Development and external validation of machine learning-based models to predict patients with cellulitis developing sepsis during hospitalisation.

OBJECTIVE: Cellulitis is the most common cause of skin-related hospitalisations, and the mortality of patients with sepsis remains high. Some stratification models have been developed, but their performance in external validation has been unsatisfactory. This study was designed to develop and compare different models for predicting patients with cellulitis developing sepsis during hospitalisation. DESIGN: This is a retrospective cohort study. SETTING: This study included both the development and the external-validation phases from two independent large cohorts internationally. PARTICIPANTS AND METHODS: A total of 6695 patients with cellulitis in the Medical Information Mart for Intensive care (MIMIC)-IV database were used to develop models with different machine-learning algorithms. The best models were selected and then externally validated in 2506 patients with cellulitis from the YiduCloud database of our university. The performances and robustness of selected models were further compared in the external-validation group by area under the curve (AUC), diagnostic accuracy, sensitivity, specificity and diagnostic OR. PRIMARY OUTCOME MEASURES: The primary outcome of interest in this study was the development based on the Sepsis-3.0 criteria during hospitalisation. RESULTS: Patient characteristics were significantly different between the two groups. In internal validation, XGBoost was the best model, with an AUC of 0.780, and AdaBoost was the worst model, with an AUC of 0.585. In external validation, the AUC of the artificial neural network (ANN) model was the highest, 0.830, while the AUC of the logistic regression (LR) model was the lowest, 0.792. The AUC values changed less in the boosting and ANN models than in the LR model when variables were deleted. CONCLUSIONS: Boosting and neural network models performed slightly better than the LR model and were more robust in complex clinical situations. The results could provide a tool for clinicians to detect hospitalised patients with cellulitis developing sepsis early.

Development and validation of a clinical predictive model for high-volume lymph node metastasis of papillary thyroid carcinoma.

The central lymph node metastasis (CLNM) status in the cervical region serves as a pivotal determinant for the extent of surgical intervention and prognosis in papillary thyroid carcinoma (PTC). This paper seeks to devise and validate a predictive model based on clinical parameters for the early anticipation of high-volume CLNM (hv-CLNM, > 5 nodes) in high-risk patients. A retrospective analysis of the pathological and clinical data of patients with PTC who underwent surgical treatment at Medical Centers A and B was conducted. The data from Center A was randomly divided into training and validation sets in an 8:2 ratio, with those from Center B serving as the test set. Multifactor logistic regression was harnessed in the training set to select variables and construct a predictive model. The generalization ability of the model was assessed in the validation and test sets. The model was evaluated through the receiver operating characteristic area under the curve (AUC) to predict the efficiency of hv-CLNM. The goodness of fit of the model was examined via the Brier verification technique. The incidence of hv-CLNM in 5897 PTC patients attained 4.8%. The occurrence rates in males and females were 9.4% (128/1365) and 3.4% (156/4532), respectively. Multifactor logistic regression unraveled male gender (OR = 2.17, p < .001), multifocality (OR = 4.06, p < .001), and lesion size (OR = 1.08 per increase of 1 mm, p < .001) as risk factors, while age emerged as a protective factor (OR = 0.95 per an increase of 1 year, p < .001). The model constructed with four predictive variables within the training set exhibited an AUC of 0.847 ([95%CI] 0.815-0.878). In the validation and test sets, the AUCs were 0.831 (0.783-0.879) and 0.845 (0.789-0.901), respectively, with Brier scores of 0.037, 0.041, and 0.056. Subgroup analysis unveiled AUCs for the prediction model in PTC lesion size groups (≤ 10 mm and > 10 mm) as 0.803 (0.757-0.85) and 0.747 (0.709-0.785), age groups (≤ 31 years and > 31 years) as 0.778 (0.720-0.881) and 0.837 (0.806-0.867), multifocal and solitary cases as 0.803 (0.767-0.838) and 0.809 (0.769-0.849), and Hashimoto's thyroiditis (HT) and non-HT cases as 0.845 (0.793-0.897) and 0.845 (0.819-0.871). Male gender, multifocality, and larger lesion size are risk factors for hv-CLNM in PTC patients, whereas age serves as a protective factor. The clinical predictive model developed in this research facilitates the early identification of high-risk patients for hv-CLNM, thereby assisting physicians in more efficacious risk stratification management for PTC patients.

Cylindrical TGR as early radiological predictor of RLT progression in GEPNETs: a proof of concept.

