Multilevel approach to male fertility by machine learning highlights a hidden link between haematological and spermatogenetic cells.
big data
infertility
machine learning
male infertility
Journal
Andrology
ISSN: 2047-2927
Titre abrégé: Andrology
Pays: England
ID NLM: 101585129
Informations de publication
Date de publication:
09 2020
09 2020
Historique:
received:
17
04
2020
revised:
15
05
2020
accepted:
19
05
2020
pubmed:
26
5
2020
medline:
28
7
2021
entrez:
26
5
2020
Statut:
ppublish
Résumé
Male infertility represents a complex clinical condition requiring an accurate multilevel assessment, in which machine learning technology, combining large data series in non-linear and highly interactive ways, could be innovatively applied. A longitudinal, observational, retrospective, big data study was carried out, applying for the first time the ML in the context of male infertility. A large database including all semen samples collected between 2010 and 2016 was generated, together with blood biochemical examinations, environmental temperature and air pollutants exposure. First, the database was analysed with principal component analysis and multivariable linear regression analyses. Second, classification analyses were performed, in which patients were a priori classified according to semen parameters. Third, machine learning algorithms were applied in a training phase (80% of the entire database) and in a tuning phase (20% of the data set). Finally, conventional statistical analyses were applied considering semen parameters and those other variables extracted during machine learning. The final database included 4239 patients, aggregating semen analyses, blood and environmental parameters. Classification analyses were able to recognize oligozoospermic, teratozoospermic, asthenozoospermic and patients with altered semen parameters (0.58 accuracy, 0.58 sensitivity and 0.57 specificity). Machine learning algorithms detected three haematological variables, that is lymphocytes number, erythrocyte distribution and mean globular volume, significantly related to semen parameters (0.69 accuracy, 0.78 sensitivity and 0.41 specificity). This is the first machine learning application to male fertility, detecting potential mathematical algorithms able to describe patients' semen characteristics changes. In this setting, a possible hidden link between testicular and haematopoietic tissues was suggested, according to their similar proliferative properties.
Sections du résumé
BACKGROUND
Male infertility represents a complex clinical condition requiring an accurate multilevel assessment, in which machine learning technology, combining large data series in non-linear and highly interactive ways, could be innovatively applied.
METHODS
A longitudinal, observational, retrospective, big data study was carried out, applying for the first time the ML in the context of male infertility. A large database including all semen samples collected between 2010 and 2016 was generated, together with blood biochemical examinations, environmental temperature and air pollutants exposure. First, the database was analysed with principal component analysis and multivariable linear regression analyses. Second, classification analyses were performed, in which patients were a priori classified according to semen parameters. Third, machine learning algorithms were applied in a training phase (80% of the entire database) and in a tuning phase (20% of the data set). Finally, conventional statistical analyses were applied considering semen parameters and those other variables extracted during machine learning.
RESULTS
The final database included 4239 patients, aggregating semen analyses, blood and environmental parameters. Classification analyses were able to recognize oligozoospermic, teratozoospermic, asthenozoospermic and patients with altered semen parameters (0.58 accuracy, 0.58 sensitivity and 0.57 specificity). Machine learning algorithms detected three haematological variables, that is lymphocytes number, erythrocyte distribution and mean globular volume, significantly related to semen parameters (0.69 accuracy, 0.78 sensitivity and 0.41 specificity).
CONCLUSION
This is the first machine learning application to male fertility, detecting potential mathematical algorithms able to describe patients' semen characteristics changes. In this setting, a possible hidden link between testicular and haematopoietic tissues was suggested, according to their similar proliferative properties.
Types de publication
Journal Article
Observational Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1021-1029Informations de copyright
© 2020 American Society of Andrology and European Academy of Andrology.
Références
Agarwal A, Mulgund A, Hamada A, Chyatte MR. A unique view on male infertility around the globe. Reproduct Biol Endocrinol. 2015;13:37.
Esteves SC. Clinical relevance of routine semen analysis and controversies surrounding the 2010 World Health Organization criteria for semen examination. Int Braz J Urol. 2014;40(4):443-453.
Eisenberg ML, Betts P, Herder D, Lamb DJ, Lipshultz LI. Increased cancer risk and azoospermia. Fertil Steril. 2013;100(3):e12.
Eisenberg ML, Betts P, Herder D, Lamb DJ, Lipshultz LI. Increased risk of cancer among azoospermic men. Fertil Steril. 2013;100(3):681-685.
Eisenberg ML, Li S, Behr B, et al. Semen quality, infertility and mortality in the USA. Human reproduction (Oxford, England). 2014;29(7):1567-1574.
