Xiangjian Wang1,2, Jin Yang1, Changlei Wei1,3, Gang Zhou4, Lanyan Wu5, Qinghong Gao6, Xin He1, Jiahong Shi1, Yingying Mei1, Ying Liu7, Xueke Shi1, Fanglong Wu1, Jingjing Luo1, Yiqing Guo1, Qizhi Zhou8, Jiaxin Yin9, Tao Hu9, Mei Lin1, Zhi Liang10, Hongmei Zhou1. 1. State Key Laboratory of Oral Diseases, Department of Oral Medicine, West China Hospital of Stomatology, Sichuan University, Chengdu, China. 2. Department of Oral Medicine, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China. 3. Department of Oral Medicine, The Affiliated Hospital of Qingdao University, Qingdao, China. 4. Department of Oral Medicine, School and Hospital of Stomatology, Wuhan University, Wuhan, China. 5. Department of Oral Pathology, West China Hospital of Stomatology, Sichuan University, Chengdu, China. 6. Department of Oral and Maxillofacial surgery, West China Hospital of Stomatology, Sichuan University, Chengdu, China. 7. Department of Oral Medicine, North Sichuan Medical College, Nanchong, China. 8. School of Acupuncture-Moxibustion and Tuina, Chengdu University of TCM, Chengdu, China. 9. Department of Preventive Dentistry, West China Hospital of Stomatology, Sichuan University, Chengdu, China. 10. Hefei National Laboratory for Physical Sciences at Microscale and School of Life Science, University of Science and Technology of China, Hefei, China.
Abstract
BACKGROUND: Despite their high accuracy to recognize oral potentially malignant disorders (OPMDs) with cancer risk, non-invasive oral assays are poor in discerning whether the risk is high or low. However, it is critical to identify the risk levels, since high-risk patients need active intervention, while low-risk ones simply need to be follow-up. This study aimed at developing a personalized computational model to predict cancer risk level of OPMDs and explore its potential web application in OPMDs screening. METHODS: Each enrolled patient was subjected to the following procedure: personal information collection, non-invasive oral examination, oral tissue biopsy and histopathological analysis, treatment, and follow-up. Patients were randomly divided into a training set (N = 159) and a test set (N = 107). Random forest was used to establish classification models. A baseline model (model-B) and a personalized model (model-P) were created. The former used the non-invasive scores only, while the latter was incremented with appropriate personal features. RESULTS: We compared the respective performance of cancer risk level prediction by model-B, model-P, and clinical experts. Our data suggested that all three have a similar level of specificity around 90%. In contrast, the sensitivity of model-P is beyond 80% and superior to the other two. The improvement of sensitivity by model-P reduced the misclassification of high-risk patients as low-risk ones. We deployed model-P in web.opmd-risk.com, which can be freely and conveniently accessed. CONCLUSION: We have proposed a novel machine-learning model for precise and cost-effective OPMDs screening, which integrates clinical examinations, machine learning, and information technology.
RCT Entities:
BACKGROUND: Despite their high accuracy to recognize oral potentially malignant disorders (OPMDs) with cancer risk, non-invasive oral assays are poor in discerning whether the risk is high or low. However, it is critical to identify the risk levels, since high-risk patients need active intervention, while low-risk ones simply need to be follow-up. This study aimed at developing a personalized computational model to predict cancer risk level of OPMDs and explore its potential web application in OPMDs screening. METHODS: Each enrolled patient was subjected to the following procedure: personal information collection, non-invasive oral examination, oral tissue biopsy and histopathological analysis, treatment, and follow-up. Patients were randomly divided into a training set (N = 159) and a test set (N = 107). Random forest was used to establish classification models. A baseline model (model-B) and a personalized model (model-P) were created. The former used the non-invasive scores only, while the latter was incremented with appropriate personal features. RESULTS: We compared the respective performance of cancer risk level prediction by model-B, model-P, and clinical experts. Our data suggested that all three have a similar level of specificity around 90%. In contrast, the sensitivity of model-P is beyond 80% and superior to the other two. The improvement of sensitivity by model-P reduced the misclassification of high-risk patients as low-risk ones. We deployed model-P in web.opmd-risk.com, which can be freely and conveniently accessed. CONCLUSION: We have proposed a novel machine-learning model for precise and cost-effective OPMDs screening, which integrates clinical examinations, machine learning, and information technology.