Deep learning-based survival prediction of oral cancer patients

The Cox proportional hazards model commonly used to evaluate prognostic variables in survival of cancer patients may be too simplistic to properly predict a cancer patient’s outcome since it assumes that the outcome is a linear combination of covariates. In this retrospective study including 255 pat...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2019-05, Vol.9 (1), p.6994-6994, Article 6994
Main Authors: Kim, Dong Wook, Lee, Sanghoon, Kwon, Sunmo, Nam, Woong, Cha, In-Ho, Kim, Hyung Jun
Format: Article
Language:English
Subjects:
631/114/1305
692/4028/546
692/4028/67/1665
Aged
Cancer
Carcinoma, Squamous Cell - diagnosis
Carcinoma, Squamous Cell - mortality
Carcinoma, Squamous Cell - pathology
Carcinoma, Squamous Cell - surgery
Deep Learning - statistics & numerical data
Female
Humanities and Social Sciences
Humans
Male
Middle Aged
Mouth Neoplasms - diagnosis
Mouth Neoplasms - mortality
Mouth Neoplasms - pathology
Mouth Neoplasms - surgery
multidisciplinary
Oral cancer
Oral squamous cell carcinoma
Prognosis
Proportional Hazards Models
Recurrence
Retrospective Studies
Science
Science (multidisciplinary)
Squamous cell carcinoma
Survival
Survival Analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Cox proportional hazards model commonly used to evaluate prognostic variables in survival of cancer patients may be too simplistic to properly predict a cancer patient’s outcome since it assumes that the outcome is a linear combination of covariates. In this retrospective study including 255 patients suitable for analysis who underwent surgical treatment in our department from 2000 to 2017, we applied a deep learning-based survival prediction method in oral squamous cell carcinoma (SCC) patients and validated its performance. Survival prediction using DeepSurv, a deep learning based-survival prediction algorithm, was compared with random survival forest (RSF) and the Cox proportional hazard model (CPH). DeepSurv showed the best performance among the three models, the c-index of the training and testing sets reaching 0.810 and 0.781, respectively, followed by RSF (0.770/0.764), and CPH (0.756/0.694). The performance of DeepSurv steadily improved with added features. Thus, deep learning-based survival prediction may improve prediction accuracy and guide clinicians both in choosing treatment options for better survival and in avoiding unnecessary treatments.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-019-43372-7