Review Article | Open Access | Full Text

¹Department of Microbiology, Faculty of Veterinary Medicine, Ataturk University, Erzurum, TR
²Department of Reproduction and Artificial Insemination, Faculty of Veterinary Medicine, Ataturk University, Erzurum, TR
³Elbistan Vocational School, Kahramanmaras İstiklal University, Kahramanmaras, TR
⁴Faculty of Veterinary Medicine, Ataturk University, Erzurum, TR
⁵Department of Medical Microbiology, Faculty of Medicine, Ataturk University, Erzurum, TR

*Corresponding author: ^aAli Dogan Omur, Department of Reproduction and Artificial Insemination, Faculty of Veterinary Medicine, Ataturk University, Erzurum, TR
^bSerkan Ali Akarsu, Elbistan Vocational School, Kahramanmaras İstiklal University, Kahramanmaras, TR

Abstract

---

Infertility is one of the most common problems worldwide. Half of the causes of infertility are due to women and half to men. For this reason, studies to overcome this problem are concentrated on the way of ensuring the continuation of the generation by using high technology. For this purpose, applications such as (in vitro fertilization) IVF and (intra cytoplasmic sperm injection) ICSI are widely applied. This process is done by experts and produces non-objective results. As a result, artificial intelligence (AI) technology has begun to be used. Devices such as computer-assisted sperm analysis (CASA), flow cytometry provide objective evaluation in the evaluation of semen. Artificial intelligence has also been used for oocyte and embryo. Similarly, artificial intelligence is used in microbiological analysis. There is a relationship between the presence of microbiota in semen and sperm quality. Thanks to artificial intelligence, rapid and reliable microbiological analysis, diagnosis, and antimicrobial resistance are measured. In this way, microbiological analyzes in semen are also measured with artificial intelligence. Therefore, it is one of the most important goals that the analyzes made in these processes give objective and reliable results and do not harm the cell to be used. This review also highlights the current computer-based software systems used in sperm, oocyte and embryo evaluation.
Keywords: Sperm; oocyte; embryo evaluation; artificial intelligence; CASA
Abbreviations: IVF: İn Vitro Fertilization, ICSI: İntra Cytoplasmic Sperm İnjection, AI: Artificial İntelligence, CASA: Computer-Assisted Sperm Analysis, ANA: Antinuclear Antibody, ML: Machine Learning, MALDI-TOF: Matrix-Assisted Laser Desorption/İonization-Time-of-Flight, VCL: Curvilinear Velocity, VAP: Average Path Velocity, VSL: Straight Line Velocity, ALH: Lateral Head Displacement, LIN: Linearity of The Curvilinear Path, STR: Straightness of The Average Path, BCF: Beat- Cross Frequency, Indo-1 AM: Indo-1 Acetoxymethylester, IBFC: İmage-Based Flow Cytometry, HSV: High-Security Pipettes, PDMS: Polydimethylsiloxane, QS: Quorum Sensing

Review

---

The use of artificial intelligence (AI) is increasing in our daily life and in the laboratory [1]. It can be used in application of antinuclear antibody (ANA) patterns and performing white blood cell differentials and performing white blood cell differentials [2]. A subset of AI algorithms is called "machine learning" (ML) [3]. It is used in the clinical microbiology laboratory of artificial intelligence, where the human mind cannot analyze all the variables at the same time. Such a wealth of visual information among, for example, data (i.e., images of microscopic slides and plate bacteria), matrix assisted laser desorption/ionization-time-of-flight (MALDITOF) mass spectra, and nucleic acid sequence data; without AI, analyzing such data is manual, tedious and requires experience [4].
Infertility creates huge economic losses in the animal industry. 50% of this is associated with male infertility [5]. There are many artificial intelligence-based studies to contribute to infertility treatment such as live birth rate estimation [6,7], semen analysis [8], embryo selection [9], uterus analysis [10], embryo-based treatment outcome estimation [11].
