Aim

JAIHL publishes rigorous, reproducible research examining how artificial intelligence, machine learning, and data-driven methods can be developed, validated, and responsibly applied to challenges in healthcare, clinical practice, and the life sciences.

Scope

The journal welcomes original research articles, systematic reviews and meta-analyses, methodological and technical papers, short communications, and editorial perspectives that demonstrate methodological rigor, reproducibility, and clear relevance to biomedical or clinical practice.

Core Areas

• Medical AI & Diagnostics: Development, validation, and clinical evaluation of machine learning models for medical imaging, radiology, computer vision, early disease diagnosis, prognostic prediction, and digital pathology.
• Drug Discovery & Genomics: Machine learning, reinforcement learning, and transformer-based methods in structural biology, molecular design, target identification, genomics, proteomics, systems biology, and personalized medicine.
• Clinical Decision Support Systems: AI-driven frameworks for treatment recommendation, clinical workflow optimization, risk stratification, remote patient monitoring, and outcome prediction.
• Healthcare Data Science & NLP: Large language models and natural language processing applied to electronic health records, clinical text mining, knowledge graph construction, and multimodal healthcare data analytics.
• Public & Global Health AI: AI applications in epidemiological surveillance, population health modeling, health-systems logistics, health policy planning, and digital solutions addressing global health disparities.
• AI Ethics, Governance & Translational Research: Algorithmic fairness, explainable AI (XAI), dataset bias, transparency, accountability, data privacy and security, and regulatory pathways for clinical AI deployment.

Scope Boundary

Submissions must demonstrate a substantive application of artificial intelligence or computational/data-driven methods to a genuine healthcare, clinical, or life-sciences problem. Purely theoretical machine learning work with no biomedical application, and purely clinical or biological studies with no meaningful computational or AI component, are normally outside scope.

Authors should clearly identify the AI/ML method used, the clinical or biological problem addressed, the data used for training and evaluation, and, where applicable, how reproducibility and fairness were assessed.

Out-of-Scope Examples

• General machine learning benchmark studies with no healthcare or life-sciences application.
• Purely clinical studies in which AI or computational methods are incidental rather than central to the contribution.
• Commercial product promotion or vendor benchmarking lacking independent scientific methodology.