Development and validation of a simple and practical model for early detection of diabetic macular edema in patients with type 2 diabetes mellitus using easily accessible systemic variables.

OBJECTIVE: Diabetic macular edema (DME) is the leading cause of visual impairment in patients with diabetes mellitus (DM). The goal of early detection has not yet achieved due to a lack of fast and convenient methods. Therefore, we aim to develop and validate a prediction model to identify DME in patients with type 2 diabetes mellitus (T2DM) using easily accessible systemic variables, which can be applied to an ophthalmologist-independent scenario. METHODS: In this four-center, observational study, a total of 1994 T2DM patients who underwent routine diabetic retinopathy screening were enrolled, and their information on ophthalmic and systemic conditions was collected. Forward stepwise multivariable logistic regression was performed to identify risk factors of DME. Machine learning and MLR (multivariable logistic regression) were both used to establish prediction models. The prediction models were trained with 1300 patients and prospectively validated with 104 patients from Guangdong Provincial People's Hospital (GDPH). A total of 175 patients from Zhujiang Hospital (ZJH), 115 patients from the First Affiliated Hospital of Kunming Medical University (FAHKMU), and 100 patients from People's Hospital of JiangMen (PHJM) were used as external validation sets. Area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity, and specificity were used to evaluate the performance in DME prediction. RESULTS: The risk of DME was significantly associated with duration of DM, diastolic blood pressure, hematocrit, glycosylated hemoglobin, and urine albumin-to-creatinine ratio stage. The MLR model using these five risk factors was selected as the final prediction model due to its better performance than the machine learning models using all variables. The AUC, ACC, sensitivity, and specificity were 0.80, 0.69, 0.80, and 0.67 in the internal validation, and 0.82, 0.54, 1.00, and 0.48 in prospective validation, respectively. In external validation, the AUC, ACC, sensitivity and specificity were 0.84, 0.68, 0.90 and 0.60 in ZJH, 0.89, 0.77, 1.00 and 0.72 in FAHKMU, and 0.80, 0.67, 0.75, and 0.65 in PHJM, respectively. CONCLUSION: The MLR model is a simple, rapid, and reliable tool for early detection of DME in individuals with T2DM without the needs of specialized ophthalmologic examinations.

Prediction of lymph node metastasis in T1 colorectal cancer based on combination of body composition and vascular invasion.

OBJECTIVES: Lymph node metastasis (LNM) in colorectal cancer (CRC) patients is not only associated with the tumor's local pathological characteristics but also with systemic factors. This study aims to assess the feasibility of using body composition and pathological features to predict LNM in early stage colorectal cancer (eCRC) patients. METHODS: A total of 192 patients with T1 CRC who underwent CT scans and surgical resection were retrospectively included in the study. The cross-sectional areas of skeletal muscle, subcutaneous fat, and visceral fat at the L3 vertebral body level in CT scans were measured using Image J software. Logistic regression analysis were conducted to identify the risk factors for LNM. The predictive accuracy and discriminative ability of the indicators were evaluated using receiver operating characteristic (ROC) curves. Delong test was applied to compare area under different ROC curves. RESULTS: LNM was observed in 32 out of 192 (16.7%) patients with eCRC. Multivariate analysis revealed that the ratio of skeletal muscle area to visceral fat area (SMA/VFA) (OR = 0.021, p = 0.007) and pathological indicators of vascular invasion (OR = 4.074, p = 0.020) were independent risk factors for LNM in eCRC patients. The AUROC for SMA/VFA was determined to be 0.740 (p < 0.001), while for vascular invasion, it was 0.641 (p = 0.012). Integrating both factors into a proposed predictive model resulted in an AUROC of 0.789 (p < 0.001), indicating a substantial improvement in predictive performance compared to relying on a single pathological indicator. CONCLUSION: The combination of the SMA/VFA ratio and vascular invasion provides better prediction of LNM in eCRC.

Assessing the Efficacy of Synthetic Optic Disc Images for Detecting Glaucomatous Optic Neuropathy Using Deep Learning.

Purpose: Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON. Methods: A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques. Results: Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model's area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image. Conclusions: Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection. Translational Relevance: Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.

