Internal Validation Dataset Research Articles

Development and Validation of a Nomogram for Preoperative Prediction of Early Recurrence after Upfront Surgery in Pancreatic Ductal Adenocarcinoma by Integrating Deep Learning and Radiological Variables.

Around 80% of pancreatic ductal adenocarcinoma (PDAC) patients experience recurrence after curative resection. We aimed to develop a deep-learning model based on preoperative CT images to predict early recurrence (recurrence within 12 months) in PDAC patients. The retrospective study included 435 patients with PDAC from two independent centers. A modified 3D-ResNet18 network was used for a deep learning model construction. A nomogram was constructed by incorporating deep learning model outputs and independent preoperative radiological predictors. The deep learning model provided the area under the receiver operating curve (AUC) values of 0.836, 0.736, and 0.720 in the development, internal, and external validation datasets for early recurrence prediction, respectively. Multivariate logistic analysis revealed that higher deep learning model outputs (odds ratio [OR]: 1.675; 95% CI: 1.467, 1.950; p < 0.001), cN1/2 stage (OR: 1.964; 95% CI: 1.036, 3.774; p = 0.040), and arterial involvement (OR: 2.207; 95% CI: 1.043, 4.873; p = 0.043) were independent risk factors associated with early recurrence and were used to build an integrated nomogram. The nomogram yielded AUC values of 0.855, 0.752, and 0.741 in the development, internal, and external validation datasets. In conclusion, the proposed nomogram may help predict early recurrence in PDAC patients.

Comprehensive bioinformatics analysis reveals the crosstalk genes and immune relationship between the systemic lupus erythematosus and venous thromboembolism.

It is well known that patients with systemic lupus erythematosus (SLE) had a high risk of venous thromboembolism (VTE). This study aimed to identify the crosstalk genes between SLE and VTE and explored their clinical value and molecular mechanism initially. We downloaded microarray datasets of SLE and VTE from the Gene Expression Omnibus (GEO) dataset. Differential expression analysis was applied to identify the crosstalk genes (CGs). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed on the shared genes. The shared diagnostic biomarkers of the two diseases were further screened from CGs using least absolute shrinkage and selection operator (Lasso) regression. Two risk scores for SLE and VTE were constructed separately to predict the likelihood of illness according to the diagnostic biomarkers using a logical regression algorithm. The immune infiltration levels of SEL and VTE were estimated via the CIBERSORT algorithm and the relationship of CGs with immune cell infiltration was investigated. Finally, we explored potential phenotype subgroups in SLE and VTE based on the expression level of CGs through the consensus clustering method and studied immune cell infiltration in different subtypes. A total of 171 CGs were obtained by the intersection of differentially expressed genes (DEGs) between SLE and VTE cohorts. The functional enrichment shown these CGs were mainly related to immune pathways. After screening by lasso regression, we found that three hub CGs (RSAD2, HSP90AB1, and FPR2) were the optimal shared diagnostic biomarkers for SLE and VTE. Based on the expression level of RSAD2 and HSP90AB1, two risk prediction models for SLE and VTE were built by multifactor logistic regression and systemically validated in internal and external validation datasets. The immune infiltration results revealed that CGs were highly correlated with multiple infiltrated immunocytes. Consensus clustering was used to respectively regroup SLE and VTE patients into C1 and C2 clusters based on the CGs expression profile. The levels of immune cell infiltration and immune activation were higher in C1 than in C2 subtypes. In our study, we further screen out diagnostic biomarkers from crosstalk genes SLE and VTE and built two risk scores. Our findings reveal a close relationship between CGs and the immune microenvironment of diseases. This provides clues for further exploring the common mechanism and interaction between the two diseases.

Detecting Paroxysmal Atrial Fibrillation From an Electrocardiogram in Sinus Rhythm: External Validation of the AI Approach