This study aims to assess the predictive capability of cylindrical Tumor Growth Rate (cTGR) in the prediction of early progression of well-differentiated gastro-entero-pancreatic tumours after Radio Ligand Therapy (RLT), compared to the conventional TGR. Fifty-eight patients were included and three CT scans per patient were collected at baseline, during RLT, and follow-up. RLT response, evaluated at follow-up according to RECIST 1.1, was calculated as a percentage variation of lesion diameters over time (continuous values) and as four different RECIST classes. TGR between baseline and interim CT was computed using both conventional (approximating lesion volume to a sphere) and cylindrical (called cTGR, approximating lesion volume to an elliptical cylinder) formulations. Receiver Operating Characteristic (ROC) curves were employed for Progressive Disease class prediction, revealing that cTGR outperformed conventional TGR (area under the ROC equal to 1.00 and 0.92, respectively). Multivariate analysis confirmed the superiority of cTGR in predicting continuous RLT response, with a higher coefficient for cTGR (1.56) compared to the conventional one (1.45). This study serves as a proof of concept, paving the way for future clinical trials to incorporate cTGR as a valuable tool for assessing RLT response.

Habitat radiomics and deep learning fusion nomogram to predict EGFR mutation status in stage I non-small cell lung cancer: a multicenter study.

Develop a radiomics nomogram that integrates deep learning, radiomics, and clinical variables to predict epidermal growth factor receptor (EGFR) mutation status in patients with stage I non-small cell lung cancer (NSCLC). We retrospectively included 438 patients who underwent curative surgery and completed driver-gene mutation tests for stage I NSCLC from four academic medical centers. Predictive models were established by extracting and analyzing radiomic features in intratumoral, peritumoral, and habitat regions of CT images to identify EGFR mutation status in stage I NSCLC. Additionally, three deep learning models based on the intratumoral region were constructed. A nomogram was developed by integrating representative radiomic signatures, deep learning, and clinical features. Model performance was assessed by calculating the area under the receiver operating characteristic (ROC) curve. The established habitat radiomics features demonstrated encouraging performance in discriminating between EGFR mutant and wild-type, with predictive ability superior to other single models (AUC 0.886, 0.812, and 0.790 for the training, validation, and external test sets, respectively). The radiomics-based nomogram exhibited excellent performance, achieving the highest AUC values of 0.917, 0.837, and 0.809 in the training, validation, and external test sets, respectively. Decision curve analysis (DCA) indicated that the nomogram provided a higher net benefit than other radiomics models, offering valuable information for treatment.

Biliary atresia and cholestasis plasma non-targeted metabolomics unravels perturbed metabolic pathways and unveils a diagnostic model for biliary atresia.

The clinical diagnosis of biliary atresia (BA) poses challenges, particularly in distinguishing it from cholestasis (CS). Moreover, the prognosis for BA is unfavorable and there is a dearth of effective non-invasive diagnostic models for detection. Therefore, the aim of this study is to elucidate the metabolic disparities among children with BA, CS, and normal controls (NC) without any hepatic abnormalities through comprehensive metabolomics analysis. Additionally, our objective is to develop an advanced diagnostic model that enables identification of BA. The plasma samples from 90 children with BA, 48 children with CS, and 47 NC without any liver abnormalities children were subjected to metabolomics analysis, revealing significant differences in metabolite profiles among the 3 groups, particularly between BA and CS. A total of 238 differential metabolites were identified in the positive mode, while 89 differential metabolites were detected in the negative mode. Enrichment analysis revealed 10 distinct metabolic pathways that differed, such as lysine degradation, bile acid biosynthesis. A total of 18 biomarkers were identified through biomarker analysis, and in combination with the exploration of 3 additional biomarkers (LysoPC(18:2(9Z,12Z)), PC (22:5(7Z,10Z,13Z,16Z,19Z)/14:0), and Biliverdin-IX-α), a diagnostic model for BA was constructed using logistic regression analysis. The resulting ROC area under the curve was determined to be 0.968. This study presents an innovative and pioneering approach that utilizes metabolomics analysis to develop a diagnostic model for BA, thereby reducing the need for unnecessary invasive examinations and contributing to advancements in diagnosis and prognosis for patients with BA.

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study.

OBJECTIVES: To develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset. MATERIALS AND METHODS: Retrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions. RESULTS: The Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort. CONCLUSION: The multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model. CLINICAL RELEVANCE STATEMENT: Predicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

Can Glypican-6 Levels Be Used to Determine Right Ventricular Remodeling After Non-ST Segment Elevation Myocardial Infarction?

