Xiao Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiao Sun has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hao Feng
Chinese Academy of Medical Sciences & Peking Union Medical College
2 shared publications - Liang Zhao
Department of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
2 shared publications - Shanrui Ma
National Central Cancer Registry, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Beijing China
2 shared publications - Xi Cheng
School of University College Birmingham, Birmingham, United Kingdom
2 shared publications - Ziran Zhao
Thoracic Surgery Department, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
2 shared publications - Xiangyin Quan
China Academy of Launch Vehicle Technology, China Aerospace Science and Technology Corporation,BeijingChina,100076
1 shared publication
Latest Publications
- Open Access
- 27 July 2021
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 9 (7) , e27110
Prediction Model of Anastomotic Leakage Among Esophageal Cancer Patients After Receiving an Esophagectomy: Machine Learning Approach
Background: Anastomotic leakage (AL) is one of the severe postoperative adverse events (5%-30%), and it is related to increased medical costs in cancer patients who undergo esophagectomies. Machine learning (ML) methods show good performance at predicting risk for AL. However, AL risk prediction based on ML models among the Chinese population is unavailable. Objective: This study uses ML techniques to develop and validate a risk prediction model to screen patients with emerging AL risk factors. Methods: Analyses were performed using medical records from 710 patients who underwent esophagectomies at the National Clinical Research Center for Cancer between January 2010 and May 2015. We randomly split (9:1) the data set into a training data set of 639 patients and a testing data set of 71 patients using a computer algorithm. We assessed multiple classification tools to create a multivariate risk prediction model. Our ML algorithms contained decision tree, random forest, naive Bayes, and logistic regression with least absolute shrinkage and selection operator. The optimal AL prediction model was selected based on model evaluation metrics. Results: The final risk panel included 36 independent risk features. Of those, 10 features were significantly identified by the logistic model, including aortic calcification (OR 2.77, 95% CI 1.32-5.81), celiac trunk calcification (OR 2.79, 95% CI 1.20-6.48), forced expiratory volume 1% (OR 0.51, 95% CI 0.30-0.89); TLco (OR 0.56, 95% CI 0.27-1.18), peripheral vascular disease (OR 4.97, 95% CI 1.44-17.07), laparoscope (OR 3.92, 95% CI 1.23-12.51), postoperative length of hospital stay (OR 1.17, 95% CI 1.13-1.21), vascular permeability activity (OR 0.46, 95% CI 0.14-1.48), and fat liquefaction of incisions (OR 4.36, 95% CI 1.86-10.21). Logistic regression with least absolute shrinkage and selection operator offered the highest prediction quality with an area under the receiver operator characteristic of 72% in the training data set. The testing model also achieved similar high performance. Conclusions: Our model offered a prediction of AL with high accuracy, assisting in AL prevention and treatment. A personalized ML prediction model with a purely data-driven selection of features is feasible and effective in predicting AL in patients who underwent esophagectomy.
