Iullia Diakova

ART-IVF Clinic, Moscow

Title: Advancing Reproductive Medicine Through Integrated AI Solutions

---

Biography

Iullia Diakova is a highly skilled Clinical Embryologist with extensive experience in Assisted Reproductive Technologies (ART) and In Vitro Fertilization (IVF). Since 2020, she has been an integral part of the ART-IVF Clinic in Moscow, where she has successfully performed over 4,000 IVF procedures, achieving remarkable success rates.

Beyond her clinical expertise, Iullia is an Expert and Traveling Embryologist, specializing in embryo biopsy for Preimplantation Genetic Testing (PGT) across various IVF clinics in Russia and internationally. She holds a key role as a PGT specialist at FirstGenetics Lab and the Genetics and Reproductive Center “Genetico” in Moscow, contributing to advancements in genetic testing and reproductive medicine.

In addition to her hands-on work, Iullia actively consults and provides technical support to embryologists, guiding them in embryo biopsy and IVF techniques as a laboratory supervisor. She is also involved in external audits to ensure laboratory compliance with regulatory standards and maintain the highest level of testing accuracy and consistency.

Her dedication to the field is further demonstrated through her contributions to scientific conferences and training courses, particularly in collaboration with CooperSurgical Corporation, where she shares her expertise to enhance the skills of fellow professionals in reproductive medicine.

Abstract

The integration of Kolmogorov-Arnold neural networks (KAN) architectures with transformer models presents a cutting-edge approach for complex decision-making tasks, in in vitro fertilization (IVF) treatment. By incorporate domain-specific rules and key performance indicators (KPIs) alongside the powerful representation learning capabilities of transformers, which utilize attention mechanisms and long-range dependencies, this approach offers an accurate and explainable framework for IVF outcome prediction with conformal calibration to obtain real success probabilities in individual treatment cycle.

We conducted a retrospective analysis of 15,779 IVF protocols. The neural network pipeline was designed in DataSpell 2024.2.1 IDE with Tensorflow 2.15.0 and Keras 2.14.0 libraries with 580000 learning parameters for transformer classifier. An analysis of prediction errors was conducted using area under the receiver operating characteristic curve (AUC), precision-recall curve (PRC), Brier score, Expected calibration error (ECE), and Maximum calibration error (MCE).

Our new predictive pipeline demonstrated AUC = 0.73 ± 0,02, PRC = 0.68, Brier score = 0,20 with ECE = 0,06 and MCE = 0,12 after calibration in patient’s subpopulations from 6 different countries. Its combination with the KPI assessment system not only provides a real probability of pregnancy based on laboratory data but also explains which factors from the patient’s history or laboratory indicators contributed most to the prediction. Our new augmented intelligence shows similar performance to ultra-precise neural networks designed for static image analysis (AUC = 0.74), including next-generation neural networks based on genetic algorithms (AUC = 0.77), and complex CNN+MLP models (AUC = 0.75–0.79) but with lower errors in predictions.