Effect of feature selection on machine learning algorithms for more accurate predictor of surgical outcomes in Benign Pro Static Hyperplasia cases (BPH)

Predicting the clinical outcome prior to minimally invasive treatments for Benign Prostatic Hperlasia (BPH) cases would be very useful. However, clinical prediction has not been reliable in spite of multiple assessment parameters, such as symptom indices and flow rates. In our prior study, Artificial Intelligence (AI) algorithms were used to train computers to predict the surgical outcome in BPH patients treated by TURP or VLAP. Our aim was to investigate whether, based on eleven clinical biomarker features, AI can reproduce the clinical outcome of known cases and assist the urologist in predicting surgical outcomes. In this paper, the objective is to perform data analysis to investigate if specific features have a greater impact on predicting whether the patients had the desired outcome after a surgical procedure is done. Finally, how the number of significant features ought to be weighted to predict the outcome after surgery, is determined to create the most accurate prediction method. Here both the Decision Tree and Naïve Bayse machine learning methods are used and compared.

[1]  R. Roberts,et al.  Natural history of prostatism: risk factors for acute urinary retention. , 1997, The Journal of urology.

[2]  Ronald J. Williams,et al.  Gradient-based learning algorithms for recurrent networks and their computational complexity , 1995 .

[3]  Jorma Rissanen,et al.  MDL-Based Decision Tree Pruning , 1995, KDD.

[4]  Wray L. Buntine.  Operations for Learning with Graphical Models , 1994, J. Artif. Intell. Res..

[5]  C. Roehrborn,et al.  Serum prostate-specific antigen concentration is a powerful predictor of acute urinary retention and need for surgery in men with clinical benign prostatic hyperplasia. PLESS Study Group. , 1999, Urology.

[6]  P. Boyle,et al.  Serum prostate-specific antigen and prostate volume predict long-term changes in symptoms and flow rate: results of a four-year, randomized trial comparing finasteride versus placebo. PLESS Study Group. , 1999, Urology.

[7]  Kevin D. Ashley.  Modeling legal argument - reasoning with cases and hypotheticals , 1991, Artificial intelligence and legal reasoning.

[8]  Alex Waibel,et al.  Consonant recognition by modular construction of large phonemic time-delay neural networks , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[9]  Michael W Kattan,et al.  Nomograms as predictive models. , 2002, Seminars in urologic oncology.

[10]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[11]  P. Boyle,et al.  Efficacy and safety of a dual inhibitor of 5-alpha-reductase types 1 and 2 (dutasteride) in men with benign prostatic hyperplasia. , 2002, Urology.

[12]  G. Casella,et al.  Statistical Inference , 2003, Encyclopedia of Social Network Analysis and Mining.

[13]  J. R. Quilan.  Decision trees and multi-valued attributes , 1988 .

[14]  Dalila B. Megherbi,et al.  Comparison of artificial intelligence and machine learning algorithms as a predictor of surgical outcomes in benign prostatic hyperlasia cases (BPH) , 2001, SPIE Defense + Commercial Sensing.

[15]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[16]  C. Roehrborn,et al.  The effect of finasteride on the risk of acute urinary retention and the need for surgical treatment among men with benign prostatic hyperplasia. Finasteride Long-Term Efficacy and Safety Study Group. , 1998, The New England journal of medicine.

[17]  Simon Kasif,et al.  A System for Induction of Oblique Decision Trees , 1994, J. Artif. Intell. Res..

[18]  C. Roehrborn,et al.  The long-term effect of doxazosin, finasteride, and combination therapy on the clinical progression of benign prostatic hyperplasia. , 2003, The New England journal of medicine.

[19]  Stefan Wess,et al.  Topics in Case-Based Reasoning , 1994 .

[20]  C. Roehrborn,et al.  The effect of finasteride on the risk of acute urinary retention and the need for surgical treatment among men with benign prostatic hyperplasia , 1998 .

[21]  D. Haussler,et al.  Boolean Feature Discovery in Empirical Learning , 1990, Machine Learning.

[22]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[23]  M. Kattan.  Comparison of Cox regression with other methods for determining prediction models and nomograms. , 2003, The Journal of urology.

[24]  J. Oesterling,et al.  Natural history of prostatism: longitudinal changes in voiding symptoms in community dwelling men. , 1996, The Journal of urology.

[25]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[26]  Yves Chauvin,et al.  Backpropagation: theory, architectures, and applications , 1995 .