The wBio-GenAI model achieved 98.21% accuracy and an AUC of 0.99 for heart failure classification using women's transcriptomic data, outperforming transformer, deep learning, and ML models.
Does a GenAI-based model improve the classification of heart failure in women using transcriptomic data compared to transformer, deep learning, and machine learning models?
A novel GenAI architecture (wBio-GenAI) demonstrated high accuracy (98.21%) and AUC (0.99) in classifying heart failure in women using transcriptomic data, outperforming traditional transformer, deep learning, and machine learning models.
Estimación del efecto: AUC 0.99
Backgrounds: Accurate early classification of heart failure (HF) in women is challenging due to sex-specific gene expression and disease patterns, which traditional models overlook. We propose a generative artificial intelligence (GenAI)-based model for the classification of HF patients using acute myocardial infarction (AMI) gene expression data. Objectives: This study aims to design and scientifically validate a novel GenAI framework, benchmarking it against transformer, deep learning (DL), and machine learning (ML) architectures for robust HF classification using women’s transcriptomic data. Methods: Total 26 models designed: A novel wBio-GenAI model, two transformers (Xmers): token diffusion gene (wTDG-Xmer) and neurotopology (wNT-Xmer), 19 deep learning models which include convolutional neural network (CNN)-, long short-term memory (LSTM)- and extended LSTM (xLSTM)-based models, and four ML. The models applied differential expression analysis (DEA) which identifies differentially expressed genes (DEGs) from the public women’s microarray GSE57345 samples. Quality control was conducted. The GenAI system was scientifically validated, benchmarked, and statistically tested for reliability. Results: The wBio-GenAI achieved an accuracy of 98.21% and an area-under-the-curve (AUC) of 0.99. The wBio-GenAI is better than the mean of two Xmers by 4.67%, the mean of 19 DLs by 5.16%, and the mean of four MLs by 15.07%. The proposed model meets the regulatory requirements of having a difference < 10% between seen and unseen paradigms. Conclusions: The wBio-GenAI architecture captures the complex transcriptomic patterns, improving HF classification in women and advancing women-specific precision cardiovascular care.
Tiwari et al. (Mié,) realizaron un estudio sobre la insuficiencia cardíaca en mujeres. Se evaluó el modelo wBio-GenAI frente a modelos de transformador, aprendizaje profundo y aprendizaje automático en precisión de clasificación de insuficiencia cardíaca y AUC (AUC 0.99). El modelo wBio-GenAI logró una precisión del 98.21% y un AUC de 0.99 para la clasificación de insuficiencia cardíaca utilizando datos transcriptómicos de mujeres, superando a los modelos de transformador, aprendizaje profundo y ML.