The objective of this study is to evaluate the combined prognostic values of 18 F-fluorodeoxyglucose ( 18 F-FDG) PET and computed tomography (CT)-derived entropy-based heterogeneity features from hybrid PET/CT scanner using machine learning in patients with lung adenocarcinoma undergoing curative surgery. Presurgical 18 F-FDG PET/CT from 131 patients with lung adenocarcinoma were divided into training ( n = 92) and temporal validation ( n = 39) cohorts. In the training cohort, we integrated entropy-based heterogeneity features from 18 F-FDG PET/CT for disease-free survival (DFS) prediction using machine learning approach. The predictive value of clinical variables and 18 F-FDG PET/CT-based machine learning for DFS was examined using Cox regression analyses, and independent prognosticators were used to develop the survival prediction model. The model was then tested in the temporal validation cohort. In the training cohort, 18 F-FDG PET/CT-based machine learning, female sex, and pN status independently predicted DFS. The model, incorporating these predictors significantly predicted DFS in the training (hazard ratio = 1.483, P < 0.001) and validation cohorts (hazard ratio = 1.753, P < 0.001). This model outperformed traditional staging system in both cohorts (c-indices = 0.717 vs. 0.621 in training; and 0.728 vs. 0.644 in validation). The model also predicted overall survival in both cohorts (hazard ratio = 1.370, P < 0.001 in training; hazard ratio = 1.574, P = 0.017 in validation). Our preliminary results suggest that integrating prognostic values from 18 F-FDG PET and CT-based heterogeneity features with clinical prognosticators is feasible and may support personalized treatment strategies for patients with resectable lung adenocarcinoma.

Machine learning survival analysis for predicting kidney disease progression in patients with acute kidney injury undergoing continuous kidney replacement therapy: An analysis of the LINKA database.

This study aimed to explore factors associated with the likelihood of surgical resection after triple-combination conversion therapy in patients with initially unresectable hepatocellular carcinoma (uHCC) and to develop an exploratory predictive model. A retrospective analysis was conducted using clinical data from 210 patients with uHCC who underwent triple-combination conversion therapy at Sichuan Cancer Hospital between January 2022 and January 2025. Patients were randomly assigned to a training cohort (n=147) and a validation cohort (n=63) in a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) regression was applied to screen candidate predictors, followed by multivariate logistic regression to identify factors associated with surgical conversion. A nomogram was constructed based on these variables, and its discriminative ability, calibration, and potential clinical utility were internally assessed using receiver operating characteristic (ROC) analysis, calibration plots, the Hosmer-Lemeshow test, and decision curve analysis (DCA). Among the 210 patients, 47 (22.4%) successfully underwent conversion and radical resection. Multivariate logistic regression analysis suggested that lower tumor burden score (TBS; OR=0.663), lower neutrophil-to-lymphocyte ratio (NLR; OR=0.572), lower C-reactive protein-to-albumin ratio (CAR; OR=0.057), and absence of cirrhosis (OR=0.289) were associated with a higher likelihood of successful surgical conversion (P<0.05). The nomogram showed moderate to good discriminative performance, with areas under the ROC curve (AUCs) of 0.850 (95% CI: 0.784-0.915) in the training cohort and 0.871 (95% CI: 0.783-0.962) in the validation cohort. Calibration plots and decision curve analysis provided descriptive information regarding model performance within the study cohort. The proposed nomogram, incorporating TBS, NLR, CAR, and cirrhosis status, represents an exploratory tool for estimating the probability of surgical conversion following triple-combination therapy in patients with uHCC. While the model may provide supplementary information to support clinical assessment and patient stratification, further multicenter and prospective studies are required to externally validate and refine its performance before broader clinical application.

A machine learning-driven app for predicting the need for post-operative respiratory support in liver transplant recipients.