BackgroundAtrial fibrillation (AF) may occur asymptomatically and can be diagnosed only with electrocardiography (ECG) while the arrhythmia is present. ObjectivesThe aim of this study was to independently validate the approach of using artificial intelligence (AI) to identify underlying paroxysmal AF from a 12-lead ECG in sinus rhythm (SR). MethodsAn AI algorithm was trained to identify patients with underlying paroxysmal AF, using electrocardiographic data from all in- and outpatients from a single center with at least 1 ECG in SR. For patients without AF, all ECGs in SR were included. For patients with AF, all ECGs in SR starting 31 days before the first AF event were included. The patients were randomly allocated to training, internal validation, and testing datasets in a 7:1:2 ratio. In a secondary analysis, the AF prevalence of the testing group was modified. Additionally, the performance of the algorithm was validated at an external hospital. ResultsThe dataset consisted of 494,042 ECGs in SR from 142,310 patients. Testing the model on the first ECG of each patient (AF prevalence 9.0%) resulted in accuracy of 78.1% (95% CI: 77.6%-78.5%), area under the receiver-operating characteristic curve of 0.87 (95% CI: 0.86-0.87), and area under the precision recall curve (AUPRC) of 0.48 (95% CI: 0.46-0.50). In a low-risk group (AF prevalence 3%), the AUPRC decreased to 0.21 (95% CI: 0.18-0.24). In a high-risk group (AF prevalence 30%), the AUPRC increased to 0.76 (95% CI: 0.75-0.78). This performance was robust when validated in an external hospital. ConclusionsThe approach of using an AI-enabled electrocardiographic algorithm for the identification of patients with underlying paroxysmal AF from ECGs in SR was independently validated.

Predicting emergency department visits among children with asthma in two academic medical systems

Objective: To develop and validate a predictive algorithm that identifies pediatric patients at risk of asthma-related emergencies, and to test whether algorithm performance can be improved in an external site via local retraining. Methods: In a retrospective cohort at the first site, data from 26 008 patients with asthma aged 2–18 years (2012–2017) were used to develop a lasso-regularized logistic regression model predicting emergency department visits for asthma within one year of a primary care encounter, known as the Asthma Emergency Risk (AER) score. Internal validation was conducted on 8634 patient encounters from 2018. External validation of the AER score was conducted using 1313 pediatric patient encounters from a second site during 2018. The AER score components were then reweighted using logistic regression using data from the second site to improve local model performance. Prediction intervals (PI) were constructed via 10 000 bootstrapped samples. Results: At the first site, the AER score had a cross-validated area under the receiver operating characteristic curve (AUROC) of 0.768 (95% PI: 0.745–0.790) during model training and an AUROC of 0.769 in the 2018 internal validation dataset (p = 0.959). When applied without modification to the second site, the AER score had an AUROC of 0.684 (95% PI: 0.624–0.742). After local refitting, the cross-validated AUROC improved to 0.737 (95% PI: 0.676–0.794; p = 0.037 as compared to initial AUROC). Conclusions: The AER score demonstrated strong internal validity, but external validity was dependent on reweighting model components to reflect local data characteristics at the external site.

Development and validation of explainable machine-learning models for carotid atherosclerosis early screening

BackgroundCarotid atherosclerosis (CAS), an important factor in the development of stroke, is a major public health concern. The aim of this study was to establish and validate machine learning (ML) models for early screening of CAS using routine health check-up indicators in northeast China.MethodsA total of 69,601 health check-up records from the health examination center of the First Hospital of China Medical University (Shenyang, China) were collected between 2018 and 2019. For the 2019 records, 80% were assigned to the training set and 20% to the testing set. The 2018 records were used as the external validation dataset. Ten ML algorithms, including decision tree (DT), K-nearest neighbors (KNN), logistic regression (LR), naive Bayes (NB), random forest (RF), multiplayer perceptron (MLP), extreme gradient boosting machine (XGB), gradient boosting decision tree (GBDT), linear support vector machine (SVM-linear), and non-linear support vector machine (SVM-nonlinear), were used to construct CAS screening models. The area under the receiver operating characteristic curve (auROC) and precision-recall curve (auPR) were used as measures of model performance. The SHapley Additive exPlanations (SHAP) method was used to demonstrate the interpretability of the optimal model.ResultsA total of 6315 records of patients undergoing carotid ultrasonography were collected; of these, 1632, 407, and 1141 patients were diagnosed with CAS in the training, internal validation, and external validation datasets, respectively. The GBDT model achieved the highest performance metrics with auROC of 0.860 (95% CI 0.839–0.880) in the internal validation dataset and 0.851 (95% CI 0.837–0.863) in the external validation dataset. Individuals with diabetes or those over 65 years of age showed low negative predictive value. In the interpretability analysis, age was the most important factor influencing the performance of the GBDT model, followed by sex and non-high-density lipoprotein cholesterol.ConclusionsThe ML models developed could provide good performance for CAS identification using routine health check-up indicators and could hopefully be applied in scenarios without ethnic and geographic heterogeneity for CAS prevention.