In embryo selection and semen analysis, which embryo will be transferred and which fertilization method will be preferred depends on this subject and the personnel who are experts in the field. The training of the personnel is also very important in terms of decision making at this stage. One of the biggest challenges in the subjective assessments of embryos is the high intra- and inter-operator variability in the assessment of morphology and morphokinetics [12-14]. In this context, embryos can be monitored continuously and the entire embryo development process can be evaluated more precisely with technologies accelerated by artificial intelligence studies [15]. Semen analysis (sperm count, motility, viability and other morphological analyzes) are the most common method used in the diagnosis of male infertility [16]. Traditionally, semen motility is assessed by a specialist who visually scores points through a microscope. This practice leads to subjective interpretations among experts [17].
Computer aided sperm analysis (CASA) systems are used for many types of sperm analysis. Subjective motility estimation methods have been replaced by CASA [18,19]. The movement of each sperm is recorded as changes in center position in successive frames, and the calculations provide output measurements that describe movement. With CASA software, motility, kinematics and velocity parameters of semen in many species such as bovine [20], horse [21], cat [22], dog [23], ram [24], human [25], rabbit [26], fish [27], rat [28], can be analyzed. In this analysis, semen is used quickly in fresh and frozen form, while a very small amount of total semen is used for analysis, while the remaining parts can be used for fertilization. Curvilinear velocity (VCL), average path velocity (VAP), straight line velocity (VSL), amplitude of lateral head displacement (ALH), linearity of the curvilinear path (LIN), straightness of the average path (STR), and beat- Cross frequency (BCF) are the parameters measured by CASA [29].
Flow cytometry is one of the image-based methods in which morphological analyzes can be made in sperm. Since the end of the 1970s, the method mentioned with sperm analysis was published by Van Dilla et al [30]. Dead-viable sperm ratio is among the parameters determined by flow cytometry. SYBR-14 and PI are among the commonly used dyes [31,32]. Indo-1 acetoxymethylester (Indo-1 AM) has been used for measuring intracellular Ca2+ in spermatozoa by flow cytometry [33]. Mitochondrial membrane potential and rate of acrosomal damage can be determined by flow cytometry. JC-1 is widely used for mitochondrial membrane potential and PNA/PI is widely used for acrosomal damage [34]. The most popular method of sex determination and commercial use is Beltsville Sperm Sex Determination Technology [35]. Flow cytometry is the method used to determine sexed semen according to DNA weight of spermatozoa. The flow cytometer measures the DNA content based on the DNA-binding fluorescent probe Hoechst 33342 [36]. There is image-based flow cytometry (IBFC) that captures images of each cell at high speeds (500 to 2000 sperm/second) [37]. This technology IBFC in animal andrology may eventually lead to the development of new approaches to semen analysis [36]. Images from the IBFC are based only on bright field data, without the need for fluorescence detection, distinguishing motile and non-motile sperm in an ejaculate [39].
