Reply to: Surgical scene understanding and the emerging challenge of independent validation in an industry-led AI ecosystem [0.03%]
述评：外科手术场景理解及以行业为主导的AI生态系统中独立验证所面临的挑战
Matthias Carstens,Shubha Vasisht,Zheyuan Zhang et al.
Matthias Carstens et al.
In this reply to MacAonghusa and Cahill, we reflect on fundamental validation challenges in AI-enabled surgical scene understanding and propose key priorities that academic, clinical, and industry stakeholders must collaboratively address t...
Surgical scene understanding and the structural validation gap in an industry-led AI ecosystem [0.03%]
外科手术场景理解及以行业为主导的人工智能生态系统中的结构验证差距
Pol MacAonghusa,Ronan A Cahill
Pol MacAonghusa
This Matters Arising builds upon the review by Carstens et al. highlighting methodological limitations within the academic surgical scene understanding (SSU) literature. Increasingly clinically deployed SSU occurs within commercial platform...
Author Correction: Clinically-guided models or foundation models? predicting cervical spondylotic myelopathy from electronic health records [0.03%]
作者更正：临床指导模型还是基础模型？从电子健康记录预测颈椎病性脊髓病
Salim Yakdan,Ben Warner,Zoher Ghogawala et al.
Salim Yakdan et al.
Published Erratum
NPJ digital medicine. 2026 Aug 8;9(1):610. DOI:10.1038/s41746-026-03043-0 2026
Promoting health equity through linguistic justice: mitigating embedded bias of large language models [0.03%]
通过语言正义促进健康公平：缓解大型语言模型的嵌入偏见
Weipeng Han,Sol Richardson,Jiming Zhu et al.
Weipeng Han et al.
The application of Large Language Models (LLMs) in healthcare prompts critical reflection on the impact of linguistic justice on health equity. Disparities in data availability across languages during the training and evaluation phases of L...
Developing interactive learning interfaces for teaching AI in health professions education using generative AI tools [0.03%]
利用生成式人工智能工具开发交互式学习界面以在健康专业教育中教授人工智能技能培训
Peter Washington,Anoop Muniyappa,Chen Liang et al.
Peter Washington et al.
Health professions education (HPE) must now equip students to use artificial intelligence (AI) tools safely. We offer an instructional design strategy for HPE educators aiming to teach fundamental AI concepts to non-technical audiences: usi...
Prehospital Injury Severity Estimate (PHISE) matches in-hospital trauma scores when embedded in AI models [0.03%]
嵌入人工智能模型中的院前损伤严重程度评估（PHISE）与院内创伤评分相匹配
Manuel Sigle,Andreas Goldschmied,Meinrad Gawaz et al.
Manuel Sigle et al.
Trauma severity scores such as the Injury Severity Score (ISS) and New Injury Severity Score (NISS) are widely used for trauma benchmarking, risk stratification and outcome prediction, but rely on diagnostic imaging unavailable in the preho...
Interpreting the clinical utility and generalizability of a multitask perioperative prediction model [0.03%]
多任务麻醉预测模型的临床效用和普适性的解读
Xiao-Min Wo,Guo-Ming Zhang
Xiao-Min Wo
This Matters Arising comments on Yoon et al.'s multitask gradient boosting model for predicting acute kidney injury, postoperative respiratory failure and in-hospital mortality after non-cardiac surgery. We ask for clarification on the clin...
D Stein,D Bobrovskiy,M Stede et al.
D Stein et al.
Language is central to psychosis, making it a key focus for both clinical evaluation and research. Many automated linguistic metrics have been developed to analyze speech in psychosis, yet few studies have compared them systematically. In t...
Reply to 'Interpreting the clinical utility and generalizability of a multitask perioperative prediction model' [0.03%]
对“多任务围手术期预测模型的临床效用和普遍性解读”的回复
Hyun-Kyu Yoon,Hyung-Chul Lee,Hyeonhoon Lee
Hyun-Kyu Yoon
We thank Wo and Zhang for their comments on our multitask prediction model for postoperative complications, including postoperative acute kidney injury, respiratory failure, and in-hospital mortality. Here, we responded by mapping specific ...
Reply to: Clinician engagement modifies effectiveness of AI enabled ECG screening [0.03%]
关于：临床医师的参与影响基于人工智能的心电图筛查的有效性
Alberto Calleri,Yigit Yazarkan,Douglas A Simonetto
Alberto Calleri
Chen highlights the importance of distinguishing algorithmic performance from deployment stability in AI-enabled screening. Drawing on a post hoc analysis evaluating AI-enabled ECG screening for chronic liver disease in primary care, we dis...