Advanced AI in Pediatric Hematology: From Diagnosis to Personalized Treatment

Pediatric hematology is a dynamic area of medicine focused on a wide array of blood-related disorders in children, encompassing malignant diseases like leukemia and lymphoma as well as non-malignant conditions such as inherited anemias, bone marrow failure, and coagulation abnormalities. This field faces unique challenges due to the biological complexity and diversity of pediatric disorders, the variability in age-specific presentations, and the lifelong clinical impact on young patients. Traditional diagnostic and therapeutic approaches are often limited by subjective interpretation, data fragmentation, and the high inter-patient variability. Recent advances in artificial intelligence (AI), particularly in machine learning, deep learning, and the integration of multimodal biomedical data, have begun to revolutionize this landscape. Emerging studies demonstrate AI’s ability to automatically classify blood smears, enhance the interpretation of flow cytometry, and extract actionable insights from high-dimensional genomic datasets, thereby offering unprecedented precision in diagnosis and risk profiling. However, key challenges remain, such as ensuring data standardization, algorithmic fairness, model explainability, and ethical deployment, as well as translating these advances into robust clinical tools that impact everyday care.This Research Topic aims to explore and accelerate the integration of AI across the full spectrum of pediatric hematology, from improved diagnostics to the personalization of therapeutic interventions. The main objectives are to examine the latest AI-driven methods designed for medical imaging, cytomics, genomics, and clinical workflows; to address the development and validation of predictive models for risk stratification, therapeutic response, and long-term outcome prediction; and to stimulate dialogue on the ethical, practical, and translational barriers to clinical implementation. Contributors are encouraged to present methodological innovations, translational research, and multidisciplinary approaches that demonstrate tangible improvements in health outcomes and quality of life for children living with hematological conditions.This Research Topic will primarily focus on studies assessing the application of advanced AI techniques within pediatric hematology, while also considering the broader context of integrating digital tools into clinical practice. Reviews of algorithmic models, clinical implementation pathways, and ethical regulations are equally welcome. To gather further insights in this evolving field, we welcome articles addressing, but not limited to, the following themes:• AI-enhanced interpretation of diagnostic data, including medical imaging, cytomics, and genomics• Predictive modeling for risk stratification, therapeutic response, and survival, leveraging multi-omics or real-world data• Development and implementation of AI-based decision support systems for personalized treatment and monitoring, including minimal residual disease and supportive care• Strategies for data standardization and interoperability in pediatric hematology AI applications• Research on algorithmic bias, fairness, model interpretability, and ethical frameworks• Case studies and clinical trials demonstrating successful translation of AI methods into patient care• Interdisciplinary collaborations between clinicians, data scientists, and translational researchersWe invite submissions of original research, reviews, systematic reviews, case reports, perspectives, and opinions. Topic editors: Liebin Zhao, Chen Li, Minghua Yang Source: https://www.frontiersin.org/research-topics/78640/advanced-ai-in-pediatric-hematology-from-diagnosis-to-personalized-treatment