The next leap for AI scribes provides eyes in the clinic
Peer-Reviewed Publication
Updates every hour. Last Updated: 9-Jun-2026 17:15 ET (9-Jun-2026 21:15 GMT/UTC)
The introduction of vision-enabled artificial intelligence (AI) to medical scribes – the recording devices used by doctors to document meetings with patients in real-time – could increase the accuracy of patient notes and save valuable time for clinicians.Researchers found that a vision-enabled AI scribe, employing a combination of Google’s Gemini model and Ray-Ban Meta smart glasses, substantially improved the documentation accuracy of pharmacist-patient consultations and reduced omissions and errors in clinical notes.
A paper titled "Tip-enhanced sum frequency generation spectroscopy using temporally asymmetric pulse for detecting weak vibrational signals," published on February 19, 2026 by a research team from the Institute for Molecular Science (Atsunori Sakurai, Shota Takahashi, Tatsuto Mochizuki, and Toshiki Sugimoto) and Tohoku University (Tomonori Hirano and Akihiro Morita), has been selected as a "Featured Article" in The Journal of Chemical Physics, published by the American Institute of Physics (AIP), in recognition of its particularly noteworthy research.
The paper is available at the following URL: https://pubs.aip.org/aip/jcp/article/164/7/074202/3380428/Tip-enhanced-sum-frequency-generation-spectroscopy
Researchers analyzed more than 35,000 images of women’s clothing spanning from 1869 to today. Team measured features like hemlines, necklines and waistlines. Mathematical model shows styles tend to rise in popularity, fall out of favor and return to popularity roughly every 20 years.
Chimeric antigen receptor-invariant natural killer T cells, or CAR-iNKT cells, have shown promise in early studies, particularly against solid tumors that traditional CAR-T therapy struggles to treat. However, these cells often lose potency after delivery to a patient’s body. The UCLA team developed a system that functions like a charging station for these immune cells. Once implanted near a tumor, it attracts CAR-iNKT cells that have been engineered to recognize cancer. In the preclinical study, the platform demonstrated promising biocompatibility. The team is continuing to refine the system and explore how it could support additional cancer immunotherapies.