Independent External Cohort Research Articles

Functional impairment in COPD can be predicted using genomic-derived data

ObjectiveReduced functional capacity and muscle weakness are two major contributors to functional impairment in chronic obstructive pulmonary disease (COPD). The underlying causes of functional impairment are poorly understood and, therefore,...

An early lung cancer diagnosis model for non-smokers incorporating ct imaging analysis and circulating genetically abnormal cells (CACs)

BackgroundAn increase in the prevalence of lung cancer that is not smoking-related has been noticed in recent years. Unfortunately, these patients are not included in low dose computer tomography (LDCT) screening programs and are not actually considered in early diagnosis. Therefore, improved early diagnosis methods are urgently needed for non-smokers. It is necessary to establish a prediction model for non-smoking individuals at intermediate to high risk of developing lung cancer (LC) and develop a tool to address the significant gap in evaluating pulmonary nodules in non-smokers.MethodsWe retrospectively investigated 1121 patients with pulmonary nodules, who underwent LDCT examinations between September 2019 and March 2023. Five artificial intelligence (AI) algorithms were used to build two kinds of models and identify which one was better at diagnosing non-smoking pulmonary nodules patients. In the first model, we assigned 554 non-smoking individuals to a training cohort and 150 non-smoking patients to an independent validation cohort. The second model included 971 patients for the training set and 150 non-smoking patients for an independent validation set. All LDCT images of participants were obtained for AI analysis. AI of LDCT scans, liquid biopsy, and clinical characteristics were collected for model building.ResultsAmong LC patients, 58,4% were non-smokers. Non-smoking patients had a high incidence of LC (71.4%), and women showed a significant excess risk compared with non-smoking men in terms of LC risk. Furthermore, our results indicated that the model built using random forest (RF) method, which integrates clinical characteristics (age, extra-thoracic cancer history, gender), radiological characteristics of pulmonary nodules (nodule diameter, nodule count, upper lobe location, malignant sign at the nodule edge, subsolid status), the artificial intelligence analysis of LDCT data, and liquid biopsy achieved the best diagnostic performance in the independent external non-smokers validation cohort (sensitivity 92%, specificity 97%, area under the curve [AUC] = 0.99).ConclusionsThese results could significantly improve early non-smoker LC diagnosis and treatment for non-smoker patients with malignant nodules. The established multi-omics model is a noninvasive prediction tool for non-smoking malignant pulmonary nodule diagnosis. Validation revealed that these models exhibited excellent discrimination and calibration capacities, especially the first model built using the RF method, suggesting their clinical utility in the early screening and diagnosis of non-smoking LC.

P0687 Development and validation of a novel multimodal model based on histology of colonoscopic biopsy to predict primary non-response to infliximab in patients with Crohn’s disease

Abstract Background Crohn’s disease (CD) is a chronic inflammatory condition of the gastrointestinal tract, and while biologics like infliximab (IFX) offer significant benefits, 10-30% of patients remain non-responders initially. This study aims to refine the prediction of treatment responses using artificial intelligence to integrate multimodal information, potentially enhancing treatment precision. Methods We conducted a retrospective analysis of clinical data from Crohn’s disease patients treated at The First Affiliated Hospital of Sun Yat-sen University from October 2016 to October 2021. The endpoint event was defined as primary non-response within 14 weeks of treatment. This study included clinical, laboratory, endoscopic, imaging, and histological data from colonoscopic biopsies. The data were split into a test set and an internal validation set in a 7:3 ratio. A deep learning (DL) model was developed using a multi-instance learning framework to incorporate this multimodal information for predicting primary non-response to IFX. Finally, the multimodal model was validated in an independent external validation cohort.[Figure1] Results The study included 170 patients, with 93 in the internal training set, 38 in the test set, and 39 in the external validation set. The DL model utilizing pathological features achieved an area under the receiver operating characteristic (AUROC) of 0.79 in 5-fold cross-validation. When combining pathological and radiological features, the AUC was 0.76, and integrating clinical features raised the AUC to 0.82. External validation upheld the efficacy of model with the highest AUC at 0.73 for the multimodal model. Conclusion The study developed several DL models to predict primary non-response to IFX with high accuracy. The most effective model integrated pathology, radiomics, and clinical data, supporting targeted treatment strategies and advancing personalized medicine for CD.