OBJECTIVE: Myocardial infarction is associated with right ventricular (RV) remodeling. Glypican-6 (GPC6), a member of the membrane proteoglycan family, plays a significant role in cardiac remodeling. This study aims to determine if GPC6 can predict RV remodeling after percutaneous coronary intervention (PCI) in patients with non-ST segment elevation myocardial infarction (NSTEMI). METHODS: The study enrolled 164 consecutive patients with NSTEMI and controls. It compared baseline plasma GPC6 levels, echocardiography, and laboratory parameters between the RV remodeling and non-RV remodeling groups with NSTEMI. Echocardiographic data were measured at baseline and at six months. RESULTS: GPC6 levels were higher in the NSTEMI group 11.06 ng/mL (4.61-18.17) vs. 5.98 ng/mL (3.81-9.83) compared to the control group in the initial phase. RV remodeling, defined as a ≥ 20% increase in RV end-diastolic area (RV EDA), was observed in 23 patients (30%). After six months, RV EDA increased significantly from baseline 18.68 ± 1.20 cm2 vs. 24.91 ± 1.08 cm2, P < 0.001. GPC6 was a significant independent predictor of RV remodeling (hazard ratio [HR]: 1.546, 95% confidence interval [CI]: 1.056-2.245, P < 0.001). Receiver operating characteristic curve (ROC) analyses showed that GPC6 values > 15.5 ng/mL (area under the curve [AUC] = 0.828, sensitivity: 70%, specificity: 74%, P < 0.001) were strong predictors of RV remodeling. CONCLUSION: NSTEMI patients should be closely monitored for RV remodeling. GPC6 appears useful in detecting RV remodeling following NSTEMI in patients undergoing PCI.

Deep Learning-Based Vascular Aging Prediction From Retinal Fundus Images.

Purpose: The purpose of this study was to establish and validate a deep learning model to screen vascular aging using retinal fundus images. Although vascular aging is considered a novel cardiovascular risk factor, the assessment methods are currently limited and often only available in developed regions. Methods: We used 8865 retinal fundus images and clinical parameters of 4376 patients from two independent datasets for training a deep learning algorithm. The gold standard for vascular aging was defined as a pulse wave velocity ≥1400 cm/s. The probability of the presence of vascular aging was defined as deep learning retinal vascular aging score, the Reti-aging score. We compared the performance of the deep learning model and clinical parameters by calculating the area under the receiver operating characteristics curve (AUC). We recruited clinical specialists, including ophthalmologists and geriatricians, to assess vascular aging in patients using retinal fundus images, aiming to compare the diagnostic performance between deep learning models and clinical specialists. Finally, the potential of Reti-aging score for identifying new-onset hypertension (NH) and new-onset carotid artery plaque (NCP) in the subsequent three years was examined. Results: The Reti-aging score model achieved an AUC of 0.826 (95% confidence interval [CI] = 0.793-0.855) and 0.779 (95% CI = 0.765-0.794) in the internal and external dataset. It showed better performance in predicting vascular aging compared with the prediction with clinical parameters. The average accuracy of ophthalmologists (66.3%) was lower than that of the Reti-aging score model, whereas geriatricians were unable to make predictions based on retinal fundus images. The Reti-aging score was associated with the risk of NH and NCP (P < 0.05). Conclusions: The Reti-aging score model might serve as a novel method to predict vascular aging through analysis of retinal fundus images. Reti-aging score provides a novel indicator to predict new-onset cardiovascular diseases. Translational Relevance: Given the robust performance of our model, it provides a new and reliable method for screening vascular aging, especially in undeveloped areas.

Development and validation of a predictive model for double-J stent encrustation after upper urinary tract calculi surgery.

