Natural language processing of admission notes to predict postpartum hemorrhage

For health and safety monitoring in civil constructions such as bridges, roads and pavements, segmenting the regions of interest is the fundamental requirement for image analysis at high-level semantic. One of the major structural problems in concrete and asphalt surfaces are cracks, which start with harming the visual aspect of the construction and further lead to failure of the construction. This study makes four contributions to extract the image foreground from the background in order to address the crack detection task on the asphalt and concrete surfaces. Specifically, we model cracks as foreground objects and concrete or asphalt surfaces as textured background. The first contribution of this research is a hybrid image processing method for crack detection. In this method, the cracks are modelled as linear structures on the background of textured concrete or asphalt surfaces, which can be extracted by combining structure extraction with global pattern distribution. There are two phases in this model towards creating the final structure-texture map. The first phase is extracting strong structures or edges using relative total variation measures, which produces a structure feature map by preserving the edges and suppressing the background noises. The second phase calculates the spatial distribution of textures across the image. A bag-of-words model is used in this phase to quantise the texture pattern, which in crack detection application is the widely distributed road texture background. The local structure map and the global distribution map extract the crack structure and the textured background, respectively. The final crack is extracted by fusing these two maps and applying binarisation as the post-processing step. This model achieved a better result compared with the local structure extraction and the saliency method. As the second contribution, a large-scale dataset of asphalt and concrete crack images is prepared, including images with their corresponding high-resolution pixel-wise labels. To the best of our knowledge, until the completion of this thesis, there has not been any crack image dataset with pixel-wise ground truth labels available. The original crack image set includes 2532 images of cracks on brick and asphalt surfaces. This image set is split into training, validation and testing sets with the ratio of 50/25/25. Two augmentation techniques of rotation and ipping are applied to only the training set while validation and testing sets are locked in order to prevent the data leakage. All models are learned on the training set after fine-tuning the hyper-parameters. After each tuning, an early estimate of the model accuracy is obtained using the validation set. Finally, an unbiased performance estimation of the fitted model is provided on the testing set. The third contribution of this thesis is developing two encoder-decoder networks by exploring the recent advances of deep learning research for crack detection and applying them on our crack dataset. The first network is inspired by DeepLab, which is a modified ResNet architecture. In this network the last pooling layer is replaced with an Atrous Spatial Pyramid Pooling (ASPP) module. This encoder-decoder structure is designed to classify each image pixel into two foreground cracks or textured background. The second model is inspired by Full Resolution Residual Network (FRRN), which is a ResNetlike network with two residual and pooling streams to extract the high- and low-level features, respectively. The combination of di erent level features in this model improves the localization of crack pixels as well as the recognition of the crack structure as a whole. As FRRN outperforms DeepLab on crack classification, we select it as the baseline for further research. In our last contribution, we optimise the FRRN model by reducing the number of parameters. Inspired by the Inception module which significantly improved the utilization of the computing resources inside the GoogLeNet, we proposed Incepted FRRN (I-FRRN) network by embedding the Inception module inside the FRRN. Combining these two structures, our proposed model records 88.14% accuracy in classifying the positive class with 0.22% improvement, while having less than half the number of parameters compared with FRRN. The results show that the proposed architecture achieves significant computational e ciency gains and comparable or higher class-accuracy in crack classification task over the baseline model.

Background and AimsThe prognosis of papillary thyroid carcinoma (PTC) is highly variable, even for high-risk cases. The predictive and prognostic role of the lymphocyte-to-monocyte ratio (LMR) has been reported in other cancers. The aim of our present study was to explore the value of LMR prognostic prediction in high-risk PTC patients.Patients and MethodsTwo hundred and twenty-four PTC high-risk cases at West China Hospital were randomized into a training set (112 cases) and testing set (112 cases), while 48 cases in Shang Jin Nan Fu Hospital were included as the external validation set.ResultsA lower preoperative LMR correlated with larger tumor size, advanced N and M stages, and an increased number of multiple PTC cases in the training, testing, and validation sets (all P<0.05 in the three sets). Patients with a high LMR exhibited significantly improved overall and PTC-free survival compared with those of patients with a low LMR in the training, testing, validation, and combined sets (all P<0.05 in the individual and combined sets). Moreover, multivariate analyses identified the LMR as an independent prognostic factor for overall and PTC-free survival. The nomograms for predicting the 5-year mortality and PTC recurrence were developed based on the risk factors in the training set and validated in the independent testing and validation sets.ConclusionThe preoperative LMR was identified as an independent prognostic factor that could be incorporated into the two nomograms with other risk factors to predict overall survival and PTC-free survival for individual patients.

