Clinical and Experimental Reproductive Medicine

  • 제51권1호
  • /
  • Pages.1-12
  • /
  • 2024
  • /
  • 2233-8233(pISSN)
  • /
  • 2233-8241(eISSN)
대한생식의학회 (The Korean Society for Reproductive Medicine)
권호 표지
DOI QR코드

DOI QR Code

Criteria for implementing artificial intelligence systems in reproductive medicine

  • 투고 : 2023.03.15
  • 심사 : 2023.08.31
  • 발행 : 2024.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This review article discusses the integration of artificial intelligence (AI) in assisted reproductive technology and provides key concepts to consider when introducing AI systems into reproductive medicine practices. The article highlights the various applications of AI in reproductive medicine and discusses whether to use commercial or in-house AI systems. This review also provides criteria for implementing new AI systems in the laboratory and discusses the factors that should be considered when introducing AI in the laboratory, including the user interface, scalability, training, support, follow-up, cost, ethics, and data quality. The article emphasises the importance of ethical considerations, data quality, and continuous algorithm updates to ensure the accuracy and safety of AI systems.

키워드

참고문헌

  1. Dimitriadis I, Zaninovic N, Badiola AC, Bormann CL. Artificial intelligence in the embryology laboratory: a review. Reprod Biomed Online 2022;44:435-48. https://doi.org/10.1016/j.rbmo.2021.11.003
  2. Martin-Climent P, Moreno-Garcia JM. Aplicacion de la inteligencia artificial en el laboratorio de reproduccion asistida. Trabajo de revision. Med Reprod Embriol Clin 2022;9:100119.
  3. Chow DJ, Wijesinghe P, Dholakia K, Dunning KR. Does artificial intelligence have a role in the IVF clinic? Reprod Fertil 2021;2:C29-34. https://doi.org/10.1530/RAF-21-0043
  4. Fernandez EI, Ferreira AS, Cecilio MH, Cheles DS, de Souza RC, Nogueira MF, et al. Artificial intelligence in the IVF laboratory: overview through the application of different types of algorithms for the classification of reproductive data. J Assist Reprod Genet 2020;37:2359-76. https://doi.org/10.1007/s10815-020-01881-9
  5. Zaninovic N, Rosenwaks Z. Artificial intelligence in human in vitro fertilization and embryology. Fertil Steril 2020;114:914-20. https://doi.org/10.1016/j.fertnstert.2020.09.157
  6. Uyar A, Bener A, Ciray HN. Predictive modeling of implantation outcome in an in vitro fertilization setting: an application of machine learning methods. Med Decis Making 2015;35:714-25. https://doi.org/10.1177/0272989X14535984
  7. Blank C, Wildeboer RR, DeCroo I, Tilleman K, Weyers B, de Sutter P, et al. Prediction of implantation after blastocyst transfer in in vitro fertilization: a machine-learning perspective. Fertil Steril 2019;111:318-26. https://doi.org/10.1016/j.fertnstert.2018.10.030
  8. Liao Q, Zhang Q, Feng X, Huang H, Xu H, Tian B, et al. Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring. Commun Biol 2021;4:415.
  9. Mendizabal-Ruiz G, Chavez-Badiola A, Aguilar Figueroa I, Martinez Nuno V, Flores-Saiffe Farias A, Valencia-Murilloa R, et al. Computer software (SiD) assisted real-time single sperm selection associated with fertilization and blastocyst formation. Reprod Biomed Online 2022;45:703-11. https://doi.org/10.1016/j.rbmo.2022.03.036
  10. Zeadna A, Khateeb N, Rokach L, Lior Y, Har-Vardi I, Harlev A, et al. Prediction of sperm extraction in non-obstructive azoospermia patients: a machine-learning perspective. Hum Reprod 2020;35:1505-14. https://doi.org/10.1093/humrep/deaa109
  11. Nayot D, Mercuri N, Krivoi A, Casper RF, Meriano J, Fjeldstad J. A novel non-invasive oocyte scoring system using AI applied to 2-dimensional images. Fertil Steril 2021;116(3 Suppl):E474.
  12. Zhao M, Li H, Li R, Li Y, Luo X, Li TC, et al. Automated and precise recognition of human zygote cytoplasm: a robust image-segmentation system based on a convolutional neural network. Biomed Signal Process Control 2021;67:102551.