There are many methods for the cryopreservation of human and animal sperm. In recent years, various technologies have been added to the sperm freezing process [40]. Slow freezing, fast freezing and ultra fast freezing are methods used in sperm freezing. Slow freezing is a method in which sperm cells are gradually cooled over a 2–4-hour period using a programmable machine [41]. In the fast freezing technique, a cryoprotectant is added to the spermatozoa and the suspension is drawn into a cryo-straw or cryovial and exposed to a liquid nitrogen vapor phase. There are methods in which fewer spermatozoa are used in the sperm freezing process. Empty zona pellucida [42]. Cryo-loops, microdroplets, cut pipettes, mini pipettes, open-drawn pipettes, alginate beads, agarose gel microspheres, cryotope, plastic capillaries, and high-security pipettes (HSV) [43,44]. Another ultrafast cooling approach to cryopreservation of sperm without cryoprotectant uses polydimethylsiloxane (PDMS) chips in microfluidics [45]. In the cryopreservation process for spermatozoa, it is necessary to use a controlled cooling system in which temperature ranges are determined [46]. In general, semen cryopreservation uses protocols of freezing curves ranging from 10 to 100 °C min-1. However, studies are underway to optimize cryopreservation protocols [47]. Cryopreservation of semen in an automatic freezing machine was first used by Almquist & Wiggins [48]. Freezing sperm in straws is an expensive, but accurate, effective method. After the semen samples are reconstituted and cooled, the sperm are drawn into 0.25 or 0.5 ml straws, placed on a rack and frozen in liquid nitrogen vapor with a styrofoam box or programmable device [49]. The advantage of the programmable freezer is the customization of the freezing curve [50]. In a study in horses, the programmable freezer provided a more consistent and reliable freezing rate than liquid nitrogen vapor. It has been noted that since the level of liquid nitrogen in the can is subjectively estimated and subject to evaporation and it is difficult to standardize it for each freezing process, it may have provided a more variable freezing rate than the programmable freezer [51].
Embryo selection in In vitro fertilization (IVF) is one of the important steps for determining the quality of fertilized oocytes, and for subsequent transfer or cryopreservation [52]. In recent years, innovation and research in the field of artificial intelligence (AI) has greatly influenced in vitro fertilization (IVF) procedures [53]. Automated embryo selection using machine learning or computer vision based on embryo images is a new area of research [54,55]. Traditionally, the main purpose of embryo evaluation was to sort the embryos according to their implantation rate [56]. Experts select oocytes/embryos by simple observational examination focusing on the morphology of their development. The examination is often subjective and varies between experts [57]. In order to reduce the subjectivity of these observations, methods such as accelerated monitoring systems of embryo development [58], the use of morphokinetics [59] have been tried.
Studies have shown that there is a relationship between inflammation in the male reproductive system and infertility [60]. Microorganisms have negative effects on semen quality [61]. Speed in microbiological diagnosis is among the most important problems in reducing the development of antimicrobial resistance. When microorganisms settle in the organs and tissues they have affinity for, they reproduce rapidly and increase the number of colonies. In this way, as the mass of microbes increases, the response of the immune system becomes long and difficult. In addition, the increased mass protects itself from antimicrobials thanks to virulence factors such as quorum sensing (QS) biofilm. In addition, mutant strains develop after gene exchange with each other in this colonization, making a big difference in competition with treatment protocols. Although artificial intelligence uses complex algorithms, AI is basically the way a computer is used. Artificial intelligence has the potential to make clinical microbiology applications more efficient, more accurate [62]. Thanks to artificial intelligence, rapid microbiological diagnosis and antimicrobial resistance monitoring, analysis and control of influencing virulence factors will make great contributions to humanity today and in the future [63,64]. Microbiological analyzes will become easier with genomic analyses, digital storage and imaging, slide scanning, bacteriological library. In the identification processes made with conventional methods, it is also necessary to distinguish between the colony morphologies of microorganisms, potentially disease-causing pathogens and microorganisms belonging to the flora. Artificial intelligence (AI) is becoming indispensable in clinical fields. Examples of these applications range from image-based applications to deep learning algorithms and in silico clinical trials [65].
Artificial insemination in livestock has been practiced for decades. In this way, the development of animal breeding, especially in cattle and pigs, has accelerated. The use of artificial intelligence in obtaining the best spermatozoa, sperm sex determination technologies and long-term storage methods of semen is increasing [66]. On the other hand, Artificial intelligence applications have started to be used in clinical microbiology laboratories to provide some convenience in all these situations [67]. In this way, by using genome analysis-based algorithms that determine the resistance genes of resistant microorganisms, increasing antimicrobial resistance and the economic loss of multidrug microorganisms, which are called red alert pathogens in the world, will be prevented in the health sector. In addition, it will be of great hope that it will contribute to the decrease in the mortality rate. However, after obtaining microbiome/proteome analyzes at the human/environment and animal/environmental level, with artificial intelligence applications, significant contributions can be made to the health of new generations in accordance with ethics [68].

