Predictors of urinary tract infection based on artificial neural networks and genetic algorithms

BACKGROUND Among women who present with urinary complaints, only 50% are found to have urinary tract infection. Individual urinary symptoms and urinalysis are not sufficiently accurate to discriminate those with and without the diagnosis. METHODS We used artificial neural networks (ANN) coupled with genetic algorithms to evolve combinations of clinical variables optimized for predicting urinary tract infection. The ANN were applied to 212 women ages 19-84 who presented to an ambulatory clinic with urinary complaints. Urinary tract infection was defined in separate models as uropathogen counts of > or =10(5) colony-forming units (CFU) per milliliter, and counts of > or =10(2) CFU per milliliter. RESULTS Five-variable sets were evolved that classified cases of urinary tract infection and non-infection with receiver-operating characteristic (ROC) curve areas that ranged from 0.853 (for uropathogen counts of > or =10(5) CFU per milliliter) to 0.792 (for uropathogen counts of > or =10(2) CFU per milliliter). Predictor variables (which included urinary frequency, dysuria, foul urine odor, symptom duration, history of diabetes, leukocyte esterase on urine dipstick, and red blood cells, epithelial cells, and bacteria on urinalysis) differed depending on the pathogen count that defined urinary tract infection. Network influence analyses showed that some variables predicted urine infection in unexpected ways, and interacted with other variables in making predictions. CONCLUSIONS ANN and genetic algorithms can reveal parsimonious variable sets accurate for predicting urinary tract infection, and novel relationships between symptoms, urinalysis findings, and infection.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Fernando Mendes de Azevedo,et al.  Hybrid expert system for decision supporting in the medical area: complexity and cognitive computing , 2001, Int. J. Medical Informatics.

[3]  Christian Jacob,et al.  Illustrating Evolutionary Computation with Mathematica , 2001 .

[4]  D. Dorfman,et al.  Maximum-likelihood estimation of parameters of signal-detection theory and determination of confidence intervals—Rating-method data , 1969 .

[5]  M F Jefferson,et al.  Evolution of Artificial Neural Network Architecture: Prediction of Depression after Mania , 1998, Methods of Information in Medicine.

[6]  Kalpana Gupta,et al.  Risk Factors Associated with Acute Pyelonephritis in Healthy Women , 2005, Annals of Internal Medicine.

[7]  Li Liu,et al.  Neural network modeling for surgical decisions on traumatic brain injury patients , 2000, Int. J. Medical Informatics.

[8]  D B Matchar,et al.  Likelihood ratios for continuous test results--making the clinicians' job easier or harder? , 1993, Journal of clinical epidemiology.

[9]  R. Wigton,et al.  Prediction of Community-Acquired Pneumonia Using Artificial Neural Networks , 2003, Medical decision making : an international journal of the Society for Medical Decision Making.

[10]  Edward J Boyko,et al.  Diabetes and the risk of acute urinary tract infection among postmenopausal women. , 2002, Diabetes care.

[11]  Torgny Groth,et al.  Transferability of neural network-based decision support algorithms for early assessment of chest-pain patients , 2000, Int. J. Medical Informatics.

[12]  L. Leibovici,et al.  A clinical model for diagnosis of urinary tract infection in young women. , 1989, Archives of internal medicine.

[13]  Tom Heskes,et al.  Partial Retraining: A New Approach to Input Relevance Determination , 1999, Int. J. Neural Syst..

[14]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[15]  Jaime G. Carbonell,et al.  Machine learning: paradigms and methods , 1990 .

[16]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[17]  Paul S. Heckerling,et al.  Parametric receiver operating characteristic curve analysis using mathematica , 2002, Comput. Methods Programs Biomed..

[18]  B S Gerber,et al.  Selection of Predictor Variables for Pneumonia Using Neural Networks and Genetic Algorithms , 2005, Methods of Information in Medicine.

[19]  Lucila Ohno-Machado,et al.  A genetic algorithm to select variables in logistic regression: example in the domain of myocardial infarction , 1999, AMIA.

[20]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[21]  Paul S. Heckerling,et al.  Entering the Black Box of Neural Networks , 2003, Methods of Information in Medicine.

[22]  Edward J Boyko,et al.  Risk factors for urinary tract infections in postmenopausal women. , 2004, Archives of internal medicine.

[23]  K. Holmes,et al.  Diagnosis of coliform infection in acutely dysuric women. , 1982, The New England journal of medicine.

[24]  A D Lovie,et al.  The bootstrapped model--Lessons for the acceptance of intellectual technology. , 1987, Applied ergonomics.

[25]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[26]  A. Komaroff,et al.  Management strategies for urinary and vaginal infections. , 1978, Archives of internal medicine.

[27]  James A. Freeman,et al.  Simulating neural networks - with Mathematica , 1993 .

[28]  J P Ornato,et al.  Use of clinical findings in the diagnosis of urinary tract infection in women. , 1985, Archives of internal medicine.

[29]  H Lunt,et al.  Vaginal symptoms and insulin dependent diabetes mellitus. , 1995, The New Zealand medical journal.

[30]  D. McPhee,et al.  Predicting cytomegalovirus disease after renal transplantation: an artificial neural network approach , 1999, Int. J. Medical Informatics.

[31]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[32]  W Penny,et al.  Neural Networks in Clinical Medicine , 1996, Medical decision making : an international journal of the Society for Medical Decision Making.

[33]  Sanjay Saint,et al.  Does this woman have an acute uncomplicated urinary tract infection? , 2002, JAMA.

[34]  A. Laupacis,et al.  Clinical prediction rules. A review and suggested modifications of methodological standards. , 1997, JAMA.

[35]  H. Sox,et al.  Clinical prediction rules. Applications and methodological standards. , 1985, The New England journal of medicine.

[36]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[37]  D. Scholes,et al.  Increasing prevalence of antimicrobial resistance among uropathogens causing acute uncomplicated cystitis in women. , 1999, JAMA.

[38]  J J Christensen-Szalanski,et al.  Physicians' Misunderstanding of Normal Findings , 1983, Medical decision making : an international journal of the Society for Medical Decision Making.

[39]  A. Komaroff,et al.  Urinalysis and urine culture in women with dysuria. , 1986, Annals of internal medicine.

[40]  C. Kunin,et al.  A Reassessment of the Importance of Low-Count Bacteriuria in Young Women with Acute Urinary Symptoms , 1993, Annals of Internal Medicine.

[41]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[42]  M. Rubenfire,et al.  Neural network in the clinical diagnosis of acute pulmonary embolism. , 1993, Chest.

[43]  Stephen Wolfram,et al.  Mathematica: a system for doing mathematics by computer (2nd ed.) , 1991 .

[44]  L. Leibovici,et al.  Urinary tract infections with low and high colony counts in young women. Spontaneous remission and single-dose vs multiple-day treatment. , 1994, Archives of internal medicine.

[45]  S Forrest,et al.  Genetic algorithms , 1996, CSUR.

[46]  James L. McClelland.  Explorations In Parallel Distributed Processing , 1988 .

[47]  Richard A. Wright,et al.  Detection of pyuria and bacteriuria in symptomatic ambulatory women , 1992, Journal of General Internal Medicine.

[48]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[49]  C. Kunin,et al.  Urinary Tract Infections: Detection, Prevention, and Management , 1997 .

[50]  W. Baxt.  Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarction. , 1992, Annals of emergency medicine.

[51]  D J Roe,et al.  Squamous cells as predictors of bacterial contamination in urine samples. , 1998, Annals of emergency medicine.