Keyword: Machine Learning

ABSTRACT: Cancer behaves as a dynamic evolutionary system, whereas conventional tissue biopsy and imaging provide incomplete temporal information about how a tumour is changing. This review critically examines whether longitudinal liquid-biopsy measurement, combined with artificial intelligence (AI), can move oncology from tumour monitoring toward genuine prediction of cancer evolution and treatment resistance. We synthesise mechanistic, clinical, and computational evidence on circulating tumour DNA, circulating tumour cells, extracellular vesicles, and multimodal liquid-biopsy platforms, together with AI approaches applied to longitudinal cancer data, drawing on landmark and recent studies across colorectal, lung, breast, and ovarian cancer. Current evidence distinguishes three increasingly demanding tasks: early detection, longitudinal monitoring, and genuine forecasting. Longitudinal circulating tumour DNA analysis can detect molecular progression and emerging resistance mutations months before radiographic progression, and machine-learning models can stratify survival using serial biomarker metrics; however, most published "AI prediction" studies demonstrate earlier detection or prognostic association rather than prospectively validated forecasting of a future, patient-specific event. Biological variability in tumour shedding, analytical noise, small and irregularly sampled longitudinal datasets, overfitting, data leakage, weak external validation, and limited interpretability constrain the transition from detection to actionable prediction. AI-enabled liquid biopsy has genuine potential to forecast tumour trajectories, but current evidence is considerably stronger for molecular monitoring and early detection than for prospectively validated, clinically actionable prediction. Realising this potential will require standardised assays, prospective longitudinal cohorts with predefined prediction horizons, rigorous external and temporal validation, calibrated and interpretable models, and interventional trials linking predictions to treatment decisions before AI-enabled liquid biopsy can be considered ready to guide clinical care.

ABSTRACT: Hematologic diagnostics has evolved considerably over the past decades, progressing from reliance on manual microscopic examination to increasingly sophisticated digital and artificial intelligence (AI)-enabled diagnostic systems. This transformation has been driven by the growing complexity of hematologic diseases, advances in molecular medicine, and the need for faster, more standardized, and more reproducible diagnostic approaches. AI has emerged as a transformative technology capable of enhancing image interpretation, automating routine laboratory processes, and integrating diverse sources of diagnostic information to support precision medicine. This narrative review critically examines the evolution of hematologic diagnostics from conventional microscopy to AI-assisted practice and explores how AI is reshaping diagnostic workflows across the hematologic diagnostic pathway. Current evidence indicates that AI has substantially improved blood smear analysis, bone marrow evaluation, disease detection and classification, and clinical decision support while reducing observer variability and improving laboratory efficiency. Moreover, the integration of morphology with flow cytometry, cytogenetics, genomics, laboratory findings, and clinical metadata is redefining hematologic diagnosis as a multidimensional, patient-centered process. Despite these advances, important challenges remain, including limited external validation, dataset heterogeneity, algorithm transparency, interoperability, regulatory oversight, and equitable implementation across diverse healthcare settings. The review further identifies key evidence gaps and proposes the Precision Hematology Evolution Framework (PHEF) as a conceptual model illustrating the transition from morphology-based diagnosis to AI-enabled precision hematology. Collectively, the evidence suggests that AI is best viewed as an enabling technology that augments expert clinical interpretation rather than replacing it. Continued multidisciplinary collaboration, rigorous validation, and responsible governance will be essential to fully realize the promise of AI in delivering more accurate, personalized, and equitable hematologic care.

ABSTRACT: Precision medicine aims to deliver the right treatment to the right patient at the right time, yet its widespread clinical adoption remains limited by challenges in accurate diagnosis, slow drug development processes and the difficulty of translating complex biological data into actionable clinical decisions. Conventional diagnostic and therapeutic approaches often rely on population averages, which can overlook individual genetic, molecular and clinical differences, leading to variable treatment responses and high drug development failure rates. In recent years, Artificial Intelligence (AI) and Machine Learning (ML) have gained increasing attention as clinical support tools capable of analyzing complex and large-scale biomedical data, improving diagnostic accuracy, accelerating drug development and enabling more personalized approaches to patient care. This study presents a systematic literature review conducted in accordance with the PRISMA guidelines, examining recent evidence on how AI and ML act as catalysts for precision medicine, particularly in diagnosis and drug development. Peer-reviewed studies published between 2019 and 2025 were systematically identified from major academic databases and screened using predefined inclusion and exclusion criteria. The selected studies were analyzed to assess clinical applications, AI techniques employed and their implications for personalized healthcare and pharmaceutical innovation. The findings indicate that AI and ML significantly enhance diagnostic accuracy through applications in medical imaging, genomics and electronic health record analysis, supporting earlier and more precise disease detection. In drug development, AI-driven methods improve target identification, lead optimization, toxicity prediction and clinical trial design, contributing to reduced development time and cost. Furthermore, the integration of multi-omics and clinical data through AI enables more personalized treatment strategies, improving therapeutic selection and dosing. This study concludes that AI and ML are powerful catalysts for precision medicine and capable of bridging the gap between complex biomedical data and clinical decision-making. With appropriate validation, explainable models and robust ethical and regulatory frameworks, these technologies have the potential to accelerate drug development and support clinicians in delivering more accurate diagnoses, more effective treatments and safer patient-centered, precision-based healthcare.