P0902 Development and validation of a novel model based on clinical characteristic variables to predict disease behavior progression in patients with stricturing Crohn's disease

Abstract Background The risk factors for disease behavior progression in CD patients with strictures remain unclear. This study aims to construct a predictive model based on commonly used clinical indicators to identify high-risk CD patients with early progression. Methods We conducted a retrospective analysis of clinical data from stricturing Crohn’s disease patients at The First Affiliated Hospital of Sun Yat-sen University from October 2016 to October 2023. The disease behavioural progression was defined as progression to B3 classification or under surgery due to intestinal strictures. The data were split into a test set and an internal validation set in a 7:3 ratio. Classification models, including logistic regression (LR), random forest (RF) and extreme-gradient Boosting (XGB) Models, were constructed. Finally, all models were validated in an independent external validation cohort from Ruijin Hospital, Shanghai Jiaotong University School of Medicine.[Figure 1] Results The study included 341 patients, with 190 in the internal training set, 81 in the test set, and 70 in the external validation set. Obstructive symptoms, globulin (GLB), erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) are independent predictors of disease behavior progression. The areas under the receiver-operating characteristic curves (AUROCs) of the LR, RF, and XGB models were 0.861, 0.477 and 0.559, respectively. The logistic regression model achieved the highest AUROC value of 0.752 in the external validation. The further transformed nomogram has a similar prediction accuracy to the logistic regression. Conclusion In patients with stricturing CD, obstructive symptoms score, CRP, ESR and GLB were independent and validated predictors of disease behavior progression in stricturing Crohn's disease. We found no evidence of better performance of machine learning-based models in predicting disease behavior progression in stricturing CD. A nomogram based on the logistic regression model might aid in the management of stricturing CD patients.

Development and validation of an explainable machine learning prediction model of hemorrhagic transformation after intravenous thrombolysis in stroke

ObjectiveTo develop and validate an explainable machine learning (ML) model predicting the risk of hemorrhagic transformation (HT) after intravenous thrombolysis.MethodsWe retrospectively enrolled patients who received intravenous tissue plasminogen activator (IV-tPA) thrombolysis within 4.5 h after symptom onset to form the original modeling cohort. HT was defined as any hemorrhage on head CT scan completed within 48 h after IV-tPA administration. We utilized the Random Forest (RF), Multilayer Perceptron (MLP), Adaptive Boosting (AdaBoost), and Gaussian Naive Bayes (GauNB) algorithms to develop ML-HT models. The models' predictive performance was evaluated using confusion matrix (including accuracy, precision, recall, and F1 score), and discriminative analysis (area under the receiver-operating-characteristic curve, ROC-AUC) in the original cohort, followed by validation in an independent external cohort. The models' explainability was assessed using SHapley Additive exPlanations (SHAP) global feature plot, SHAP Summary Plot, and Partial Dependence Plot.ResultsA total of 1,007 patients were included in the original modeling cohort, with an HT incidence of 8.94%. The RF-based ML-HT model showed metrics of 0.874 (accuracy), 0.972 (precision), 0.890 (recall), 0.929 (F1 score); with ROC-AUC of 0.7847 in the original cohort and 0.7119 in the external validation cohort. The MLP model showed 0.878, 0.967, 0.989, 0.978, 0.7710, and 0.6768, respectively. The AdaBoost model showed 0.907, 0.967, 0.989, 0.978, 0.7798, and 0.6606, respectively. The GauNB model showed 0.848, 0.983, 0.598, 0.716, 0.6953, and 0.6289, respectively. The explainable analysis of the RF-based ML model indicated that the National Institute of Health Stroke Scale (NIHSS) score, age, platelet count, and atrial fibrillation were the primary determinants for HT following IV-tPA thrombolysis.ConclusionThe RF-based explainable ML model demonstrated promising predictive ability for estimating the risk of HT after IV-tPA thrombolysis and may have the potential to assist the clinical decision-making in emergency settings.

Electrocardiogram-based machine learning for risk stratification of patients with suspected acute coronary syndrome.

The importance of risk stratification in patients with chest pain extends beyond diagnosis and immediate treatment. This study sought to evaluate the prognostic value of electrocardiogram feature-based machine learning models to risk-stratify all-cause mortality in those with chest pain. This was a prospective observational cohort study of consecutive, non-traumatic patients with chest pain. All-cause death was ascertained from multiple sources, including the CDC National Death Index registry. Six machine learning models were trained for survival analysis using 73 morphological electrocardiogram features (80% training with 10-fold cross-validation and 20% testing), followed by a variational Bayesian Gaussian mixture model to define distinct risk groups. The resulting classification performance was compared against the HEART score. The derivation cohort included 4015 patients (age 59 ± 16 years, 47% women). The mortality rate was 20.3% after a median follow-up period of 3.05 years (interquartile range 1.75-5.32). Extra Survival Trees outperformed other forecasting models, and the derived risk groups successfully classified patients into low-, moderate-, and high-risk groups (log-rank test statistic = 121.14, P < .001). This model outperformed the HEART score, reducing the rate of missed events by >90% with a negative predictive value and sensitivity of 93.4% and 85.9%, compared to 89.0% and 75.0%, respectively. In an independent external testing cohort (N = 3095, age 59 ± 15 years, 44% women, 30-day mortality 3.5%), patients in the moderate [odds ratio 3.62 (1.35-9.74)] and high [odds ratio 6.12 (2.38-15.75)] risk groups had significantly higher odds of mortality compared to those in the low-risk group. The externally validated machine learning-based model, exclusively utilizing features from the 12-lead electrocardiogram, outperformed the HEART score in stratifying the mortality risk of patients with acute chest pain. This may have the potential to impact the precision of care delivery and the allocation of resources to those at highest risk of adverse events.

