Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception
Abstract Infertility affects one-in-six couples, often necessitating in vitro fertilization treatment (IVF). IVF generates complex data, which can challenge the utilization of the full richness of data during decision-making, leading to reliance on simple ‘rules-of-thumb’. Machine learning technique...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55301-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544430626013184 |
|---|---|
| author | Simon Hanassab Scott M. Nelson Artur Akbarov Arthur C. Yeung Artsiom Hramyka Toulin Alhamwi Rehan Salim Alexander N. Comninos Geoffrey H. Trew Tom W. Kelsey Thomas Heinis Waljit S. Dhillo Ali Abbara |
| author_facet | Simon Hanassab Scott M. Nelson Artur Akbarov Arthur C. Yeung Artsiom Hramyka Toulin Alhamwi Rehan Salim Alexander N. Comninos Geoffrey H. Trew Tom W. Kelsey Thomas Heinis Waljit S. Dhillo Ali Abbara |
| author_sort | Simon Hanassab |
| collection | DOAJ |
| description | Abstract Infertility affects one-in-six couples, often necessitating in vitro fertilization treatment (IVF). IVF generates complex data, which can challenge the utilization of the full richness of data during decision-making, leading to reliance on simple ‘rules-of-thumb’. Machine learning techniques are well-suited to analyzing complex data to provide data-driven recommendations to improve decision-making. In this multi-center study (n = 19,082 treatment-naive female patients), including 11 European IVF centers, we harnessed explainable artificial intelligence to identify follicle sizes that contribute most to relevant downstream clinical outcomes. We found that intermediately-sized follicles were most important to the number of mature oocytes subsequently retrieved. Maximizing this proportion of follicles by the end of ovarian stimulation was associated with improved live birth rates. Our data suggests that larger mean follicle sizes, especially those >18 mm, were associated with premature progesterone elevation by the end of ovarian stimulation and a negative impact on live birth rates with fresh embryo transfer. These data highlight the potential of computer technologies to aid in the personalization of IVF to optimize clinical outcomes pending future prospective validation. |
| format | Article |
| id | doaj-art-5438fd027de84983a1dd4732338f7d33 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-5438fd027de84983a1dd4732338f7d332025-01-12T12:31:25ZengNature PortfolioNature Communications2041-17232025-01-0116111110.1038/s41467-024-55301-yExplainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conceptionSimon Hanassab0Scott M. Nelson1Artur Akbarov2Arthur C. Yeung3Artsiom Hramyka4Toulin Alhamwi5Rehan Salim6Alexander N. Comninos7Geoffrey H. Trew8Tom W. Kelsey9Thomas Heinis10Waljit S. Dhillo11Ali Abbara12Department of Metabolism, Digestion, and Reproduction, Imperial College LondonSchool of Medicine, University of GlasgowDepartment of Computing, Imperial College LondonDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonSchool of Computer Science, University of St AndrewsDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonImperial College Healthcare NHS TrustDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonSchool of Computer Science, University of St AndrewsDepartment of Computing, Imperial College LondonDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonDepartment of Metabolism, Digestion, and Reproduction, Imperial College LondonAbstract Infertility affects one-in-six couples, often necessitating in vitro fertilization treatment (IVF). IVF generates complex data, which can challenge the utilization of the full richness of data during decision-making, leading to reliance on simple ‘rules-of-thumb’. Machine learning techniques are well-suited to analyzing complex data to provide data-driven recommendations to improve decision-making. In this multi-center study (n = 19,082 treatment-naive female patients), including 11 European IVF centers, we harnessed explainable artificial intelligence to identify follicle sizes that contribute most to relevant downstream clinical outcomes. We found that intermediately-sized follicles were most important to the number of mature oocytes subsequently retrieved. Maximizing this proportion of follicles by the end of ovarian stimulation was associated with improved live birth rates. Our data suggests that larger mean follicle sizes, especially those >18 mm, were associated with premature progesterone elevation by the end of ovarian stimulation and a negative impact on live birth rates with fresh embryo transfer. These data highlight the potential of computer technologies to aid in the personalization of IVF to optimize clinical outcomes pending future prospective validation.https://doi.org/10.1038/s41467-024-55301-y |
| spellingShingle | Simon Hanassab Scott M. Nelson Artur Akbarov Arthur C. Yeung Artsiom Hramyka Toulin Alhamwi Rehan Salim Alexander N. Comninos Geoffrey H. Trew Tom W. Kelsey Thomas Heinis Waljit S. Dhillo Ali Abbara Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception Nature Communications |
| title | Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| title_full | Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| title_fullStr | Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| title_full_unstemmed | Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| title_short | Explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| title_sort | explainable artificial intelligence to identify follicles that optimize clinical outcomes during assisted conception |
| url | https://doi.org/10.1038/s41467-024-55301-y |
| work_keys_str_mv | AT simonhanassab explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT scottmnelson explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT arturakbarov explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT arthurcyeung explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT artsiomhramyka explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT toulinalhamwi explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT rehansalim explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT alexanderncomninos explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT geoffreyhtrew explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT tomwkelsey explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT thomasheinis explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT waljitsdhillo explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception AT aliabbara explainableartificialintelligencetoidentifyfolliclesthatoptimizeclinicaloutcomesduringassistedconception |