Artificial Intelligence and Big Data for Precision Medicine: A Review of Bioinformatics-Driven Healthcare Applications
6 affiliations
- 1California State Polytechnic University, Pomona, California, USA
- 2Pacific States University, Los Angeles, California, USA
- 3St. Francis College, Brooklyn, New York, USA
- 4Central Michigan University, Mount Pleasant, Michigan, USA
- 5Texas Tech University, Lubbock, Texas, USA
- 6The University of Texas at Tyler, Tyler, Texas, USA
Abstract
Healthcare is in the middle of a quiet but profound shift. Genomic sequencers, hospital information systems, wearables and imaging archives now generate data faster than clinicians can read it, and that flood is reshaping what “evidence-based care” means. We review more than forty recent studies that bring artificial intelligence (AI), machine learning and big-data analytics into bioinformatics and precision medicine, spanning oncology, drug discovery, cardiology, neurology, public-health surveillance and healthcare operations. Reported accuracies and AUCs range from roughly 80% in early drug-discovery pipelines to above 94% in deep-learning-based pancreatic and breast imaging. Yet our reading also suggests a more cautious story: many models still suffer from limited external validation, opaque decision logic and uneven access to high-quality multi-omics data. We propose a layered conceptual framework that connects heterogeneous data sources, federated and privacy-preserving pre-processing, predictive and explainable AI engines, and downstream clinical applications. The paper closes with a discussion of remaining barriers, interpretability, fairness, regulatory uncertainty and workflow integration and outlines research directions for the next several years.
Related
- Artificial Intelligence in Acute Stroke: Applications and Implications for the Portuguese National Healthcare System
- Editorial: Artificial intelligence and anti-cancer drugs: advancing discovery, personalization, and precision oncology
- Toward Precision Colorectal Cancer Screening: Integrating Clinical Risk Stratification, Molecular Biomarkers, and Artificial Intelligence
- Artificial Intelligence, Multi-Omics, and Multimodal Integration in Precision Radiotherapy for Head and Neck Cancer: From Biological Insights to Treatment Decisions
- Artificial Intelligence‐Assisted Automated Optical Coherence Tomography Analysis for Percutaneous Coronary Intervention Planning: From Plaque Analysis to Precision Lesion Preparation and Stent Optimization
BibTeX
@article{sami2026artificial,
title = {{Artificial Intelligence and Big Data for Precision Medicine: A Review of Bioinformatics-Driven Healthcare Applications}},
author = {Mohammad Abdus Sami and Md Lutfor Rahman and Zerin Akter Tanni and Zakia Sultana Munmun and Sabiha Nusrat and Bidhan Biswas},
journal = {Frontiers in Computer Science and Artificial Intelligence},
year = {2026},
month = may,
doi = {10.32996/fcsai.2026.5.6.7},
url = {https://doi.org/10.32996/fcsai.2026.5.6.7},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial Intelligence and Big Data for Precision Medicine: A Review of Bioinformatics-Driven Healthcare Applications
AU - Mohammad Abdus Sami
AU - Md Lutfor Rahman
AU - Zerin Akter Tanni
AU - Zakia Sultana Munmun
AU - Sabiha Nusrat
AU - Bidhan Biswas
PY - 2026
DA - 2026/05/09
JO - Frontiers in Computer Science and Artificial Intelligence
DO - 10.32996/fcsai.2026.5.6.7
UR - https://doi.org/10.32996/fcsai.2026.5.6.7
AB - Healthcare is in the middle of a quiet but profound shift. Genomic sequencers, hospital information systems, wearables and imaging archives now generate data faster than clinicians can read it, and that flood is reshaping what “evidence-based care” means. We review more than forty recent studies that bring artificial intelligence (AI), machine learning and big-data analytics into bioinformatics and precision medicine, spanning oncology, drug discovery, cardiology, neurology, public-health surveillance and healthcare operations. Reported accuracies and AUCs range from roughly 80% in early drug-discovery pipelines to above 94% in deep-learning-based pancreatic and breast imaging. Yet our reading also suggests a more cautious story: many models still suffer from limited external validation, opaque decision logic and uneven access to high-quality multi-omics data. We propose a layered conceptual framework that connects heterogeneous data sources, federated and privacy-preserving pre-processing, predictive and explainable AI engines, and downstream clinical applications. The paper closes with a discussion of remaining barriers, interpretability, fairness, regulatory uncertainty and workflow integration and outlines research directions for the next several years.
SN - 2978-8048
ER -