High-risk habitat radiomics model based on ultrasound images for predicting lateral neck lymph node metastasis in differentiated thyroid cancer

BackgroundThis study aims to evaluate the predictive usefulness of a habitat radiomics model based on ultrasound images for anticipating lateral neck lymph node metastasis (LLNM) in differentiated thyroid cancer (DTC), and for pinpointing high-risk habitat regions and significant radiomics traits.MethodsA group of 214 patients diagnosed with differentiated thyroid carcinoma (DTC) between August 2021 and August 2023 were included, consisting of 107 patients with confirmed postoperative lateral lymph node metastasis (LLNM) and 107 patients without metastasis or lateral cervical lymph node involvement. An additional cohort of 43 patients was recruited to serve as an independent external testing group for this study. Patients were randomly divided into training and internal testing group at an 8:2 ratio. Region of interest (ROI) was manually outlined, and habitat analysis subregions were defined using the K-means method. The ideal number of subregions (n = 5) was determined using the Calinski-Harabasz score, leading to the creation of a habitat radiomics model with 5 subregions and the identification of the high-risk habitat model. Area under the curve (AUC) values were calculated for all models to assess their validity, and predictive model nomograms were created by integrating clinical features. The internal and external testing dataset is employed to assess the predictive performance and stability of the model.ResultsIn internal testing group, Habitat 3 was identified as the high-risk habitat model in the study, showing the best diagnostic efficacy among all models (AUC(CRM) vs. AUC(Habitat 3) vs. AUC(CRM + Habitat 3) = 0.84(95%CI:0.71–0.97) vs. 0.90(95%CI:0.80-1.00) vs. 0.79(95%CI:0.65–0.93)). Moreover, integrating the Habitat 3 model with clinical features and constructing nomograms enhanced the predictive capability of the combined model (AUC = 0.95(95%CI:0.88-1.00)). In this study, an independent external testing cohort was utilized to assess the model’s accuracy, yielding an AUC of 0.88 (95%CI: 0.78–0.98).ConclusionThe integration of the High-Risk Habitats (Habitat 3) radiomics model with clinical characteristics demonstrated a high predictive accuracy in identifying LLNM. This model has the potential to offer valuable guidance to surgeons in deciding the necessity of LLNM dissection for DTC.Clinical trial numberNot applicable.

Deep learning radiomics nomograms predict Isocitrate dehydrogenase (IDH) genotypes in brain glioma: A multicenter study.

To explore the feasibility of Deep learning radiomics nomograms (DLRN) in predicting IDH genotype. A total of 402 glioma patients from two independent centers were retrospectively included, and the data from center I was randomly divided into a training cohort (n = 239) and an internal validation cohort (n = 103) on a 7:3 basis. Center II served as an independent external validation cohort (n = 60). We developed a DLRN for IDH classification of gliomas based on T2 images. This hybrid model integrates deep learning features, radiomics features, and clinical features most relevant to IDH genotypes and finally classifies them using multivariate logistic regression analysis. We used the area under the curve (AUC) of the receiver operating characteristic (ROC) to evaluate the performance of the model and applied the DLRN score to the survival analysis of some of the follow-up glioma patients. The proposed model had an area under the curve (AUC) of 0.98 in an externally validated cohort, and DLRN scores were significantly associated with the overall survival of glioma patients. Deep learning radiomics nomograms performed well in non-invasively predicting IDH mutation status in gliomas, assisting stratified management and targeted therapy for glioma patients.

Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography.