Differences of survival benefits brought by various treatments in ovarian cancer patients with different tumor stages

PurposeThe current study aimed to explore the prognosis of ovarian cancer patients in different subgroup using three prognostic research indexes. The current study aimed to build a prognostic model for ovarian cancer patients.MethodsThe study dataset was downloaded from Surveillance Epidemiology and End Results database. Accelerated Failure Time algorithm was used to construct a prognostic model for ovary cancer.ResultsThe mortality rate in the model group was 51.6% (9,314/18,056), while the mortality rate in the validation group was 52.1% (6,358/12,199). The current study constructed a prognostic model for ovarian cancer patients. The C indexes were 0.741 (95% confidence interval: 0.731–0.751) in model dataset and 0.738 (95% confidence interval: 0.726–0.750) in validation dataset. Brier score was 0.179 for model dataset and validation dataset. The C indexes were 0.741 (95% confidence interval: 0.733–0.749) in bootstrap internal validation dataset. Brier score was 0.178 for bootstrap internal validation dataset.ConclusionThe current research indicated that there were significant differences in the survival benefits of treatments among ovarian cancer patients with different stages. The current research developed an individual mortality risk predictive system that could provide valuable predictive information for ovarian cancer patients.Graphical

Determination and characterization of molecular heterogeneity and precision medicine strategies of patients with pancreatic cancer and pancreatic neuroendocrine tumor based on oxidative stress and mitochondrial dysfunction-related genes.

Mitochondria are significant both for cellular energy production and reactive oxygen/nitrogen species formation. However, the significant functions of mitochondrial genes related to oxidative stress (MTGs-OS) in pancreatic cancer (PC) and pancreatic neuroendocrine tumor (PNET) are yet to be investigated integrally. Therefore, in pan-cancer, particularly PC and PNET, a thorough assessment of the MTGs-OS is required. Expression patterns, prognostic significance, mutation data, methylation rates, and pathway-regulation interactions were studied to comprehensively elucidate the involvement of MTGs-OS in pan-cancer. Next, we separated the 930 PC and 226 PNET patients into 3 clusters according to MTGs-OS expression and MTGs-OS scores. LASSO regression analysis was utilized to construct a novel prognostic model for PC. qRT-PCR(Quantitative real-time PCR) experiments were performed to verify the expression levels of model genes. The subtype associated with the poorest prognosis and lowerest MTGs-OS scores was Cluster 3, which could demonstrate the vital function of MTGs-OS for the pathophysiological processes of PC. The three clusters displayed distinct variations in the expression of conventional cancer-associated genes and the infiltration of immune cells. Similar molecular heterogeneity was observed in patients with PNET. PNET patients with S1 and S2 subtypes also showed distinct MTGs-OS scores. Given the important function of MTGs-OS in PC, a novel and robust MTGs-related prognostic signature (MTGs-RPS) was established and identified for predicting clinical outcomes for PC accurately. Patients with PC were separated into the training, internal validation, and external validation datasets at random; the expression profile of MTGs-OS was used to classify patients into high-risk (poor prognosis) or low-risk (good prognosis) categories. The variations in the tumor immune microenvironment may account for the better prognoses observed in high-risk individuals relative to low-risk ones. Overall, our study for the first time identified and validated eleven MTGs-OS remarkably linked to the progression of PC and PNET, and elaborated the biological function and prognostic value of MTGs-OS. Most importantly, we established a novel protocol for the prognostic evaluation and individualized treatment for patients with PC.

CT-based radiomics can identify physiological modifications of bone structure related to subjects' age and sex.

Radiomics of vertebral bone structure is a promising technique for identification of osteoporosis. We aimed at assessing the accuracy of machine learning in identifying physiological changes related to subjects' sex and age through analysis of radiomics features from CT images of lumbar vertebrae, and define its generalizability across different scanners. We annotated spherical volumes-of-interest (VOIs) in the center of the vertebral body for each lumbar vertebra in 233 subjects who had undergone lumbar CT for back pain on 3 different scanners, and we evaluated radiomics features from each VOI. Subjects with history of bone metabolism disorders, cancer, and vertebral fractures were excluded. We performed machine learning classification and regression models to identify subjects' sex and age respectively, and we computed a voting model which combined predictions. The model was trained on 173 subjects and tested on an internal validation dataset of 60. Radiomics was able to identify subjects' sex within single CT scanner (ROC AUC: up to 0.9714), with lower performance on the combined dataset of the 3 scanners (ROC AUC: 0.5545). Higher consistency among different scanners was found in identification of subjects' age (R2 0.568 on all scanners, MAD 7.232years), with highest results on a single CT scanner (R2 0.667, MAD 3.296years). Radiomics features are able to extract biometric data from lumbar trabecular bone, and determine bone modifications related to subjects' sex and age with great accuracy. However, acquisition from different CT scanners reduces the accuracy of the analysis.

