The AID-ME trial demonstrates that an AI-powered clinical decision support system significantly improves remission rates and accelerates symptom improvement in moderate to severe major depressive disorder.
A study assessing the AI-based platform Diagnocat reveals high sensitivity but moderate specificity in detecting periapical radiolucencies on CBCT scans of non-root-filled molars, with decreased accuracy post-root treatment, underscoring th
A randomized controlled trial demonstrates that integrating deep language learning model (DLM) simulations into surgical training significantly improves history-taking skills and communication confidence among senior medical students.
A randomized controlled trial demonstrates that AI assistance moderately improves dentists’ accuracy in diagnosing periapical radiolucencies, mainly by reducing false positives, with significant benefits for junior clinicians and a sh
Machine learning models trained on clinical data improve prediction of coronary artery disease on CT scans compared to traditional risk scores, potentially guiding better resource utilization in cardiovascular care.
A 28-day RCT demonstrates that a conversational AI trained on a large language model effectively reduces mild depression and anxiety symptoms in young adults through dialog interventions integrated in short video apps.
A randomized trial demonstrates that leaving small non-neoplastic colorectal polyps in situ with AI-assisted optical diagnosis is as safe and effective as systematic removal, supporting less invasive colonoscopy strategies.
A novel deep learning model predicted retinal nerve fiber layer thickness from optic disc photos, enabling risk stratification for primary open-angle glaucoma in ocular hypertension patients, with baseline and longitudinal changes strongly
Deep learning models predicting RNFL thickness from optic disc photographs can identify ocular hypertension patients at higher risk for primary open-angle glaucoma, enhancing early risk assessment and monitoring disease progression.
スマートフォンを用いたスマートデジタル介入（Smart-T）は、低所得者成人において26週間の7日間禁煙率を有意に改善し、ニコチン置換療法と組み合わせた場合、標準的なQuitGuideアプリを上回ることが示されました。
The Smart-T smartphone intervention significantly improves 7-day smoking abstinence at 26 weeks in low-income adults, outperforming the standard QuitGuide app when combined with nicotine replacement therapy.
Artificial intelligence is dramatically transforming pharmaceutical R&D by accelerating drug discovery, formulation, and clinical trials, while presenting new opportunities and challenges for the industry, especially in China.
AI-enhanced ECG models, initially designed for specific cardiac diagnoses, reveal broader cardiovascular risk detection and prediction capabilities, challenging their use as condition-specific tools and supporting their role as comprehensiv
AI holds promise to alleviate peer review challenges, improving efficiency and quality while preserving human oversight to ensure fairness and integrity in scientific publishing.
A multidisciplinary Chinese team has developed an AI-driven MRI-pathology foundation model that enables accurate, non-invasive diagnosis and grading of prostate cancer, significantly improving clinical decision-making and reducing unnecessa
Mobile app-assisted screening in primary care settings identified new heart failure cases in one-third of at-risk patients, especially those with preserved ejection fraction, highlighting a promising route for early diagnosis.
A study comparing large language model-generated versus physician-generated discharge summaries found comparable quality and safety, suggesting AI-assisted documentation could reduce clinical burden without compromising patient care.
A randomized trial shows that personalized foot progression angle modifications significantly reduce medial knee pain and slow cartilage degeneration in medial compartment knee osteoarthritis.
A randomized trial assessing AI-generated study materials revealed no significant impact on pharmacy students’ objective structured clinical examination scores or test anxiety levels, highlighting the need for further research on long-term
A 16-week randomized trial demonstrates that AI chatbots with high-social-cue design significantly reduce depression and anxiety symptoms in college students compared to text-only chatbots, improving adherence, satisfaction, and therapeutic
Open language-specific specialty feeds and department pages.