The accurate distinction between benign and malignant biliary strictures (BS) poses a significant challenge. Despite the use of bile duct biopsies and brush cytology via endoscopic retrograde cholangiopancreaticography (ERCP), the results remain suboptimal. Single-operator cholangioscopy can enhance the diagnostic yield in BS, but its limited availability and high costs are substantial barriers. Convolutional Neural Network (CNN)-based systems may improve the diagnostic process and enhance reproducibility. Therefore, we assessed the feasibility of using deep learning to differentiate BS using fluoroscopy images during ERCP. We conducted a retrospective review of adult patients (n=251) from three university centers in Germany (Leipzig, Dresden, Halle) who underwent ERCP. We developed and evaluated a deep learning-based model using fluoroscopy images. The performance of the classifier was evaluated by measuring the area under the receiver operating characteristic curve (AUROC) and we utilized saliency map analyses to understand the decision-making process of the model. In cross-validation experiments, malignant BS were detected with a mean AUROC of 0.89 ± 0.03. The test set of the Leipzig cohort demonstrated an AUROC of 0.90. In two independent external validation cohorts (Dresden, Halle), the deep learning-based classifier achieved an AUROC of 0.72 and 0.76, respectively. The artificial intelligence model's predictions identified plausible characteristics within the fluoroscopy images. By using a deep learning model, we were able to discriminate malignant BS from benign biliary conditions. The application of artificial intelligence enhances the diagnostic yield of malignant BS and should be validated in a prospective design.

Unveiling the hidden causal links: skin flora and cutaneous melanoma.

The presence of skin flora (SF) has been identified as a significant factor in the onset and progression of cutaneous melanoma (CM). However, the vast diversity and abundance of SF present challenges to fully understanding the causal relationship between SF and CM. A Two Sample Mendelian Randomization (TSMR) analysis was conducted to investigating the causal relationship between SF and CM. The Inverse-Variance Weighted (IVW) method was utilized as the primary approach to assess the causal relationship under investigation. Furthermore, an independent external cohort was employed to validate the initial findings, followed by a meta-analysis of the consolidated results. To address potential confounding factors related to the influence of SF on CM, a Multivariate Mendelian Randomization (MVMR) analysis was also conducted. Finally, a Reverse Mendelian Randomization (RMR) was conducted to further validate the causal association. TSMR results showed that 9 SF have a causal relationship with CM in the training cohort. Although these 9 SF weren't confirmed in the testing cohort, 4 SF remained significant in the meta-analysis after integrating results from both cohorts. MVMR analysis indicated that 3 SF were still significantly associated with CM after accounting for the interactions between different SF in the training cohort. No reverse causal relationship was identified in RMR analysis. A total of 9 SF were identified as having a potential causal relationship with CM; however, a large randomized controlled trial is needed to verify these results.

Prognostic value of CTF1 in glioma and its role in the tumor microenvironment.

Within the realm of primary brain tumors, specifically glioblastoma (GBM), presents a notable obstacle due to their unfavorable prognosis and differing median survival rates contingent upon tumor grade and subtype. Despite a plethora of research connecting cardiotrophin-1 (CTF1) modifications to a range of illnesses, its correlation with glioma remains uncertain. This study investigated the clinical value of CTF1 in glioma and its potential as a biomarker of the disease. Glioma project in The Cancer Genome Atlas (TCGA) database served as the training cohort, and CGGA 325 series in the Chinese Glioma Genome Atlas (CGGA) database served as the external independent validation cohort. First, the difference in the expression level of CTF1 between glioma tissue and normal tissue was analyzed, and the results were verified with the CGGA database. The relationship between CTF1 expression and the prognosis of glioma patients was evaluated using Univariate and Multivariate Cox analysis and the Kaplan-Meier (KM) curve. We used CIBERSOFT to explore the association between CTF1 and immune cell infiltration in GBM, as well as performing gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA) analyses. Furthermore, we analyzed the relationship between CTF1 and gene mutations and drug sensitivity. Using Weighted gene co-expression network analysis (WGCNA) analysis, we pinpointed the gene set most correlated with CTF1 and conducted Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) gene enrichment analyses to anticipate the pathways that could be influenced by CTF1. Finally, we constructed a nomogram using a multifactorial regression model to further predict patient prognosis. CTF1 expression was significantly elevated in glioma tissues compared to normal tissues in the TCGA dataset (P<0.001) and was associated with poorer survival in both TCGA and CGGA datasets (P<0.001). Receiver operating characteristic (ROC) analysis demonstrated the diagnostic potential of CTF1, with an area under the curve (AUC) of 0.889 [95% confidence interval (CI): 0.803-0.974] in TCGA and 0.664 (95% CI: 0.599-0.729) in CGGA. High CTF1 levels were correlated with advanced glioma grades, and Cox regression analysis identified CTF1 as an independent risk factor. A nomogram incorporating CTF1 levels, isocitrate dehydrogenase 1 (IDH1) mutation status, O6-methylguanine-DNA methyltransferase (MGMT) methylation status, age, and gender were developed and validated to predict 1- and 2-year survival probabilities. In GBM, drug sensitivity analysis revealed significant associations between CTF1 expression and responsiveness to gemcitabine, dasatinib, and other agents. CTF1 expression was also linked to immune infiltration (monocytes, neutrophils, M0 macrophages) and pathways involved in tumor progression, including IL2_STAT5, P53, and IL6_JAK_STAT3 signaling pathways. CTF1 could serve as a prognostic marker for glioma. It acts as a predictive indicator and is associated with immune cell infiltration in GBM. These findings provide a foundation for further research into the molecular function of CTF1 and offer new insights for exploring the underlying mechanisms and developing treatments for glioma.