The study is aimed to establish a predictive model of double-J stent encrustation after upper urinary tract calculi surgery. We collected the clinical data of 561 patients with indwelling double-J tubes admitted to a hospital in Shandong Province from January 2019 to December 2020 as the modeling group and 241 cases of indwelling double-J tubes from January 2021 to January 2022 as the verification group. Univariate and binary logistic regression analyses were used to explore risk factors, the risk prediction equation was established, and the receiver operating characteristic (ROC) curve analysis model was used for prediction. In this study, 104 of the 561 patients developed double-J stent encrustation, with an incidence rate of 18.5%. We finally screened out BMI (body mass index) > 23.9 (OR = 1.648), preoperative urine routine white blood cell quantification (OR = 1.149), double-J tube insertion time (OR = 1.566), postoperative water consumption did not reach 2000 ml/d (OR = 8.514), a total of four factors build a risk prediction model. From the ROC curve analysis, the area under the curve (AUC) was 0.844, and the maximum Oden index was 0.579. At this time, the sensitivity was 0.735 and the specificity was 0.844. The research established in this study has a high predictive value for the occurrence of double-J stent encrustation in the double-J tube after upper urinary tract stone surgery, which provides a basis for the prevention and treatment of double-J stent encrustation.

Enhancing prostate cancer diagnosis and reducing unnecessary biopsies with [18F]DCFPyL PET/CT imaging in PI-RADS 3/4 patients.

For patients presenting with prostate imaging reporting and data system (PI-RADS) 3/4 findings on magnetic resonance imaging (MRI) examinations, the standard recommendation typically involves undergoing a biopsy for pathological assessment to ascertain the nature of the lesion. This course of action, though essential for accurate diagnosis, invariably amplifies the psychological distress experienced by patients and introduces a host of potential complications associated with the biopsy procedure. However, [18F]DCFPyL PET/CT imaging emerges as a promising alternative, demonstrating considerable diagnostic efficacy in discerning benign prostate lesions from malignant ones. This study aims to explore the diagnostic value of [18F]DCFPyL PET/CT imaging for prostate cancer in patients with PI-RADS 3/4 lesions, assisting in clinical decision-making to avoid unnecessary biopsies. 30 patients diagnosed with PI-RADS 3/4 lesions through mpMRI underwent [18F]DCFPyL PET/CT imaging, with final biopsy pathology results as the "reference standard". Diagnostic performance was assessed through receiver operating characteristic (ROC) analysis, evaluating the diagnostic efficacy of molecular imaging PSMA (miPSMA) visual analysis and semi-quantitative analysis in [18F]DCFPyL PET/CT imaging. Lesions were assigned miPSMA scores according to the prostate cancer molecular imaging standardized evaluation criteria. Among the 30 patients, 13 were pathologically confirmed to have prostate cancer. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of visual analysis in [18F]DCFPyL PET/CT imaging for diagnosing PI-RADS 3/4 lesions were 61.5%, 88.2%, 80.0%, 75.0%, and 76.5%, respectively. Using SUVmax 4.17 as the optimal threshold, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy for diagnosis were 92.3%, 88.2%, 85.7%, 93.8%, and 90.0%, respectively. The area under the ROC curve (AUC) for semi-quantitative analysis was 0.94, significantly higher than visual analysis at 0.80. [18F]DCFPyL PET/CT imaging accurately diagnosed benign lesions in 15 (50%) of the PI-RADS 3/4 patients. For patients with PI-RADS 4 lesions, the positive predictive value of [18F]DCFPyL PET/CT imaging reached 100%. [18F]DCFPyL PET/CT imaging provides potential preoperative prediction of lesion nature in mpMRI PI-RADS 3/4 patients, which may aid in treatment decision-making and reducing unnecessary biopsies.

Superiority of the triglyceride glucose index over the homeostasis model in predicting metabolic syndrome based on NHANES data analysis.

The triglyceride-glucose (TyG) index is a simple and inexpensive new marker of insulin resistance that is being increasingly used for the clinical prediction of metabolic syndrome (MetS). Nevertheless, there are only a few comparative studies on its predictive capacity for MetS versus those using the traditional homeostasis model assessment (HOMA). We conducted a cross-sectional study using a database from the National Health and Nutrition Examination Survey (1999 March to 2020 pre-pandemic period). Using statistical methods, we compared the predictive abilities of the TyG index and HOMA (including HOMA of insulin resistance [HOMA-IR] and HOMA of beta-cell function [HOMA-ß]) for MetS. A total of 34,195 participants were enrolled and divided into the MetS group (23.1%) or no MetS group (76.9%) according to the International Diabetes Federation (IDF) diagnostic criteria. After applying weighted data, the baseline characteristics of the population were described. Following the exclusion of medication influences, the final count was 31,304 participants. Receiver operating characteristic curve analysis revealed that while distinguishing between MetS and no MetS, the TyG index had an area under the curve (AUC) of 0.827 (sensitivity = 71.9%, specificity = 80.5%), and the cutoff was 8.75, slightly outperforming HOMA-IR (AUC = 0.784) and HOMA-ß (AUC = 0.614) with a significance of P < 0.01. The prevalence of MetS in the total population calculated using the TyG index cutoff value was 30.9%, which was higher than that reported in the IDF diagnostic criteria. Weighted data analysis using univariate and multivariate logistic regression displayed an independent association between elevated TyG and HOMA-IR with the risk of MetS. Subgroup analysis further revealed differences in the predictive ability of the TyG index among adult populations across various genders and ethnicities, whereas such differences were not observed for children and adolescents. The TyG index is slightly better than HOMA in predicting MetS and may identify more patients with MetS; thus, its applications in a clinical setting can be appropriately increased.

