A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma

Abstract The radiological dosimetric parameters and clinical features were screened by machine learning to construct a prediction model for the short-term efficacy of locally advanced Nasopharyngeal Carcinoma (LANPC). Patients diagnosed with Nasopharyngeal Carcinoma were retrospectively collected in...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiulu Zhong, Xiangde Li, Qinghua Du, Qianfu Liang, Danjing Luo, Jiaying Wen, Haiying Yue, Wenqi Liu, Xiaodong Zhu, Jian Li
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02897-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731817179971584
author Qiulu Zhong
Xiangde Li
Qinghua Du
Qianfu Liang
Danjing Luo
Jiaying Wen
Haiying Yue
Wenqi Liu
Xiaodong Zhu
Jian Li
author_facet Qiulu Zhong
Xiangde Li
Qinghua Du
Qianfu Liang
Danjing Luo
Jiaying Wen
Haiying Yue
Wenqi Liu
Xiaodong Zhu
Jian Li
author_sort Qiulu Zhong
collection DOAJ
description Abstract The radiological dosimetric parameters and clinical features were screened by machine learning to construct a prediction model for the short-term efficacy of locally advanced Nasopharyngeal Carcinoma (LANPC). Patients diagnosed with Nasopharyngeal Carcinoma were retrospectively collected in the study. Twenty-four clinical features and twelve radiological dosimetric features were included. Three machine learning algorithms were used to construct predictive models for the short-term efficacy of LANPC. Kaplan–Meier log-rank method was used to compare the prognosis of patients with different efficacies in the model. The reliability of the model was evaluated using the calibration curve and the area under the curve (AUC). There were 194 patients who met the inclusion criteria. Among the three models being constructed, Random forest (RSF) model showed the best predictive ability, with AUC values of 1.000 in the training group and 0.944 in the test group, followed by XGBoost decision tree (GBDT) model (0.866/0.849) and decision tree (DT) model (0.848/0.783). In RSF model, the 3-year and 5-year overall survival rates of patients in complete remission (CR) group were 98.9% (95% CI 0.9688–1.0000) and 89.7% (95% CI 0.8256–0.9752), respectively.While for patients in non-CR group, the 3-year and 5-year overall survival (OS) rate was 100% (95%CI 1.000~1.000) and 98.8% (95% CI 0.9652–1.0000), respectively. There has statistically significant difference between the two groups (P = 0.0037). RSF model constructed by machine-learning algorithm based on radiological dosimetric parameters and clinical characteristics can better predict the short-term efficacy of LANPC, and is an effective tool to evaluate the short-term efficacy of different LANPC patients during treatment.
format Article
id doaj-art-b8e8a0322e294adbb4bea442324bd1f5
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b8e8a0322e294adbb4bea442324bd1f52025-08-20T03:08:25ZengNature PortfolioScientific Reports2045-23222025-05-0115111410.1038/s41598-025-02897-wA machine learning based prediction model for short term efficacy of nasopharyngeal carcinomaQiulu Zhong0Xiangde Li1Qinghua Du2Qianfu Liang3Danjing Luo4Jiaying Wen5Haiying Yue6Wenqi Liu7Xiaodong Zhu8Jian Li9Department of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, Wuming Hospital of Guangxi Medical UniversityDepartment of Radiation Oncology, The Second Affiliated Hospital of Guangxi Medical UniversityAbstract The radiological dosimetric parameters and clinical features were screened by machine learning to construct a prediction model for the short-term efficacy of locally advanced Nasopharyngeal Carcinoma (LANPC). Patients diagnosed with Nasopharyngeal Carcinoma were retrospectively collected in the study. Twenty-four clinical features and twelve radiological dosimetric features were included. Three machine learning algorithms were used to construct predictive models for the short-term efficacy of LANPC. Kaplan–Meier log-rank method was used to compare the prognosis of patients with different efficacies in the model. The reliability of the model was evaluated using the calibration curve and the area under the curve (AUC). There were 194 patients who met the inclusion criteria. Among the three models being constructed, Random forest (RSF) model showed the best predictive ability, with AUC values of 1.000 in the training group and 0.944 in the test group, followed by XGBoost decision tree (GBDT) model (0.866/0.849) and decision tree (DT) model (0.848/0.783). In RSF model, the 3-year and 5-year overall survival rates of patients in complete remission (CR) group were 98.9% (95% CI 0.9688–1.0000) and 89.7% (95% CI 0.8256–0.9752), respectively.While for patients in non-CR group, the 3-year and 5-year overall survival (OS) rate was 100% (95%CI 1.000~1.000) and 98.8% (95% CI 0.9652–1.0000), respectively. There has statistically significant difference between the two groups (P = 0.0037). RSF model constructed by machine-learning algorithm based on radiological dosimetric parameters and clinical characteristics can better predict the short-term efficacy of LANPC, and is an effective tool to evaluate the short-term efficacy of different LANPC patients during treatment.https://doi.org/10.1038/s41598-025-02897-wLocoregionally advanced nasopharyngeal carcinomaShort-term efficacyMachine-learning algorithmRadiological dosimetric parameters
spellingShingle Qiulu Zhong
Xiangde Li
Qinghua Du
Qianfu Liang
Danjing Luo
Jiaying Wen
Haiying Yue
Wenqi Liu
Xiaodong Zhu
Jian Li
A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
Scientific Reports
Locoregionally advanced nasopharyngeal carcinoma
Short-term efficacy
Machine-learning algorithm
Radiological dosimetric parameters
title A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
title_full A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
title_fullStr A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
title_full_unstemmed A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
title_short A machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
title_sort machine learning based prediction model for short term efficacy of nasopharyngeal carcinoma
topic Locoregionally advanced nasopharyngeal carcinoma
Short-term efficacy
Machine-learning algorithm
Radiological dosimetric parameters
url https://doi.org/10.1038/s41598-025-02897-w
work_keys_str_mv AT qiuluzhong amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT xiangdeli amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT qinghuadu amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT qianfuliang amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT danjingluo amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT jiayingwen amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT haiyingyue amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT wenqiliu amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT xiaodongzhu amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT jianli amachinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT qiuluzhong machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT xiangdeli machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT qinghuadu machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT qianfuliang machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT danjingluo machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT jiayingwen machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT haiyingyue machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT wenqiliu machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT xiaodongzhu machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma
AT jianli machinelearningbasedpredictionmodelforshorttermefficacyofnasopharyngealcarcinoma