Novel prognostication of patients with spinal and pelvic chondrosarcoma using deep survival neural networks

Background We used the Surveillance, Epidemiology, and End Results (SEER) database to develop and validate deep survival neural network machine learning (ML) algorithms to predict survival following a spino-pelvic chondrosarcoma diagnosis. Methods The SEER 18 registries were used to apply the Risk E...

Full description

Saved in:
Bibliographic Details
Published in:BMC medical informatics and decision making Vol. 20; no. 1; pp. 3 - 10
Main Authors: Ryu, Sung Mo, Seo, Sung Wook, Lee, Sun-Ho
Format: Journal Article
Language:English
Published: London BioMed Central 06.01.2020
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Age
Algorithms
Artificial intelligence
Artificial neural networks
Bone Neoplasms
Cancer therapies
Chemotherapy
Chondrosarcoma
Clinical decision-making
Confidence intervals
Diagnosis
Epidemiology
Health aspects
Health Informatics
Humans
Indexing
Information Systems and Communication Service
Intelligence gathering
knowledge support systems
Learning algorithms
Machine Learning
Management of Computing and Information Systems
Medical prognosis
Medicine
Medicine & Public Health
Neural network
Neural networks
Neural Networks, Computer
Patients
Pelvis
Prediction
Prognosis
Radiation
Radiation (Physics)
Radiation therapy
Radiotherapy
Research Article
Statistical analysis
Subgroups
Surgery
Survival
Test sets
theory
Time
Training
Tumors
Windows (intervals)
South Korea
United States > US
Chondrosarcoma
Neural network
Artificial intelligence
Survival
Prediction
ISSN:1472-6947, 1472-6947
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background We used the Surveillance, Epidemiology, and End Results (SEER) database to develop and validate deep survival neural network machine learning (ML) algorithms to predict survival following a spino-pelvic chondrosarcoma diagnosis. Methods The SEER 18 registries were used to apply the Risk Estimate Distance Survival Neural Network (RED_SNN) in the model. Our model was evaluated at each time window with receiver operating characteristic curves and areas under the curves (AUCs), as was the concordance index (c-index). Results The subjects ( n  = 1088) were separated into training (80%, n  = 870) and test sets (20%, n  = 218). The training data were randomly sorted into training and validation sets using 5-fold cross validation. The median c-index of the five validation sets was 0.84 (95% confidence interval 0.79–0.87). The median AUC of the five validation subsets was 0.84. This model was evaluated with the previously separated test set. The c-index was 0.82 and the mean AUC of the 30 different time windows was 0.85 (standard deviation 0.02). According to the estimated survival probability (by 62 months), we divided the test group into five subgroups. The survival curves of the subgroups showed statistically significant separation ( p  < 0.001). Conclusions This study is the first to analyze population-level data using artificial neural network ML algorithms for the role and outcomes of surgical resection and radiation therapy in spino-pelvic chondrosarcoma.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1472-6947
1472-6947
DOI:10.1186/s12911-019-1008-4