The Prognostic Value of the Triglyceride-Glucose Index in Forecasting Ten-Year Major Adverse Cardiovascular Events in Non-Diabetic Patients with Acute Myocardial Infarction Undergoing Percutaneous Coronary Intervention.

OBJECTIVE: This study aimed to explore the association between the triglyceride-glucose (TyG) index and major adverse cardiovascular events (MACE) over a ten-year period in non-diabetic patients with acute myocardial infarction (MI) undergoing primary percutaneous coronary intervention (PCI). METHODS: We included 375 consecutive non-diabetic patients presenting with acute MI who underwent primary PCI. The TyG index was calculated and patients were divided based on a cut-off value of ≥ 8.84 into high and low TyG index groups. The incidence of MACE, including all-cause mortality, target vessel revascularization, reinfarction, and rehospitalization for heart failure, was assessed over 10 years. RESULTS: Over the next 10 years, patients who underwent PCI for acute MI experienced a significantly higher incidence of MACE in the group with a high TyG index (≥ 8.84) (P = 0.004). Multivariable analysis revealed that the TyG index independently predicted MACE in these patients [odds ratio = 1.64; 95% confidence interval (CI): 1.22-2.21; P = 0.002]. Analysis of the receiver operating characteristic curve indicated that the TyG index effectively predicted MACE in patients with acute MI following PCI, with an area under the curve of 0.562 (95% CI: 0.503-0.621; P = 0.038). CONCLUSION: This study established a correlation between high TyG index levels and an elevated risk of MACE in non-diabetic patients with acute MI. The findings suggest that the TyG index could be a reliable indicator of clinical outcomes for non-diabetic acute MI patients undergoing PCI.

Specific pelvic shape in patients with developmental dysplasia of the hip on 3D morphometric homologous model analysis.

PURPOSE: To clarify the morphological factors of the pelvis in patients with developmental dysplasia of the hip (DDH), three-dimensional (3D) pelvic morphology was analyzed using a template-fitting technique. METHODS: Three-dimensional pelvic data of 50 patients with DDH (DDH group) and 3D pelvic data of 50 patients without obvious pelvic deformity (Normal group) were used. All patients were female. A template model was created by averaging the normal pelvises into a symmetrical and isotropic mesh. Next, 100 homologous models were generated by fitting the pelvic data of each group of patients to the template model. Principal component analysis was performed on the coordinates of each vertex (15,235 vertices) of the pelvic homologous model. In addition, a receiver-operating characteristic (ROC) curve was calculated from the sensitivity of DDH positivity for each principal component, and principal components for which the area under the curve was significantly large were extracted (p<0.05). Finally, which components of the pelvic morphology frequently seen in DDH patients are related to these extracted principal components was evaluated. RESULTS: The first, third, and sixth principal components showed significantly larger areas under the ROC curves. The morphology indicated by the first principal component was associated with a decrease in coxal inclination in both the coronal and horizontal planes. The third principal component was related to the sacral inclination in the sagittal plane. The sixth principal component was associated with narrowing of the superior part of the pelvis. CONCLUSION: The most important factor in the difference between normal and DDH pelvises was the change in the coxal angle in both the coronal and horizontal planes. That is, in the anterior and superior views, the normal pelvis is a triangle, whereas in DDH, it was more like a quadrilateral.

Development and validation of risk prediction model for bacterial infections in acute liver failure patients.

Infections significantly increase mortality in acute liver failure (ALF) patients, and there are no risk prediction models for early diagnosis and treatment of infections in ALF patients. This study aims to develop a risk prediction model for bacterial infections in ALF patients to guide rational antibiotic therapy. The data of ALF patients admitted to the Second Hospital of Hebei Medical University in China from January 2017 to January 2022 were retrospectively analyzed for training and internal validation. Patients were selected according to the updated 2011 American Association for the Study of Liver Diseases position paper on ALF. Serological indicators and model scores were collected within 24 h of admission. New models were developed using the multivariate logistic regression analysis. An optimal model was selected by receiver operating characteristic (ROC) analysis, Hosmer-Lemeshow test, the calibration curve, the Brier score, the bootstrap resampling, and the decision curve analysis. A nomogram was plotted to visualize the results. A total of 125 ALF patients were evaluated and 79 were included in the training set. The neutrophil-to-lymphocyte ratio and sequential organ failure assessment (SOFA) were integrated into the new model as independent predictive factors. The new SOFA-based model outperformed other models with an area under the ROC curve of 0.799 [95% confidence interval (CI): 0.652-0.926], the superior calibration and predictive performance in internal validation. High-risk individuals with a nomogram score ≥26 are recommended for antibiotic therapy. The new SOFA-based model demonstrates high accuracy and clinical utility in guiding antibiotic therapy in ALF patients.