References

---

1. Bizzaro N, Antico A, Platzgummer S, et al. (2014) Automated antinuclear immunofluorescence antibody screening: a comparative study of six computer-aided diagnostic systems. Autoimmunity Reviews. 13(3): 292-298. [PubMed.]
2. Kratz A, Bengtsson HI, Casey JE, et al. (2005) Performance evaluation of the CellaVision DM96 system: WBC differentials by automated digital image analysis supported by an artificial neural network. American journal of clinical pathology. 124(5): 770-781. [PubMed.]
3. Smith KP, Wang H, Durant TJ., et al. (2020) Applications of artificial intelligence in clinical microbiology diagnostic testing. Clinical Microbiology Newsletter. 42(8): 61-70. [Ref.]
4. Garcia E, Kundu I, Ali A, et al. (2018) The American Society for Clinical Pathology’s 2016-2017 vacancy survey of medical laboratories in the United States.American journal of clinical pathology. 149(5): 387-400. [Ref.]
5. Rahman MS, Kwon WS, Pang MG. (2017) Prediction of male fertility using capacitation‐associated proteins in spermatozoa. Molecular reproduction and development. 84(9): 749-759. [Ref.]
6. Vogiatzi P, Pouliakis A, Siristatidis C. (2019) An artificial neural network for the prediction of assisted reproduction outcome. Journal of assisted reproduction and genetics. 36(7): 1441-1448. [Ref.]
7. La Marca A, Nelson SM, Sighinolfi G, et al. (2011) Anti-Müllerian hormone-based prediction model for a live birth in assisted reproduction. Reproductive biomedicine online. 22(4): 341-349. [Ref.]
8. Yi WJ, Park KS, & Paick JS. (1998) Morphological classification of sperm heads using artificial neural networks. In MEDINFO'98. 1071-1074. [Ref.]
9. Morales DA, Bengoetxea E, Larrañaga P, et al. (2008) Bayesian classification for the selection of in vitro human embryos using morphological and clinical data. Computer methods and programs in biomedicine. 90(2): 104-116. [Ref.]
10. Burai P, Hajdu A, Manuel FRE, et al. (2018) Segmentation of the uterine wall by an ensemble of fully convolutional neural networks. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 49-52. [Ref.]
11. Uyar A, Bener A, Ciray HN. (2015) Predictive modeling of implantation outcome in an in vitro fertilization setting: an application of machine learning methods. Medical Decision Making. 35(6): 714-725. [Ref.]
12. Paternot G, Devroe J, Debrock S, et al. (2009) Intra- and inter-observer analysis in the morphological assessment of early-stage embryos. Reprod Biol Endocrinol. 7: 105. [Ref.]
13. Sundvall L, Ingerslev HJ, Breth Knudsen U, et al. (2013) Inter- and intra-observer variability of time-lapse annotations. Hum Reprod. 28: 3215-3221. [Ref.]
14. Storr A, Venetis CA, Cooke S, et al. (2017) Inter-observer and intra-observer agreement between embryologists during selection of a single Day 5 embryo for transfer: a multicenter study. Hum Reprod. 32: 307-314. [Ref.]
15. Riegler MA, Stensen MH, Witczak O, et al. (2021) Artificial intelligence in the fertility clinic: status, pitfalls and possibilities, Human Reproduction. 36(9): 2429-2442. [Ref.]
16. Agarwal A, Said TM. (2003) Role of sperm chromatin abnormalities and DNA damage in male infertility. Human reproduction update. 9(4): 331-345. [Ref.]
