Development and validation of a machine learning-based predictive model to improve the prediction of inguinal status of anal cancer patients: A preliminary report

// Berardino De Bari 1 , Mauro Vallati 2 , Roberto Gatta 3 , Laëtitia Lestrade 4, 5 , Stefania Manfrida 3 , Christian Carrie 4 , Vincenzo Valentini 3 1 Radiation Oncology Department, Centre Hospitalier Universitaire Vaudois-CHUV, Lausanne, Switzerland 2 University of Huddersfield, School of Computing and Engineering, Huddersfield, UK 3 Radiation Oncology Department, Catholic University of Sacred Heart, Rome, Italy 4 Service de Radiothérapie, Léon Bérard Cancer Center, Lyon, France 5 Radiation Oncology Department, Hôpitaux universitaires de Genève-HUG, Geneva, Switzerland Correspondence to: Berardino De Bari, email: berardino.de-bari@chuv.ch Keywords: anal canal cancer, radiochemotherapy, prophylactic inguinal irradiation, machine learning, predicitive models Received: May 30, 2016 Accepted: July 07, 2016 Published: July 21, 2016 ABSTRACT Introduction : The role of prophylactic inguinal irradiation (PII) in the treatment of anal cancer patients is controversial. We developped an innovative algorithm based on the Machine Learning (ML) allowing the tailoring of the prescription of PII. Results : Once verified on the independent testing set, J48 showed the better performances, with specificity, sensitivity, and accuracy rates in predicting relapsing patients of 86.4%, 50.0% and 83.1% respectively (vs 36.5%, 90.4% and 80.25%, respectively, for LR). Methods : We classified 194 anal cancer patients with Logistic Regression (LR) and other 3 ML techniques based on decision trees (J48, Random Tree and Random Forest), using a large set of clinical and therapeutic variables. We tested obtained ML algorithms on an independent testing set of 65 anal cancer patients. TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis) methodology was used for the development, the Quality Assurance and the description of the experimental procedures. Conclusion : In an internationally approved quality assurance framework, ML seems promising in predicting the outcome of patients that would benefit or not of the PII. Once confirmed in larger and/or multi-centric databases, ML could support the physician in tailoring the treatment and in deciding if deliver or not the PII.