Predictive value of triglyceride glucose index combined with neutrophil-to-lymphocyte ratio for major adverse cardiac events after PCI for acute ST-segment elevation myocardial infarction.

Acute ST-segment elevation myocardial infarction (STEMI) is a severe cardiovascular disease that poses a significant threat to the life and health of patients. This study aimed to investigate the predictive value of triglyceride glucose index (TyG) combined with neutrophil-to-lymphocyte ratio (NLR) for in-hospital cardiac adverse event (MACE) after PCI in STEMI patients. From October 2019 to June 2023, 398 STEMI patients underwent emergency PCI in the Second People's Hospital of Hefei. Stepwise regression backward method and multivariate logistic regression analysis were used to screen the independent risk factors of MACE in STEMI patients. To construct the prediction model of in-hospital MACE after PCI in STEMI patients: Grace score model is the old model (model A); TyG combined with NLR model (model B); Grace score combined with TyG and NLR model is the new model (model C). We assessed the clinical usefulness of the predictive model by comparing Integrated Discrimination Improvement (IDI), Net Reclassification Index (NRI), Receiver Operating Characteristic Curve (ROC), and Decision Curve Analysis (DCA). Stepwise regression and multivariate logistic regression analysis showed that TyG and NLR were independent risk factors for in-hospital MACE after PCI in STEMI patients. The constructed Model C was compared to Model A. Results showed NRI 0.5973; NRI + 0.3036, NRI - 0.2937, IDI 0.3583. These results show that the newly developed model C predicts the results better than model A, indicating that the model is more accurate. The ROC analysis results showed that the AUC of Model A for predicting MACE in STEMI was 0.749. Model B predicted MACE in STEMI with an AUC of 0.685. Model C predicted MACE in STEMI with an AUC of 0.839. For DCA, Model C has a better net return between threshold probability 0.1 and 0.78, which is better than Model A and Model B. In this study, by combining TyG, NLR, and Grace score, it was shown that TyG combined with NLR could reasonably predict the occurrence of MACE after PCI in STEMI patients and the clinical utility of the prediction model.

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections.

OBJECTIVE: To develop an AI-assisted MRI model to identify surgical target areas in pediatric hip and periarticular infections. METHODS: A retrospective study was conducted on the pediatric patients with hip and periarticular infections who underwent Magnetic Resonance Imaging(MRI)examinations from January 2010 to January 2023 in three hospitals in China. A total of 7970 axial Short Tau Inversion Recovery (STIR) images were selected, and the corresponding regions of osteomyelitis (label 1) and abscess (label 2) were labeled using the Labelme software. The images were randomly divided into training group, validation group, and test group at a ratio of 7:2:1. A Mask R-CNN model was constructed and optimized, and the performance of identifying label 1 and label 2 was evaluated using receiver operating characteristic (ROC) curves. Calculation of the average time it took for the model and specialists to process an image in the test group. Comparison of the accuracy of the model in the interpretation of MRI images with four orthopaedic surgeons, with statistical significance set at P < 0.05. RESULTS: A total of 275 patients were enrolled, comprising 197 males and 78 females, with an average age of 7.10 ± 3.59 years, ranging from 0.00 to 14.00 years. The area under curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 1 were 0.810, 0.976, 0.995, 0.969, 0.922, and 0.957, respectively. The AUC, accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 2 were 0.890, 0.957, 0.969, 0.915, 0.976, and 0.972, respectively. The model demonstrated a significant speed advantage, taking only 0.2 s to process an image compared to average 10 s required by the specialists. The model identified osteomyelitis with an accuracy of 0.976 and abscess with an accuracy of 0.957, both statistically better than the four orthopaedic surgeons, P < 0.05. CONCLUSION: The Mask R-CNN model is reliable for identifying surgical target areas in pediatric hip and periarticular infections, offering a more convenient and rapid option. It can assist unexperienced physicians in pre-treatment assessments, reducing the risk of missed and misdiagnosis.

