Scilight Press

Aims:

AI in Health & Science (AIHS) is a gold open-access, peer-reviewed journal that aims to serve as a central hub for academic exchange, achievement translation, and innovative methodology dissemination in the interdisciplinary field of AI-enabled health and life, environmental and engineering sciences. Amid the paradigm shift driven by the deep integration of AI with healthcare, biomedicine, the environment and public health, the journal seeks to move beyond the limitations of one-way communication in traditional academic publishing and establish a robust multi-way feedback mechanism among journals, readers, and contributors. It focuses on bridging unexplored questions in basic science research, technical bottlenecks in clinical and industrial applications, and AI-powered innovative solutions, thereby fostering the deep integration and collaborative evolution of interdisciplinary knowledge.

The journal prioritizes technology implementation and paradigm innovation in AI-enabled health, environmental and engineering sciences, guiding the practical application of AI technologies—including algorithm models, simulation tools, data-driven methods, and interpretable AI—across key health scenarios such as disease diagnosis, treatment planning, patient monitoring, drug discovery, genomics, medical imaging, epidemiological forecasting, and personalized medicine. In doing so, it drives the transformation of the discipline from theoretical exploration toward practical clinical and public health validation.

Adhering to a problem-oriented academic philosophy, the journal explores the academic value and application potential of cutting-edge issues including health equity, data privacy, and clinical workflow integration. It also cultivates an open, shared, and collaborative academic ecosystem by lowering participation barriers for global scholars, clinical practitioners, data scientists, industry experts, and interdisciplinary researchers. AIHS is published quarterly online by Scilight Press.

Scope:

The scope of AI in Health & Science (AIHS) focuses on the interdisciplinary intersection of AI technology with health, life, environmental and engineering sciences, encompassing all key areas of AI-enabled research, application, and innovation. Specifically, it includes but is not limited to the following domains:

1) Basic Health Science Theory Exploration

Research on fundamental health and biomedical issues addressable through AI, including AI-driven modeling of disease pathogenesis and molecular mechanisms (e.g., protein folding, gene regulatory networks, host–pathogen interactions); data-driven discovery of novel biomarkers from multi-omics data (genomics, proteomics, metabolomics); AI-based causal inference in epidemiological studies; and theoretical exploration of complex physiological and pathological processes (e.g., immune system dynamics, neural circuit function) using deep learning and network medicine approaches.

2) Clinical and Experimental Technology Optimization

AI-driven optimization of diagnostic, therapeutic, and experimental methodologies, including machine learning–enhanced medical imaging (e.g., MRI, CT, ultrasound) reconstruction and interpretation; AI-assisted real-time analysis of clinical and laboratory data (e.g., electronic health records, continuous glucose monitoring, wearable sensor streams) to improve diagnostic accuracy and prognostic prediction; intelligent design of clinical trials (e.g., adaptive trial design, patient stratification via clustering algorithms); and optimization of laboratory workflows (e.g., automated image cytometry, high-content screening) through reinforcement learning and Bayesian optimization.

3) Clinical and Public Health Application Bottlenecks

AI-based solutions for pressing challenges in clinical practice and public health, such as multi-objective optimization of personalized treatment regimens (balancing efficacy, safety, adherence, and cost); AI-driven clinical decision support systems to reduce misdiagnosis and treatment delays in resource-limited settings; intelligent prediction of patient deterioration (e.g., sepsis, acute kidney injury) using time-series models in intensive care units; AI process simulation for optimizing hospital operations (e.g., bed allocation, surgical scheduling, emergency response); and large-scale epidemiological forecasting for infectious disease outbreak control and vaccine distribution.

4) Innovation in AI-Enabled Health Methods

Development and improvement of AI models and methodologies tailored for health, emvironmental, engineering and life sciences, including enhancing the generalizability and interpretability of graph neural networks (GNNs) and transformers for molecular property prediction, drug–target interaction, and patient outcome modeling; application of large language models (LLMs) and retrieval-augmented generation (RAG) in clinical documentation, literature synthesis, and patient communication; AI-assisted simulation integrating physiological models (e.g., pharmacokinetic/pharmacodynamic models, computational fluid dynamics for blood flow) with deep learning surrogate models; construction of high-quality, privacy-preserving health databases (e.g., via federated learning, synthetic data generation); and development of explainable AI (XAI) and uncertainty quantification methods for high-stakes medical decision-making.

The journal also welcomes non-AI-based solutions that demonstrate disruptive innovation (e.g., novel clinical paradigms, breakthrough experimental assays, fundamental advances in health economics or implementation science), provided they elaborate on potential integration pathways with AI technologies. The journal encompasses problem submissions, solution presentations, and academic discussions related to the above areas, promoting the scenario-based implementation of technical achievements and the collaborative development of the interdisciplinary field of AI in health and science.