Integrating Metabolomics Domain Knowledge with Explainable Machine Learning in Atherosclerotic Cardiovascular Disease Classification.

Metabolomic data often present challenges due to high dimensionality, collinearity, and variability in metabolite concentrations. Machine learning (ML) application in metabolomic analyses is enabling the extraction of meaningful information from complex data. Bringing together domain-specific knowledge from metabolomics with explainable ML methods can refine the predictive performance and interpretability of models used in atherosclerosis research. In this work, we aimed to identify the most impactful metabolites associated with the presence of atherosclerotic cardiovascular disease (ASCVD) in cross-sectional case-control studies using explainable ML methods integrated with metabolomics domain knowledge. For this, a subset from the FLEMENGHO cohort with metabolomic data available was used as the training cohort, including 63 patients with a history of ASCVD and 52 non-smoking controls matched by age, sex, and body mass index from the same population. First, Partial Least Squares Discriminant Analysis (PLS-DA) was applied for dimensionality reduction. The selected metabolites' correlations were analyzed by considering their chemical categorization. Then, eXtreme Gradient Boosting (XGBoost) was used to identify metabolites that characterize ASCVD. Next, the selected metabolites were evaluated in an external cohort to determine their effectiveness in distinguishing between cases and controls. A total of 56 metabolites were selected for ASCVD discrimination using PLS-DA. The primary identified metabolites' superclasses included lipids, organic acids, and organic oxygen compounds. Upon integrating these metabolites with the XGBoost model, the classification yielded a test area under the curve (AUC) of 0.75. SHAP analyses ranked cholesterol, 3-methylhistidine, and glucuronic acid among the most impactful features and showed the diversity of metabolites considered for building the ASCVD discriminator. Also using XGBoost, the selected metabolites achieved an AUC of 0.93 in an independent external validation cohort. In conclusion, the combination of different metabolites has the potential to build classifiers for ASCVD. Integrating metabolite categorization within the SHAP analysis further enhanced the interpretability of the model, offering insights into metabolite-specific contributions to ASCVD risk.

Multiparametric MRI-based Machine Learning Radiomics for Predicting Treatment Response to Transarterial Chemoembolization Combined with Targeted and Immunotherapy in Unresectable Hepatocellular Carcinoma: A Multicenter Study

Rationale and ObjectivesTo develop and validate multiple machine learning predictive models incorporating clinical features and pretreatment multiparametric magnetic resonance imaging (MRI) radiomic features for predicting treatment response to transarterial chemoembolization combined with molecular targeted therapy plus immunotherapy in unresectable hepatocellular carcinoma (HCC). Materials and methodsThis retrospective study involved 276 patients with unresectable HCC who received combination therapy from 4 medical centers. Patients were divided into one training cohort and two independent external validation cohorts. 16 radiomic features from six multiparametric MRI sequences and 2 clinical features were used to build six machine learning models. The models were evaluated using the area under the curve (AUC), decision curve analysis, and incremental predictive value. ResultsAlpha-fetoprotein and neutrophil-to-lymphocyte ratio are clinical independent predictors of treatment response. In the training cohort and two external validation cohorts, the AUCs and 95% confidence intervals for predicting treatment response were respectively 0.782 (0.673–0.793), 0.695 (0.514–0.708), and 0.679 (0.526–0.719) for the clinical model; 0.942 (0.846–0.932), 0.869 (0.700–0.881), and 0.868 (0.730–0.885) for the radiomics model; and 0.956 (0.859–0.942), 0.895 (0.738–0.903), and 0.892 (0.667–0.828) for the combined clinical-radiomics model. In the three cohorts, the incremental predictive value of the radiomics model over the clinical model was 49.2% (P < 0.001), 28.8% (P < 0.001), and 31.5% (P < 0.001). ConclusionThe combined clinical-radiomics model may provide a reliable and non-invasive tool to predict individual treatment responses and guide and improve clinical decision-making in combination therapy of HCC patients.