Machine learning-based prediction model for postoperative delirium in non-cardiac surgery

BackgroundPostoperative delirium is a common complication that is distressing. This study aimed to demonstrate a prediction model for delirium.MethodsAmong 203,374undergoing non-cardiac surgery between January 2011 and June 2019 at Samsung Medical Center, 2,865 (1.4%) were diagnosed with postoperative delirium. After comparing performances of machine learning algorithms, we chose variables for a prediction model based on an extreme gradient boosting algorithm. Using the top five variables, we generated a prediction model for delirium and conducted an external validation. The Kaplan–Meier and Cox survival analyses were used to analyse the difference of delirium occurrence in patients classified as a prediction model.ResultsThe top five variables selected for the postoperative delirium prediction model were age, operation duration, physical status classification, male sex, and surgical risk. An optimal probability threshold in this model was estimated to be 0.02. The area under the receiver operating characteristic (AUROC) curve was 0.870 with a 95% confidence interval of 0.855–0.885, and the sensitivity and specificity of the model were 0.76 and 0.84, respectively. In an external validation, the AUROC was 0.867 (0.845–0.877). In the survival analysis, delirium occurred more frequently in the group of patients predicted as delirium using an internal validation dataset (p < 0.001).ConclusionBased on machine learning techniques, we analyzed a prediction model of delirium in patients who underwent non-cardiac surgery. Screening for delirium based on the prediction model could improve postoperative care. The working model is provided online and is available for further verification among other populations.Trial registrationKCT 0006363.

Development of a Bispectral index score prediction model based on an interpretable deep learning algorithm

BackgroundProper maintenance of hypnosis is crucial for ensuring the safety of patients undergoing surgery. Accordingly, indicators, such as the Bispectral index (BIS), have been developed to monitor hypnotic levels. However, the black-box nature of the algorithm coupled with the hardware makes it challenging to understand the underlying mechanisms of the algorithms and integrate them with other monitoring systems, thereby limiting their use. ObjectiveWe propose an interpretable deep learning model that forecasts BIS values 25 s in advance using 30 s electroencephalogram (EEG) data. Material and methodsThe proposed model utilized EEG data as a predictor, which is then decomposed into amplitude and phase components using fast Fourier Transform. An attention mechanism was applied to interpret the importance of these components in predicting BIS. The predictability of the model was evaluated on both regression and binary classification tasks, where the former involved predicting a continuous BIS value, and the latter involved classifying a dichotomous status at a BIS value of 60. To evaluate the interpretability of the model, we analyzed the attention values expressed in the amplitude and phase components according to five ranges of BIS values. The proposed model was trained and evaluated using datasets collected from two separate medical institutions. Results and conclusionThe proposed model achieved excellent performance on both the internal and external validation datasets. The model achieved a root-mean-square error of 6.614 for the regression task, and an area under the receiver operating characteristic curve of 0.937 for the binary classification task. Interpretability analysis provided insight into the relationship between EEG frequency components and BIS values. Specifically, the attention mechanism revealed that higher BIS values were associated with increased amplitude attention values in high-frequency bands and increased phase attention values in various frequency bands. This finding is expected to facilitate a more profound understanding of the BIS prediction mechanism, thereby contributing to the advancement of anesthesia technologies.

Classification of Hypoglycemic Events in Type 1 Diabetes Using Machine Learning Algorithms.

To improve the utilization of continuous- and flash glucose monitoring (CGM/FGM) data we have tested the hypothesis that a machine learning (ML)modelcan be trained to identify the most likely root causes for hypoglycemic events. CGM/FGM data were collected from 449 patients with type 1 diabetes. Of the 42,120 identified hypoglycemic events, 5041 wererandomly selected for classification by two clinicians. Three causes of hypoglycemia were deemed possible to interpret and later validate by insulin and carbohydrate recordings:(1)overestimated bolus (27%), (2)overcorrection of hyperglycemia (29%) and (3)excessive basal insulin presure (44%). The dataset wassplit into a training (n = 4026 events, 304 patients) and an internal validation dataset (n = 1015 events, 145 patients). A number of ML model architectures were applied and evaluated. A separate dataset was generated from 22 patients (13 'known' and 9 'unknown') with insulin and carbohydrate recordings. Hypoglycemic events from this dataset were also interpreted by five clinicians independently. Of the evaluated ML models, a purpose-built convolutional neural network (HypoCNN) performed best. Masking the time series, adding time features and using class weights improvedthe performance of this model, resulting in an average area under the curve (AUC) of 0.921 in the original train/test split. In the dataset validated by insulin and carbohydrate recordings (n = 435 events), i.e. 'ground truth,' our HypoCNN model achieved an AUC of 0.917. The findings support the notion that ML models can be trained to interpret CGM/FGM data. Our HypoCNN model provides a robust and accurate method to identify root causes of hypoglycemic events.