Analysis of the performance of the CorneAI for iOS in the classification of corneal diseases and cataracts based on journal photographs.

CorneAI for iOS is an artificial intelligence (AI) application to classify the condition of the cornea and cataract into nine categories: normal, infectious keratitis, non-infection keratitis, scar, tumor, deposit, acute primary angle closure, lens opacity, and bullous keratopathy. We evaluated its performance to classify multiple conditions of the cornea and cataract of various races in images published in the Cornea journal. The positive predictive value (PPV) of the top classification with the highest predictive score was 0.75, and the PPV for the top three classifications exceeded 0.80. For individual diseases, the highest PPVs were 0.91, 0.73, 0.42, 0.72, 0.77, and 0.55 for infectious keratitis, normal, non-infection keratitis, scar, tumor, and deposit, respectively. CorneAI for iOS achieved an area under the receiver operating characteristic curve of 0.78 (95% confidence interval [CI] 0.5-1.0) for normal, 0.76 (95% CI 0.67-0.85) for infectious keratitis, 0.81 (95% CI 0.64-0.97) for non-infection keratitis, 0.55 (95% CI 0.41-0.69) for scar, 0.62 (95% CI 0.27-0.97) for tumor, and 0.71 (95% CI 0.53-0.89) for deposit. CorneAI performed well in classifying various conditions of the cornea and cataract when used to diagnose journal images, including those with variable imaging conditions, ethnicities, and rare cases.

Differentiation of glioma and solitary brain metastasis: a multi-parameter magnetic resonance imaging study using histogram analysis.

BACKGROUND: Differentiation of glioma and solitary brain metastasis (SBM), which requires biopsy or multi-disciplinary diagnosis, remains sophisticated clinically. Histogram analysis of MR diffusion or molecular imaging hasn't been fully investigated for the differentiation and may have the potential to improve it. METHODS: A total of 65 patients with newly diagnosed glioma or metastases were enrolled. All patients underwent DWI, IVIM, and APTW, as well as the T1W, T2W, T2FLAIR, and contrast-enhanced T1W imaging. The histogram features of apparent diffusion coefficient (ADC) from DWI, slow diffusion coefficient (Dslow), perfusion fraction (frac), fast diffusion coefficient (Dfast) from IVIM, and MTRasym@3.5ppm from APTWI were extracted from the tumor parenchyma and compared between glioma and SBM. Parameters with significant differences were analyzed with the logistics regression and receiver operator curves to explore the optimal model and compare the differentiation performance. RESULTS: Higher ADCkurtosis (P = 0.022), frackurtosis (P<0.001),and fracskewness (P<0.001) were found for glioma, while higher (MTRasym@3.5ppm)10 (P = 0.045), frac10 (P<0.001),frac90 (P = 0.001), fracmean (P<0.001), and fracentropy (P<0.001) were observed for SBM. frackurtosis (OR = 0.431, 95%CI 0.256-0.723, P = 0.002) was independent factor for SBM differentiation. The model combining (MTRasym@3.5ppm)10, frac10, and frackurtosis showed an AUC of 0.857 (sensitivity: 0.857, specificity: 0.750), while the model combined with frac10 and frackurtosis had an AUC of 0.824 (sensitivity: 0.952, specificity: 0.591). There was no statistically significant difference between AUCs from the two models. (Z = -1.14, P = 0.25). CONCLUSIONS: The frac10 and frackurtosis in enhanced tumor region could be used to differentiate glioma and SBM and (MTRasym@3.5ppm)10 helps improving the differentiation specificity.

Urinary microbiome dysbiosis is associated with an inflammatory environment and perturbed fatty acids metabolism in the pathogenesis of bladder cancer.