Get Your Brain in the Game: Using Machine Learning to Predict Recovery Timelines Following Sports-Related Concussion.

Colonoscopy with biopsy is the "gold" standard for evaluating disease activity in inflammatory bowel diseases (IBD). Current research is geared toward finding non-invasive, cost-efficient methods that estimate disease activity. We aimed to develop a neural network (NN) model for the non-invasive prediction of histologic activity in IBD using routinely available clinical-biological parameters. Standard clinical-biological parameters and histologic activity from 371 ulcerative colitis (UC) and 115 Crohn's disease (CD) patient records were collected. A training set, a test set, and a validation set were used for building/validating 2 models for each disease. All models had binary output predicting the active/inactive histologic disease status. For both diseases, the first model used both clinical and biological inputs, while the second used only biological data. First UC model obtained an accuracy of 95.59% on the test set and 96.67% on the validation set. The second UC model achieved accuracies of 88.24% and 86.67% on the test and validation sets, respectively. The First CD classifier resulted in 90.48% accuracy on the test set and 91.67% on the validation set. Finally, the second CD classifier obtained an accuracy of 85.71% on the test set and 91.67% on the validation set. An accurate and non-invasive artificial intelligence system to predict histologic disease activity in IBD is designed. Our models achieved similar or better results compared to the documented performance of fecal calprotectin (the best non-invasive IBD biomarker to date). Given these favorable results, we anticipate the future utility in the clinical setting of a non-invasive disease activity prediction.

10011 Background: We previously presented (ASCO 04 #9506) an exploratory analysis of 13 molecular markers in relation to clinical outcomes in 846 patients treated with fluorouracil (FU), or FU+irinotecan, or FU+oxaliplatin in a large UK-based randomized controlled trial (FOCUS - ASCO ’05 #3518). High TS IHC expression and tumor grade were highly significantly associated with reduced failure-free survival (FFS) in a multivariable model. We now present data from an independent validation set of 449 FOCUS patients and on the combined test and validation sets. Methods: Formalin-fixed, paraffin embedded blocks were retrieved from consenting patients and tissue microarrays made for IHC assessment. Factors assessed for the effect on FFS of first-line therapy were: liver metastases; ALP; grade; mucoid status; age; and IHC for dUTPase and TS. Log-rank univariate analyses and Cox Model multivariable analysis was performed. Results: Univariate analysis of the validation set failed to confirm evidence of the previously observed association between high TS expression and FFS (p=0.2); however high dUTPase IHC (p=0.01), ALP (p&lt;0.0001) and grade (p=0.001) showed significant associations. Table 1 illustrates the results of univariate and multivariable analysis of the combined test and validation sets. In the Cox Model, high TS IHC expression, tumor grade and baseline serum ALP were highly significant predictors of reduced FFS. Conclusions: We failed to confirm a significant association between high TS expression and reduced FFS in an independent validation set. However, in an exploratory analysis of the combined validation and test sets (n&gt;1000), TS IHC expression remained a highly significant predictor of FFS. Overall, our results cannot be taken to demonstrate a powerful and clinically useful influence of TS on treatment efficacy, but are consistent with a moderate effect. [Table: see text] No significant financial relationships to disclose.

Objective: This study intends to investigate the causal association between 35 blood and urine biomarkers and postmenopausal osteoporosis (PMOP) through two-way Mendelian randomization analysis. Methods: This study adopted a two-way Mendelian randomization analysis, with data sourced from the UK Biobank and the Finnish Biobank Study. Among them, the R12 dataset of the Finnish Biobank Study was used as the test set, and the R11 dataset as the validation set. The study regarded 35 biomarkers as exposure factors and PMOP (a condition characterized by decreased bone density after menopause) as the outcome variable. It was analyzed through methods such as the inverse variance weighting method, the weighted median method, and MR-Egger regression, and combined with the MR-PRESSO test to exclude the influence of pleiotropy. Results: In the positive direction analysis, alkaline phosphatase, glomerular filtration rate, sex hormone-binding globulin, and total protein showed statistical significance in both the test set and the validation set, and they were all risk factors for PMOP. Direct bilirubin and uric acid demonstrated statistical significance in both the test and validation sets, and they served as protective factors against PMOP. In the negative direction analysis, alkaline phosphatase showed statistical significance in both the test set and the validation set, being a positive result for PMOP; sex hormone-binding globulin and total bilirubin showed statistical significance in both the test set and the validation set, being negative results for PMOP. Conclusion: Employing bidirectional Mendelian randomization methodology, this investigation elucidated the causal relationships between multiple hematological and urinary biomarkers and PMOP. The results provide promising biomarker candidates for future diagnostic and therapeutic strategies targeting PMOP, while simultaneously establishing a robust framework for subsequent exploration of its underlying pathophysiological mechanisms.