17. Broekhuijse MLWJ, Šoštarić E, Feitsma H, et al. (2011) Additional value of computer assisted semen analysis (CASA) compared to conventional motility assessments in pig artificial insemination. Theriogenology. 76(8): 1473-1486. [Ref.]
18. Verstegen J, Iguer-Ouada M, Onclin K. (2002) Computer assisted semen analyzers in andrology research and veterinary practice. Theriogenology. 57(1): 149-179. [Ref.]
19. Kime DE, Van Look KW, McAllister BG, et al. (2001) Computer-assisted sperm analysis (CASA) as a tool for monitoring sperm quality in fish. Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology. 130(4): 425-433. [Ref.]
20. Tırpan MB, Olğaç KT, Gürler H, et al. (2017) Effects of Different Equilibration Conditions on Cryopreserved Bovine Sperm Quality. Kocatepe Veterinary Journal. 10(2): 57-62. [Ref.]
21. Kavak A, Johannisson A, Lundeheim N, et al. (2003) Evaluation of cryopreserved stallion semen from Tori and Estonian breeds using CASA and flow cytometry. Animal Reproduction Science, 76(3-4): 205-216. [Ref.]
22. Cheuquemán C, Sánchez R, Risopatrón J. (2017) Effect of Sperm Selection Techniques in Frozen/Thawed Cat Spermatozoa on Sperm Motility Analyzed by CASA System. International Journal of Morphology. 35(4). [Ref.]
23. Neagu VR, García BM, Sandoval CS, et al. (2010) Freezing dog semen in presence of the antioxidant butylated hydroxytoluene improves postthaw sperm membrane integrity. Theriogenology. 73(5): 645-650. [Ref.]
24. Özer Kaya Ş, Güngör İH, Dayan Ci̇nkara S, et al. (2021) Effect of different doses of hydrated C60 fullerene nanoparticles on ram semen during cool storage. Turk J Vet Anim Sci. 45: 139-147. [Ref.]
25. Verheyen G, Pletincx I, Van Steirteghem A. (1993) Andrology: Effect of freezing method, thawing temperature and post-thaw dilution/washing on motility (CASA) and morphology characteristics of high-quality human sperm. Human Reproduction. 8(10): 1678-1684. [Ref.]
26. Roychoudhury S, Massanyi P. (2008) In vitro copper inhibition of the rabbit spermatozoa motility. Journal of Environmental Science and Health, Part A. 43(6): 651-656. [Ref.]
27. Wilson-Leedy JG, Ingermann RL. (2007) Development of a novel CASA system based on open-source software for characterization of zebrafish sperm motility parameters. Theriogenology. 67(3): 661-672. [Ref.]
28. Moore HD, Akhondı MA. (1996) Fertilizing capacity of rat spermatozoa is correlated with decline in straight‐line velocity measured by Continuous Computer‐Aided Sperm Analysis: epididymal rat spermatozoa from the proximal cauda have a greater fertilizing capacity in vitro than those from the distal cauda or vas deferens. Journal of Andrology. 17(1): 50-60. [Ref.]
29. Boyers SP, Davis RO, Katz DF. (1989) Automated semen analysis. Year Book Medical Publishers. [Ref.]
30. Van Dilla MA, Gledhill BL, Lake S, et al. (1977) Measurement of mammalian sperm deoxyribonucleic acid by flow cytometry. Problems and approaches. Journal of Histochemistry & Cytochemistry. 25(7): 763-773. [Ref.]
31. Peña FJ, Ball BA, Squires EL. (2018) A new method for evaluating stallion sperm viability and mitochondrial membrane potential in fixed semen samples. Cytometry Part B: Clinical Cytometry. 94(2): 302-311. [Ref.]
32. Siemieniuch MJ, Woclawek‐Potocka I. (2008) Assessment of selected quality parameters of epididymal cat (Felis catus s. domestica, L. (1758) sperm using flow cytometry method and computer assisted sperm analyser. Reproduction in domestic animals. 43(5): 633-637. [Ref.]