Application of artificial intelligence for overall survival risk stratification in oropharyngeal carcinoma: A validation of ProgTOOL

BackgroundIn recent years, there has been a surge in machine learning-based models for diagnosis and prognostication of outcomes in oncology. However, there are concerns relating to the model’s reproducibility and generalizability to a separate patient cohort (i.e., external validation). ObjectivesThis study primarily provides a validation study for a recently introduced and publicly available machine learning (ML) web-based prognostic tool (ProgTOOL) for overall survival risk stratification of oropharyngeal squamous cell carcinoma (OPSCC). Additionally, we reviewed the published studies that have utilized ML for outcome prognostication in OPSCC to examine how many of these models were externally validated, type of external validation, characteristics of the external dataset, and diagnostic performance characteristics on the internal validation (IV) and external validation (EV) datasets were extracted and compared. Methods: We used a total of 163 OPSCC patients obtained from the Helsinki University Hospital to externally validate the ProgTOOL for generalizability. In addition, PubMed, OvidMedline, Scopus, and Web of Science databases were systematically searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. ResultsThe ProgTOOL produced a predictive performance of 86.5% balanced accuracy, Mathew's correlation coefficient of 0.78, Net Benefit (0.7) and Brier score (0.06) for overall survival stratification of OPSCC patients as either low-chance or high-chance. In addition, out of a total of 31 studies found to have used ML for the prognostication of outcomes in OPSCC, only seven (22.6%) reported a form of EV. Three studies (42.9%) each used either temporal EV or geographical EV while only one study (14.2%) used expert as a form of EV. Most of the studies reported a reduction in performance when externally validated. ConclusionThe performance of the model in this validation study indicates that it may be generalized, therefore, bringing recommendations of the model for clinical evaluation closer to reality. However, the number of externally validated ML-based models for OPSCC is still relatively small. This significantly limits the transfer of these models for clinical evaluation and subsequently reduces the likelihood of the use of these models in daily clinical practice. As a gold standard, we recommend the use of geographical EV and validation studies to reveal biases and overfitting of these models. These recommendations are poised to facilitate the implementation of these models in clinical practice.

Development and validation of a diagnostic aid for convulsive epilepsy in sub-Saharan Africa: a retrospective case-control study.

Identification of convulsive epilepsy in sub-Saharan Africa relies on access to resources that are often unavailable. Infrastructure and resource requirements can further complicate case verification. Using machine-learning techniques, we have developed and tested a region-specific questionnaire panel and predictive model to identify people who have had a convulsive seizure. These findings have been implemented into a free app for health-care workers in Kenya, Uganda, Ghana, Tanzania, and South Africa. In this retrospective case-control study, we used data from the Studies of the Epidemiology of Epilepsy in Demographic Sites in Kenya, Uganda, Ghana, Tanzania, and South Africa. We randomly split these individuals using a 7:3 ratio into a training dataset and a validation dataset. We used information gain and correlation-based feature selection to identify eight binary features to predict convulsive seizures. We then assessed several machine-learning algorithms to create a multivariate prediction model. We validated the best-performing model with the internal dataset and a prospectively collected external-validation dataset. We additionally evaluated a leave-one-site-out model (LOSO), in which the model was trained on data from all sites except one that, in turn, formed the validation dataset. We used these features to develop a questionnaire-based predictive panel that we implemented into a multilingual app (the Epilepsy Diagnostic Companion) for health-care workers in each geographical region. We analysed epilepsy-specific data from 4097 people, of whom 1985 (48·5%) had convulsive epilepsy, and 2112 were controls. From 170 clinical variables, we initially identified 20 candidate predictor features. Eight features were removed, six because of negligible information gain and two following review by a panel of qualified neurologists. Correlation-based feature selection identified eight variables that demonstrated predictive value; all were associated with an increased risk of an epileptic convulsion except one. The logistic regression, support vector, and naive Bayes models performed similarly, outperforming the decision-tree model. We chose the logistic regression model for its interpretability and implementability. The area under the receiver operator curve (AUC) was 0·92 (95% CI 0·91-0·94, sensitivity 85·0%, specificity 93·7%) in the internal-validation dataset and 0·95 (0·92-0·98, sensitivity 97·5%, specificity 82·4%) in the external-validation dataset. Similar results were observed for the LOSO model (AUC 0·94, 0·93-0·96, sensitivity 88·2%, specificity 95·3%). On the basis of these findings, we developed the Epilepsy Diagnostic Companion as a predictive model and app offering a validated culture-specific and region-specific solution to confirm the diagnosis of a convulsive epileptic seizure in people with suspected epilepsy. The questionnaire panel is simple and accessible for health-care workers without specialist knowledge to administer. This tool can be iteratively updated and could lead to earlier, more accurate diagnosis of seizures and improve care for people with epilepsy. The Wellcome Trust, the UK National Institute of Health Research, and the Oxford NIHR Biomedical Research Centre.

