Medicine & Health

This review argues that immune reconstitution assessment after allogeneic hematopoietic cell transplantation is highly heterogeneous, which hampers the production of solid evidence and limits its potential use as a clinical endpoint, and that cross-center standardization is therefore needed, covering pre-analytical variables such as sample collection and handling as well as analytical procedures, drawing on the experience of international flow cytometry standardization consortia and achievable through existing working groups.

This review summarizes the established clinical framework for atopic dermatitis (AD) diagnosis alongside emerging tools intended to complement it—circulating and skin-derived biomarkers, minimally invasive tape stripping, the skin microbiome, instrumental barrier assessment, noninvasive biofluids, advanced optical imaging (reflectance confocal microscopy, optical coherence tomography and line-field confocal OCT), and artificial-intelligence and digital tools, with attention to special populations—concluding that clinical diagnosis remains the reference standard, that the experienced clinician still outperforms any single test, and that these tools are promising adjuncts though few are standardized or prospectively validated.

In 203 patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and curative-intent resection and were restricted to minor pathologic response, an AI-enabled pipeline segmented cancer and stroma from routine H&E whole-slide images and quantified spatial composition and configuration, finding that a fragmented, interface-rich tumor-stroma ecology was independently associated with shorter disease-free survival; two spatial risk models (cancer mean shape index plus stromal shape index variability, adjusted HR 1.71, P = 0.003; mean stromal patch area plus edge density, adjusted HR 2.19, P = 0.

This prospective shadow-mode study evaluated an FDA-cleared AI algorithm (Aidoc) for intracranial aneurysm detection on 3,856 consecutive brain CT angiographies (November 7 to December 19, 2023) with radiologists blinded to AI, finding that AI alone achieved higher sensitivity (0.846) than radiologists alone (0.718) with similar specificity (0.987 vs 0.985), radiologist-AI concordance was 96.3%, AI surfaced additional aneurysms missed by radiologists with a relative enhanced detection rate (rEDR) of 39% (55 AI-only true-positives per 140 radiologist true-positives), an AI:radiologist incremental detection ratio of 1.83 (55 of 30), a favorable gain-to-pain ratio (GPR) of 1.20 (55 of 46), and a number-needed-to-examine (NNE) of 70.

This paper identifies and names the phenomenon of "inference impersonation"—ambient AI scribes generate rather than transcribe clinical reasoning in the Assessment and Plan, producing text indistinguishable from transcription in the final note, so trainees may edit AI drafts instead of reasoning independently and risk never developing the judgment training exists to build; it proposes vendor-side learner-specific configurations and section-level transparency plus training-program responses such as reasoning-before-note, competency gating, and oral assessment.

Drawing on the diagnostic and therapeutic characteristics of otology, rhinology, laryngology, and head and neck oncology, this article summarizes representative applications of multimodal artificial intelligence in otolaryngology–head and neck surgery, analyzes translational issues including data standards and cross-modal alignment, missing modalities and model generalization, privacy protection and multicenter collaboration, interpretability, clinical evidence, and workflow integration, and proposes establishing specialty data standards suited to clinical practice in China, building a staged multicenter validation system, forming a human–machine collaboration model supervised by specialty physicians, and cautiously advancing general and specialty large models toward multimodal clinical ap

In this single-center retrospective study of 1,034 women aged 45-65 undergoing health checkups, 4,185 serial noncontrast chest CT examinations were used to derive AI-quantified T11 and T12 bone mineral density and build individual longitudinal trajectories, showing that women with low baseline bone status defined as mean T11-T12 AI-derived CT-BMD <= 128 mg/cm3 had smaller absolute BMD loss (10.82 vs 12.52 mg/cm3; P = 0.022) and a less negative T12 slope (-3.08 vs -3.91 mg/cm3/year; P = 0.011), while the greater relative decline seen in unadjusted analysis was not sustained after covariate adjustment or T11-only sensitivity analysis, and adding T11 BMD to clinical variables gave no clear incremental discrimination for rapid loss (AUC 0.708 vs 0.716; P = 0.128).