In the modern world, the application of Artificial Intelligence (AI), machine learning, and biomedical data science has opened new possibilities for improving cancer research and early disease detection. Bangladeshi researcher Umme Habiba is contributing to this important field through her doctoral research in Mathematical and Statistical Sciences at The University of Texas Rio Grande Valley (UTRGV), USA.
Her research focuses on developing advanced statistical and machine learning frameworks for analyzing gene expression data, particularly for the early detection of breast cancer. Breast cancer remains a major public health concern across the world, including in Bangladesh, India, Pakistan, the United States, and many countries in Africa, where delayed diagnosis and unequal access to advanced diagnostic resources continue to increase the disease burden. According to the World Health Organization, breast cancer occurs in every country and was the most common cancer among women in 157 of 185 countries in 2022. Therefore, early detection remains one of the most important factors in improving treatment outcomes and reducing cancer-related suffering.
A Unique Synergy of Mathematics, Statistics, and Cancer Research
Umme Habiba’s work brings together mathematical modeling, statistical learning, machine learning, and biomedical data analysis. Her academic background in nonlinear partial differential equations, fractional differential equations, and complex systems has helped her build a strong foundation for studying high-dimensional and nonlinear biological data.
In her current research, she is applying this mathematical and statistical foundation to cancer-related gene expression data. Gene expression data show which genes are active or inactive in a biological sample. By analyzing these patterns, researchers can better understand how cancer develops and how early molecular changes may indicate disease risk.
AI-Based Gene Expression Modeling for Early Breast Cancer Detection
A major contribution of Habiba’s research is the development of machine learning-based gene expression models for early breast cancer detection. Her project aims to identify molecular patterns that may distinguish normal biological variation from early breast cancer-related changes.
To make this process more biologically meaningful, she is developing a Biologically Informed Super-Pathway Transformer Framework. In this framework, gene-level data are first mapped into known biological pathways. These pathways are then grouped into higher-level structures called super-pathways, which represent coordinated biological processes. A transformer-based AI model is then used to learn interactions among these pathways and super-pathways.
This approach moves beyond simple prediction. Instead of treating genes as isolated data points, Habiba’s model organizes them into meaningful biological structures. This may help researchers better understand which genes, pathways, and super-pathways contribute to early breast cancer risk.
Real-World Impact and Future Vision
The broader goal of Habiba’s research is to support earlier breast cancer detection and more interpretable biomedical decision-making. Early detection can help patients receive treatment at a more manageable stage of disease and may reduce the need for more aggressive and costly treatment.
Her work may also contribute to future cancer research efforts in countries such as Bangladesh, where delayed diagnosis and limited access to advanced diagnostic tools remain important challenges. By developing interpretable AI-based models for early breast cancer detection, Habiba’s research supports a broader vision of making precision oncology more data-driven, accessible, and globally relevant.
By combining mathematics, statistics, artificial intelligence, and cancer biology, Umme Habiba aims to develop computational tools that are not only accurate but also interpretable and useful for biomedical research.
Her research reflects a growing direction in modern healthcare: using AI not only to make predictions, but also to uncover meaningful biological insights that may support earlier diagnosis and improved patient outcomes.