  13. Kan-Tor Y, Zabari N, Erlich I, Szeskin A, Amitai T, Richter D, et al. Automated evaluation of human embryo blastulation and implantation potential using deep-learning. Adv Intell Syst 2020;2:2000080.
  14. Feyeux M, Reignier A, Mocaer M, Lammers J, Meistermann D, Barriere P, et al. Development of automated annotation software for human embryo morphokinetics. Hum Reprod 2020;35:557-64. https://doi.org/10.1093/humrep/deaa001
  15. Lucio CM, Lopez JT, Zamora ML, Esteve AG, Martinez MB, Suarez ME, et al. CHLOE (FAIRTILITY) can automatically annotate images from time-lapse cultured embryos for Pronucleate (PN) count, morphokinetics and ranking according to ploidy and implantation potential, with a strong agreement compared to experienced embryologists. Reprod Biomed Online 2022;45:e34-5. https://doi.org/10.1016/j.rbmo.2022.08.058
  16. Khosravi P, Kazemi E, Zhan Q, Toschi M, Malmsten JE, Hickman C, et al. Robust automated assessment of human blastocyst quality using deep learning. bioRxiv 2018 Aug 20 [Priprint]. https://doi.org/10.1101/394882
  17. Yang L, Peavey M, Kaskar K, Chappell N, Devlin DJ, Woodard T, et al. Predicting clinical pregnancy by machine learning algorithm using noninvasive embryo morphokinetics at an academic center. Fertil Steril 2019;112:e181.
  18. Liang B, Gao Y, Xu J, Song Y, Xuan L, Shi T, et al. Raman profiling of embryo culture medium to identify aneuploid and euploid embryos. Fertil Steril 2019;111:753-62. https://doi.org/10.1016/j.fertnstert.2018.11.036
  19. Chavez-Badiola A, Flores-Saiffe-Farias A, Mendizabal-Ruiz G, Drakeley AJ, Cohen J. Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation. Reprod Biomed Online 2020;41:585-93. https://doi.org/10.1016/j.rbmo.2020.07.003
  20. Diakiw SM, Hall JM, VerMilyea MD, Amin J, Aizpurua J, Giardini L, et al. Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF. Hum Reprod 2022;37:1746-59. https://doi.org/10.1093/humrep/deac131
  21. Diakiw SM, Hall JM, VerMilyea M, Lim AY, Quangkananurug W, Chanchamroen S, et al. An artificial intelligence model correlated with morphological and genetic features of blastocyst quality improves ranking of viable embryos. Reprod Biomed Online 2022;45:1105-17. https://doi.org/10.1016/j.rbmo.2022.07.018
  22. Barnes J, Brendel M, Gao VR, Rajendran S, Kim J, Li Q, et al. A non-invasive artificial intelligence approach for the prediction of human blastocyst ploidy: a retrospective model development and validation study. Lancet Digit Health 2023;5:e28-40.
  23. Berntsen J, Rimestad J, Lassen JT, Tran D, Kragh MF. Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences. PLoS One 2022;17:e0262661.
  24. Theilgaard Lassen J, Fly Kragh M, Rimestad J, Nygard Johansen M, Berntsen J. Development and validation of deep learning based embryo selection across multiple days of transfer. Sci Rep 2023;13:4235.
  25. Glatstein I, Chavez-Badiola A, Curchoe CL. New frontiers in embryo selection. J Assist Reprod Genet 2023;40:223-34. https://doi.org/10.1007/s10815-022-02708-5
  26. Cimadomo D, Marconetto A, Trio S, Chiappetta V, Innocenti F, Albricci L, et al. Human blastocyst spontaneous collapse is associated with worse morphological quality and higher degeneration and aneuploidy rates: a comprehensive analysis standardized through artificial intelligence. Hum Reprod 2022;37:2291-306. https://doi.org/10.1093/humrep/deac175
  27. De Gheselle S, Jacques C, Chambost J, Blank C, Declerck K, De Croo I, et al. Machine learning for prediction of euploidy in human embryos: in search of the best-performing model and predictive features. Fertil Steril 2022;117:738-46. https://doi.org/10.1016/j.fertnstert.2021.11.029