33. Brewıs IA, Morton IE, Mohammad SN, et al. (2000) Measurement Of İntracellular Calcium Concentration and Plasma Membrane Potential In Human Spermatozoa Using Flow Cytometry. Journal Of Andrology. 21(2): 238-249. [Ref.]
34. Martínez‐Pastor F, Mata‐Campuzano M, Álvarez‐Rodríguez M, et al. (2010) Probes and techniques for sperm evaluation by flow cytometry. Reproduction in domestic animals. 45: 67-78. [Ref.]
35. Zuidema D, Kerns K, Sutovsky P. (2021) An Exploration of Current and Perspective Semen Analysis and Sperm Selection for Livestock Artificial Insemination. Animals: an open access journal from MDPI. 11(12): 3563. [Ref.]
36. Johnson LA, Welch GR. (1999) Sex preselection: high-speed flow cytometric sorting of X and Y sperm for maximum efficiency. Theriogenology. 52(8): 1323-1341. [Ref.]
37. Kennedy CE, Krieger KB, Sutovsky M, et al. (2014) Protein expression pattern of PAWP in bull spermatozoa is associated with sperm quality and fertility following artificial insemination. Mol. Reprod. Dev. 81: 436-449. [Ref.]
38. Rubessa M, Feugang JM, Kandel ME, et al. (2020) High-throughput sperm assay using label-free microscopy: Morphometric comparison between different sperm structures of boar and stallion spermatozoa. Anim. Reprod. Sci. 219: 106509. [Ref.]
39. Kerns K, Jankovitz J, Robinson J, et al. (2020) Relationship between the Length of Sperm Tail Mitochondrial Sheath and Fertility Traits in Boars Used for Artificial Insemination. Antioxidants. 9: 1033. [Ref.]
40. Sharma V. (2011) Sperm storage for cancer patients in the UK: a review of current practice. Human reproduction. 26(11): 2935-2943. [Ref.]
41. Di Santo M, Tarozzi N, Nadalini M, et al. (2012) Human sperm cryopreservation: update on techniques, effect on DNA integrity, and implications for ART. Advances in urology, 2012. [Ref.]
42. Cohen J, Garrisi GJ. (1997) Video. Micromanipulation of gametes and embryos: cryopreservation of a single human spermatozoon within an isolated zona pellucida. Human reproduction update. 3(5): 453-453. [Ref.]
43. Desai N, Blackmon H, Goldfarb J. (2003) Single sperm cryopreservation on cryoloops: an alternative to hamster zona for cryopreservation of individual spermatozoa. Fertility and Sterility. 80: 55-56. [Ref.]
44. Isachenko V, Isachenko E, Montag M, et al. (2005) Clean technique for cryoprotectant-free vitrification of human spermatozoa. Reproductive biomedicine online. 10(3): 350-354. [Ref.]
45. Zou Y, Yin T, Chen S, et al. (2013) On-chip cryopreservation: a novel method for ultra-rapid cryoprotectant-free cryopreservation of small amounts of human spermatozoa. PloS one. 8(4): e61593. [Ref.]
46. Moran DM, Jasko DJ, Squires EL, et al. (1992) Determination of temperature and cooling rate which induce cold shock in stallion spermatozoa. Theriogenology. 38(6): 999-1012. [Ref.]
47. Agca Y, Critser JK. (2002) Cryopreservation of spermatozoa in assisted reproduction. In Seminars in reproductive medicine. 20(1): 015-024. 584-4662. [Ref.]
48. Almquist JO, Wiggin HB. (1973) Survival of bull spermatozoa frozen and thawed by different methods in plastic straws. Ai digest. [Ref.]
49. Evans G, Maxwell WMC. (1987) Frozen storage of semen. Salamon’s artificial insemination of sheep and goats. Butterworths, Wellington. 122-141. [Ref.]
