoencoders, offer the potential to enhance predictive accuracy. This study aims to evaluate the efficacy of autoencoders compared to traditional ML models in predicting tumor progression or regression after GKRS. <b>Objectives:</b> The primary objective of this study is to assess whether integrating autoencoder-derived features into traditional ML models can improve their performance in predicting tumor dynamics three months post-GKRS in patients with brain metastases. <b>Methods:</b> This retrospective analysis utilized clinical data from 77 patients treated at the “Prof. Dr. Nicolae Oblu” Emergency Clinic Hospital-Iasi. Twelve variables, including socio-demographic, clinical, treatment, and radiosurgery-related factors, were considered. Tumor progression or regression within three months post-GKRS was the primary outcome, with 71 cases of regression and 6 cases of progression. Traditional ML models, such as Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Extra Trees, Random Forest, and XGBoost, were trained and evaluated. The study further explored the impact of incorporating features derived from autoencoders, particularly focusing on the effect of compression in the bottleneck layer on model performance. <b>Results:</b> Traditional ML models achieved accuracy rates ranging from 0.91 (KNN) to 1.00 (Extra Trees). Integrating autoencoder-derived features generally enhanced model performance. Logistic Regression saw an accuracy increase from 0.91 to 0.94, and SVM improved from 0.85 to 0.96. XGBoost maintained consistent performance with an accuracy of 0.94 and an AUC of 0.98, regardless of the feature set used. These results demonstrate that hybrid models combining deep learning and traditional ML techniques can improve predictive accuracy. <b>Conclusion:</b> The study highlights the potential of hybrid models incorporating autoencoder-derived features to enhance the predictive accuracy and robustness of traditional ML models in forecasting tumor dynamics post-GKRS. These advancements could significantly contribute to personalized medicine, enabling more precise and individualized treatment planning based on refined predictive insights, ultimately improving patient outcomes.https://www.mdpi.com/2075-4418/14/18/2091gamma knife radiosurgery (GKRS)brain metastasistumor dynamics forecastingmachine learning modelsautoencoders |
| spellingShingle | Simona Ruxandra Volovăț Tudor Ovidiu Popa Dragoș Rusu Lăcrămioara Ochiuz Decebal Vasincu Maricel Agop Călin Gheorghe Buzea Cristian Constantin Volovăț Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics Diagnostics gamma knife radiosurgery (GKRS) brain metastasis tumor dynamics forecasting machine learning models autoencoders |
| title | Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics |
| title_full | Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics |
| title_fullStr | Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics |
| title_full_unstemmed | Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics |
| title_short | Comparative Performance of Autoencoders and Traditional Machine Learning Algorithms in Clinical Data Analysis for Predicting Post-Staged GKRS Tumor Dynamics |
| title_sort | comparative performance of autoencoders and traditional machine learning algorithms in clinical data analysis for predicting post staged gkrs tumor dynamics |
| topic | gamma knife radiosurgery (GKRS) brain metastasis tumor dynamics forecasting machine learning models autoencoders |
| url | https://www.mdpi.com/2075-4418/14/18/2091 |
| work_keys_str_mv | AT simonaruxandravolovat comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT tudorovidiupopa comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT dragosrusu comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT lacramioaraochiuz comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT decebalvasincu comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT maricelagop comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT calingheorghebuzea comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics AT cristianconstantinvolovat comparativeperformanceofautoencodersandtraditionalmachinelearningalgorithmsinclinicaldataanalysisforpredictingpoststagedgkrstumordynamics |