NIMG-29. EARLY REDUCTION IN MRI DIFFUSION APPARENT DIFFUSION COEFFICIENT (ADC) STRONGLY PREDICTS LONG TERM RESPONSE TO ONC201 THERAPY IN PATIENTS WITH H3K27M-DMG

Abstract ONC201 is the first monotherapy to improve outcomes in H3K27M- diffuse midline glioma (DMG) beyond radiation. Despite impressive early efficacy in H3K27M-DMG, individual response to ONC201 is variable and no radiographic biomarkers predict long term response. Previous studies demonstrated baseline MRI diffusion apparent diffusion coefficient (ADC) is lower in DMG with H3K27M compared to wildtype but change after radiation therapy was not correlated with improved OS or PFS. We hypothesize ADC will enable stratification of patients more likely to respond to ONC201. Imaging and clinical data were abstracted from chart review of patients treated with ONC201 at University of Michigan. Two neuroradiologists performed centralized review for RAPNO measurements and mean ADC was assessed using ROI measured in consistent anatomic locations, with areas of cystic degeneration or necrosis excluded. Sixty-one patients were identified for review. Preliminary analysis was performed on twenty-three patients, with upfront ONC201 therapy, median age 14.8 years old (5-25yo), primary site includes pontine (n=15), thalamic (n=7). Baseline characteristics of age, ADC and size at diagnosis or follow-up RAPNO scored size were not statistically significant. Patients with longer than median survival (334 days) demonstrated increased ADC (+58.25x10-6mm2/s) from baseline to cycle 2 whereas patients with shorter than median survival demonstrated decreased ADC (-174.8x10-6mm2/s) (p = 0.0076). Further, patients with decreased ADC demonstrated mean OS of 302.8 days and patients with increased ADC had mean OS of 588.0 (p = 0.0054). In H3K27M-DMG patients treated with ONC201, increased ADC after two cycles of ONC201 was strongly predictive of longer overall survival. Our recent work demonstrated that ONC201 disrupts metabolic and epigenetic pathways to restore pathognomonic H3K27me3 reduction, which may underline greater change in ADC. Ongoing work will validate these findings in an independent external cohort and integrate histogram analysis, parametric assessments, MRI perfusion and liquid biopsy biomarkers (cf-tDNA and metabolomics).

The Risk Genes S1PR5, CMC1, and ASAH1 as Potential Targets for the Diagnosis, Immunotherapy, and Treatment of Colon Adenocarcinoma by Single-Cell and Bulk RNA Sequencing Analysis

Globally, one of the main causes of cancer-related mortality is Colon Adenocarcinoma (COAD). In this study, a new special Immune Cell Functions (ICF) risk model was constructed using single-cell and bulk RNA sequencing data to develop a new understanding and clinical applications for COAD. The immune function gene sets were downloaded from a literature reference, and the COAD single-cell dataset GSE146771 was downloaded from the Tumour Immune Single Cell Hub database. Using Lasso analysis, a multiple gene signature was made from the enrichment scores of immune function gene sets that were enriched in different ways. Robust validation of the signature was then performed in multiple independent cohorts. After that, we built the model using a 10-fold cross-test and evaluated its independence for clinical usage using a nomogram. We also investigated the connection between signature and immune function, genetic variation, immunotherapy, and the cancer immunological microenvironment. Lastly, we used qPCR and immunohistochemistry to examine the expression of the unreported model genes. To find the regulatory functions of unreported model genes, an EdU assay was employed. First, 20 differentially enriched immune function gene sets were identified. Ten genes can be used as a risk profile to assess the prognosis of colon cancer, according to Lasso regression analysis. Signature performance was stable in both the training cohort and two independent GEO external cohorts, and risk scores were confirmed as independent prognostic factors. At the same time, our risk model continued to be highly predictive across various clinical clusters and clinical characteristics, such as immune checkpoints, tumour genome mutations, and chemotherapeutic drug resistance. Patients in the low-risk group have exhibited a higher chance of benefiting from immunotherapy, according to immunotherapy response research. qPCR and immunohistochemistry analysis have revealed S1PR5 expression as high in COAD tissues, while CMC1 and ASAH1 expression has been found to be low. According to the findings of the functional experiment, S1PR5, CMC1, and ASAH1 may control the ability of CRC cells to proliferate. In this study, using scRNA-seq and bulk RNA-seq data, we created a risk model to predict the prognosis and effectiveness of immunotherapy in patients with COAD. In addition, we have discovered three model genes (S1PR5, CMC1, and ASAH1) that have not been reported before. These genes have the potential to be novel therapeutic targets in Colorectal Cancer (CRC). These findings suggest that this model could be used to evaluate the prognostic risk and identify potential targets for COAD patient treatment.