Latif T, Kold Jensen T, Mehlsen J, et al. Semen quality as a predictor of subsequent morbidity: A Danish Cohort Study of 4,712 men with long-term follow-up. Am J Epidemiol. 2017;186(8):910-917.
Ventimiglia E, Capogrosso P, Boeri L, et al. Infertility as a proxy of general male health: results of a cross-sectional survey. Fertil Steril. 2015;104(1):48-55.
Pellati D, Mylonakis I, Bertoloni G, et al. Genital tract infections and infertility. Eur J Obstet Gynecol Reprod Biol. 2008;140(1):3-11.
Carp HJ, Selmi C, Shoenfeld Y. The autoimmune bases of infertility and pregnancy loss. J Autoimmun. 2012;38(2-3):J266-274.
Michalakis K, Mintziori G, Kaprara A, Tarlatzis BC, Goulis DG. The complex interaction between obesity, metabolic syndrome and reproductive axis: a narrative review. Metabolism. 2013;62(4):457-478.
Iglesias P, Carrero JJ, Diez JJ. Gonadal dysfunction in men with chronic kidney disease: clinical features, prognostic implications and therapeutic options. J Nephrol. 2012;25(1):31-42.
Hofny ERM, Ali MEM, Taha EA, et al. Semen and hormonal parameters in men with chronic hepatitis C infection. Fertil Steril. 2011;95(8):2557-2559.
Glazer CH, Eisenberg ML, Tøttenborg SS, et al. Male factor infertility and risk of death: a nationwide record-linkage study. Human Reprod. 2019;34(11):2266-2273.
Archana SS, Selvaraju S, Binsila BK, Arangasamy A, Krawetz SA. Immune regulatory molecules as modifiers of semen and fertility: A review. Mol Reprod Dev. 2019;86(11):1485-1504.
Kose S, Yersal N, Onen S, Korkusuz P. Comparison of hematopoietic and spermatogonial stem cell niches from the regenerative medicine aspect. Adv Exp Med Biol. 2018;1107:15-40.
Jung JH, Kim MH, Kim J, et al. Treatment of leukocytospermia in male infertility: a systematic review. World J Men's Health. 2016;34(3):165-172.
Eldamnhoury EM, Elatrash GA, Rashwan HM, El-Sakka AI. Association between leukocytospermia and semen interleukin-6 and tumor necrosis factor-alpha in infertile men. Andrology. 2018;6(5):775-780.
Kasperczyk A, Dobrakowski M, Czuba ZP, Kapka-Skrzypczak L, Kasperczyk S. Environmental exposure to zinc and copper influences sperm quality in fertile males. Ann Agric Environ Med. 2016;23(1):138-143.
Kasperczyk A, Dobrakowski M, Czuba ZP, Horak S, Kasperczyk S. Environmental exposure to lead induces oxidative stress and modulates the function of the antioxidant defense system and the immune system in the semen of males with normal semen profile. Toxicol Appl Pharmacol. 2015;284(3):339-344.
Santi D, Magnani E, Michelangeli M, et al. Seasonal variation of semen parameters correlates with environmental temperature and air pollution: A big data analysis over 6 years. Environ Pollut. 1987;2018(235):806-813.
Michailov Y, Lunenfeld E, Kapelushnik J, Huleihel M. Leukemia and male infertility: past, present, and future. Leuk Lymphoma. 2019;60(5):1126-1135.
Öztekin Ü, Caniklioğlu M, Sarı S, et al. Are there any relationships between abnormal seminal parameters and neutrophil-lymphocyte ratio, platelet-lymphocyte ratio, and red blood cell distribution-platelet ratio? Cureus. 2019;11(7):e5242.
Obermeyer Z, Emanuel EJ. Predicting the future - big data, machine learning, and clinical medicine. New Engl J Med. 2016;375(13):1216-1219.
Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402-2410.
Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA. 2017;318(6):517-518.
Vabalas A, Gowen E, Poliakoff E, Casson AJ. Machine learning algorithm validation with a limited sample size. PLoS One. 2019;14(11):e0224365.
Krautenbacher N, Theis FJ, Fuchs C. Correcting classifiers for sample selection bias in two-phase case-control studies. Comput Math Methods Med. 2017;2017:1-18.
Bjorndahl L, Barratt CL, Mortimer D, Jouannet P. 'How to count sperm properly': checklist for acceptability of studies based on human semen analysis. Human Reprod. 2016;31(2):227-232.
WHO. WHO laboratory manual for the examination and processing of human semen, 5th ed. WHO, 2010.
Baser O, Crown WH, Pollicino C. Guidelines for selecting among different types of bootstraps. Curr Med Res Opin. 2006;22(4):799-808.
Li Y, Li M, Teng Y, Zhang C, Liu Q, Hou H. The association between red cell distribution width, erythropoietin levels, and coronary artery disease. Coron Artery Dis. 2018;29(1):74-80.