Risk factor analysis and nomogram for predicting poor symptom control in smoking asthmatics.

BACKGROUND: Smoking induces and modifies the airway immune response, accelerating the decline of asthmatics' lung function and severely affecting asthma symptoms' control level. To assess the prognosis of asthmatics who smoke and to provide reasonable recommendations for treatment, we constructed a nomogram prediction model. METHODS: General and clinical data were collected from April to September 2021 from smoking asthmatics aged ≥14 years attending the People's Hospital of Zhengzhou University. Patients were followed up regularly by telephone or outpatient visits, and their medication and follow-up visits were recorded during the 6-months follow-up visit, as well as their asthma control levels after 6 months (asthma control questionnaire-5, ACQ-5). The study employed R4.2.2 software to conduct univariate and multivariate logistic regression analyses to identify independent risk factors for 'poorly controlled asthma' (ACQ>0.75) as the outcome variable. Subsequently, a nomogram prediction model was constructed. Internal validation was used to test the reproducibility of the model. The model efficacy was evaluated using the consistency index (C-index), receiver operating characteristic (ROC) curve, calibration curve, and decision curve. RESULTS: Invitations were sent to 231 asthmatics who smoked. A total of 202 participants responded, resulting in a final total of 190 participants included in the model development. The nomogram established five independent risk factors (P<0.05): FEV1%pred, smoking index (100), comorbidities situations, medication regimen, and good or poor medication adherence. The area under curve (AUC) of the modeling set was 0.824(95%CI 0.765-0.884), suggesting that the nomogram has a high ability to distinguish poor asthma control in smoking asthmatics after 6 months. The calibration curve showed a C-index of 0.824 for the modeling set and a C-index of 0.792 for the self-validation set formed by 1000 bootstrap sampling, which means that the prediction probability of the model was consistent with reality. Decision curve analysis (DCA) of the nomogram revealed that the net benefit was higher when the risk threshold probability for poor asthma control was 4.5 - 93.9%. CONCLUSIONS: FEV1%pred, smoking index (100), comorbidities situations, medication regimen, and medication adherence were identified as independent risk factors for poor asthma control after 6 months in smoking asthmatics. The nomogram established based on these findings can effectively predict relevant risk and provide clinicians with a reference to identify the poorly controlled population with smoking asthma as early as possible, and to select a better therapeutic regimen. Meanwhile, it can effectively improve the medication adherence and the degree of attention to complications in smoking asthma patients.

The impact of hyperkalemia on ICU admission and mortality: a retrospective study of Chinese emergency department data.

OBJECTIVE: This study assesses the influence of hyperkalemia on both disease severity and the risk of mortality among patients admitted to the emergency room. METHODS: This retrospective observational study utilized data from the Chinese Emergency Triage Assessment and Treatment database (CETAT, version 2.0), which was designed to evaluate and optimize management strategies for emergency room (ER) patients. Patients were systematically categorized based on serum potassium levels. Relationships between serum potassium levels, risk of mortality, and the severity of illness were then analyzed using multifactorial logistic regression and through Receiver Operating Characteristic (ROC) analysis. The effectiveness of various treatments at lowering potassium levels was also investigated. RESULTS: 12,799 emergency patients were enrolled, of whom 20.1% (n = 2,577) were hypokalemic and 2.98% (n = 381) were hyperkalemic. Among hyperkalemic patients, the leading reasons for visiting the ER were altered consciousness 23.88% (n = 91), cardiovascular symptoms 22.31% (n = 85), and gastrointestinal symptoms 20.47% (n = 78). Comparative analysis with patients exhibiting normal potassium levels revealed hyperkalemia as an independent factor associated with mortality in the ER. Mortality risk appears to positively correlate with increasing potassium levels, reaching peaks when blood potassium levels ranged between 6.5 and 7.0. Hyperkalemia emerged as a strong predictor of death in the ER, with an Area Under the Curve (AUC) of 0.89. The most frequently prescribed treatment for hyperkalemia patients was diuretics (57.32%, n = 188), followed by intravenous sodium bicarbonate (50.91%, n = 167), IV calcium (37.2%, n = 122), insulin combined with high glucose (27.74%, n = 91), and Continuous Renal Replacement Therapy (CRRT) for 19.82% (n = 65). Among these, CRRT appeared to be the most efficacious at reducing potassium levels. Diuretics appeared relatively ineffective, while high-glucose insulin, sodium bicarbonate, and calcium preparations having no significant effect on the rate of potassium decline. CONCLUSION: Hyperkalemia is common in emergency situations, especially among patients with altered consciousness. There is a strong positive correlation between the severity of hyperkalemia and mortality risk. CRRT appears to be the most effective potassium reducting strategy, while the use of diuretics should be approached with caution.

