Artificial intelligence and transforming cancer care
Abstract
Artificial Intelligence (AI) is reshaping oncology by addressing key limitations in traditional cancer care and enabling data-driven, personalized approaches from diagnosis to treatment. This review explores the transformative role of AI across the cancer care continuum, highlighting its contributions, challenges, and future directions. AI has significantly advanced cancer detection and diagnosis by improving the interpretation of medical imaging (CT, MRI, PET scans, digital pathology) and liquid biopsies, allowing for early and accurate identification of tumors and biomarkers. In genomics and molecular profiling, AI facilitates the analysis of large-scale sequencing data to uncover actionable mutations and support targeted therapy decisions. This review also examines AI-powered prognostic models that integrate clinical, genomic, and electronic health record data to predict outcomes such as survival rates and recurrence risks, allowing for more precise treatment planning. In the therapeutic landscape, AI aids in optimizing radiation dosing, guiding surgical interventions, and predicting individual responses to chemotherapy, immunotherapy, and targeted treatments, thereby reducing uncertainty and improving outcomes. Key limitations, such as data privacy concerns, algorithmic bias, model opacity, and integration hurdles are discussed, along with strategies to address them, including explainable AI, standardized validation, and clinician training. Looking ahead, innovations…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.