Tectonic infarct analysis: A computational tool for automated whole-brain infarct analysis from TTC-stained tissue

BackgroundInfarct volume measured from 2,3,5-triphenyltetrazolium chloride (TTC)-stained brain slices is critical to in vivo stroke models. In this study, we developed an interactive, tunable, software that automatically computes whole-brain infarct metrics from serial TTC-stained brain sections. MethodsThree rat ischemic stroke cohorts were used in this study (Total n = 91 rats; Cohort 1 n = 21, Cohort 2 n = 40, Cohort 3 n = 30). For each, brains were serially-sliced, stained with TTC and scanned on both anterior and posterior sides. Ground truth annotation and infarct morphometric analysis (e.g., brain-Vbrain, infarct-Vinfarct, and non-infarct-Vnon-infarct volumes) were completed by domain experts. We used Cohort 1 for brain and infarct segmentation model development (n = 3 training cases with 36 slices [18 anterior and posterior faces], n = 18 testing cases with 218 slices [109 anterior and posterior faces]), as well as infarct morphometrics automation. The infarct quantification pipeline and pre-trained model were packaged as a standalone software and applied to Cohort 2, an internal validation dataset. Finally, software and model trainability were tested as a use-case with Cohort 3, a dataset from a separate institute. ResultsBoth high segmentation and statistically significant quantification performance (correlation between manual and software) were observed across all datasets. Segmentation performance: Cohort 1 brain accuracy = 0.95/f1-score = 0.90, infarct accuracy = 0.96/f1-score = 0.89; Cohort 2 brain accuracy = 0.97/f1-score = 0.90, infarct accuracy = 0.97/f1-score = 0.80; Cohort 3 brain accuracy = 0.96/f1-score = 0.92, infarct accuracy = 0.95/f1-score = 0.82. Infarct quantification (cohort average): Vbrain (ρ = 0.87, p < 0.001), Vinfarct (0.92, p < 0.001), Vnon-infarct (0.80, p < 0.001), %infarct (0.87, p = 0.001), and infarct:non-infact ratio (ρ = 0.92, p < 0.001). ConclusionTectonic Infarct Analysis software offers a robust and adaptable approach for rapid TTC-based stroke assessment.

An immune-related gene signature predicts the 28-day mortality in patients with sepsis.

Sepsis is the leading cause of death in intensive care units and is characterized by multiple organ failure, including dysfunction of the immune system. In the present study, we performed an integrative analysis on publicly available datasets to identify immune-related genes (IRGs) that may play vital role in the pathological process of sepsis, based on which a prognostic IRG signature for 28-day mortality prediction in patients with sepsis was developed and validated. Weighted gene co-expression network analysis (WGCNA), Cox regression analysis and least absolute shrinkage and selection operator (LASSO) estimation were used to identify functional IRGs and construct a model for predicting the 28-day mortality. The prognostic value of the model was validated in internal and external sepsis datasets. The correlations of the IRG signature with immunological characteristics, including immune cell infiltration and cytokine expression, were explored. We finally validated the expression of the three IRG signature genes in blood samples from 12 sepsis patients and 12 healthy controls using qPCR. We established a prognostic IRG signature comprising three gene members (LTB4R, HLA-DMB and IL4R). The IRG signature demonstrated good predictive performance for 28-day mortality on the internal and external validation datasets. The immune infiltration and cytokine analyses revealed that the IRG signature was significantly associated with multiple immune cells and cytokines. The molecular pathway analysis uncovered ontology enrichment in myeloid cell differentiation and iron ion homeostasis, providing clues regarding the underlying biological mechanisms of the IRG signature. Finally, qPCR detection verified the differential expression of the three IRG signature genes in blood samples from 12 sepsis patients and 12 healthy controls. This study presents an innovative IRG signature for 28-day mortality prediction in sepsis patients, which may be used to facilitate stratification of risky sepsis patients and evaluate patients' immune state.

Deep learning for real-time detection of breast cancer presenting pathological nipple discharge by ductoscopy.

