Henrike Krenz1, Andrea Sansone2,3, Michael Fujarski1, Claudia Krallmann2, Michael Zitzmann2, Martin Dugas4, Sabine Kliesch2, Julian Varghese1, Frank Tüttelmann5, Jörg Gromoll2. 1. Institute of Medical Informatics, University of Münster, Münster, Germany. 2. Centre of Reproductive Medicine and Andrology, University Hospital Münster, Münster, Germany. 3. Chair of Endocrinology and Sexual Medicine (ENDOSEX), Department of Systems Medicine, University of Rome Tor Vergata, Rome, Italy. 4. Institute of Medical Informatics, Heidelberg University Hospital, Heidelberg, Germany. 5. Institute of Reproductive Genetics, University of Münster, Münster, Germany.
Abstract
BACKGROUND: Due to the highly variable clinical phenotype, Klinefelter Syndrome is underdiagnosed. OBJECTIVE: Assessment of supervised machine learning based prediction models for identification of Klinefelter Syndrome among azoospermic patients, and comparison to expert clinical evaluation. MATERIALS AND METHODS: Retrospective patient data (karyotype, age, height, weight, testis volume, follicle-stimulating hormone, luteinizing hormone, testosterone, estradiol, prolactin, semen pH and semen volume) collected between January 2005 and June 2019 were retrieved from a patient data bank of a University Centre. Models were trained, validated and benchmarked based on different supervised machine learning algorithms. Models were then tested on an independent, prospectively acquired set of patient data (between July 2019 and July 2020). Benchmarking against physicians was performed in addition. RESULTS: Based on average performance, support vector machines and CatBoost were particularly well-suited models, with 100% sensitivity and >93% specificity on the test dataset. Compared to a group of 18 expert clinicians, the machine learning models had significantly better median sensitivity (100% vs. 87.5%, p = 0.0455) and fared comparably with regards to specificity (90% vs. 89.9%, p = 0.4795), thereby possibly improving diagnosis rate. A Klinefelter Syndrome Score Calculator based on the prediction models is available on http://klinefelter-score-calculator.uni-muenster.de. DISCUSSION: Differentiating Klinefelter Syndrome patients from azoospermic patients with normal karyotype (46,XY) is a problem that can be solved with supervised machine learning techniques, improving patient care. CONCLUSIONS: Machine learning could improve the diagnostic rate of Klinefelter Syndrome among azoospermic patients, even more for less-experienced physicians.
BACKGROUND: Due to the highly variable clinical phenotype, Klinefelter Syndrome is underdiagnosed. OBJECTIVE: Assessment of supervised machine learning based prediction models for identification of Klinefelter Syndrome among azoospermic patients, and comparison to expert clinical evaluation. MATERIALS AND METHODS: Retrospective patient data (karyotype, age, height, weight, testis volume, follicle-stimulating hormone, luteinizing hormone, testosterone, estradiol, prolactin, semen pH and semen volume) collected between January 2005 and June 2019 were retrieved from a patient data bank of a University Centre. Models were trained, validated and benchmarked based on different supervised machine learning algorithms. Models were then tested on an independent, prospectively acquired set of patient data (between July 2019 and July 2020). Benchmarking against physicians was performed in addition. RESULTS: Based on average performance, support vector machines and CatBoost were particularly well-suited models, with 100% sensitivity and >93% specificity on the test dataset. Compared to a group of 18 expert clinicians, the machine learning models had significantly better median sensitivity (100% vs. 87.5%, p = 0.0455) and fared comparably with regards to specificity (90% vs. 89.9%, p = 0.4795), thereby possibly improving diagnosis rate. A Klinefelter Syndrome Score Calculator based on the prediction models is available on http://klinefelter-score-calculator.uni-muenster.de. DISCUSSION: Differentiating Klinefelter Syndrome patients from azoospermic patients with normal karyotype (46,XY) is a problem that can be solved with supervised machine learning techniques, improving patient care. CONCLUSIONS: Machine learning could improve the diagnostic rate of Klinefelter Syndrome among azoospermic patients, even more for less-experienced physicians.