Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders

• Published in: Cancers Vol. 13; no. 23; p. 6054
• Main Authors: Adeoye, John, Koohi-Moghadam, Mohamad, Lo, Anthony Wing Ip, Tsang, Raymond King-Yin, Chow, Velda Ling Yu, Zheng, Li-Wu, Choi, Siu-Wai, Thomson, Peter, Su, Yu-Xiong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2021; MDPI
• Subjects: Alcohol; Algorithms; Artificial intelligence; Biopsy; Calibration; Clinical outcomes; Datasets; Decision making; Deep learning; Diagnosis; Disease; Electronic medical records; Head & neck cancer; Hospitals; Intelligence; Irritable bowel syndrome; Learning algorithms; Lesions; Leukokeratosis; Machine learning; Malignancy; Maxillofacial surgery; Medical prognosis; Mouth; Oral carcinoma; Otolaryngology; Probability; Survival; Tumors; Variables; Hong Kong China; China
• ISSN: 2072-6694; 2072-6694
• DOI: 10.3390/cancers13236054

Machine-intelligence platforms for the prediction of the probability of malignant transformation of oral potentially malignant disorders are required as adjunctive decision-making platforms in contemporary clinical practice. This study utilized time-to-event learning models to predict malignant transformation in oral leukoplakia and oral lichenoid lesions. A total of 1098 patients with oral white lesions from two institutions were included in this study. In all, 26 features available from electronic health records were used to train four learning algorithms—Cox-Time, DeepHit, DeepSurv, random survival forest (RSF)—and one standard statistical method—Cox proportional hazards model. Discriminatory performance, calibration of survival estimates, and model stability were assessed using a concordance index (c-index), integrated Brier score (IBS), and standard deviation of the averaged c-index and IBS following training cross-validation. This study found that DeepSurv (c-index: 0.95, IBS: 0.04) and RSF (c-index: 0.91, IBS: 0.03) were the two outperforming models based on discrimination and calibration following internal validation. However, DeepSurv was more stable than RSF upon cross-validation. External validation confirmed the utility of DeepSurv for discrimination (c-index—0.82 vs. 0.73) and RSF for individual survival estimates (0.18 vs. 0.03). We deployed the DeepSurv model to encourage incipient application in clinical practice. Overall, time-to-event models are successful in predicting the malignant transformation of oral leukoplakia and oral lichenoid lesions.