Decision tree algorithm in locally advanced rectal cancer: an example of over-interpretation and misuse of a machine learning approach.

Journal: Journal of cancer research and clinical oncology
Published Date: Nov 29, 2019

Abstract

PURPOSE: To analyse the classification performances of a decision tree method applied to predictor variables in survival outcome in patients with locally advanced rectal cancer (LARC). The aim was to offer a critical analysis to better apply tree-based approach in clinical practice and improve its interpretation.

Authors

  • Francesca De Felice
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy. fradefelice@hotmail.it.
  • D Crocetti
    Department of Surgery "Pietro Valdoni", Policlinico Umberto I, "Sapienza" University of Rome, Rome, Italy.
  • M Parisi
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • V Maiuri
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • E Moscarelli
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • R Caiazzo
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • N Bulzonetti
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • D Musio
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.
  • V Tombolini
    Department of Radiotherapy, Policlinico Umberto I, "Sapienza" University of Rome, Viale Regina Elena 326, 00161, Rome, Italy.

Keywords

External Resources

Popular Topics
Recent Journals