BackgroundNailfold capillary microscopy is used for diagnostic purposes in rheumatology since many years. Abnormal nailfold capillaries are also listed in the 2013 ACR/EULAR classification criteria for systemic sclerosis (SSc) [1]....

To develop a method for identifying high-risk patients among septic populations requiring mechanical ventilation, and to conduct phenotypic analysis based on this method. Data from four sources were utilized: the Medical Information Mart for Intensive Care (MIMIC-IV 2.0, MIMIC-III 1.4), the Philips eICU-Collaborative Research Database 2.0 (eICU-CRD 2.0), and the Anhui Medical University Second Affiliated Hospital dataset. The adult patients in intensive care unit (ICU) who met Sepsis-3 and received invasive mechanical ventilation (IMV) on the first day of first admission were enrolled. The MIMIC-IV dataset with the highest data integrity was divided into a training set and a test set at a 6:1 ratio, while the remaining datasets were served as validation sets. The demographic information, comorbidities, laboratory indicators, commonly used ICU scores, and treatment measures of patients were extracted. Clinical data collected within first day of ICU admission were used to calculate the sequential organ failure assessment (SOFA) score. K-means clustering was applied to cluster SOFA score components, and the sum of squared errors (SSE) and Davies-Bouldin index (DBI) were used to determine the optimal number of disease subtypes. For clustering results, normalized methods were employed to compare baseline characteristics by visualization, and Kaplan-Meier curves were used to analyze clinical outcomes across phenotypes. This study enrolled patients from MIMIC-IV dataset (n = 11 166), MIMIC-III dataset (n = 4 821), eICU-CRD dataset (n = 6 624), and a local dataset (n = 110), with the four datasets showing similar median ages and male proportions exceeding 50%; using 85% of the MIMIC-IV dataset as the training set, 15% as the test set, and the rest dataset as the validation set. K-means clustering based on the six-item SOFA score was performed to determine the optimal number of clusters as 3, and patients were finally classified into three phenotypes. In the training set, compared with the patients with phenotype II and phenotype III, those with phenotype I had the more severe circulatory and respiratory dysfunction, a higher proportion of vasoactive drug usage, more obvious metabolic acidosis and hypoxia, and a higher incidence of congestive heart failure. The patients with phenotype II was dominated by respiratory dysfunction with higher visceral injury. The patients with phenotype III had relatively stable organ function. The above characteristics were consistent in both the test and validation sets. Analysis of infection-related indicators showed that the patients with phenotype I had the highest SOFA score within 7 days after ICU admission, initial decreases and later increases in platelet count (PLT), and higher counts of neutrophils, lymphocytes, and monocytes as compared with those with phenotype II and phenotype III, their blood cultures had a higher positivity rates for Gram-positive bacteria, Gram-negative bacteria and fungi as compared with those with phenotype II and phenotype III. The Kaplan-Meier curve indicated that in the training, test, and validation sets, the 28-day cumulative mortality of patients with phenotype I was significantly higher than that of patients with phenotypes II and phenotype III. Three distinct phenotypes in septic patients receiving IMV based on unsupervised machine learning is derived, among which phenotype I, characterized by cardiorespiratory failure, can be used for the early identification of high-risk patients in this population. Moreover, this population is more prone to bloodstream infections, posing a high risk and having a poor prognosis.

