Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers
Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/14/3540 |
| _version_ | 1797589990553681920 |
|---|---|
| author | Yoon Kyoung So Zero Kim Taek Yoon Cheong Myung Jin Chung Chung-Hwan Baek Young-Ik Son Jungirl Seok Yuh-Seog Jung Myung-Ju Ahn Yong Chan Ahn Dongryul Oh Baek Hwan Cho Man Ki Chung |
| author_facet | Yoon Kyoung So Zero Kim Taek Yoon Cheong Myung Jin Chung Chung-Hwan Baek Young-Ik Son Jungirl Seok Yuh-Seog Jung Myung-Ju Ahn Yong Chan Ahn Dongryul Oh Baek Hwan Cho Man Ki Chung |
| author_sort | Yoon Kyoung So |
| collection | DOAJ |
| description | Pretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model’s performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (<i>N</i> = 778), data were augmented to split the training dataset (<i>N</i> = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset. |
| first_indexed | 2024-03-11T01:14:00Z |
| format | Article |
| id | doaj.art-d279be35d600466aa48a49ed98b74bda |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-11T01:14:00Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-d279be35d600466aa48a49ed98b74bda2023-11-18T18:40:29ZengMDPI AGCancers2072-66942023-07-011514354010.3390/cancers15143540Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck CancersYoon Kyoung So0Zero Kim1Taek Yoon Cheong2Myung Jin Chung3Chung-Hwan Baek4Young-Ik Son5Jungirl Seok6Yuh-Seog Jung7Myung-Ju Ahn8Yong Chan Ahn9Dongryul Oh10Baek Hwan Cho11Man Ki Chung12Department of Otorhinolaryngology-Head & Neck Surgery, Inje University College of Medicine, Ilsan Paik Hospital, Goyang-Si 10380, Republic of KoreaMedical AI Research Center, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Otorhinolaryngology-Head & Neck Surgery, Inje University College of Medicine, Ilsan Paik Hospital, Goyang-Si 10380, Republic of KoreaMedical AI Research Center, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Otolaryngology-Head & Neck Surgery, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Otolaryngology-Head & Neck Surgery, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaCenter for Thyroid Cancer, Department of Otolaryngology-Head and Neck Surgery, Research Institute and Hospital, National Cancer Center, Goyang-si 10408, Republic of KoreaCenter for Thyroid Cancer, Department of Otolaryngology-Head and Neck Surgery, Research Institute and Hospital, National Cancer Center, Goyang-si 10408, Republic of KoreaDivison of Hematology and Medical Oncology, Department of Medicine, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Radiation Oncology, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Radiation Oncology, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaDepartment of Biomedical Informatics, CHA University School of Medicine, CHA University, Seongnam-Si 13488, Republic of KoreaDepartment of Otolaryngology-Head & Neck Surgery, Sungkyunkwan University School of Medicine, Samsung Medical Center, Seoul 06351, Republic of KoreaPretreatment values of the neutrophil-to-lymphocyte ratio (NLR) and the platelet-to-lymphocyte ratio (PLR) are well-established prognosticators in various cancers, including head and neck cancers. However, there are no studies on whether temporal changes in the NLR and PLR values after treatment are related to the development of recurrence. Therefore, in this study, we aimed to develop a deep neural network (DNN) model to discern cancer recurrence from temporal NLR and PLR values during follow-up after concurrent chemoradiotherapy (CCRT) and to evaluate the model’s performance compared with conventional machine learning (ML) models. Along with conventional ML models such as logistic regression (LR), random forest (RF), and gradient boosting (GB), the DNN model to discern recurrences was trained using a dataset of 778 consecutive patients with primary head and neck cancers who received CCRT. There were 16 input features used, including 12 laboratory values related to the NLR and the PLR. Along with the original training dataset (<i>N</i> = 778), data were augmented to split the training dataset (<i>N</i> = 900). The model performance was measured using ROC-AUC and PR-AUC values. External validation was performed using a dataset of 173 patients from an unrelated external institution. The ROC-AUC and PR-AUC values of the DNN model were 0.828 ± 0.032 and 0.663 ± 0.069, respectively, in the original training dataset, which were higher than the ROC-AUC and PR-AUC values of the LR, RF, and GB models in the original training dataset. With the recursive feature elimination (RFE) algorithm, five input features were selected. The ROC-AUC and PR-AUC values of the DNN-RFE model were higher than those of the original DNN model (0.883 ± 0.027 and 0.778 ± 0.042, respectively). The ROC-AUC and PR-AUC values of the DNN-RFE model trained with a split dataset were 0.889 ± 0.032 and 0.771 ± 0.044, respectively. In the external validation, the ROC-AUC values of the DNN-RFE model trained with the original dataset and the same model trained with the split dataset were 0.710 and 0.784, respectively. The DNN model with feature selection using the RFE algorithm showed the best performance among the ML models to discern a recurrence after CCRT in patients with head and neck cancers. Data augmentation by splitting training data was helpful for model performance. The performance of the DNN-RFE model was also validated with an external dataset.https://www.mdpi.com/2072-6694/15/14/3540deep neural networkmachine learninghead and neck cancerscancer recurrenceconcurrent chemoradiotherapy |
| spellingShingle | Yoon Kyoung So Zero Kim Taek Yoon Cheong Myung Jin Chung Chung-Hwan Baek Young-Ik Son Jungirl Seok Yuh-Seog Jung Myung-Ju Ahn Yong Chan Ahn Dongryul Oh Baek Hwan Cho Man Ki Chung Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers Cancers deep neural network machine learning head and neck cancers cancer recurrence concurrent chemoradiotherapy |
| title | Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers |
| title_full | Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers |
| title_fullStr | Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers |
| title_full_unstemmed | Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers |
| title_short | Detection of Cancer Recurrence Using Systemic Inflammatory Markers and Machine Learning after Concurrent Chemoradiotherapy for Head and Neck Cancers |
| title_sort | detection of cancer recurrence using systemic inflammatory markers and machine learning after concurrent chemoradiotherapy for head and neck cancers |
| topic | deep neural network machine learning head and neck cancers cancer recurrence concurrent chemoradiotherapy |
| url | https://www.mdpi.com/2072-6694/15/14/3540 |
| work_keys_str_mv | AT yoonkyoungso detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT zerokim detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT taekyooncheong detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT myungjinchung detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT chunghwanbaek detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT youngikson detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT jungirlseok detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT yuhseogjung detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT myungjuahn detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT yongchanahn detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT dongryuloh detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT baekhwancho detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers AT mankichung detectionofcancerrecurrenceusingsystemicinflammatorymarkersandmachinelearningafterconcurrentchemoradiotherapyforheadandneckcancers |