BACKGROUND: Bladder cancer is a common malignancy with high recurrence rate. Early diagnosis and recurrence surveillance are pivotal to patients' outcomes, which require novel minimal-invasive diagnostic tools. The urinary microbiome is associated with bladder cancer and can be used as biomarkers, but the underlying mechanism is to be fully illustrated and diagnostic performance to be improved. METHODS: A total of 23 treatment-naïve bladder cancer patients and 9 non-cancerous subjects were enrolled into the Before group and Control group. After surgery, 10 patients from the Before group were further assigned into After group. Void mid-stream urine samples were collected and sent for 16S rDNA sequencing, targeted metabolomic profiling, and flow cytometry. Next, correlations were analyzed between microbiota, metabolites, and cytokines. Finally, receiver operating characteristic (ROC) curves of the urinary biomarkers were plotted and compared. RESULTS: Comparing to the Control group, levels of IL-6 (p < 0.01), IL-8 (p < 0.05), and IL-10 (p < 0.05) were remarkably elevated in the Before group. The α diversity of urine microbiome was also significantly higher, with the feature microbiota positively correlated to the level of IL-6 (r = 0.58, p < 0.01). Significant differences in metabolic composition were also observed between the Before and Control groups, with fatty acids and fatty acylcarnitines enriched in the Before group. After tumor resection, cytokine levels and the overall microbiome structure in the After group remained similar to that of the Before group, but fatty acylcarnitines were significantly reduced (p < 0.05). Pathway enrichment analysis revealed beta-oxidation of fatty acids was significantly involved (p < 0.001). ROC curves showed that the biomarker panel of Actinomycetaceae + arachidonic acid + IL-6 had superior diagnostic performance, with sensitivity of 0.94 and specificity of 1.00. CONCLUSIONS: Microbiome dysbiosis, proinflammatory environment and altered fatty acids metabolism are involved in the pathogenesis of bladder cancer, which may throw light on novel noninvasive diagnostic tool development.

[Research on the classification model of chronic sinusitis based on VGG].

Objective:To build a VGG-based computer-aided diagnostic model for chronic sinusitis and evaluate its efficacy. Methods:①A total of 5 000 frames of diagnosed sinus CT images were collected. The normal group consisted of 1 000 frames（250 frames each of maxillary sinus, frontal sinus, septal sinus, and pterygoid sinus）, while the abnormal group consisted of 4 000 frames（1 000 frames each of maxillary sinusitis, frontal sinusitis, septal sinusitis, and pterygoid sinusitis）. ②The models were trained and simulated to obtain five classification models for the normal group, the pteroid sinusitis group, the frontal sinusitis group, the septal sinusitis group and the maxillary sinusitis group, respectively. The classification efficacy of the models was evaluated objectively in six dimensions: accuracy, precision, sensitivity, specificity, interpretation time and area under the ROC curve（AUC）. ③Two hundred randomly selected images were read by the model with three groups of physicians（low, middle and high seniority） to constitute a comparative experiment. The efficacy of the model was objectively evaluated using the aforementioned evaluation indexes in conjunction with clinical analysis. Results:①Simulation experiment: The overall recognition accuracy of the model is 83.94%, with a precision of 89.52%, sensitivity of 83.94%, specificity of 95.99%, and the average interpretation time of each frame is 0.2 s. The AUC for sphenoid sinusitis was 0.865（95%CI 0.849-0.881）, for frontal sinusitis was 0.924（0.991-0.936）, for ethmoidoid sinusitis was 0.895（0.880-0.909）, and for maxillary sinusitis was 0.974（0.967-0.982）. ②Comparison experiment: In terms of recognition accuracy, the model was 84.52%, while the low-seniority physicians group was 78.50%, the middle-seniority physicians group was 80.50%, and the seniority physicians group was 83.50%; In terms of recognition accuracy, the model was 85.67%, the low seniority physicians group was 79.72%, the middle seniority physicians group was 82.67%, and the high seniority physicians group was 83.66%. In terms of recognition sensitivity, the model was 84.52%, the low seniority group was 78.50%, the middle seniority group was 80.50%, and the high seniority group was 83.50%. In terms of recognition specificity, the model was 96.58%, the low-seniority physicians group was 94.63%, the middle-seniority physicians group was 95.13%, and the seniority physicians group was 95.88%. In terms of time consumption, the average image per frame of the model is 0.20 s, the average image per frame of the low-seniority physicians group is 2.35 s, the average image per frame of the middle-seniority physicians group is 1.98 s, and the average image per frame of the senior physicians group is 2.19 s. Conclusion:This study demonstrates the potential of a deep learning-based artificial intelligence diagnostic model for chronic sinusitis to classify and diagnose chronic sinusitis; the deep learning-based artificial intelligence diagnosis model for chronic sinusitis has good classification performance and high diagnostic efficacy.