Idiopathic Pulmonary Fibrosis (IPF) is a progressive and fatal interstitial lung disease characterized by excessive extracellular matrix (ECM) deposition and tissue stiffening. Matrix stiffness is a key driver of fibrosis, yet diagnostic biomarkers directly linked to this physical property are lacking. This study aimed to identify robust matrix stiffness-related diagnostic biomarkers and potential therapeutic targets for IPF using an integrated machine learning approach. Gene expression profiles were obtained from the GEO database (Training set: GSE33566; Validation set: GSE93606). Differentially expressed genes (DEGs) were intersected with a matrix stiffness-related gene set. Three machine learning algorithms (SVM-RFE, LASSO, and Naive Bayes) were employed to screen diagnostic feature genes. A diagnostic nomogram was constructed and evaluated. Functional enrichment (GO/KEGG/GSEA), immune infiltration (ssGSEA), and molecular docking analyses were performed to explore biological functions and predict therapeutic drugs. Eighteen matrix stiffness-related DEGs were identified. Through machine learning screening, GSN and ARG1 were determined as robust key genes, exhibiting high diagnostic accuracy (AUC>0.7) in both training and validation cohorts. Functional analysis revealed that GSN is involved in actin cytoskeleton regulation, while ARG1 participates in immune response modulation. Both genes showed strong positive correlations with the infiltration of macrophages and neutrophils. Furthermore, molecular docking identified RA-2 as a potential therapeutic agent targeting ARG1 with high binding affinity (-9.2kcal/mol). We identified GSN and ARG1 as novel matrix stiffness-related diagnostic biomarkers for IPF, linking mechanotransduction to immune microenvironment remodeling. The diagnostic nomogram offers high clinical predictive value, and RA-2 emerged as a putative ARG1-targeting compound with favorable docking energy and warrants further experimental validation as a potential antifibrotic agent.

Integration of various sources of information for prediction of disease progression is an unmet need in glaucoma diagnostics. We designed a deep learning-based prognostic model incorporating clinical and structural data for forecasting functional glaucoma progression and compared its performance to clinicians. Retrospective, comparative cohort study of prognostic accuracy. We included 1599 eyes (908 patients) with definite or suspected glaucoma with ≥5 24-2 visual fields (VF) and 3 or more years of follow-up. VF mean deviation (MD) rates of change were estimated with linear regression. Sequential MD rates of change were estimated with each series spanning only 5 years of follow-up. VF progression was declared when four sequential statistically significant negative MD slopes were observed, and slope for the entire follow-up was significant. A convolutional neural network pretrained on ImageNet was designed to predict VF progression using baseline clinical and demographic data, disc photographs, and optical coherence tomography-derived global and sectoral retinal nerve fiber layer and macular thickness measurements. In addition, average intraocular pressure and treatment information during follow-up were put into the model. The same data for a subset of patients was provided to two clinicians to independently predict future progression. The model was validated on a separate cohort of eyes in which optical coherence tomography imaging was done with a different device (291 eyes). Model's area under receiver operating characteristic curves (AUC), accuracy, and area under the precision and recall curves. Average (SD) baseline MD and number of VF exams were -3.5 (4.9) dB and 10.1 (4.7). 399 eyes (25%) deteriorated. The best-performing model incorporated baseline disc photographs, and retinal nerve fiber layer and macular thickness: AUC, 0.839 (0.771-0.906), accuracy, 76.0% (62.0%-85.0%), and area under the precision and recall curves, 0.558 (0.385-0.733). Deep learning model significantly outperformed clinical graders (AUC : 0.629 [0.531-0738], P < .001 and 0.680 [0.584-0.776], P = .001, for grader one and two, respectively). Model performance was similar on the validation cohort (AUC: 0.754 [0.671-0.837], and accuracy: 77% [71%-82%], respectively, P = .122). The model performed well when predicting fast-progression, defined as MD rate <-1.0 dB/y (AUC: 0.869 [0.792-0.947]). Our newly designed deep learning model can combine baseline demographic and clinical data with widely available structural measurements and provide clinically relevant information for the prediction of glaucoma progression.

The impact of age on six-minute walk distance, functional class, and right ventricular function in pulmonary arterial hypertension.

Proteomics Profiling Identifies MCM4 as a Prognostic Biomarker for Postoperative Metastasis in Solid Pseudopapillary Neoplasms of the Pancreas.

Automated hemodynamic modeling to explore arterial curvature effects on intracranial aneurysm initiation.