- 27 July 2021
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 9 (7) , e27110
Open AccessPrediction Model of Anastomotic Leakage Among Esophageal Cancer Patients After Receiving an Esophagectomy: Machine Learning Approach
Background: Anastomotic leakage (AL) is one of the severe postoperative adverse events (5%-30%), and it is related to increased medical costs in cancer patients who undergo esophagectomies. Machine learning (ML) methods show good performance at predicting risk for AL. However, AL risk prediction based on ML models among the Chinese population is unavailable. Objective: This study uses ML techniques to develop and validate a risk prediction model to screen patients with emerging AL risk factors. Methods: Analyses were performed using medical records from 710 patients who underwent esophagectomies at the National Clinical Research Center for Cancer between January 2010 and May 2015. We randomly split (9:1) the data set into a training data set of 639 patients and a testing data set of 71 patients using a computer algorithm. We assessed multiple classification tools to create a multivariate risk prediction model. Our ML algorithms contained decision tree, random forest, naive Bayes, and logistic regression with least absolute shrinkage and selection operator. The optimal AL prediction model was selected based on model evaluation metrics. Results: The final risk panel included 36 independent risk features. Of those, 10 features were significantly identified by the logistic model, including aortic calcification (OR 2.77, 95% CI 1.32-5.81), celiac trunk calcification (OR 2.79, 95% CI 1.20-6.48), forced expiratory volume 1% (OR 0.51, 95% CI 0.30-0.89); TLco (OR 0.56, 95% CI 0.27-1.18), peripheral vascular disease (OR 4.97, 95% CI 1.44-17.07), laparoscope (OR 3.92, 95% CI 1.23-12.51), postoperative length of hospital stay (OR 1.17, 95% CI 1.13-1.21), vascular permeability activity (OR 0.46, 95% CI 0.14-1.48), and fat liquefaction of incisions (OR 4.36, 95% CI 1.86-10.21). Logistic regression with least absolute shrinkage and selection operator offered the highest prediction quality with an area under the receiver operator characteristic of 72% in the training data set. The testing model also achieved similar high performance. Conclusions: Our model offered a prediction of AL with high accuracy, assisting in AL prevention and treatment. A personalized ML prediction model with a purely data-driven selection of features is feasible and effective in predicting AL in patients who underwent esophagectomy.
- Open Access
- 14 January 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Prediction Model of Anastomotic Leakage Among Esophageal Cancer Patients After Receiving an Esophagectomy: Machine Learning Approach (Preprint)
BACKGROUND Anastomotic leakage (AL) is one of the severe postoperative adverse events (5%-30%), and it is related to increased medical costs in cancer patients who undergo esophagectomies. Machine learning (ML) methods show good performance at predicting risk for AL. However, AL risk prediction based on ML models among the Chinese population is unavailable. OBJECTIVE This study uses ML techniques to develop and validate a risk prediction model to screen patients with emerging AL risk factors. METHODS Analyses were performed using medical records from 710 patients who underwent esophagectomies at the National Clinical Research Center for Cancer between January 2010 and May 2015. We randomly split (9:1) the data set into a training data set of 639 patients and a testing data set of 71 patients using a computer algorithm. We assessed multiple classification tools to create a multivariate risk prediction model. Our ML algorithms contained decision tree, random forest, naive Bayes, and logistic regression with least absolute shrinkage and selection operator. The optimal AL prediction model was selected based on model evaluation metrics. RESULTS The final risk panel included 36 independent risk features. Of those, 10 features were significantly identified by the logistic model, including aortic calcification (OR 2.77, 95% CI 1.32-5.81), celiac trunk calcification (OR 2.79, 95% CI 1.20-6.48), forced expiratory volume 1% (OR 0.51, 95% CI 0.30-0.89); TLco (OR 0.56, 95% CI 0.27-1.18), peripheral vascular disease (OR 4.97, 95% CI 1.44-17.07), laparoscope (OR 3.92, 95% CI 1.23-12.51), postoperative length of hospital stay (OR 1.17, 95% CI 1.13-1.21), vascular permeability activity (OR 0.46, 95% CI 0.14-1.48), and fat liquefaction of incisions (OR 4.36, 95% CI 1.86-10.21). Logistic regression with least absolute shrinkage and selection operator offered the highest prediction quality with an area under the receiver operator characteristic of 72% in the training data set. The testing model also achieved similar high performance. CONCLUSIONS Our model offered a prediction of AL with high accuracy, assisting in AL prevention and treatment. A personalized ML prediction model with a purely data-driven selection of features is feasible and effective in predicting AL in patients who underwent esophagectomy.
