AI-Driven Techniques for Disease Diagnosis and Control

Artificial intelligence (AI) is transforming how we understand, detect, and manage disease, from the molecular scale to global public health. With the explosion of multi-omics data, high-resolution imaging, electronic health records, wearable sensors, and real-time epidemiological data, there is an urgent need for robust, interpretable, and scalable AI methods that can turn this complexity into actionable insight. This Research Topic involves cutting-edge contributions at the intersection of AI, computational biology, and biomedical data science.

The aim of this Research Topic is to showcase how AI can support the full pipeline of disease management: early detection, precise diagnosis, patient stratification, prognosis prediction, therapy selection, monitoring, and large-scale surveillance and control. We are particularly interested in work that moves beyond proof-of-concept, demonstrating robustness, interpretability, generalizability, and clinical or public health relevance.

We welcome methodological, translational, and integrative studies that leverage AI-driven approaches to tackle challenges in:

o Molecular and systems-level understanding of disease mechanisms

o Multi-omics and data integration for precision diagnosis

o Clinical decision support for individualized treatment and risk prediction

o Epidemiological modeling, outbreak detection, and population-level control strategies

o Real-time disease monitoring using biosensors, mobile health, and wearable data

Submissions may include, but are not limited to:

1. AI and Multi-Omics for Disease Diagnosis Studies that apply machine learning or deep learning to genomics, transcriptomics, proteomics, metabolomics, microbiomics, or radiogenomics to identify diagnostic biomarkers, molecular signatures, or disease subtypes. We encourage contributions that integrate multiple data modalities and address batch effects, missing data, or data imbalance, as well as methods that explicitly model biological networks or pathways.

2. Clinical AI for Early Detection, Prognosis, and Decision Support Work that develops or evaluates AI models using clinical, imaging, or electronic health record data for early disease detection, risk stratification, or treatment response prediction. This includes models for rare diseases, complex multimorbid patients, and longitudinal trajectories. Studies that address interpretability, uncertainty quantification, fairness, bias mitigation, or model calibration in real-world clinical settings are especially welcome.

3. AI-Enhanced Disease Surveillance and Public Health Control Research that uses AI for forecasting disease spread, identifying emerging hotspots, designing interventions, or optimizing resource allocation at the population level. This includes integrating heterogeneous data such as environmental, mobility, social media, and public health surveillance data to improve outbreak detection and control strategies.

4. Novel Algorithms, Architectures, and Representations for Bioinformatics Methodological work proposing new AI models tailored to biological and biomedical data, such as graph neural networks for biological networks, foundation models for sequences or structures, generative models for synthetic data, and representation learning approaches for noisy, sparse, or high-dimensional bioinformatics datasets. Contributions that provide open-source tools or reproducible pipelines are encouraged.

5. Robustness, Interpretability, and Ethics in AI for Disease Control Studies that critically evaluate the reliability, explainability, transparency, and ethical implications of AI systems used in disease diagnosis and control. This includes benchmark studies, methods to improve robustness across populations and institutions, approaches to handle data drift, and frameworks for responsible deployment in clinical and public health contexts.

We invite original research articles, methods papers, reviews, mini-reviews, and perspectives. Interdisciplinary collaborations between computational scientists, clinicians, biologists, epidemiologists, and public health experts are strongly encouraged. Submissions should clearly describe data sources, validation strategies, and limitations, and, where possible, provide access to code and data to support reproducibility.

By bringing together AI-driven innovations for disease diagnosis and control, this Research Topic aims to advance the state of the art in bioinformatics and support the development of reliable, interpretable, and impactful tools for both precision medicine and population health.