As a common breast cancer-related complaint, pathological nipple discharge (PND) detected by ductoscopy is often missed diagnosed. Deep learning techniques have enabled great advances in clinical imaging but are rarely applied in breast cancer with PND. This study aimed to design and validate an Intelligent Ductoscopy for Breast Cancer Diagnostic System (IDBCS) for breast cancer diagnosis by analyzing real-time imaging data acquired by ductoscopy. The present multicenter, case-control trial was carried out in 6 hospitals in China. Images for consecutive patients, aged ≥18 years, with no previous ductoscopy, were obtained from the involved hospitals. All individuals with PND confirmed from breast lesions by ductoscopy were eligible. Images from Beijing Chao-Yang Hospital were randomly assigned (8:2) to the training (IDBCS development) and internal validation (performance evaluation of the IDBCS) datasets. Diagnostic performance was further assessed with internal and prospective validation datasets from Beijing Chao-Yang Hospital; further external validation was carried out with datasets from 5 primary care hospitals. Diagnostic accuracies, sensitivities, specificities, and positive and negative predictive values for IDBCS and endoscopists (expert, competent, or trainee) in the detection of malignant lesions were obtained by the Clopper-Pearson method. Totally 11305 ductoscopy images in 1072 patients were utilized for developing and testing the IDBCS. Area under the curves (AUCs) in breast cancer detection were 0·975 (95%CI 0·899-0·998) and 0·954 (95%CI 0·925-0·975) in the internal validation and prospective datasets, respectively, and ranged between 0·922 (95%CI 0·866-0·960) and 0·965 (95%CI 0·892-0·994) in the 5 external validation datasets. The IDBCS had superior diagnostic accuracy compared with expert (0.912 [95%CI 0.839-0.959] vs 0.726 [0.672-0.775]; p<0.001), competent (0.699 [95%CI 0.645-0.750], p<0.001), and trainee (0.703 [95%CI 0.648-0.753], p<0.001) endoscopists. IDBCS outperforms clinical oncologists, achieving high accuracy in diagnosing breast cancer with PND. The novel system could help endoscopists improve their diagnostic efficacy in breast cancer diagnosis.

A Deep Learning Radiomics Nomogram to Predict Response to Neoadjuvant Chemotherapy for Locally Advanced Cervical Cancer: A Two-Center Study

Purpose: This study aimed to establish a deep learning radiomics nomogram (DLRN) based on multiparametric MR images for predicting the response to neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC). Methods: Patients with LACC (FIGO stage IB-IIIB) who underwent preoperative NACT were enrolled from center 1 (220 cases) and center 2 (independent external validation dataset, 65 cases). Handcrafted and deep learning-based radiomics features were extracted from T2WI, DWI and contrast-enhanced (CE)-T1WI, and radiomics signatures were built based on the optimal features. Two types of radiomics signatures and clinical features were integrated into the DLRN for prediction. The AUC, calibration curve and decision curve analysis (DCA) were employed to illustrate the performance of these models and their clinical utility. In addition, disease-free survival (DFS) was assessed by Kaplan-Meier survival curves based on the DLRN. Results: The DLRN showed favorable predictive values in differentiating responders from nonresponders to NACT with AUCs of 0.963, 0.940 and 0.910 in the three datasets, with good calibration (all p > 0.05). Furthermore, the DLRN performed better than the clinical model and handcrafted radiomics signature in all datasets (all p < 0.05) and slightly higher than the DL-based radiomics signature in the internal validation dataset (p = 0.251). DCA indicated that the DLRN has potential in clinical applications. Furthermore, the DLRN was strongly correlated with the DFS of LACC patients (HR = 0.223; p = 0.004). Conclusion: The DLRN performed well in preoperatively predicting the therapeutic response in LACC and could provide valuable information for individualized treatment.

Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study

We explored a new artificial intelligence-assisted method to assist junior ultrasonographers in improving the diagnostic performance of uterine fibroids and further compared it with senior ultrasonographers to confirm the effectiveness and feasibility of the artificial intelligence method. In this retrospective study, we collected a total of 3870 ultrasound images from 667 patients with a mean age of 42.45 years ± 6.23 [SD] for those who received a pathologically confirmed diagnosis of uterine fibroids and 570 women with a mean age of 39.24 years ± 5.32 [SD] without uterine lesions from Shunde Hospital of Southern Medical University between 2015 and 2020. The DCNN model was trained and developed on the training dataset (2706 images) and internal validation dataset (676 images). To evaluate the performance of the model on the external validation dataset (488 images), we assessed the diagnostic performance of the DCNN with ultrasonographers possessing different levels of seniority. The DCNN model aided the junior ultrasonographers (Averaged) in diagnosing uterine fibroids with higher accuracy (94.72% vs. 86.63%, P < 0.001), sensitivity (92.82% vs. 83.21%, P = 0.001), specificity (97.05% vs. 90.80%, P = 0.009), positive predictive value (97.45% vs. 91.68%, P = 0.007), and negative predictive value (91.73% vs. 81.61%, P = 0.001) than they achieved alone. Their ability was comparable to that of senior ultrasonographers (Averaged) in terms of accuracy (94.72% vs. 95.24%, P = 0.66), sensitivity (92.82% vs. 93.66%, P = 0.73), specificity (97.05% vs. 97.16%, P = 0.79), positive predictive value (97.45% vs. 97.57%, P = 0.77), and negative predictive value (91.73% vs. 92.63%, P = 0.75). The DCNN-assisted strategy can considerably improve the uterine fibroid diagnosis performance of junior ultrasonographers to make them more comparable to senior ultrasonographers.

Predictive factors of microvascular invasion in patients with intrahepatic mass-forming cholangiocarcinoma based on magnetic resonance images.

The aim of this retrospective study was to develop and validate a preoperative nomogram for predicting microvascular invasion (MVI) in patients with intrahepatic mass-forming cholangiocarcinoma (IMCC) based on magnetic resonance imaging (MRI). In this retrospective study, 224 consecutive patients with clinicopathologically confirmed IMCC were enrolled. Patients whose data were collected from February 2010 to December 2020 were randomly divided into the training (131 patients) and internal validation (51 patients) datasets. The data from January 2021 to November 2021 (42 patients) were allocated to the time-independent validation dataset. Univariate and multivariate forward logistic regression analyses were used to identify preoperative MRI features that were significantly related to MVI, which were then used to develop the nomogram. We used the area under the receiver operating characteristic curve (AUC) and calibration curve to evaluate the performance of the nomogram. Interobserver agreement of MRI qualitative features was good to excellent, with κ values of 0.613-0.882. Multivariate analyses indicated that the following variables were independent predictors of MVI: multiple tumours (odds ratio [OR]) = 4.819, 95% confidence interval [CI] 1.562-14.864, P = 0.006), ill-defined margin (OR = 6.922, 95% CI 2.883-16.633, P < 0.001), and carbohydrate antigen 19-9 (CA 19-9) > 37U/ml (OR = 2.890, 95% CI 1.211-6.897, P = 0.017). A nomogram incorporating these factors was established using well-fitted calibration curves. The nomogram showed good diagnostic efficacy for MVI, with AUC values of 0.838, 0.819, and 0.874 for the training, internal validation, and time-independent validation datasets, respectively. A nomogram constructed using independent factors, namely the presence of multiple tumours, ill-defined margins, and CA 19-9 > 37U/ml could predict the presence of MVI. This can facilitate personalised therapeutic strategy and clinical management in patients with IMCC.

Nomograms for Predicting Survival Outcomes in Patients with Neuroendocrine Neoplasms of the Gallbladder Undergoing Primary Tumor Resection: A Population-Based Study.

Neuroendocrine neoplasms of the gallbladder (GB-NENs) are a rare group of histologically heterogeneous tumors, and surgical resection of the primary tumor is the mainstream treatment at the moment. The current study aimed to establish and validate novel nomograms for patients with GB-NENs undergoing primary tumor resection to predict the 6-, 12-, and 18-month overall survival (OS) and cancer-specific survival (CSS). Clinicopathological information of patients with GB-NENs undergoing primary tumor resection between 2004 and 2018 was derived from the Surveillance, Epidemiology, and End Results (SEER) database. Candidate prognostic factors were selected by Cox regression analyses, and the nomograms were constructed. Finally, concordance index (C-index), calibration plot, area under the curve from the receiver operating characteristic curve (AUC), and decision curve analysis (DCA) were utilized to assess the effective performance of the nomograms. A total of 221 patients with GB-NENs undergoing resection were enrolled in this retrospective study. Using the Cox regression analyses, age, pathological classification, tumor size, and SEER stage were identified as the independent prognostic factors of patients with GB-NENs undergoing resection, and nomograms were constructed. The C-indexes of OS and CSS in training dataset were 0.802 (95% CI: 0.757-0.848) and 0.846 (95% CI: 0.798-0.895), while those of internal validation dataset were 0.862 (95% CI: 0.802-0.922) and 0.879 (95% CI: 0.824-0.934), respectively. Taken together, the nomograms are accurate enough to predict the prognostic factors of GB-NEN patients undergoing resection, allowing for treatment decision-making and clinical monitoring for future clinical work.