Development of a Ready-to-Use Graphical Tool Based on Artificial Neural Network Classification: Application for the Prediction of Late Fecal Incontinence After Prostate Cancer Radiation Therapy

Mauro Carrara, Eleonora Massari, Alessandro Cicchetti, Tommaso Giandini, Barbara Avuzzi, Federica Palorini, Claudio Stucchi, Giovanni Fellin, Pietro Gabriele, Vittorio Vavassori, Claudio Degli Esposti, Cesare Cozzarini, Emanuele Pignoli, Claudio Fiorino, Tiziana Rancati, Riccardo Valdagni

Research output: Contribution to journalArticle

Abstract

PURPOSE: This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool.

MATERIALS AND METHODS: In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables.

RESULTS: An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8% sensitivity and 63.7% ± 1.0% specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes.

CONCLUSIONS: An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.

Original languageEnglish
JournalInternational Journal of Radiation Oncology Biology Physics
DOIs
Publication statusE-pub ahead of print - Aug 6 2018

Fingerprint

Fecal Incontinence
radiation therapy
Prostatic Neoplasms
Radiotherapy
cancer
predictions
neurons
surgery
dosage
grade
drugs
anticoagulants
hormones
Neurons
Neural Networks (Computer)
set theory
therapy
education
Anticoagulants
Antihypertensive Agents

Cite this

@article{c5c4dca3c5ba45159cf5589a448375e2,
title = "Development of a Ready-to-Use Graphical Tool Based on Artificial Neural Network Classification: Application for the Prediction of Late Fecal Incontinence After Prostate Cancer Radiation Therapy",
abstract = "PURPOSE: This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool.MATERIALS AND METHODS: In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables.RESULTS: An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8{\%} sensitivity and 63.7{\%} ± 1.0{\%} specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes.CONCLUSIONS: An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.",
author = "Mauro Carrara and Eleonora Massari and Alessandro Cicchetti and Tommaso Giandini and Barbara Avuzzi and Federica Palorini and Claudio Stucchi and Giovanni Fellin and Pietro Gabriele and Vittorio Vavassori and {Degli Esposti}, Claudio and Cesare Cozzarini and Emanuele Pignoli and Claudio Fiorino and Tiziana Rancati and Riccardo Valdagni",
note = "Copyright {\circledC} 2018 Elsevier Inc. All rights reserved.",
year = "2018",
month = "8",
day = "6",
doi = "10.1016/j.ijrobp.2018.07.2014",
language = "English",
journal = "International Journal of Radiation Oncology Biology Physics",
issn = "0360-3016",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Development of a Ready-to-Use Graphical Tool Based on Artificial Neural Network Classification

T2 - Application for the Prediction of Late Fecal Incontinence After Prostate Cancer Radiation Therapy

AU - Carrara, Mauro

AU - Massari, Eleonora

AU - Cicchetti, Alessandro

AU - Giandini, Tommaso

AU - Avuzzi, Barbara

AU - Palorini, Federica

AU - Stucchi, Claudio

AU - Fellin, Giovanni

AU - Gabriele, Pietro

AU - Vavassori, Vittorio

AU - Degli Esposti, Claudio

AU - Cozzarini, Cesare

AU - Pignoli, Emanuele

AU - Fiorino, Claudio

AU - Rancati, Tiziana

AU - Valdagni, Riccardo

N1 - Copyright © 2018 Elsevier Inc. All rights reserved.

PY - 2018/8/6

Y1 - 2018/8/6

N2 - PURPOSE: This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool.MATERIALS AND METHODS: In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables.RESULTS: An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8% sensitivity and 63.7% ± 1.0% specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes.CONCLUSIONS: An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.

AB - PURPOSE: This study was designed to apply artificial neural network (ANN) classification methods for the prediction of late fecal incontinence (LFI) after high-dose prostate cancer radiation therapy and to develop a ready-to-use graphical tool.MATERIALS AND METHODS: In this study, 598 men recruited in 2 national multicenter trials were analyzed. Information was recorded on comorbidity, previous abdominal surgery, use of drugs, and dose distribution. Fecal incontinence was prospectively evaluated through self-reported questionnaires. To develop the ANN, the study population was randomly split into training (n = 300), validation (n = 149), and test (n = 149) sets. Mean grade of longitudinal LFI (ie, expressed as the average incontinence grade over the first 3 years after radiation therapy) ≥1 was considered the endpoint. A suitable subset of variables able to better predict LFI was selected by simulating 100,000 ANN configurations. The search for the definitive ANN was then performed by varying the number of inputs and hidden neurons from 4 to 5 and from 1 to 9, respectively. A final classification model was established as the average of the best 5 among 500 ANNs with the same architecture. An ANN-based graphical method to compute LFI prediction was developed to include one continuous and n dichotomous variables.RESULTS: An ANN architecture was selected, with 5 input variables (mean dose, previous abdominal surgery, use of anticoagulants, use of antihypertensive drugs, and use of neoadjuvant and adjuvant hormone therapy) and 4 hidden neurons. The developed classification model correctly identified patients with LFI with 80.8% sensitivity and 63.7% ± 1.0% specificity and an area under the curve of 0.78. The developed graphical tool may efficiently classify patients in low, intermediate, and high LFI risk classes.CONCLUSIONS: An ANN-based model was developed to predict LFI. The model was translated in a ready-to-use graphical tool for LFI risk classification, with direct interpretation of the role of the predictors.

U2 - 10.1016/j.ijrobp.2018.07.2014

DO - 10.1016/j.ijrobp.2018.07.2014

M3 - Article

C2 - 30092335

JO - International Journal of Radiation Oncology Biology Physics

JF - International Journal of Radiation Oncology Biology Physics

SN - 0360-3016

ER -