Analysis of risk factors related to chronic non-healing wound infection and the construction of a clinical prediction model.

This study is aimed to analyse the risk factors associated with chronic non-healing wound infections, establish a clinical prediction model, and validate its performance. Clinical data were retrospectively collected from 260 patients with chronic non-healing wounds treated in the plastic surgery ward of Shanxi Provincial People's Hospital between January 2022 and December 2023 who met the inclusion criteria. Risk factors were analysed, and a clinical prediction model was constructed using both single and multifactor logistic regression analyses to determine the factors associated with chronic non-healing wound infections. The model's discrimination and calibration were assessed via the concordance index (C-index), receiver operating characteristic (ROC) curve and calibration curve. Multivariate logistic regression analysis identified several independent risk factors for chronic non-healing wound infection: long-term smoking (odds ratio [OR]: 4.122, 95% CI: 3.412-5.312, p < 0.05), history of diabetes (OR: 3.213, 95% CI: 2.867-4.521, p < 0.05), elevated C-reactive protein (OR: 2.981, 95% CI: 2.312-3.579, p < 0.05), elevated procalcitonin (OR: 2.253, 95% CI: 1.893-3.412, p < 0.05) and reduced albumin (OR: 1.892, 95% CI: 1.322-3.112, p < 0.05). The clinical prediction model's C-index was 0.762, with the corrected C-index from internal validation using the bootstrap method being 0.747. The ROC curve indicated an area under the curve (AUC) of 0.762 (95% CI: 0.702-0.822). Both the AUC and C-indexes ranged between 0.7 and 0.9, suggesting moderate-to-good predictive accuracy. The calibration chart demonstrated a good fit between the model's calibration curve and the ideal curve. Long-term smoking, diabetes, elevated C-reactive protein, elevated procalcitonin and reduced albumin are confirmed as independent risk factors for bacterial infection in patients with chronic non-healing wounds. The clinical prediction model based on these factors shows robust performance and substantial predictive value.

The inflammatory markers combined with CA125 may predict postoperative survival in endometrial cancer.

BACKGROUND: Endometrial cancer (EC) has a high latency, making prognosis difficult to predict. Cancer antigen 125 (CA125) is not specific as a tumour marker for EC; however, complete blood count (CBC) inflammatory markers are associated with prognosis in various malignancies. Thus, this study investigated the value of CBC inflammatory markers combined with CA125 levels in predicting the prognosis of patients with EC. METHODS: In this study, 517 patients with EC were recruited between January 2015 and January 2022, and clinical characteristics, CBC inflammatory markers, and CA125 levels were assessed. Differences in each index at different EC stages and the correlation between the index and EC stage were analysed, and the influence of the index on EC prognosis was evaluated. RESULTS: Platelet distribution width (PDW) levels were significantly lower in patients with advanced EC than in those with early EC, whereas the systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), and CA125 levels were significantly higher in patients with advanced EC (all P < 0.05). ROC curve and multivariate logistic regression analyses indicated that decreased PDW and increased CA125 levels were independent risk factors for EC staging progression. In addition, multivariate Cox regression analysis showed that the combination of low PDW and high CA125 (PDW + CA125 = 2) was an independent prognostic factor of survival in EC patients. Kaplan-Meier survival analysis indicated that patients with low PDW and high CA125 had worse overall survival. CONCLUSIONS: The PDW and CA125 score may be an independent prognostic factor for postoperative overall survival in patients with EC and a useful marker for predicting the prognosis of these patients.

Endometrial cancer (EC) has a high latency period, and the prognosis of EC is difficult to predict. The inflammatory response within the tumour microenvironment plays an important role in the occurrence and development of cancer. In our study, various inflammatory indicators in complete blood counts were comprehensively analysed, and cancer antigen 125 (CA125) was further used to predict the stage and prognosis of EC. The results showed that patients with low platelet distribution width (PDW) and high CA125 levels had poorer overall survival. The PDW and CA125 score may be used as a new independent prognostic indicator.

Development and validation of machine learning models to predict MDRO colonization or infection on ICU admission by using electronic health record data.

