J. Kather

Artificial intelligence in oncology: from isolated task-specific tools toward integrated decision support systems

Accelerating equitable cancer genomics and precision oncology in health care and research: a Lancet Oncology Commission.

The Commission developed a value-based resource-stratified implementation framework, a system-readiness assessment tool, a precision oncology workforce competency-based framework, a precision oncology monitoring and evaluation framework, and principles for responsible data sharing and health-system learning.

On-premise medical AI agents for reliable clinical decision-making.

A fully on-premise clinical agent that couples local operational control with a multi-perspective reliability framework to support selective autonomy is developed and evaluated, supporting a practical framework for institutionally governed clinical agents.

Machine learning for population-level risk prediction of future cholangiocarcinoma

It is shown that ML models integrating biliary-disease associated health records and Gamma glutamyltransferase can stratify risk of future CCA, and demonstrates the potential of data-driven models in personalised screening for hepatobiliary cancer.

Federated Learning for surgical vision in appendicitis classification: Results of the FedSurg EndoVis 2024 challenge.

The authors' analysis identifies temporal modeling as the architectural factor most consistently associated with generalization to the unseen center, although the effect is not uniform across metrics in the controlled baseline comparison, and both parameter-efficient baselines remain more costly than a constant predict...

Clinician expertise and prompt engineering enhance cancer information extraction in electronic health records by small language models.

This is the first study to benchmark SLMs on Italian EHRs and investigate the role of clinical expertise in prompt engineering, offering valuable insights for the future integration of SLMs into real-world clinical workflows.

Safety and security of large language models in healthcare

The Review examines rapid LLM adoption in clinical care, outlining emerging security and safety risks across development stages, key protective layers, clinically relevant threats and current mitigation responsibilities in a single integrated framework.