Association analysis between an epigenetic alcohol risk score and blood pressure

BackgroundEpigenome‐wide association studies have identified multiple DNA methylation sites (CpGs) associated with alcohol consumption, an important lifestyle risk factor for cardiovascular diseases. This study aimed to test the hypothesis that an alcohol consumption epigenetic risk score (ERS) is associated with blood pressure (BP) traits.ResultsWe implemented an ERS based on a previously reported epigenetic signature of 144 alcohol-associated CpGs in meta-analysis of participants of European ancestry. We found a one-unit increment of ERS was associated with eleven drinks of alcohol consumed per day, on average, across several cohorts (p < 0.0001). We examined the association of the ERS with systolic blood pressure (SBP), diastolic blood pressure (DBP), and hypertension (HTN) in 3,898 Framingham Heart Study (FHS) participants. Cross-sectional analyses in FHS revealed that a one-unit increment of the ERS was associated with 1.93 mm Hg higher SBP (p = 4.64E−07), 0.68 mm Hg higher DBP (p = 0.006), and an odds ratio of 1.78 for HTN (p < 2E−16). Meta-analysis of the cross-sectional association of the ERS with BP traits in eight independent external cohorts (n = 11,544) showed similar relationships with BP levels, i.e., a one-unit increase in ERS was associated with 0.74 mm Hg (p = 0.002) higher SBP and 0.50 mm Hg (p = 0.0006) higher DBP, but not with HTN. Longitudinal analyses in FHS (n = 3260) and five independent external cohorts (n = 4021) showed that the baseline ERS was not associated with a change in BP over time or with incident HTN.ConclusionsOur findings demonstrate that the ERS has potential clinical utility in assessing lifestyle factors related to cardiovascular risk, especially when self-reported behavioral data (e.g., alcohol consumption) are unreliable or unavailable.Graphic

SDS-Net: A Synchronized Dual-Stage Network for Predicting Patients Within 4.5-h Thrombolytic Treatment Window Using MRI.

Timely and precise identification of acute ischemic stroke (AIS) within 4.5h is imperative for effective treatment decision-making. This study aims to construct a novel network that utilizes limited datasets to recognize AIS patients within this critical window. We conducted a retrospective analysis of 265 AIS patients who underwent both fluid attenuation inversion recovery (FLAIR) and diffusion-weighted imaging (DWI) within 24h of symptom onset. Patients were categorized based on the time since stroke onset (TSS) into two groups: TSS ≤ 4.5 h and TSS > 4.5 h. The TSS was calculated as the time from stroke onset to MRI completion. We proposed a synchronized dual-stage network (SDS-Net) and a sequential dual-stage network (Dual-stage Net), which were comprised of infarct voxel identification and TSS classification stages. The models were trained on 181 patients and validated on an independent external cohort of 84 patients using metrics of area under the curve (AUC), sensitivity, specificity, and accuracy. A DeLong test was used to statistically compare the performance of the two models. SDS-Net achieved an accuracy of 0.844 with an AUC of 0.914 in the validation dataset, outperforming the Dual-stage Net, which had an accuracy of 0.822 and an AUC of 0.846. In the external test dataset, SDS-Net further demonstrated superior performance with an accuracy of 0.800 and an AUC of 0.879, compared to the accuracy of 0.694 and AUC of 0.744 of Dual-stage Net (P = 0.049). SDS-Net is a robust and reliable tool for identifying AIS patients within a 4.5-h treatment window using MRI. This model can assist clinicians in making timely treatment decisions, potentially improving patient outcomes.

Clinical target volume (CTV) automatic delineation using deep learning network for cervical cancer radiotherapy: A study with external validation.

