Machine learning for predicting elective fertility preservation outcomes.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
02 May 2024
02 May 2024
Historique:
received:
10
10
2023
accepted:
25
04
2024
medline:
3
5
2024
pubmed:
3
5
2024
entrez:
2
5
2024
Statut:
epublish
Résumé
This retrospective study applied machine-learning models to predict treatment outcomes of women undergoing elective fertility preservation. Two-hundred-fifty women who underwent elective fertility preservation at a tertiary center, 2019-2022 were included. Primary outcome was the number of metaphase II oocytes retrieved. Outcome class was based on oocyte count (OC): Low (≤ 8), Medium (9-15) or High (≥ 16). Machine-learning models and statistical regression were used to predict outcome class, first based on pre-treatment parameters, and then using post-treatment data from ovulation-triggering day. OC was 136 Low, 80 Medium, and 34 High. Random Forest Classifier (RFC) was the most accurate model (pre-treatment receiver operating characteristic (ROC) area under the curve (AUC) was 77%, and post-treatment ROC AUC was 87%), followed by XGBoost Classifier (pre-treatment ROC AUC 74%, post-treatment ROC AUC 86%). The most important pre-treatment parameters for RFC were basal FSH (22.6%), basal LH (19.1%), AFC (18.2%), and basal estradiol (15.6%). Post-treatment parameters were estradiol levels on trigger-day (17.7%), basal FSH (11%), basal LH (9%), and AFC (8%). Machine-learning models trained with clinical data appear to predict fertility preservation treatment outcomes with relatively high accuracy.
Identifiants
pubmed: 38698132
doi: 10.1038/s41598-024-60671-w
pii: 10.1038/s41598-024-60671-w
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
10158Informations de copyright
© 2024. The Author(s).
Références
Rudick, B., Opper, N., Paulson, R., Bendikson, K. & Chung, K. The status of oocyte cryopreservation in the United States. Fertil. Steril. 94, 2642–2646. https://doi.org/10.1016/j.fertnstert.2010.04.079 (2010).
doi: 10.1016/j.fertnstert.2010.04.079
pubmed: 20723535
Johnson, J. A., Tough, S., Genetics, S. O. G. C. & Committee.,. Delayed child-bearing. J. Obstet. Gynaecol. Can. 34, 80–93. https://doi.org/10.1016/S1701-2163(16)35138-6 (2012).
doi: 10.1016/S1701-2163(16)35138-6
pubmed: 22260768
Committee Opinion No. 589: Female age-related fertility decline. Obstet. Gynecol. 123, 719–721. https://doi.org/10.1097/01.AOG.0000444440.96486.61 (2014).
doi: 10.1097/01.AOG.0000444440.96486.61
Ng, Y. & Ng, S.-C. Oocyte cryopreservation as a strategy to overcome age-related fertility loss. Expert Rev. Obstet. Gynecol. 8, 417–424. https://doi.org/10.1586/17474108.2013.825478 (2013).
doi: 10.1586/17474108.2013.825478
Stoop, D., Nekkebroeck, J. & Devroey, P. A survey on the intentions and attitudes towards oocyte cryopreservation for non-medical reasons among women of reproductive age. Hum. Reprod. 26, 655–661. https://doi.org/10.1093/humrep/deq367 (2011).
doi: 10.1093/humrep/deq367
pubmed: 21212052
Shkedi-Rafid, S. & Hashiloni-Dolev, Y. Egg freezing for age-related fertility decline: Preventive medicine or a further medicalization of reproduction? Analyzing the new Israeli policy. Fertil. Steril. 96, 291–294. https://doi.org/10.1016/j.fertnstert.2011.06.024 (2011).
doi: 10.1016/j.fertnstert.2011.06.024
pubmed: 21722891
De Groot, M. et al. Perceptions of oocyte banking from women intending to circumvent age-related fertility decline. Acta Obstet. Gynecol. Scand. 95, 1396–1401. https://doi.org/10.1111/aogs.13019 (2016).
doi: 10.1111/aogs.13019
pubmed: 27623090
Doyle, J. O. et al. Successful elective and medically indicated oocyte vitrification and warming for autologous in vitro fertilization, with predicted birth probabilities for fertility preservation according to number of cryopreserved oocytes and age at retrieval. Fertil. Steril. 105, 459–466. https://doi.org/10.1016/j.fertnstert.2015.10.026 (2016).