  28. Ortiz JA, Morales R, Lledo B, Vicente JA, Gonzalez J, Garcia-Hernandez EM, et al. Application of machine learning to predict aneuploidy and mosaicism in embryos from in vitro fertilization cycles. AJOG Glob Rep 2022;2:100103.
  29. Yu JL, Su YF, Zhang C, Jin L, Lin XH, Chen LT, et al. Tracking of menstrual cycles and prediction of the fertile window via measurements of basal body temperature and heart rate as well as machine-learning algorithms. Reprod Biol Endocrinol 2022;20:118.
  30. Bormann CL, Curchoe CL, Thirumalaraju P, Kanakasabapathy MK, Gupta R, Pooniwala R, et al. Deep learning early warning system for embryo culture conditions and embryologist performance in the ART laboratory. J Assist Reprod Genet 2021;38:1641-6. https://doi.org/10.1007/s10815-021-02198-x
  31. Khodabandelu S, Basirat Z, Khaleghi S, Khafri S, Montazery Kordy H, Golsorkhtabaramiri M. Developing machine learning-based models to predict intrauterine insemination (IUI) success by address modeling challenges in imbalanced data and providing modification solutions for them. BMC Med Inform Decis Mak 2022;22:228.
  32. Letterie G, Mac Donald A. Artificial intelligence in in vitro fertilization: a computer decision support system for day-to-day management of ovarian stimulation during in vitro fertilization. Fertil Steril 2020;114:1026-31. https://doi.org/10.1016/j.fertnstert.2020.06.006
  33. Hariton E, Chi EA, Chi G, Morris JR, Braatz J, Rajpurkar P, et al. A machine learning algorithm can optimize the day of trigger to improve in vitro fertilization outcomes. Fertil Steril 2021;116:1227-35. https://doi.org/10.1016/j.fertnstert.2021.06.018
  34. Fanton M, Nutting V, Solano F, Maeder-York P, Hariton E, Barash O, et al. An interpretable machine learning model for predicting the optimal day of trigger during ovarian stimulation. Fertil Steril 2022;118:101-8. https://doi.org/10.1016/j.fertnstert.2022.04.003
  35. Correa N, Cerquides J, Arcos JL, Vassena R. Supporting first FSH dosage for ovarian stimulation with machine learning. Reprod Biomed Online 2022;45:1039-45. https://doi.org/10.1016/j.rbmo.2022.06.010
  36. Guell Penas E, Vives Perello A, Esquerra Pares M, Mladenova Koleva M. P-179 Aneuploid embryos as a proposal for improving artificial intelligence performance. Hum Reprod 2022;37(Supplement 1):deac106-059.
  37. Goyal A, Kuchana M, Ayyagari KP. Machine learning predicts livebirth occurrence before in-vitro fertilization treatment. Sci Rep 2020;10:20925.
  38. Miyagi Y, Habara T, Hirata R, Hayashi N. Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age. Reprod Med Biol 2019;18:190-203. https://doi.org/10.1002/rmb2.12266
  39. Huang B, Tan W, Li Z, Jin L. An artificial intelligence model (euploid prediction algorithm) can predict embryo ploidy status based on time-lapse data. Reprod Biol Endocrinol 2021;19:185.
  40. Loewke K, Cho JH, Brumar CD, Maeder-York P, Barash O, Malmsten JE, et al. Characterization of an artificial intelligence model for ranking static images of blastocyst stage embryos. Fertil Steril 2022;117:528-35. https://doi.org/10.1016/j.fertnstert.2021.11.022
  41. Tran D, Cooke S, Illingworth PJ, Gardner DK. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum Reprod 2019;34:1011-8. https://doi.org/10.1093/humrep/dez064
  42. VerMilyea M, Hall JM, Diakiw SM, Johnston A, Nguyen T, Perugini D, et al. Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF. Hum Reprod 2020;35:770-84. https://doi.org/10.1093/humrep/deaa013
  43. Cimadomo D, Chiappetta V, Innocenti F, Saturno G, Taggi M, Marconetto A, et al. Towards automation in IVF: pre-clinical validation of a deep learning-based embryo grading system during PGT-A cycles. J Clin Med 2023;12:1806.
  44. Afnan MAM, Rudin C, Conitzer V, Savulescu J, Mishra A, Liu Y, et al. Ethical implementation of artificial intelligence to select embryos in in vitro fertilization. In: AIES'21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society; 2021 May 19-21; Virtual Event, USA. Association for Computing Machinery. 2021; pp 316-26. Available from: https://doi.org/10.1145/3461702.3462589
