Increasing studies have captured the heterogeneity of the ageing process and introduced the concept of “biological age”. This review provides a comprehensive summary of currently identified ageing biomarkers in humans, spanning from molecular changes and imaging characteristics to clinical phenotypes with a contemporary perspective.

This review provides an overview of large-scale AI models, including language models (e.g., ChatGPT), vision-language models, and language-conditioned multiagent models, and discusses their potential applications in medicine, as well as their limitations and future trends. We also propose how large-scale AI models can be integrated into various scenarios of clinical applications.

With the development of medical image analysis, many successful cases have shown the clinical potential of Transformer. Thus, this paper collected 273 latest (2021–2022) works that based their frameworks on Transformer. To facilitate the readers, 76 public medical image datasets have also been listed. Considering the diversity of these 273 works, we organize this paper as the following sequences: task-modality-disease.

VEGF-A is a key factor mediating ocular neovascularization through their receptors. VEGF-A inhibitors are standard therapies for the treatment of ocular neovascular diseases, including ranibizumab, bevacizumab, aflibercept, conbercept, and faricimab. Although anti-VEGF therapy has achieved great success, many challenges and unmet needs exist. This perspective discusses the status of currently available anti-VEGF drugs, the evolving anti-VEGF formulations, and emerging antiangiogenic therapeutics for ocular neovascular diseases.

VDDB highlights 848 clinical vaccines and 199 clinical antibodies, as well as over 710,000 small molecules targeting 39 medically important viruses including severe acute respiratory syndrome coronavirus 2. VDDB also integrates 57 cell infection- and 117 target-based associated high-accuracy machine learning models to support various antiviral identification-related tasks, such as compound activity prediction, virtual screening, drug repositioning, and target fishing.

In this 20-year retrospective analysis of a nationwide database, people living with HIV who were exposed to nucleoside reverse transcriptase inhibitors (NRTIs) had a decreased risk of developing prediabetes or progressing from prediabetes to type 2 diabetes mellitus.

Ferredoxin 1 (FDX1) is a key gene in the process of Cuproptosis, and its expression level reflects the role of copper death in cell renal cell carcinoma (ccRCC) to a certain extent. For the first time, we used a combination of bioinformatics and experimental validation to explore the role of FDX1 in ccRCC prognosis, immunotherapy, and immune cell infiltration.

The structural imaging of the eye across various modalities, combined with artificial intelligences end-to-end models and feature extraction of ocular biomarkers, provides valuable insights into systemic diseases and their ophthalmic implications. This integrative approach significantly enhances the early detection of diseases, thereby improving patient care.

Multiple preclinical experiments and clinical trials have shown that oncolytic viruses (OVs) exhibit good antitumor activity in treating gliomas. This article summarizes the crucial clinical progress of various OVs in the treatment of glioma, the challenges faced by OVs in the treatment of glioma, and looks forward to the future development prospects of OVs.

The combined model based on Radscore, conventional image features, and clinical molecular characteristics had better performance in predicting progression-free survival than other models based on uniparameter or biparameter, which could be informative for individualized treatments. The predictive factors in the combined model include age, peritumoral edema, proportion necrosis, Satellites, Midline Displacement, WHO grades, IDH mutation, 1p/19q co-deletion, and Radscore.

Oridonin, a natural diterpenoid, exhibits broad-spectrum anticancer effects by targeting multiple oncogenic proteins mainly via Michael addition between its unsaturated ketone and the cysteines in the target proteins. Thus, oridonin and its derivatives hold the potential to be developed as multitargeting anticancer drugs.