Pan Pan, Jin Chen, Tiantian Zhang, Cheng Haibo, Zhang Wanyi, Xiaobo Han, Han Xinjie, Hu Xingshuo, Yang Qingyun, Gu Hongjun, Liu Yuhong, Lixin Xie
ARDS (Acute Respiratory Distress Syndrome) poses significant challenges in critical care, particularly during the COVID-19 pandemic. The new global definition of ARDS includes some patients who are not previously considered to have ARDS. This study aims to look at the prognostic characteristics of these patients and develop a prediction model. This multicenter retrospective study included 5,214 patients from the Chinese People's Liberation Army General Hospital between December 2022 and February 2023. Patients were categorized into four groups based on the 2023 Global Definition and 2012 Berlin Definition: Global-definition-only ARDS + COVID-19, Global-definition-only ARDS−COVID-19, Berlin ARDS + COVID-19, and Berlin ARDS−COVID-19. Patient characteristics were analyzed using LASSO regression and Cox proportional hazards models to identify factors associated with 28-day mortality. A prognostic model was developed using key variables. Among ARDS patients, the Berlin ARDS + COVID-19 group had the highest mortality, while the observed 28-day mortality in the Global-definition-only ARDS + COVID-19 group was of a similar magnitude to that in the Berlin ARDS without COVID-19 group. LASSO selected seven candidate predictors: heart rate, lactate dehydrogenase, platelet count, total bilirubin, D-dimer, age, and antiviral therapy. In the multivariable Cox model, lactate dehydrogenase, age, and antiviral therapy were independently associated with 28-day mortality. Compared with patients aged <75 years, the HRs for 28-day mortality were 2.09 (95% CI 1.07–4.10) for those aged 75 to <85 years and 3.78 (95% CI 2.08–6.86) for those aged ≥85 years. Antiviral therapy was associated with a lower hazard of 28-day mortality (HR 0.58, 95% CI 0.40–0.84).The model's AUC for predicting 28-day mortality was 0.732 in the training set and 0.726 in the validation set. The 2023 Global ARDS definition holds significant value in identifying COVID-19 patients receiving high-flow nasal oxygen (HFNO), the Global definition may facilitate earlier identification of ARDS patients. Age is a critical risk factor, highlighting the need for heightened clinical attention in elderly patients. Antiviral therapy was associated with a lower hazard of 28-day mortality. Seven candidate predictors were selected by LASSO and evaluated in a Cox prognostic model for 28-day mortality.
The global myopia epidemic, especially among children, poses a major public health burden. Orthokeratology (OK) is an established intervention for slowing myopia progression, yet its conventional practice is constrained by variable treatment responses, an experience-dependent fitting process, and the need for vigilant long-term safety monitoring. Artificial intelligence (AI) offers an approach to enhance precision, efficiency, and accessibility across the entire OK care cycle. This review assesses AI applications in OK, encompassing pre-treatment efficacy prediction, AI-assisted lens fitting and automated fit assessment during treatment, and post-treatment safety monitoring with complication risk alert. Evidence indicates that AI models perform comparably to, and in some tasks surpass, human experts in predicting outcomes and determining optimal lens parameters. However, translation from research to routine practice is hindered by limited data quality and diversity, the opacity of complex algorithms, insufficient external validation, and unresolved ethical concerns. Progress depends on building large-scale, diverse datasets, developing interpretable and robust models, and fostering effective human-AI collaboration.
