AI-based biomarkers for treatment decisions in oncology
Artificial intelligence (AI)-based biomarkers derived from routine clinical data could enhance the accessibility of personalized medicine by providing rapid and cost-effective alternatives to traditional molecular biomarkers.
AI-based decision support systems could automate time-consuming tasks, thereby reducing the workload of healthcare practitioners and supporting smaller oncological centers with limited access to expert tumor boards.
Large language models (LLMs) and multimodal integration of pathology, radiology, and clinical data have the potential to improve the accuracy of predictive biomarkers for patient stratification.
The implementation of AI-based biomarkers in clinical practice requires large-scale validation, prospective clinical trials, and medicoeconomic evaluations to demonstrate their trustworthiness and cost-effectiveness while extending personalized medicine to a broader population.
https://www.cell.com/trends/cancer/fulltext/S2405-8033(24)00280-2
