JMIR Medical Informatics

Federated learning (FL) enables multi-institutional model training on clinical text without sharing raw data; however, gradient inversion methods can reconstruct sensitive information from shared model updates. The extent of such privacy leakage in FL applied to radiology reports, and the role of tokenizer design, remains unclear.

The Global Burden of Disease (GBD) study provides the most comprehensive global burden estimates available, but translating GBD data downloads into structured analyses requires an integrated, multimethod workflow spanning trend estimation, changepoint detection, demographic decomposition, frontier benchmarking, and health inequality measurement. Existing tools cover portions of this workflow, but none integrate it end-to-end in a code-free interface, creating a substantial technical barrier, particularly for investigators in resource-limited settings.

The secondary use of electronic health record data requires robust privacy protection. k-Anonymity is widely used to enable data sharing by ensuring that each quasi-identifier combination occurs in at least k records; yet, its analytical impact on clinically meaningful structures remains insufficiently characterized, particularly for the combination of record suppression and microaggregation that arises when a numeric attribute lacks a natural generalization hierarchy. A further gap is that anonymization tools report internal information-loss values but do not signal the downstream distributional and inferential distortions these transformations introduce.

The clinical progression of chronic gastritis involves intricate temporal dependencies, which makes it difficult to capture both the dynamic trajectory of the disease and the underlying relationships among medical events using conventional methods.

Tuberculosis (TB) remains a major global health challenge despite prevention efforts. AI offers promising approaches to long-standing challenges in TB diagnosis, drug resistance detection, and case management; however, a systematic mapping of global research priorities and translational gaps in AI applications to TB is currently lacking.

Preoperative stratification for non–small cell lung cancer (NSCLC) necessitates separate evaluations of lymph node metastasis (LNM) to guide surgical decisions and of programmed death-ligand 1 (PD-L1) expression to inform immunotherapy.

Ambient AI technologies, commonly known as AI scribes, are transforming clinical practice by autonomously capturing patient-provider conversations and structuring them into clinical notes. Short-term studies suggest that ambient AI can significantly reduce documentation time and improve job satisfaction. However, as health care systems accelerate the adoption of these tools, the medical education community must seek to answer unresolved questions regarding their full impact on learners. The inevitable integration of ambient AI in teaching hospitals presents both transformative opportunities and significant challenges for medical education. This viewpoint discusses the potential benefits and risks of ambient AI in both undergraduate and graduate medical education and considers its impact on learning and clinical skills acquisition. Robust research studies are urgently needed to navigate this new frontier and ensure that the integration of ambient AI in the clinical learning environment ultimately enriches, rather than diminishes, the practice of medicine.

Perioperative computed tomography (CT) imaging is essential for detecting postoperative recurrence and metastasis in cancer patients. However, large-scale automated extraction of oncological outcomes from CT reports remains limited by the unstructured nature of report text and wide variability in reporting styles. Radiology reports frequently contain linguistic ambiguities, including negations, hedging, and expressions conveying diagnostic uncertainty (eg, “cannot exclude recurrence” or “possibly metastatic”). Manual review is labor-intensive and constrains consistent extraction at scale. The inability to systematically account for diagnostic uncertainty represents a major barrier to reliable automated surveillance systems.

No preview text available.

The Charlson Comorbidity Index (CCI) is widely used to quantify comorbidity burden in observational research. Applying it to real-world data requires accurate International Classification of Diseases–based mappings. The commonly used mapping does not reflect current German coding standards.

Personalized follow-up for type 2 diabetes may improve the alignment between monitoring intensity and patient needs, but operational approaches that jointly consider follow-up timing, modality, expected health benefits, and resource use remain limited.