Nonalcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease, and if it is accurately predicted, severe fibrosis and cirrhosis can be prevented. While liver biopsies, the gold standard for NAFLD diagnosis, is intrusive, expensive, and prone to sample errors, noninvasive studies are extremely promising but are still in their infancy due to a dearth of comprehensive study data and sophisticated multimodal data methodologies. This paper proposes a novel approach for diagnosing NAFLD by integrating a comprehensive clinical dataset with a multimodal learning-based prediction method. The dataset comprises physical examinations, laboratory and imaging studies, detailed questionnaires, and facial photographs of a substantial number of participants, totaling more than 6000. This comprehensive collection of data holds significant value for clinical studies. The dataset is subjected to quantitative analysis to identify which clinical metadata, such as metadata and facial images, has the greatest impact on the prediction of NAFLD. Furthermore, a multimodal learning-based prediction method (DeepFLD) is proposed that incorporates several modalities and demonstrates superior performance compared to the methodology that relies only on metadata. Additionally, satisfactory performance is assessed through verification of the results using other unseen data. Inspiringly, the proposed DeepFLD prediction method can achieve competitive results by solely utilizing facial images as input rather than relying on metadata, paving the way for a more robust and simpler noninvasive NAFLD diagnosis.

The study reveals that nicotinic acid (vitamin B3) significantly protects the liver during ischemia-reperfusion injury by suppressing ferroptosis through improved mitochondrial health. In mouse and cell models, pretreatment with nicotinic acid reduced oxidative stress, enhanced mitophagy and mitochondrial biogenesis, and lowered liver enzyme levels, offering a promising, low-cost therapeutic strategy for liver surgery and transplantation.

 Chimeric antigen receptor natural killer (CAR-NK) cell therapy is emerging as a promising next-generation immunotherapy with the potential to overcome key limitations of current chimeric antigen receptor T-cell therapy (CAR-T) treatments. 

A review paper by scientists at Imperial College London explores groundbreaking techniques that integrate interpersonal interactions within therapy and healthcare, focusing on multiplayer games that strengthen real-time social connections, alongside social robots and virtual agents designed to simulate human-like affective interactions.

The review paper, published on Dec. 16, 2025 in the journal Cyborg and Bionic Systems.

Adults age 65 and older who faced more stress before surgery were more likely to experience delirium, uncontrolled pain, and longer hospital stays — and more than 40% reported moderate to high distress. Duke School of Medicine researchers say it’s a major missed opportunity: a quick stress check before surgery could help prevent complications and improve recovery. 

Insilico Medicine (“Insilico”), a world-leading artificial intelligence (AI)-driven drug discovery company, today announced a multi-year research and development (R&D) collaboration with Servier, an independent international pharmaceutical company governed by a foundation. This strategic alliance is focused on identifying and developing novel therapeutics for challenging targets in the oncology space by leveraging Insilico's proprietary AI platform, Pharma.AI. 

Persistent pharmaceutical residues such as carbamazepine are increasingly detected in natural waters, posing long-term ecological and human health risks due to their resistance to conventional treatment processes.