doi: 10.1016/j.fertnstert.2015.10.026
pubmed: 26604065
Solé, M. et al. How does vitrification affect oocyte viability in oocyte donation cycles? A prospective study to compare outcomes achieved with fresh versus vitrified sibling oocytes. Hum. Reprod. 28, 2087–2092. https://doi.org/10.1093/humrep/det242 (2013).
doi: 10.1093/humrep/det242
pubmed: 23744895
Gameiro, S., Boivin, J., Peronace, L. & Verhaak, C. M. Why do patients discontinue fertility treatment? A systematic review of reasons and predictors of discontinuation in fertility treatment. Hum. Reprod. Update 18, 652–669. https://doi.org/10.1093/humupd/dms031 (2012).
doi: 10.1093/humupd/dms031
pubmed: 22869759
pmcid: 3461967
Fritz, R. & Jindal, S. Reproductive aging and elective fertility preservation. J. Ovarian Res. 11, 66. https://doi.org/10.1186/s13048-018-0438-4 (2018).
doi: 10.1186/s13048-018-0438-4
pubmed: 30098598
pmcid: 6087539
Goldman, R. H. et al. Predicting the likelihood of live birth for elective oocyte cryopreservation: A counseling tool for physicians and patients. Hum. Reprod. 32, 853–859. https://doi.org/10.1093/humrep/dex008 (2017).
doi: 10.1093/humrep/dex008
pubmed: 28166330
Bzdok, D., Altman, N. & Krzywinski, M. Statistics versus machine learning. Nat. Methods 15, 233–234. https://doi.org/10.1038/nmeth.4642 (2018).
doi: 10.1038/nmeth.4642
pubmed: 30100822
pmcid: 6082636
Rajula, H. S. R., Verlato, G., Manchia, M., Antonucci, N. & Fanos, V. Comparison of conventional statistical methods with machine learning in medicine: Diagnosis, drug development, and treatment. Medicina 6, 455. https://doi.org/10.1093/humrep/dex008.10.3390/medicina56090455 (2020).
doi: 10.1093/humrep/dex008.10.3390/medicina56090455
Huang, B. et al. Using deep learning to predict the outcome of live birth from more than 10,000 embryo data. BMC Pregnancy Childbirth 22, 36. https://doi.org/10.1186/s12884-021-04373-5 (2022).
doi: 10.1186/s12884-021-04373-5
pubmed: 35034623
pmcid: 8761300
Goyal, A., Kuchana, M. & Ayyagari, K. P. R. Machine learning predicts live-birth occurrence before in-vitro fertilization treatment. Sci. Rep. 10, 20925. https://doi.org/10.1038/s41598-020-76928-z (2020).
doi: 10.1038/s41598-020-76928-z
pubmed: 33262383
pmcid: 7708502
Cobo, A. et al. Oocyte vitrification as an efficient option for elective fertility preservation. Fertil. Steril. 105, 755–764. https://doi.org/10.1016/j.fertnstert.2015.11.027 (2016).
doi: 10.1016/j.fertnstert.2015.11.027
pubmed: 26688429
Blom, J. N., Tan, L., Hughes, L., Tekpetey, F. & Abu, R. B. Serum estradiol level on the fifth day of ovarian stimulation in a GnRH antagonist protocol can predict pregnancy outcomes in IVF/ICSI. Fertil. Steril. https://doi.org/10.1016/j.fertnstert.2018.07.618 (2018).
doi: 10.1016/j.fertnstert.2018.07.618
Panchal, S. & Nagori, C. Comparison of anti-mullerian hormone and antral follicle count for assessment of ovarian reserve. J. Hum. Reprod. Sci. 5, 274–278. https://doi.org/10.4103/0974-1208.106340 (2012).
doi: 10.4103/0974-1208.106340
pubmed: 23531919
pmcid: 3604835
ESHRE Capri Workshop Group. Fertility and ageing. Hum. Reprod. Update 11, 261–276. https://doi.org/10.1093/humupd/dmi006 (2005).
doi: 10.1093/humupd/dmi006
Sonigo, C., Beau, I., Binart, N. & Grynberg, M. Anti-Müllerian hormone in fertility preservation: Clinical and therapeutic applications. Clin. Med. Insights Reprod. Health 13, 1–7. https://doi.org/10.1177/1179558119854755 (2019).
doi: 10.1177/1179558119854755
Kalayeh, H. M. & Landgrebe, D. A. Predicting the required number of training samples. IEEE Trans. Pattern Anal. Mach. Intell. 6, 664–667. https://doi.org/10.1109/TPAMI.1983.4767459 (1983).
doi: 10.1109/TPAMI.1983.4767459