Aneuploid embryos as a proposal for improving Artificial Intelligence performance
Guell, E.; Esquerra, M.; Vives, A.; Mladenova, M.
Show abstract
RESEARCH QUESTIONCould we improve the performance of Machine Learning algorithms by using aneuploid embryos instead of non-implanted embryos as the contrary reference to Live-Birth embryos? DESIGNA single-center retrospective analysis of 343 embryos through 3 ML algorithms, based on manually annotated morphokinetics from Day 1 to Day 3. Two datasets were built including the same Live-Birth embryos (117). Dataset A included 123 non-implanted embryos, while Dataset B included 103 aneuploid embryos. V-Fold Cross-Validation was performed for each dataset and algorithm and the Area Under the Curve (AUC) was registered. RESULTSAUC for Dataset A did not reach 0.6 for any of the algorithms; while AUC values for "Dataset B" surpassed 0.7. According to this, different morphokinetic patterns were detected by Machine Learning algorithms. CONCLUSIONSAlgorithms minor performance with non-implanted embryos may be due to an increased Label Noise effect, suggesting that including aneuploid embryos could be more appropriate when building predictive algorithms for embryo viability. Machine Learning algorithms results were improved when aneuploid embryos were taken into consideration.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Genome-wide identification of a regulatory mutation in BMP15 controlling prolificacy in sheep 89%
- Prenatal Diagnosis of Fetuses with Increased Nuchal Translucency by Genome Sequencing Analysis 87%
- Improving short and long term genetic gain by accounting for within family variance in optimal cross selection 87%
Similar papers in this journal
Similar papers in this journal
- Serum hormone levels in infertile women between conceived with and without hormone replacement therapy: Safety of estradiol and progesterone replacement therapy in frozen-thawed embryo transfer cycles for breast cancer survivors. 90%
- Effect of xenon and argon inhalation on erythropoiesis and steroidogenesis: a systematic review 87%
- Cloud-controlled microscopy enables remote project-based biology education in Latinx communities in the United States and Latin America 86%
Similar papers in this journal
- Production of common carp donor-derived offspring from goldfish surrogate broodstock 91%
- Who is the best surrogate for germ stem cell transplantation in fish? 91%
- Providing recombinant gonadotropin-based therapies that induce complete oogenesis and produce viable larvae from an immature teleost, flathead grey mullet (Mugil cephalus) 91%
Similar papers in this journal
- Oxygen level alters energy metabolism in bovine preimplantation embryos 94%
- Targeted gene expression profiling for accurate endometrial receptivity testing 92%
- Recombinant Fsh and Lh therapy for spawning induction of previtellogenic and early spermatogenic arrested teleost, the flathead grey mullet (Mugil cephalus) 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.