Progression from minimally invasive adenocarcinoma (MIA) to invasive adenocarcinoma (IA) in lung adenocarcinoma (LUAD) is associated with a significantly worse prognosis and lacks predictive markers. The genomic molecular mechanisms of progression and genetic signatures mediating the MIA to IA transition in early-stage LUAD are still largely uncharacterized. In our study, a genomic signature driving MIA to IA was developed by 243 MIA and 532 IA stage I LUAD patients, and its ability to predict outcomes was validated in multiple cohorts. Among patients with stage I LUAD, 19 genes exhibited significant differences in frequency between MIA and IA groups, with notable enrichment in the MAPK, PI3K-Akt and ErbB pathways. A genomic signature of 11 genes associated with LUAD invasion progression, with TP53 and CDKN2A playing key functional roles, was developed and correlated with poor prognosis by internal and external cohorts (p < 0.05). The high-risk group exhibited elevated tumor mutational burden, mutation-allele tumor heterogeneity, and variant allele frequency values both in train and validation cohorts (p < 0.001). Mixed ground-glass opacity and solid nodules, predominantly larger than 1 cm, were more common in the high-risk population (p < 0.001), while the low-risk group exhibited a higher proportion of high-medium differentiated LUAD (p < 0.001). Our results reveal an 11-gene genomic signature driving invasive progression from MIA to IA associated with poor outcome in stage I LUAD patients by validating internal and external cohorts, radiological, pathological and tumor size, with potential future implications for disease monitoring, prognosis, and future therapeutic interventions.

Eicosapentaenoic acid attenuates heart failure with preserved ejection fraction via promoting TREM2-dependent efferocytosis.

PREDICT - patient referral evaluation to determine indication for computed tomography to identify small aortic annulus size in patients with severe aortic stenosis.

Development and Validation of a Prognostic Risk Score for Patients With Cancer and Neutropenic Fever Presenting to the Emergency Department.

Sarcopenia is an age-related condition characterized by progressive muscle mass, strength and physical performance declines, contributing to frailty and adverse health outcomes. Despite increasing interest in molecular biomarkers, longitudinal data with external validation are limited. This study applied high-throughput proteomic analysis to identify and validate biomarkers associated with sarcopenia progression in two independent prospective cohorts. The discovery cohort (n = 171) was classified into three groups: (1) nonsarcopenic at both baseline and the 2-year follow-up; (2) newly developed sarcopenia; and (3) persistently sarcopenic. The validation cohort (n = 93) was followed up for 2 years. Plasma proteomic profiling was conducted using data-independent acquisition (DIA) mass spectrometry. For the validation cohort, targeted quantification (Hyper Reaction Monitoring-DIA) and immunoassays were employed to verify key findings. Statistical analyses included multivariable regression and pathway enrichment analysis. In the discovery cohort, 102 proteins were differentially expressed between groups (p < 0.05). Compared to the stable nonsarcopenic group, individuals who developed sarcopenia demonstrated significant APOA1 (fold change -1.42, p < 0.001) and KLKB1 downregulation and LECT2 upregulation. Those who remained sarcopenic exhibited persistent B2M (+1.58, p < 0.001), S100A9 and LYZ elevation. We identified seven robust protein signatures (LRG1, CST3, TIMP1, C2, ITIH1, AMBP and LYZ) that showed consistent significant associations with sarcopenia components in both cohorts. LRG1 and TIMP1, CST3 and C2 were reproducibly associated with muscle strength, physical performance and muscle mass, respectively. Pathway enrichment analyses consistently highlighted LXR/RXR signalling, acute phase response signalling and complement cascade activation as central mechanisms across these domains. This study identified and validated plasma protein signatures and pathways associated with sarcopenia progression. Complement activation, acute inflammatory response and lipid dysregulation emerged as central mechanisms. These robustly validated biomarkers may represent targets for early detection and intervention strategies in sarcopenia.

A clinical nomogram for predicting postoperative renal function improvement in children with UPJO.

From slides to AI-ready maps: Standardized multi-layer tissue maps as metadata for artificial intelligence in digital pathology.

Artificial Intelligence-Guided Endpoint Selection for Neuroprotection Trials in Glaucoma.

Development and temporal validation of an odds ratio-weighted prognostic score (NPH-RKP) for idiopathic normal pressure hydrocephalus shunt surgery: a retrospective cohort study.

Development and validation of machine learning models to predict PTSD at multiple time points in hospitalized trauma patients.

Identification of mitochondrial dysfunction-related biomarkers and immune infiltration in liver ischemia-reperfusion injury via integrated bioinformatics and machine learning.