BACKGROUND: Multidrug-resistant organisms (MDRO) pose a significant threat to public health. Intensive Care Units (ICU), characterized by the extensive use of antimicrobial agents and a high prevalence of bacterial resistance, are hotspots for MDRO proliferation. Timely identification of patients at high risk for MDRO can aid in curbing transmission, enhancing patient outcomes, and maintaining the cleanliness of the ICU environment. This study focused on developing a machine learning (ML) model to identify patients at risk of MDRO during the initial phase of their ICU stay. METHODS: Utilizing patient data from the First Medical Center of the People's Liberation Army General Hospital (PLAGH-ICU) and the Medical Information Mart for Intensive Care (MIMIC-IV), the study analyzed variables within 24 h of ICU admission. Machine learning algorithms were applied to these datasets, emphasizing the early detection of MDRO colonization or infection. Model efficacy was evaluated by the area under the receiver operating characteristics curve (AUROC), alongside internal and external validation sets. RESULTS: The study evaluated 3,536 patients in PLAGH-ICU and 34,923 in MIMIC-IV, revealing MDRO prevalence of 11.96% and 8.81%, respectively. Significant differences in ICU and hospital stays, along with mortality rates, were observed between MDRO positive and negative patients. In the temporal validation, the PLAGH-ICU model achieved an AUROC of 0.786 [0.748, 0.825], while the MIMIC-IV model reached 0.744 [0.723, 0.766]. External validation demonstrated reduced model performance across different datasets. Key predictors included biochemical markers and the duration of pre-ICU hospital stay. CONCLUSIONS: The ML models developed in this study demonstrated their capability in early identification of MDRO risks in ICU patients. Continuous refinement and validation in varied clinical contexts remain essential for future applications.

Development and validation of a nomogram for breast cancer-related lymphedema.

To establish and validate a predictive model for breast cancer-related lymphedema (BCRL) among Chinese patients to facilitate individualized risk assessment. We retrospectively analyzed data from breast cancer patients treated at a major single-center breast hospital in China. From 2020 to 2022, we identified risk factors for BCRL through logistic regression and developed and validated a nomogram using R software (version 4.1.2). Model validation was achieved through the application of receiver operating characteristic curve (ROC), a calibration plot, and decision curve analysis (DCA), with further evaluated by internal validation. Among 1485 patients analyzed, 360 developed lymphedema (24.2%). The nomogram incorporated body mass index, operative time, lymph node count, axillary dissection level, surgical site infection, and radiotherapy as predictors. The AUCs for training (N = 1038) and validation (N = 447) cohorts were 0.779 and 0.724, respectively, indicating good discriminative ability. Calibration and decision curve analysis confirmed the model's clinical utility. Our nomogram provides an accurate tool for predicting BCRL risk, with potential to enhance personalized management in breast cancer survivors. Further prospective validation across multiple centers is warranted.

Diagnostic value of contrast-enhanced ultrasound and shear-wave elastography for small breast nodules.

Background: The study aims to evaluate the diagnostic efficacy of contrast-enhanced ultrasound (CEUS) and shear-wave elastography (SWE) in detecting small malignant breast nodules in an effort to inform further refinements of the Breast Imaging Reporting and Data System (BI-RADS) classification system. Methods: This study retrospectively analyzed patients with breast nodules who underwent conventional ultrasound, CEUS, and SWE at Gongli Hospital from November 2015 to December 2019. The inclusion criteria were nodules ≤ 2 cm in diameter with pathological outcomes determined by biopsy, no prior treatments, and solid or predominantly solid nodules. The exclusion criteria included pregnancy or lactation and low-quality images. Imaging features were detailed and classified per BI-RADS. Diagnostic accuracy was assessed using receiver operating characteristic curves. Results: The study included 302 patients with 305 breast nodules, 113 of which were malignant. The diagnostic accuracy was significantly improved by combining the BI-RADS classification with CEUS and SWE. The combined approach yielded a sensitivity of 88.5%, specificity of 87.0%, positive predictive value of 80.0%, negative predictive value of 92.8%, and accuracy of 87.5% with an area under the curve of 0.877. Notably, 55.8% of BI-RADS 4A nodules were downgraded to BI-RADS 3 and confirmed as benign after pathological examination, suggesting the potential to avoid unnecessary biopsies. Conclusion: The integrated use of the BI-RADS classification, CEUS, and SWE enhances the accuracy of differentiating benign and malignant small breast nodule, potentially reducing the need for unnecessary biopsies.