  45. Martinez-Granados L, Serrano M, Gonzalez-Utor A, Ortiz N, Badajoz V, Olaya E, et al. Inter-laboratory agreement on embryo classification and clinical decision: conventional morphological assessment vs. time lapse. PLoS One 2017;12:e0183328.
  46. Fordham DE, Rosentraub D, Polsky AL, Aviram T, Wolf Y, Perl O, et al. Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity? Hum Reprod 2022;37:2275-90. https://doi.org/10.1093/humrep/deac171
  47. Barrie A, McDowell G, Troup S. An investigation into the effect of potential confounding patient and treatment parameters on human embryo morphokinetics. Fertil Steril 2021;115:1014-22. https://doi.org/10.1016/j.fertnstert.2020.10.037
  48. Meseguer M, Valera MA. The journey toward personalized embryo selection algorithms. Fertil Steril 2021;115:898-9. https://doi.org/10.1016/j.fertnstert.2021.01.039
  49. Curchoe CL, Flores-Saiffe Farias A, Mendizabal-Ruiz G, Chavez-Badiola A. Evaluating predictive models in reproductive medicine. Fertil Steril 2020;114:921-6. https://doi.org/10.1016/j.fertnstert.2020.09.159
  50. Zhu X, Wu X. Class noise vs. attribute noise: a quantitative study. Artif Intell Rev 2004;22:177-210. https://doi.org/10.1007/s10462-004-0751-8
  51. Frenay B, Verleysen M. Classification in the presence of label noise: a survey. IEEE Trans Neural Netw Learn Syst 2014;25:845-69. https://doi.org/10.1109/TNNLS.2013.2292894
  52. Song H, Kim M, Park D, Shin Y, Lee JG. Learning from noisy labels with deep neural networks: a survey. IEEE Trans Neural Netw Learn Syst 2023;34:8135-53.
  53. Popovic M, Dheedene A, Christodoulou C, Taelman J, Dhaenens L, Van Nieuwerburgh F, et al. Chromosomal mosaicism in human blastocysts: the ultimate challenge of preimplantation genetic testing? Hum Reprod 2018;33:1342-54. https://doi.org/10.1093/humrep/dey106
  54. Orvieto R, Jonish-Grossman A, Maydan SA, Noach-Hirsh M, Dratviman-Storobinsky O, Aizer A. Cleavage-stage human embryo arrest, is it embryo genetic composition or others? Reprod Biol Endocrinol 2022;20:52.
  55. Kragh MF, Karstoft H. Embryo selection with artificial intelligence: how to evaluate and compare methods? J Assist Reprod Genet 2021;38:1675-89. https://doi.org/10.1007/s10815-021-02254-6
  56. Nasir V, Sassani F. A review on deep learning in machining and tool monitoring: methods, opportunities, and challenges. Int J Adv Manuf Technol 2021;115:2683-709. https://doi.org/10.1007/s00170-021-07325-7
  57. Rudin C, Chen C, Chen Z, Huang H, Semenova L, Zhong C. Interpretable machine learning: fundamental principles and 10 grand challenges. Stat Surv 2022;16:1-85. https://doi.org/10.1214/21-SS133
  58. Swain J, VerMilyea MT, Meseguer M, Ezcurra D; Fertility AI Forum Group. AI in the treatment of fertility: key considerations. J Assist Reprod Genet 2020;37:2817-24. https://doi.org/10.1007/s10815-020-01950-z
  59. Fitz VW, Kanakasabapathy MK, Thirumalaraju P, Kandula H, Ramirez LB, Boehnlein L, et al. Should there be an "AI" in TEAM?: embryologists selection of high implantation potential embryos improves with the aid of an artificial intelligence algorithm. J Assist Reprod Genet 2021;38:2663-70. https://doi.org/10.1007/s10815-021-02318-7
  60. Simopoulou M, Sfakianoudis K, Maziotis E, Antoniou N, Rapani A, Anifandis G, et al. Are computational applications the "crystal ball" in the IVF laboratory?: the evolution from mathematics to artificial intelligence. J Assist Reprod Genet 2018;35:1545-57. https://doi.org/10.1007/s10815-018-1266-6
  61. Sfakianoudis K, Maziotis E, Grigoriadis S, Pantou A, Kokkini G, Trypidi A, et al. Reporting on the value of artificial intelligence in predicting the optimal embryo for transfer: a systematic review including data synthesis. Biomedicines 2022;10:697.