To explore the accuracy and feasibility of a proposed deep learning (DL) algorithm for clinical target volume (CTV) delineation in cervical cancer radiotherapy and evaluate whether it can perform well in external cervical cancer and endometrial cancer cases for generalization validation. A total of 332 patients were enrolled in this study. A state-of-the-art network called ResCANet, which added the cascademulti-scale convolution in the skip connections to eliminate semantic differences between different feature layers based on ResNet-UNet. The atrous spatial pyramid pooling in the deepest feature layer combined the semantic information of different receptive fields without losing information. A total of 236 cervical cancer cases were randomly grouped into 5-fold cross-training (n=189) and validation (n=47) cohorts. External validations were performed ina separate cohort of 54 cervical cancer and 42 endometrial cancer cases. The performances of the proposed network were evaluated by dice similarity coefficient (DSC), sensitivity (SEN), positive predictive value (PPV), 95% Hausdorff distance (95HD), and oncologist clinical score when comparing them with manual delineation in validation cohorts. In internal validation cohorts, the mean DSC, SEN, PPV, 95HD for ResCANet achieved 74.8%, 81.5%, 73.5%, and 10.5mm. In external independent validation cohorts, ResCANet achieved 73.4%, 72.9%, 75.3%, 12.5mm for cervical cancer cases and 77.1%, 81.1%, 75.5%, 10.3mm for endometrial cancer cases, respectively. The clinical assessment score showed that minor and no revisions (delineation time was shortened to within 30min) accountedforabout 85% of all cases in DL-aided automatic delineation. We demonstrated the problem of model generalizability for DL-based automatic delineation. The proposed network can improve the performance of automatic delineation for cervical cancer and shorten manual delineation time at no expense to quality. The network showed excellent clinical viability, which can also be even generalized for endometrial cancer with excellent performance.

Artificial Intelligence Hybrid Survival Assessment System for Robot-Assisted Proctectomy: A Retrospective Cohort Study.

Robotic-assisted proctectomy (RAP) has emerged as the predominant surgical approach for patients with rectal cancer in recent years; although good postoperative patient recovery with accurate prediction is a guarantee of adaptive surveillance management, there is still a lack of easy-to-use prognostic tools and risk scores designed specifically for those patients undergoing RAP. This study used the electronic health records of 506 RAP participants, including a National Specialist Center for da Vinci Robotic Colorectal Surgery (NSCVRCS) meta cohort, and an independent external validation Sun Yat-sen Memorial Hospital cohort. In the NSCVRCS meta cohort, patients were divided into a discovery cohort (70%, n = 268), where the best-fit model was applied to model our prediction system, RAP-AIscore. Subsequently, an internal validation process for RAP-AIscore was conducted using a replication cohort (30%, n = 116). The study designed and implemented a large-scale artificial intelligence (AI) hybrid framework to identify the best strategy for building a survival assessment system, the RAP-AIscore, from 132 potential modeling scenarios through a combination of iterative cross-validation, Monte Carlo cross-validation, and bootstrap resampling. The 10 variables most relevant to clinical interpretability were identified on the basis of the AI hybrid optimal model values, which helps provide reliable prognostic survival guidance for new patients. The consistent evaluation of discrimination, calibration, generalization, and prognostic value across cohorts reaffirmed the accuracy and robust extrapolation capability of this system. The 10 feature variables most associated with clinical interpretability on the basis of Shapley values were identified, facilitating reliable prognostic survival guidance for new patients. This study introduces a promising and informative tool, the RAP-AIscore, which can be explained through nomograms for interpreting clinical outcomes. It facilitates postoperative risk stratification management and enhances clinical management of prognosis for RAP patients.

Radiomics parameters of epicardial adipose tissue predict mortality in acute pulmonary embolism

BackgroundAccurate prediction of short-term mortality in acute pulmonary embolism (APE) is very important. The aim of the present study was to analyze the prognostic role of radiomics values of epicardial adipose tissue (EAT) in APE.MethodsOverall, 508 patients were included into the study, 209 female (42.1%), mean age, 64.7 ± 14.8 years. 4.6%and 12.4% died (7- and 30-day mortality, respectively). For external validation, a cohort of 186 patients was further analysed. 20.2% and 27.7% died (7- and 30-day mortality, respectively). CTPA was performed at admission for every patient before any previous treatment on multi-slice CT scanners. A trained radiologist, blinded to patient outcomes, semiautomatically segmented the EAT on a dedicated workstation using ImageJ software. Extraction of radiomic features was applied using the pyradiomics library. After correction for correlation among features and feature cleansing by random forest and feature ranking, we implemented feature signatures using 247 features of each patient. In total, 26 feature combinations with different feature class combinations were identified. Patients were randomly assigned to a training and a validation cohort with a ratio of 7:3. We characterized two models (30-day and 7-day mortality). The models incorporate a combination of 13 features of seven different image feature classes.FindingsWe fitted the characterized models to a validation cohort (n = 169) in order to test accuracy of our models. We observed an AUC of 0.776 (CI 0.671–0.881) and an AUC of 0.724 (CI 0.628–0.820) for the prediction of 30-day mortality and 7-day mortality, respectively. The overall percentage of correct prediction in this regard was 88% and 79% in the validation cohorts. Lastly, the AUC in an independent external validation cohort was 0.721 (CI 0.633–0.808) and 0.750 (CI 0.657–0.842), respectively.InterpretationRadiomics parameters of EAT are strongly associated with mortality in patients with APE.Clinical trial numberNot applicable.