ObjectiveThe primary objective of this study was to investigate the risk factors for diabetic peripheral neuropathy (DPN) and to establish an early diagnostic prediction model for its onset, based on clinical data and biochemical indices.MethodsRetrospective data were collected from 1,446 diabetic patients at the First Affiliated Hospital of Anhui University of Chinese Medicine and were split into training and internal validation sets in a 7:3 ratio. Additionally, 360 diabetic patients from the Second Affiliated Hospital were used as an external validation cohort. Feature selection was conducted within the training set, where univariate logistic regression identified variables with a p-value < 0.05, followed by backward elimination to construct the logistic regression model. Concurrently, the random forest algorithm was applied to the training set to identify the top 10 most important features, with hyperparameter optimization performed via grid search combined with cross-validation. Model performance was evaluated using ROC curves, decision curve analysis, and calibration curves. Model fit was assessed using the Hosmer-Lemeshow test, followed by Brier Score evaluation for the random forest model. Ten-fold cross-validation was employed for further validation, and SHAP analysis was conducted to enhance model interpretability.ResultsA nomogram model was developed using logistic regression with key features: limb numbness, limb pain, diabetic retinopathy, diabetic kidney disease, urinary protein, diastolic blood pressure, white blood cell count, HbA1c, and high-density lipoprotein cholesterol. The model achieved AUCs of 0.91, 0.88, and 0.88 for the training, validation, and test sets, respectively, with a mean AUC of 0.902 across 10-fold cross-validation. Hosmer-Lemeshow test results showed p-values of 0.595, 0.418, and 0.126 for the training, validation, and test sets, respectively. The random forest model demonstrated AUCs of 0.95, 0.88, and 0.88 for the training, validation, and test sets, respectively, with a mean AUC of 0.886 across 10-fold cross-validation. The Brier score indicates a good calibration level, with values of 0.104, 0.143, and 0.142 for the training, validation, and test sets, respectively.ConclusionThe developed nomogram exhibits promise as an effective tool for the diagnosis of diabetic peripheral neuropathy in clinical settings.

(1) Background: This study aims to explore the predictive capability of the Gastric Cancer Immune Prognostic Score (GCIPS) for an unfavorable prognosis in gastric cancer patients undergoing immune checkpoint inhibitor (ICI) treatment. (2) Methods: This study included 302 gastric cancer patients who underwent treatment with ICIs at our institution from January 2017 to December 2022. The patients were randomly divided into a test set (201 cases) and a validation set (101 cases) using a random number table. Kaplan-Meier survival analysis and the log-rank test were used to investigate survival differences. Cox regression analysis and Lasso regression analysis were employed to establish the GCIPS and identify independent prognostic indicators. ROC curves, time-ROC curves, and nomograms were utilized to further explore the predictive performance of GCIPS. (3) Results: The test set and validation set showed no statistical differences in clinical and pathological features, as well as blood parameters (all p > 0.05). Cox regression analysis revealed that white blood cells (WBC), lymphocytes (LYM), and the international normalized ratio (INR) emerged as independent prognostic blood indicators after eliminating collinearity through Lasso analysis. The GCIPS was established using β coefficients with the following formula: GCIPS = WBC (109/L) × 0.071 - LYM (109/L) × 0.375 + INR × 2.986. ROC curves based on death and time-ROC curves demonstrated that the GCIPS had higher AUCs than other classical markers at most time points. Survival analyses of all subgroups also revealed a significant correlation between the GCIPS and patients' progression-free survival (PFS) and overall survival (OS) (all p < 0.05). Furthermore, the GCIPS was identified as an independent prognostic factor for both PFS and OS. Analyses in the validation set further confirmed the reliability and stability of the GCIPS in predicting patient prognosis. Finally, nomograms incorporating the GCIPS exhibited high accuracy in both the test and validation sets. Additionally, the nomograms revealed that the GCIPS had a higher prognostic value than any other factor, including the TNM stage. (4) Conclusions: The GCIPS demonstrated its ability to predict adverse outcomes in gastric cancer patients undergoing ICIs treatment and had a high prognostic value. As a readily accessible and simple novel biomarker, it effectively identified high-risk patients.

