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.

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.

[1]  D. Wells,et al.  A medical expert system approach using artificial neural networks for standardized treatment planning. , 1998, International journal of radiation oncology, biology, physics.

[2]  G. Naldi,et al.  Late rectal bleeding after 3D-CRT for prostate cancer: development of a neural-network-based predictive model , 2012, Physics in medicine and biology.

[3]  M Carrara,et al.  Multispectral imaging and artificial neural network: mimicking the management decision of the clinician facing pigmented skin lesions , 2007, Physics in medicine and biology.

[4]  Bulat Ibragimov,et al.  Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks , 2017, Medical physics.

[5]  P. Cerveri,et al.  Tumor radio-sensitivity assessment by means of volume data and magnetic resonance indices measured on prostate tumor bearing rats , 2016, Medical physics.

[6]  A. van der Schaaf,et al.  Embracing phenomenological approaches to normal tissue complication probability modeling: a question of method. , 2015, International journal of radiation oncology, biology, physics.

[7]  Steve Webb,et al.  Using dose-surface maps to predict radiation-induced rectal bleeding: a neural network approach , 2009, Physics in medicine and biology.

[8]  D. Sahota,et al.  Gene Expression Pattern Associated with Radiotherapy Sensitivity in Cervical Cancer , 2006, Cancer journal.

[9]  K. Murase,et al.  Survival prediction using artificial neural networks in patients with uterine cervical cancer treated by radiation therapy alone , 2002, International Journal of Clinical Oncology.

[10]  Joseph O Deasy,et al.  Predicting radiotherapy outcomes using statistical learning techniques , 2009, Physics in medicine and biology.

[11]  E. Berner,et al.  Benefits and Risks of Machine Learning Decision Support Systems. , 2017, JAMA.

[12]  Kazutaka Saito,et al.  Development, validation, and head-to-head comparison of logistic regression-based nomograms and artificial neural network models predicting prostate cancer on initial extended biopsy. , 2008, European urology.

[13]  C. Fiorino,et al.  Modelling the impact of fractionation on late urinary toxicity after postprostatectomy radiation therapy. , 2014, International journal of radiation oncology, biology, physics.

[14]  Joos V Lebesque,et al.  The benefits of including clinical factors in rectal normal tissue complication probability modeling after radiotherapy for prostate cancer. , 2012, International journal of radiation oncology, biology, physics.

[15]  Peter Tiño,et al.  Artificial Neural Network Models , 2015, Handbook of Computational Intelligence.

[16]  Michele Stasi,et al.  Predictors for rectal and intestinal acute toxicities during prostate cancer high-dose 3D-CRT: results of a prospective multicenter study. , 2007, International journal of radiation oncology, biology, physics.

[17]  Xiao-dong Zhu,et al.  Prediction of radiation induced liver disease using artificial neural networks. , 2006, Japanese journal of clinical oncology.

[18]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[19]  Lucila Ohno-Machado,et al.  A Comparison of Machine Learning Methods for the Diagnosis of Pigmented Skin Lesions , 2001, J. Biomed. Informatics.

[20]  C. Fiorino,et al.  Clinical and dosimetric predictors of late rectal syndrome after 3D-CRT for localized prostate cancer: preliminary results of a multicenter prospective study. , 2008, International journal of radiation oncology, biology, physics.

[21]  C. Fiorino,et al.  Long term rectal function after high-dose prostatecancer radiotherapy: results from a prospective cohort study. , 2014, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[22]  Satomi Shiraishi,et al.  Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy. , 2015, Medical physics.

[23]  C. Fiorino,et al.  Clinical and dosimetric predictors of late rectal toxicity after conformal radiation for localized prostate cancer: results of a large multicenter observational study. , 2009, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[24]  S Nill,et al.  The comparative performance of four respiratory motion predictors for real-time tumour tracking , 2011, Physics in medicine and biology.

[25]  Antonello Pasini,et al.  Artificial neural networks for small dataset analysis. , 2015, Journal of thoracic disease.

[26]  S. Webb,et al.  Use of artificial neural networks to predict biological outcomes for patients receiving radical radiotherapy of the prostate. , 2004, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[27]  Ulf Isacsson,et al.  The effectiveness of artificial neural networks in evaluating treatment plans for patients requiring external beam radiotherapy. , 2004, Oncology reports.

[28]  Pietro Cerveri,et al.  Real-time tumor tracking with an artificial neural networks-based method: a feasibility study. , 2013, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[29]  Ariel Linden.  Measuring diagnostic and predictive accuracy in disease management: an introduction to receiver operating characteristic (ROC) analysis. , 2006, Journal of evaluation in clinical practice.

[30]  C. Fiorino,et al.  Late fecal incontinence after high-dose radiotherapy for prostate cancer: better prediction using longitudinal definitions. , 2011, International journal of radiation oncology, biology, physics.

[31]  Steve B. Jiang,et al.  Markerless gating for lung cancer radiotherapy based on machine learning techniques , 2009, Physics in medicine and biology.

[32]  Cristina Garibaldi,et al.  Use of machine learning methods for prediction of acute toxicity in organs at risk following prostate radiotherapy. , 2011, Medical physics.

[33]  Joos V Lebesque,et al.  Rectal bleeding, fecal incontinence, and high stool frequency after conformal radiotherapy for prostate cancer: normal tissue complication probability modeling. , 2006, International journal of radiation oncology, biology, physics.

[34]  G Baroni,et al.  Robustness of external/internal correlation models for real-time tumor tracking to breathing motion variations , 2012, Physics in medicine and biology.

[35]  J. Deasy,et al.  Combining multiple models to generate consensus: application to radiation-induced pneumonitis prediction. , 2008, Medical physics.