Constructing and validating a predictive nomogram for osteoporosis risk among Chinese single-center male population using the systemic immune-inflammation index.

Osteoporosis (OP) is a bone metabolism disease that is associated with inflammatory pathological mechanism. Nonetheless, rare studies have investigated the diagnostic effectiveness of immune-inflammation index in the male population. Therefore, it is interesting to achieve early diagnosis of OP in male population based on the inflammatory makers from blood routine examination. We developed a prediction model based on a training dataset of 826 Chinese male patients through a retrospective study, and the data was collected from January 2022 to May 2023. All participants underwent the dual-energy X-ray absorptiometry (DXEA) and blood routine examination. Inflammatory markers such as systemic immune-inflammation index (SII) and platelet-to-lymphocyte ratio (PLR) was calculated and recorded. We utilized the least absolute shrinkage and selection operator (LASSO) regression model to optimize feature selection. Multivariable logistic regression analysis was applied to construct a predicting model incorporating the feature selected in the LASSO model. This predictive model was displayed as a nomogram. Receiver operating characteristic (ROC) curve, C-index, calibration curve, and clinical decision curve analysis (DCA) to evaluate model performance. Internal validation was test by the bootstrapping method. This study was approved by the Ethic Committee of the First Affiliated Hospital of Guangzhou University of Traditional Chinese Medicine (Ethic No. JY2023012) and conducted in accordance with the relevant guidelines and regulations. The predictive factors included in the prediction model were age, BMI, cardiovascular diseases, cerebrovascular diseases, neuropathy, thyroid diseases, fracture history, SII, PLR, C-reactive protein (CRP). The model displayed well discrimination with a C-index of 0.822 (95% confidence interval: 0.798-0.846) and good calibration. Internal validation showed a high C-index value of 0.805. Decision curve analysis (DCA) showed that when the threshold probability was between 3 and 76%, the nomogram had a good clinical value. This nomogram can effectively predict the incidence of OP in male population based on SII and PLR, which would help clinicians rapidly and conveniently diagnose OP with men in the future.

Association between monocyte-lymphocyte ratio and all-cause and cardiovascular mortality in patients with chronic kidney diseases: A data analysis from national health and nutrition examination survey (NHANES) 2003-2010.

BACKGROUND: The relationship between monocyte-to-lymphocyte ratio (MLR) and prognosis in patients with chronic kidney disease (CKD) remains unclear. The aim of this study was to investigate the association between MLR and both all-cause mortality and cardiovascular disease (CVD) mortality in patients with CKD. METHODS: This study analyzed data from National Health and Nutrition Examination Survey 2003-2010. This study included 11262 eligible subjects, and 3015 of them were with CKD. We first compared the differences in clinical characteristics between individuals with and without CKD, and then grouped the CKD population based on quartiles of MLR. The partial correlation analysis was conducted to assess the relationships between MLR and some important clinical features. Cox proportional hazards models were used to investigate the associations between MLR and mortality from all-cause and cardiovascular disease. Restricted cubic spline (RCS) was used to investigate the dose-response relationship between MLR and mortality, the receiver operating characteristic (ROC) curves is used to compare the efficacy of MLR with different clinical biological indicators in assessing the risk of death. RESULTS: During a median follow-up of 10.3 years in CKD population, 1398 (43%) all-cause deaths and 526 (16%) CVD deaths occurred. It has been found that individuals with CKD have higher MLR level. The partial correlation analysis results showed that even after adjusting for age, sex, and race, MLR is still correlated with blood glucose, lipid levels, and kidney function indicators. The results of the cox proportional hazards regression model and Kaplan-Meier curve shown after adjusting for covariates, higher MLR was significantly associated with an increased risk of mortality. Consistent results were also observed when MLR was examined as categorical variable (quartiles). The RCS demonstrated a positive association between MLR and the risk of all-cause mortality and cardiovascular mortality. The ROC results indicate that the predictive efficacy of MLR for all-cause mortality risk is comparable to eGFR, higher than NLR and CRP. The predictive efficacy of MLR for cardiovascular mortality risk is higher than these three indicators. CONCLUSION: Compared to non-CKD population, the CKD population has higher levels of MLR. In the CKD population, MLR is positively correlated with the risk of death. Furthermore, the predictive efficacy of MLR for mortality risk is higher than other clinical indicators. This suggests that MLR can serve as a simple and effective clinical indicator for predicting mortality risk in CKD patients.

