ABSTRACT
Various studies have emphasized the importance of identifying the optimal Trigger Timing (TT) for the trigger shot in In Vitro Fertilization (IVF), which is crucial for the successful maturation and release of oocytes, especially in minimal ovarian stimulation treatments. Despite its significance for the ultimate success of IVF, determining the precise TT remains a complex challenge for physicians due to the involvement of multiple variables. This study aims to enhance TT by developing a machine learning multi-output model that predicts the expected number of retrieved oocytes, mature oocytes (MII), fertilized oocytes (2 PN), and useable blastocysts within a 48-h window after the trigger shot in minimal stimulation cycles. By utilizing this model, physicians can identify patients with possible early, late, or on-time trigger shots. The study found that approximately 27 % of treatments administered the trigger shot on a suboptimal day, but optimizing the TT using the developed Artificial Intelligence (AI) model can potentially increase useable blastocyst production by 46 %. These findings highlight the potential of predictive models as a supplementary tool for optimizing trigger shot timing and improving IVF outcomes, particularly in minimal ovarian stimulation. The experimental results underwent statistical validation, demonstrating the accuracy and performance of the model. Overall, this study emphasizes the value of AI prediction models in enhancing TT and making the IVF process safer and more efficient.
ABSTRACT
Assessing the viability of a blastosyst is still empirical and non-reproducible nowadays. We developed an algorithm based on artificial vision and machine learning (and other classifiers) that predicts pregnancy using the beta human chorionic gonadotropin (b-hCG) test from both the morphology of an embryo and the age of the patients. We employed two high-quality databases with known pregnancy outcomes (n = 221). We created a system consisting of different classifiers that is feed with novel morphometric features extracted from the digital micrographs, along with other non-morphometric data to predict pregnancy. It was evaluated using five different classifiers: probabilistic bayesian, Support Vector Machines (SVM), deep neural network, decision tree, and Random Forest (RF), using a k-fold cross validation to assess the model's generalization capabilities. In the database A, the SVM classifier achieved an F1 score of 0.74, and AUC of 0.77. In the database B the RF classifier obtained a F1 score of 0.71, and AUC of 0.75. Our results suggest that the system is able to predict a positive pregnancy test from a single digital image, offering a novel approach with the advantages of using a small database, being highly adaptable to different laboratory settings, and easy integration into clinical practice.
Subject(s)
Algorithms , Embryo Transfer/methods , Fertilization in Vitro/methods , Machine Learning , Neural Networks, Computer , Oocytes/cytology , Adult , Bayes Theorem , Female , Humans , Pregnancy , Pregnancy Outcome , Pregnancy TestsABSTRACT
Resumen OBJETIVO: Evaluar los desenlaces de una estrategia combinada para fertilización in vitro: mínima estimulación ovárica, diagnóstico genético preimplantación para aneuploidias y transferencia de un solo embrión. MATERIALES Y MÉTODOS: Estudio de cohorte, retrospectivo, efectuado en dos centros de reproducción de México, en un periodo de tres años. Se incluyeron pacientes entre 25 y 45 años, en protocolo de fertilización in vitro, con mínima estimulación, diagnóstico genético preimplantación para aneuploidias (PGT-A) y transferencia de embrión único. El diagnóstico genético preimplantación se estableció mediante microarreglos y secuenciación de nueva generación (NGS). Para el análisis estadístico se integraron 5 grupos, según la edad de las pacientes: menores de 35 años; 35 a 37 años; 38 a 40 años; 41 a 42 años; y mayores de 42 años. Mediante estadística descriptiva se analizaron las variables numéricas y categóricas. RESULTADOS: Se analizaron 175 ciclos, en 125 pacientes (edad promedio: 39 años ± 5). Se obtuvieron, en promedio, 5 óvulos por ciclo. La tasa de fertilización fue de 86.5% y la de blastocisto por óvulo fertilizado de 50.7%. Se tomó biopsia para diagnóstico genético preimplantación para aneuploidias a 404 embriones. La tasa general de euploidia fue de 33%. Se efectuaron 69 transferencias de embrión único, con una tasa de embarazo por transferencia de 71%. La tasa de nacimiento por transferencia fue de 60.8% (42 nacimientos). CONCLUSIONES: La combinación de mínima estimulación, diagnóstico genético preimplantación para aneuploidias y transferencia de embrión único, es un procedimiento adecuado para alcanzar una tasa de nacimiento alta.
Abstract OBJECTIVE: To evaluate results of a combined approach in IVF, using minimal stimulation, preimplantation genetic testing for aneuploidy, and single blastocyst transfer. MATERIALS AND METHODS: Retrospective cohort study over a three years' period in two fertility centers in Mexico. A total of 125 patients were included, between 25 and 45 years old, with minimal stimulation IVF, preimplantation genetic testing for aneuploidy (PGT-A) and single euploid embryo transfer. PGT was performed using microarrays and next generation sequencing (NGS). RESULTS: A total of 175 cycles (mean age: 39 years old) were analyzed in 125 patients. On average, five eggs were collected per cycle; fertilization rate was 86.57%; blastocyst rate was 50.7% per fertilized egg. Only 33% of embryos were euploid. Pregnancy rate per transferred embryo was 71%. Live birth rate was 60.8% (42 births). CONCLUSIONS: A combination of minimal stimulation, PGT-A and single blastocyst embryo transfer can yield a high live birth rate.