- 14 January 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPrediction Model of Anastomotic Leakage Among Esophageal Cancer Patients After Receiving an Esophagectomy: Machine Learning Approach (Preprint)
BACKGROUND Anastomotic leakage (AL) is one of the severe postoperative adverse events (5%-30%), and it is related to increased medical costs in cancer patients who undergo esophagectomies. Machine learning (ML) methods show good performance at predicting risk for AL. However, AL risk prediction based on ML models among the Chinese population is unavailable. OBJECTIVE This study uses ML techniques to develop and validate a risk prediction model to screen patients with emerging AL risk factors. METHODS Analyses were performed using medical records from 710 patients who underwent esophagectomies at the National Clinical Research Center for Cancer between January 2010 and May 2015. We randomly split (9:1) the data set into a training data set of 639 patients and a testing data set of 71 patients using a computer algorithm. We assessed multiple classification tools to create a multivariate risk prediction model. Our ML algorithms contained decision tree, random forest, naive Bayes, and logistic regression with least absolute shrinkage and selection operator. The optimal AL prediction model was selected based on model evaluation metrics. RESULTS The final risk panel included 36 independent risk features. Of those, 10 features were significantly identified by the logistic model, including aortic calcification (OR 2.77, 95% CI 1.32-5.81), celiac trunk calcification (OR 2.79, 95% CI 1.20-6.48), forced expiratory volume 1% (OR 0.51, 95% CI 0.30-0.89); TLco (OR 0.56, 95% CI 0.27-1.18), peripheral vascular disease (OR 4.97, 95% CI 1.44-17.07), laparoscope (OR 3.92, 95% CI 1.23-12.51), postoperative length of hospital stay (OR 1.17, 95% CI 1.13-1.21), vascular permeability activity (OR 0.46, 95% CI 0.14-1.48), and fat liquefaction of incisions (OR 4.36, 95% CI 1.86-10.21). Logistic regression with least absolute shrinkage and selection operator offered the highest prediction quality with an area under the receiver operator characteristic of 72% in the training data set. The testing model also achieved similar high performance. CONCLUSIONS Our model offered a prediction of AL with high accuracy, assisting in AL prevention and treatment. A personalized ML prediction model with a purely data-driven selection of features is feasible and effective in predicting AL in patients who underwent esophagectomy.
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 998-1002
Intelligent Recognition Method Based on Deep Learning for Locally Damaged Ship Targets
Owing to the explosion effect and local ship damage caused by multi-round missile attacks, it becomes very difficult to accurately recognize the specific ship target. To solve this problem, this paper properly combines the convolutional neural network (CNN) with the support vector machine, and proposes a new recognition method for locally damaged ship targets. By migrating the deep convolutional neural network to locally damaged ship targets recognition the proposed technique is able to learn the robust features of locally damaged ship targets, which can avoid difficult manual designed feature extraction processes. When the target characteristics of the ship vary on account of the explosion effect and local ship damage, it performs better than other methods. Since it is difficult to obtain the target samples of military ships, our method introduces transfer learning into the target recognition of ships. By training the CNN with the samples of general object and using damaged ship samples to fine-tuning characteristic network parameters and classifiers, the ship recognition capacity of our method still achieves excellent performance. The experimental results show that its recognition rate can reach 97%. And it is robust to the explosion effect and local ship damage, which change the target characteristics of the ship.
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 998-1002
Intelligent Recognition Method Based on Deep Learning for Locally Damaged Ship Targets
Owing to the explosion effect and local ship damage caused by multi-round missile attacks, it becomes very difficult to accurately recognize the specific ship target. To solve this problem, this paper properly combines the convolutional neural network (CNN) with the support vector machine, and proposes a new recognition method for locally damaged ship targets. By migrating the deep convolutional neural network to locally damaged ship targets recognition the proposed technique is able to learn the robust features of locally damaged ship targets, which can avoid difficult manual designed feature extraction processes. When the target characteristics of the ship vary on account of the explosion effect and local ship damage, it performs better than other methods. Since it is difficult to obtain the target samples of military ships, our method introduces transfer learning into the target recognition of ships. By training the CNN with the samples of general object and using damaged ship samples to fine-tuning characteristic network parameters and classifiers, the ship recognition capacity of our method still achieves excellent performance. The experimental results show that its recognition rate can reach 97%. And it is robust to the explosion effect and local ship damage, which change the target characteristics of the ship.