50. Purdy PH. (2006) A review on goat sperm cryopreservation. Small ruminant research. 63(3): 215-225. [Ref.]
51. Clulow JR, Mansfield LJ, Morris LHA, et al. (2008) A comparison between freezing methods for the cryopreservation of stallion spermatozoa. Animal Reproduction Science. 108(3-4): 298-308. [Ref.]
52. Kragh MF, Karstoft H. (2021) Embryo selection with artificial intelligence: how to evaluate and compare methods? Journal of Assisted Reproduction and Genetics. 38(7): 1675-1689. [Ref.]
53. Zaninovic N, Elemento O, Rosenwaks Z. (2019) Artificial intelligence: its applications in reproductive medicine and the assisted reproductive technologies. Fertility and sterility. 112(1): 28-30. [Ref.]
54. Wong CC, Loewke KE, Bossert NL, et al. (2010) Non-invasive imaging of human embryos before embryonic genome activation predicts development to the blastocyst stage. Nature biotechnology. 28(10): 1115-1121. [Ref.]
55. Petersen BM, Boel M, Montag M, et al. (2016) Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3. Human reproduction. 31(10): 2231-2244. [Ref.]
56. Steyerberg EW. (2019) Clinical Prediction Models. Statistics for Biology and Health. 2nd edn. [Ref.]
57. Balaban B, Brison D, Calderon G, et al. (2011) Alpha scientists in reproductive medicine and ESHRE special interest group of embryology. The Istanbul consensus workshop on embryo assessment: proceedings of an expert meeting. Hum Reprod, 26(6): 1270-1283. [Ref.]
58. Cruz M, Gadea B, Garrido N, et al. (2011) Embryo quality, blastocyst and ongoing pregnancy rates in oocyte donation patients whose embryos were monitored by time-lapse imaging. Journal of Assisted Reproduction and Genetics. 28(7): 569-573. [Ref.]
59. Meseguer M, Herrero J, Tejera A, et al. (2011) The use of morphokinetics as a predictor of embryo implantation. Human reproduction. 26(10): 2658-2671. [Ref.]
60. Comhaire FH, Mahmoud AMA, Depuydt CE, et al. (1999) Mechanisms and effects of male genital tract infection on sperm quality and fertilizing potential: the andrologist's viewpoint. Human Reproduction Update. 5(5): 393-398. [Ref.]
61. Ömür AD, Akarsu SA, Ayyıldız B, et al. (2022) Relationship of Microbiota with Male Reproductive Potential Journal of Clinical Veterinary Research. 2(1). [Ref.]
62. Winstanley T, Courvalin P. (2011) Expert systems in clinical microbiology. Clinical microbiology reviews. 24(3): 515-556. [Ref.]
63. Shortliffe EH, Axline SG, Buchanan BG, et al. (1973) An artificial intelligence program to advise physicians regarding antimicrobial therapy. Computers and Biomedical Research. 6(6): 544-560. [Ref.]
64. Demirhan A, Kiliç YA, İnan G. (2010) Intelligence applications in medicine. Journal of Intensive Care. 9(1): 31-41. [Ref.]
65. Walter W, Haferlach C, Nadarajah N, et al. (2021) How artificial intelligence might disrupt diagnostics in hematology in the near future. Oncogene. 40(25): 4271-4280. [Ref.]
66. Zuidema D, Kerns K, Sutovsky P. (2021) An Exploration of Current and Perspective Semen Analysis and Sperm Selection for Livestock Artificial Insemination. Animals. 11(12): 3563. [Ref.]
67. Begley RJ, Riege M, Rosenblum J, et al. (2000) Adding intelligence to medical devices. Medical Device and Diagnostic Industry. 22(3): 150-175. [Ref.]
68. Smith KP, Kirby JE. (2020) Image analysis and artificial intelligence in infectious disease diagnostics. Clinical Microbiology and Infection. 26(10): 1318-1323. [Ref.]