To evaluate whether large language models (LLMs) applied to prenatal clinical notes can predict postpartum hemorrhage (PPH) before the onset of labor and to compare model performance across outcome definitions, including a novel intervention-based definition. We conducted a retrospective cohort study within a large regional health network. Two outcome definitions for PPH were used: 1) estimated or quantitative blood loss (EBL-QBL) extracted from clinical notes; and 2) a clinical intervention-based PPH definition (cPPH) designed to capture significant hemorrhage requiring intervention, including transfusion, uterotonics, Bakri balloon, or hysterectomy. We evaluated three PPH prediction pipelines: 1) structured data only-supervised machine learning that used structured electronic medical record data; 2) LLM-direct-direct prediction that used a fine-tuned LLM applied to clinical notes; and 3) LLM-extract-interpretable models that used LLM-extracted features combined with structured data. Model performance was evaluated using an area under the receiver operating characteristic curve (AUROC) on a temporally held-out test set. Among 19,992 deliveries, 1,156 patients (5.8%) met the EBL-QBL definition of PPH, 321 (1.6%) met the cPPH definition, and 309 (1.5%) met both definitions. The LLM-based direct prediction model achieved the highest AUROC for both PPH definitions (AUROC 0.79-0.80), followed by interpretable models that combined LLM-extracted features with structured data (AUROC 0.76-0.78). Models that used only structured data had the lowest AUROC (0.65-0.71). The LLM-extracted features approach identified 47 significant predictors, including established risk factors such as multiple gestation and previous cesarean delivery. These findings highlight the potential of LLM-based approaches to improve PPH risk stratification beyond structured data alone, with the feature extraction method offering a promising balance between predictive performance and clinical utility. Eventual integration of these methods into clinical workflows could improve early detection and guide targeted preventive interventions.

Artificial intelligence for the assessment of bowel preparation

Development of an IgG4-Based Predictor of Endemic Pemphigus Foliaceus (Fogo Selvagem)

We introduce the Densely Segmented Supermarket (D2S) dataset, a novel benchmark for instance-aware semantic segmentation in an industrial domain. It contains 21 000 high-resolution images with pixel-wise labels of all object instances. The objects comprise groceries and everyday products from 60 categories. The benchmark is designed such that it resembles the real-world setting of an automatic checkout, inventory, or warehouse system. The training images only contain objects of a single class on a homogeneous background, while the validation and test sets are much more complex and diverse. To further benchmark the robustness of instance segmentation methods, the scenes are acquired with different lightings, rotations, and backgrounds. We ensure that there are no ambiguities in the labels and that every instance is labeled comprehensively. The annotations are pixel-precise and allow using crops of single instances for articial data augmentation. The dataset covers several challenges highly relevant in the field, such as a limited amount of training data and a high diversity in the test and validation sets. The evaluation of state-of-the-art object detection and instance segmentation methods on D2S reveals significant room for improvement.

ObjectivesTo establish an MRI-based radiomics model for predicting the microvascular invasion (MVI) status of cHCC-CCA and to investigate biological processes underlying the radiomics model.MethodsThe study consisted of a retrospective dataset (82 in the training set, 36 in the validation set) and a prospective dataset (25 patients in the test set) from two hospitals. Based on the training set, logistic regression analyses were employed to develop the clinical-imaging model, while radiomic features were extracted to construct a radiomics model. The diagnosis performance was further validated in the validation and test sets. Prognostic aspects of the radiomics model were investigated using the Kaplan–Meier method and log-rank test. Differential gene expression analysis and gene ontology (GO) analysis were conducted to explore biological processes underlying the radiomics model based on RNA sequencing data.ResultsOne hundred forty-three patients (mean age, 56.4 ± 10.5; 114 men) were enrolled, in which 73 (51.0%) were confirmed as MVI-positive. The radiomics model exhibited good performance in predicting MVI status, with the area under the curve of 0.935, 0.873, and 0.779 in training, validation, and test sets, respectively. Overall survival (OS) was significantly different between the predicted MVI-negative and MVI-positive groups (median OS: 25 vs 18 months, p = 0.008). Radiogenomic analysis revealed associations between the radiomics model and biological processes involved in regulating the immune response.ConclusionA robust MRI-based radiomics model was established for predicting MVI status in cHCC-CCA, in which potential prognostic value and underlying biological processes that regulate immune response were demonstrated.Critical relevance statementMVI is a significant manifestation of tumor invasiveness, and the MR-based radiomics model established in our study will facilitate risk stratification. Furthermore, underlying biological processes demonstrated in the radiomics model will offer valuable insights for guiding immunotherapy strategies.Key PointsMVI is of prognostic significance in cHCC-CCA, but lacks reliable preoperative assessment.The MRI-based radiomics model predicts MVI status effectively in cHCC-CCA.The MRI-based radiomics model demonstrated prognostic value and underlying biological processes.The radiomics model could guide immunotherapy and risk stratification in cHCC-CCA.Graphical