A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling.
Stefan LegerAlexander ZwanenburgKaroline PilzFabian LohausAnnett LingeKlaus ZöphelJörg KotzerkeAndreas SchreiberInge TinhoferVolker BudachAli SakMartin StuschkePanagiotis BalermpasClaus RödelUte GanswindtClaus BelkaSteffi PigorschStephanie E CombsDavid MönnichDaniel ZipsMechthild KrauseMichael BaumannEsther G C TroostSteffen LöckChristian RichterPublished in: Scientific reports (2017)
C-Index = 0.71 and BT-COX: C-Index = 0.70 in combination with Spearman feature selection. Using the best performing models, patients were stratified into groups of low and high risk of recurrence. Significant differences in LRC were obtained between both groups on the validation cohort. Based on the presented analysis, we identified a subset of algorithms which should be considered in future radiomics studies to develop stable and clinically relevant predictive models for time-to-event endpoints.
Keyphrases
- machine learning
- end stage renal disease
- big data
- deep learning
- chronic kidney disease
- newly diagnosed
- ejection fraction
- lymph node metastasis
- artificial intelligence
- free survival
- contrast enhanced
- peritoneal dialysis
- prognostic factors
- squamous cell carcinoma
- electronic health record
- data analysis
- patient reported
- breast cancer risk