Computational models for detection of endocrinopathy in subfertile males

Charles Powell, R. A. Desai, A. A. Makhlouf, M. Sigman, J. P. Jarow, L. S. Ross, C. S. Niederberger

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The observation that men with sperm density greater than 10 million/ml had low probability of endocrinopathy led to a refinement in the evaluation of subfertility. Using statistical methods, we sought to provide a more accurate prediction of which patients have an endocrinopathy, and to report the outcome as the odds of having disease. In addition, by examining the parameters that influenced the model significantly, the underlying pathophysiology might be better understood. Records of 1035 men containing variables including testis volume, sperm density, motility as well as the presence of endocrinopathy were randomized into 'training' and 'test' data sets. We modeled the data set using linear and quadratic discriminant function analysis, logistic regression (LR) and a neural network. Wilk's regression analysis was performed to determine which variables influenced the model significantly. Of the four models investigated, LR and a neural network performed the best with receiver operating characteristic areas under the curve of 0.93 and 0.95, respectively, correlating to a sensitivity of 28% and a specificity of 99% for the LR model, and a sensitivity and specificity of 56 and 97% for the neural network model. Reverse regression yielded P-values for the testis volume and sperm density of

Original languageEnglish (US)
Pages (from-to)79-84
Number of pages6
JournalInternational Journal of Impotence Research
Volume20
Issue number1
DOIs
StatePublished - Jan 2008
Externally publishedYes

Fingerprint

Logistic Models
Spermatozoa
Testis
Neural Networks (Computer)
Sperm Motility
Discriminant Analysis
ROC Curve
Infertility
Area Under Curve
Regression Analysis
Sensitivity and Specificity
Datasets

Keywords

  • Endocrinopathy
  • Infertility
  • Semen analysis
  • Testis volume

ASJC Scopus subject areas

  • Urology

Cite this

Powell, C., Desai, R. A., Makhlouf, A. A., Sigman, M., Jarow, J. P., Ross, L. S., & Niederberger, C. S. (2008). Computational models for detection of endocrinopathy in subfertile males. International Journal of Impotence Research, 20(1), 79-84. https://doi.org/10.1038/sj.ijir.3901593

Computational models for detection of endocrinopathy in subfertile males. / Powell, Charles; Desai, R. A.; Makhlouf, A. A.; Sigman, M.; Jarow, J. P.; Ross, L. S.; Niederberger, C. S.

In: International Journal of Impotence Research, Vol. 20, No. 1, 01.2008, p. 79-84.

Research output: Contribution to journalArticle

Powell, C, Desai, RA, Makhlouf, AA, Sigman, M, Jarow, JP, Ross, LS & Niederberger, CS 2008, 'Computational models for detection of endocrinopathy in subfertile males', International Journal of Impotence Research, vol. 20, no. 1, pp. 79-84. https://doi.org/10.1038/sj.ijir.3901593
Powell, Charles ; Desai, R. A. ; Makhlouf, A. A. ; Sigman, M. ; Jarow, J. P. ; Ross, L. S. ; Niederberger, C. S. / Computational models for detection of endocrinopathy in subfertile males. In: International Journal of Impotence Research. 2008 ; Vol. 20, No. 1. pp. 79-84.
@article{4084bd89beaf405cbd8a45a6b6e30cf1,
title = "Computational models for detection of endocrinopathy in subfertile males",
abstract = "The observation that men with sperm density greater than 10 million/ml had low probability of endocrinopathy led to a refinement in the evaluation of subfertility. Using statistical methods, we sought to provide a more accurate prediction of which patients have an endocrinopathy, and to report the outcome as the odds of having disease. In addition, by examining the parameters that influenced the model significantly, the underlying pathophysiology might be better understood. Records of 1035 men containing variables including testis volume, sperm density, motility as well as the presence of endocrinopathy were randomized into 'training' and 'test' data sets. We modeled the data set using linear and quadratic discriminant function analysis, logistic regression (LR) and a neural network. Wilk's regression analysis was performed to determine which variables influenced the model significantly. Of the four models investigated, LR and a neural network performed the best with receiver operating characteristic areas under the curve of 0.93 and 0.95, respectively, correlating to a sensitivity of 28{\%} and a specificity of 99{\%} for the LR model, and a sensitivity and specificity of 56 and 97{\%} for the neural network model. Reverse regression yielded P-values for the testis volume and sperm density of",
keywords = "Endocrinopathy, Infertility, Semen analysis, Testis volume",
author = "Charles Powell and Desai, {R. A.} and Makhlouf, {A. A.} and M. Sigman and Jarow, {J. P.} and Ross, {L. S.} and Niederberger, {C. S.}",
year = "2008",
month = "1",
doi = "10.1038/sj.ijir.3901593",
language = "English (US)",
volume = "20",
pages = "79--84",
journal = "International Journal of Impotence Research",
issn = "0955-9930",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Computational models for detection of endocrinopathy in subfertile males

AU - Powell, Charles

AU - Desai, R. A.

AU - Makhlouf, A. A.

AU - Sigman, M.

AU - Jarow, J. P.

AU - Ross, L. S.

AU - Niederberger, C. S.

PY - 2008/1

Y1 - 2008/1

N2 - The observation that men with sperm density greater than 10 million/ml had low probability of endocrinopathy led to a refinement in the evaluation of subfertility. Using statistical methods, we sought to provide a more accurate prediction of which patients have an endocrinopathy, and to report the outcome as the odds of having disease. In addition, by examining the parameters that influenced the model significantly, the underlying pathophysiology might be better understood. Records of 1035 men containing variables including testis volume, sperm density, motility as well as the presence of endocrinopathy were randomized into 'training' and 'test' data sets. We modeled the data set using linear and quadratic discriminant function analysis, logistic regression (LR) and a neural network. Wilk's regression analysis was performed to determine which variables influenced the model significantly. Of the four models investigated, LR and a neural network performed the best with receiver operating characteristic areas under the curve of 0.93 and 0.95, respectively, correlating to a sensitivity of 28% and a specificity of 99% for the LR model, and a sensitivity and specificity of 56 and 97% for the neural network model. Reverse regression yielded P-values for the testis volume and sperm density of

AB - The observation that men with sperm density greater than 10 million/ml had low probability of endocrinopathy led to a refinement in the evaluation of subfertility. Using statistical methods, we sought to provide a more accurate prediction of which patients have an endocrinopathy, and to report the outcome as the odds of having disease. In addition, by examining the parameters that influenced the model significantly, the underlying pathophysiology might be better understood. Records of 1035 men containing variables including testis volume, sperm density, motility as well as the presence of endocrinopathy were randomized into 'training' and 'test' data sets. We modeled the data set using linear and quadratic discriminant function analysis, logistic regression (LR) and a neural network. Wilk's regression analysis was performed to determine which variables influenced the model significantly. Of the four models investigated, LR and a neural network performed the best with receiver operating characteristic areas under the curve of 0.93 and 0.95, respectively, correlating to a sensitivity of 28% and a specificity of 99% for the LR model, and a sensitivity and specificity of 56 and 97% for the neural network model. Reverse regression yielded P-values for the testis volume and sperm density of

KW - Endocrinopathy

KW - Infertility

KW - Semen analysis

KW - Testis volume

UR - http://www.scopus.com/inward/record.url?scp=38149080468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38149080468&partnerID=8YFLogxK

U2 - 10.1038/sj.ijir.3901593

DO - 10.1038/sj.ijir.3901593

M3 - Article

VL - 20

SP - 79

EP - 84

JO - International Journal of Impotence Research

JF - International Journal of Impotence Research

SN - 0955-9930

IS - 1

ER -