Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer
Abstract Purpose The study aims to enhance the efficiency and accuracy of literature reviews on normal tissue complication probability (NTCP) in head and neck cancer patients using radiation therapy. It employs meta-analysis (MA) and natural language processing (NLP). Material and methods The study...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13014-023-02381-7 |
| _version_ | 1797355588065165312 |
|---|---|
| author | Tsair-Fwu Lee Yang-Wei Hsieh Pei-Ying Yang Chi-Hung Tseng Shen-Hao Lee Jack Yang Liyun Chang Jia-Ming Wu Chin-Dar Tseng Pei-Ju Chao |
| author_facet | Tsair-Fwu Lee Yang-Wei Hsieh Pei-Ying Yang Chi-Hung Tseng Shen-Hao Lee Jack Yang Liyun Chang Jia-Ming Wu Chin-Dar Tseng Pei-Ju Chao |
| author_sort | Tsair-Fwu Lee |
| collection | DOAJ |
| description | Abstract Purpose The study aims to enhance the efficiency and accuracy of literature reviews on normal tissue complication probability (NTCP) in head and neck cancer patients using radiation therapy. It employs meta-analysis (MA) and natural language processing (NLP). Material and methods The study consists of two parts. First, it employs MA to assess NTCP models for xerostomia, dysphagia, and mucositis after radiation therapy, using Python 3.10.5 for statistical analysis. Second, it integrates NLP with convolutional neural networks (CNN) to optimize literature search, reducing 3256 articles to 12. CNN settings include a batch size of 50, 50–200 epoch range and a 0.001 learning rate. Results The study's CNN-NLP model achieved a notable accuracy of 0.94 after 200 epochs with Adamax optimization. MA showed an AUC of 0.67 for early-effect xerostomia and 0.74 for late-effect, indicating moderate to high predictive accuracy but with high variability across studies. Initial CNN accuracy of 66.70% improved to 94.87% post-tuning by optimizer and hyperparameters. Conclusion The study successfully merges MA and NLP, confirming high predictive accuracy for specific model-feature combinations. It introduces a time-based metric, words per minute (WPM), for efficiency and highlights the utility of MA and NLP in clinical research. |
| first_indexed | 2024-03-08T14:14:18Z |
| format | Article |
| id | doaj.art-89dec3a1cb2d4b93b408dfe57e208d93 |
| institution | Directory Open Access Journal |
| issn | 1748-717X |
| language | English |
| last_indexed | 2024-03-08T14:14:18Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj.art-89dec3a1cb2d4b93b408dfe57e208d932024-01-14T12:31:19ZengBMCRadiation Oncology1748-717X2024-01-0119112110.1186/s13014-023-02381-7Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancerTsair-Fwu Lee0Yang-Wei Hsieh1Pei-Ying Yang2Chi-Hung Tseng3Shen-Hao Lee4Jack Yang5Liyun Chang6Jia-Ming Wu7Chin-Dar Tseng8Pei-Ju Chao9Medical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics at Monmouth Medical Center, Barnabas Health Care at Long BranchDepartment of Medical Imaging and Radiological Sciences, I-Shou UniversityHeavy Ion Center of Wuwei Cancer Hospital, Gansu Wuwei Academy of Medical Sciences, Gansu Wuwei Tumor HospitalMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyMedical Physics and Informatics Laboratory of Electronics Engineering, National Kaohsiung University of Science and TechnologyAbstract Purpose The study aims to enhance the efficiency and accuracy of literature reviews on normal tissue complication probability (NTCP) in head and neck cancer patients using radiation therapy. It employs meta-analysis (MA) and natural language processing (NLP). Material and methods The study consists of two parts. First, it employs MA to assess NTCP models for xerostomia, dysphagia, and mucositis after radiation therapy, using Python 3.10.5 for statistical analysis. Second, it integrates NLP with convolutional neural networks (CNN) to optimize literature search, reducing 3256 articles to 12. CNN settings include a batch size of 50, 50–200 epoch range and a 0.001 learning rate. Results The study's CNN-NLP model achieved a notable accuracy of 0.94 after 200 epochs with Adamax optimization. MA showed an AUC of 0.67 for early-effect xerostomia and 0.74 for late-effect, indicating moderate to high predictive accuracy but with high variability across studies. Initial CNN accuracy of 66.70% improved to 94.87% post-tuning by optimizer and hyperparameters. Conclusion The study successfully merges MA and NLP, confirming high predictive accuracy for specific model-feature combinations. It introduces a time-based metric, words per minute (WPM), for efficiency and highlights the utility of MA and NLP in clinical research.https://doi.org/10.1186/s13014-023-02381-7Meta-analysisNatural language processingHead and neck cancerSquamous cell carcinoma of the head and neckNormal tissue complication probability predictionConvolutional neural networks |
| spellingShingle | Tsair-Fwu Lee Yang-Wei Hsieh Pei-Ying Yang Chi-Hung Tseng Shen-Hao Lee Jack Yang Liyun Chang Jia-Ming Wu Chin-Dar Tseng Pei-Ju Chao Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer Radiation Oncology Meta-analysis Natural language processing Head and neck cancer Squamous cell carcinoma of the head and neck Normal tissue complication probability prediction Convolutional neural networks |
| title | Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| title_full | Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| title_fullStr | Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| title_full_unstemmed | Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| title_short | Using meta-analysis and CNN-NLP to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| title_sort | using meta analysis and cnn nlp to review and classify the medical literature for normal tissue complication probability in head and neck cancer |
| topic | Meta-analysis Natural language processing Head and neck cancer Squamous cell carcinoma of the head and neck Normal tissue complication probability prediction Convolutional neural networks |
| url | https://doi.org/10.1186/s13014-023-02381-7 |
| work_keys_str_mv | AT tsairfwulee usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT yangweihsieh usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT peiyingyang usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT chihungtseng usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT shenhaolee usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT jackyang usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT liyunchang usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT jiamingwu usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT chindartseng usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer AT peijuchao usingmetaanalysisandcnnnlptoreviewandclassifythemedicalliteraturefornormaltissuecomplicationprobabilityinheadandneckcancer |