Shao Q, Korantzopoulos P, Letsas KP, et al. Red blood cell distribution width as a predictor of atrial fibrillation. J Clin Lab Anal. 2018;32(5):e22378.
Tonelli M, Wiebe N, James MT, et al. Red cell distribution width associations with clinical outcomes: A population-based cohort study. PLoS One. 2019;14(3):e0212374.
Salvagno GL, Sanchis-Gomar F, Picanza A, Lippi G. Red blood cell distribution width: A simple parameter with multiple clinical applications. Crit Rev Clin Lab Sci. 2015;52(2):86-105.
Li N, Zhou H, Tang Q. Red blood cell distribution width: A novel predictive indicator for cardiovascular and cerebrovascular diseases. Dis Markers. 2017;2017:1-23.
Wu T-H, Fann J-Y, Chen S-S, et al. Gradient relationship between increased mean corpuscular volume and mortality associated with cerebral ischemic stroke and ischemic heart disease: a longitudinal study on 66,294 Taiwanese. Sci Rep. 2018;8(1):16517.
Horne BD, Muhlestein JB, Bennett ST, et al. Extreme erythrocyte macrocytic and microcytic percentages are highly predictive of morbidity and mortality. JCI Insight. 2018;3(14).
Hsieh YP, Chang CC, Kor CT, Yang Y, Wen YK, Chiu PF. Mean Corpuscular Volume and Mortality in Patients with CKD. Clin J Am Soc Nephrol. 2017;12(2):237-244.
Shirazi R, Zarnani AH, Soleimani M, Nayernia K, Ragerdi KI. Differentiation of bone marrow-derived stage-specific embryonic antigen 1 positive pluripotent stem cells into male germ cells. Microsc Res Tech. 2017;80(4):430-440.
Mulquiney PJ, Kuchel PW. Model of the pH-dependence of the concentrations of complexes involving metabolites, haemoglobin and magnesium ions in the human erythrocyte. Eur J Biochem. 1997;245(1):71-83.
Fraczek M, Kurpisz M. Cytokines in the male reproductive tract and their role in infertility disorders. J Reprod Immunol. 2015;108:98-104.
Hamada A, Esteves SC, Nizza M, Agarwal A. Unexplained male infertility: diagnosis and management. Int Braz J. 2012;38(5):576-594.
Aykan S, Canat L, Gonultas S, Atalay HA, Altunrende F. Are there relationships between seminal parameters and the neutrophil-to-lymphocyte ratio or the platelet-to-lymphocyte ratio? World J Men's Health. 2017;35(1):51-56.
Paoli D, Pelloni M, Lenzi A, Lombardo F. Cryopreservation of sperm: effects on chromatin and strategies to prevent them. Adv Exp Med Biol. 2019;1166:149-167.
Pallotti F, Cargnelutti F, Senofonte G, et al. In vitro effects of myo-inositol on normokinetic human semen samples with nonlinear motility. Eur Rev Med Pharmacol Sci. 2019;23(23):10557-10563.
Santi D, Vezzani S, Granata ARM, et al. Sperm quality and environment: A retrospective, cohort study in a Northern province of Italy. Environ Res. 2016;150:144-153.
Davies S, Henthorn J, Brozovic M. Iron deficiency in sickle cell anaemia. J Clin Pathol. 1983;36(9):1012-1015.
Abbasi AA, Prasad AS, Ortega J, Congco E, Oberleas D. Gonadal function abnormalities in sickle cell anemia. Studies in adult male patients. Ann Intern Med. 1976;85(5):601-605.
Chatterjee R, Katz M, Cox T, Bantock H. Evaluation of growth hormone in thalassaemic boys with failed puberty: spontaneous versus provocative test. Eur J Pediatr. 1993;152(9):721-726.
Balcerek M, Reinmuth S, Hohmann C, Keil T, Borgmann-Staudt A. Suspected infertility after treatment for leukemia and solid tumors in childhood and adolescence. Deutsches Arzteblatt international. 2012;109(7):126-131.
Chang X, Zhou L, Chen X, et al. Impact of imatinib on the fertility of male patients with chronic myelogenous leukaemia in the chronic phase. Targeted Oncol. 2017;12(6):827-832.
Garozzo G, Disca S, Fidone C, Bonomo P. Azoospermia in a patient with sickle cell disease treated with hydroxyurea. Haematologica. 2000;85(11):1216-1218.
Zambrano F, Carrau T, Gärtner U, et al. Leukocytes coincubated with human sperm trigger classic neutrophil extracellular traps formation, reducing sperm motility. Fertil Steril. 2016;106(5):1053-1060.e1051.