Pelvic lymph node metastasis is a major determinant of staging, recurrence risk, and treatment selection in cervical cancer, yet conventional magnetic resonance imaging criteria based on nodal size and morphology remain insufficient for occult nodal disease. We developed and temporally validated a multi-sequence magnetic resonance imaging radiomics-clinical fusion framework for pretreatment prediction of pelvic lymph node metastasis. This single-center retrospective-prospective cohort study included 200 women with histologically confirmed cervical cancer who underwent pretreatment pelvic magnetic resonance imaging. A retrospective training cohort ( n = 100) was accrued from January 2018 to December 2022, and a prospective temporal validation cohort ( n = 100) was accrued from January 2023 to December 2024. Reference standards comprised surgical histopathology in 154 patients and composite clinical-imaging adjudication in 46 patients. Primary tumors were manually segmented on axial T2-weighted imaging and registered to T1-weighted imaging, diffusion-weighted imaging/apparent diffusion coefficient maps, and dynamic contrast-enhanced imaging. An Image Biomarker Standardisation Initiative-compliant radiomics pipeline was used, including resampling, intensity discretization, reproducibility filtering, correlation pruning, and nested feature selection. Clinical, radiomics, clinical-radiomics, and deep fusion models were evaluated in the prospective cohort using discrimination, calibration, decision-curve, and reclassification analyses. The deep fusion model achieved the best validation discrimination, with an area under the receiver operating characteristic curve of 0.910 (95% confidence interval, 0.845–0.959) and an area under the precision-recall curve of 0.849. At the training-derived threshold, accuracy was 0.84, sensitivity was 0.79, specificity was 0.86, positive predictive value was 0.75, negative predictive value was 0.89, and Brier score was 0.125. Deep fusion outperformed the clinical model (area under the curve, 0.730; mean delta area under the curve, 0.180; P < 0.001) and improved reclassification relative to the clinical model. Multi-sequence magnetic resonance imaging radiomics-clinical fusion improved pretreatment risk stratification for pelvic lymph node metastasis in cervical cancer. External multicenter validation is warranted before clinical implementation. These preliminary single-center findings should be interpreted cautiously and require multicenter external validation before broad clinical implementation.
Shahid Mehmood, Abeer A. K. Alharbi, Mona Alkhattabi, Muhammad Adnan Khan, Muhammad Amir Khan
Automated classification of white blood cell (WBC) images may support cell-morphology workflows, but high accuracy alone does not establish clinical readiness. We developed an Uncertainty-Guided Deep Ensemble (UGDE) combining MobileNetV3-Large, EfficientNet-B0, and ShuffleNetV2 with Monte Carlo dropout, temperature scaling, split conformal prediction, and Grad-CAM. The primary dataset contained 16,027 single-cell images from 78 patients (33 with leukemia and 45 without leukemia). All stated development partitions were grouped by patient, and augmentation was restricted to the proper training subset. On the held-out internal test set (3,205 images from 16 patients), UGDE achieved approximately 99% image-level accuracy and macro-F1 of 0.99. Expected calibration error was 2.3% before and 0.8% after temperature scaling. Internal empirical conformal coverage was 94.2%, 89.7%, and 79.7% at nominal coverage levels of 95%, 90%, and 80%, respectively; these slight shortfalls are reported without claiming that the targets were met. External evaluation used 2000 Raabin-WBC images after mapping the nine model outputs to five shared leukocyte categories and yielded 94% descriptive accuracy. Grad-CAM examples were used as post-hoc visualizations and were not interpreted as causal explanations. These retrospective results support further evaluation of uncertainty-aware WBC image classification, but they do not demonstrate performance on whole slides, automated differential counts, prospective patients, or clinical workflows.
Natalia Katarzyna Mazur-Ejankowska, Anna Abacjew-Chmylko, Maciej Ejankowski, Dariusz Grzegorz Wydra, Magdalena Emilia Grzybowska
Cesarean section is among the most common surgical procedures worldwide, with rates exceeding 48% in some European countries and continuing to rise for both primary and repeat cases. Multiple cesarean deliveries have become routine in many developed countries. This trend has increased the incidence of intrapartum and long-term complications, particularly cesarean scar defects, which are symptomatic in up to 40% of affected women. A cesarean scar defect, also known as a uterine niche or isthmocele, is one of the most critical conditions in modern obstetrics and gynecology, with continuously increasing prevalence, as 56%–84% of women who undergo cesarean section develop a niche. Judicious indication for cesarean delivery and an appropriate uterine suturing technique are key factors in minimizing post-cesarean complications, including uterine niches. Uterine niche epidemiology and risk factors are widely investigated with partially contradictory conclusions. In this systematic review, a detailed analysis of surgery-related factors connected to uterine niche formation is presented. Aspects of uterine suturing technique, including the number of suture layers, locked or unlocked suturing, inclusion of the endometrium, and the choice of suture material, are compared. The aspect of single- and double-layer uterine closure remains under debate, as most studies do not show the superiority of either technique with regard to uterine niche incidence. Optimizing the hysterotomy surgical technique may decrease the rate of cesarean scar defects and their complications, including pelvic pain, abnormal uterine bleeding, dyspareunia, placenta accreta spectrum disorders, and cesarean scar pregnancies. All patients undergoing cesarean delivery should be screened for cesarean scar defects and informed about the potential complications of cesarean section.
