Kabuki Syndrome Diagnosis and Analysis using PhenoBCBERT and PhenoGPT

DOI

10.2991/978-94-6463-831-8_13How to use a DOI?

Keywords

Generative AI; Natural Language Processing (NLP); PhenoBCBERT; PhenoGPT Transformer Models

Abstract

Alterations in the KMT2D or KDM6A genes, which play a role in regulating gene expression, lead to Kabuki syndrome, a rare genetic disorder. Individuals with Kabuki syndrome often face learning difficulties, ranging from mild to severe intellectual disabilities, as well as developmental delays. The diagnosis can be confirmed through genetic testing. This research operates at the convergence of genomics, rare disease diagnostics, natural language processing (NLP), and machine learning, with the goal of enhancing the diagnosis of Kabuki Syndrome (KS). Traditional diagnostic methods, which often depend on expensive genetic testing, can be slow and may produce inconclusive findings. By utilizing generative AI models such as phenoBCBERT and PhenoGPT, this study harnesses advanced NLP to extract and interpret phenotypic data directly from clinical documentation. PhenoBCBERT is specifically designed to identify phenotypic terms related to KS, whereas PhenoGPT synthesizes patient narratives to create potential diagnostic recommendations. This AI-powered strategy aids clinicians by delivering quicker and more precise diagnostic insights, minimizing the dependence on genetic tests, and improving early detection. The study illustrates the capabilities of generative AI in diagnosing rare diseases. Through thorough evaluation on clinical datasets, our method shows significant enhancements in both diagnostic sensitivity and specificity, especially in differentiating KS from phenotypically similar disorders. Furthermore, our models offer transparency by emphasizing the specific phenotypic characteristics that contribute to each diagnostic recommendation, which could assist clinicians in their decision-making process. Our results with accuracy of 92.4% suggest that incorporating phenoBCBERT and PhenoGPT into clinical practices has the potential to improve the early detection and diagnosis of KS, potentially speeding up interventions and resulting in better outcomes for patients. This study highlights the promise of generative AI in the realm of rare disease diagnostics and sets the stage for future applications in other intricate genetic disorders.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nikam Jagruti
AU  - Kalpana Thakre
AU  - Girija Chiddarwar
AU  - Smita Chaudhary
PY  - 2025
DA  - 2025/08/31
TI  - Kabuki Syndrome Diagnosis and Analysis using PhenoBCBERT and PhenoGPT
BT  - Proceeding of the 1st International Conference on Lifespan Innovation (ICLI 2025)
PB  - Atlantis Press
SP  - 101
EP  - 109
SN  - 2468-5739
UR  - https://doi.org/10.2991/978-94-6463-831-8_13
DO  - 10.2991/978-94-6463-831-8_13
ID  - Jagruti2025
ER  -