Fibrinogen-albumin ratio predicts treatment response in phospholipase A2 receptor-associated membranous nephropathy with nephrotic syndrome.

BACKGROUND: The M-type phospholipase A2 receptor (PLA2R)-associated primary membranous nephropathy (PMN) is an immune-related disease in adults with increasing morbidity and variable treatment response, in which inflammation may contribute to the multifactorial immunopathogenesis. The relationship between fibrinogen-albumin ratio (FAR), serving as a novel inflammatory biomarker, and PMN is still unclear. Therefore, this study aims to clarify the association between FAR and disease activity and therapy response of PMN. METHODS: 110 biopsy-proven phospholipase A2 receptor (PLA2R) -associated PMN participants with nephrotic syndrome from January 2017 to December 2021 were recruited in the First Affiliated Hospital of Nanjing Medical University. The independent risk factors of non-remission (NR) and the predictive ability of FAR were explored by Cox regression and receiver-operating characteristic (ROC) curve analysis. According to the optimal cutoff value, study patients were categorized into the low-FAR group (≤the cutoff value) and the high-FAR group (>the cutoff value). Spearman's correlations were used to examine the associations between FAR and baseline clinicopathological characteristics. Kaplan-Meier method was used to assess the effects of FAR on remission. RESULTS: In the entire study cohort, 78 (70.9%) patients reached complete or partial remission (CR or PR). The optimal cutoff value of FAR for predicting the remission outcome (CR + PR) was 0.233. The Kaplan-Meier survival analysis demonstrated that the high-FAR group (>0.233) had a significantly lower probability to achieve CR or PR compared to the low-FAR group (≤0.233) (Log Rank test, p = 0.021). Higher levels of FAR were identified as an independent risk factor for NR, and the high-FAR group was associated with a 2.27 times higher likelihood of NR than the low-FAR group (HR 2.27, 95% CI 1.01, 5.13, p = 0.048). These relationships remained robust with further analysis among calcineurin inhibitors (CNIs)-receivers. In the multivariate Cox regression model, the incidence of NR was 4.00 times higher in the high-FAR group than in the low-FAR group (HR 4.00, 95% CI 1.41, 11.31, p = 0.009). Moreover, ROC analysis revealed the predictive value of FAR for CR or PR with a 0.738 area under curve (AUC), and the AUC of anti-PLA2R Ab was 0.675. When combining FAR and anti-PLA2R Ab, the AUC was boosted to 0.766. CONCLUSIONS: FAR was significantly correlated with proteinuria and anti-PLA2R Ab in PMN. As an independent risk factor for NR, FAR might serve as a potential inflammation-based prognostic tool for identifying cases with poor treatment response, and the best predictive cutoff value for outcomes was 0.233.

Integration of deep learning and habitat radiomics for predicting the response to immunotherapy in NSCLC patients.

BACKGROUND: The non-invasive biomarkers for predicting immunotherapy response are urgently needed to prevent both premature cessation of treatment and ineffective extension. This study aimed to construct a non-invasive model for predicting immunotherapy response, based on the integration of deep learning and habitat radiomics in patients with advanced non-small cell lung cancer (NSCLC). METHODS: Independent patient cohorts from three medical centers were enrolled for training (n = 164) and test (n = 82). Habitat imaging radiomics features were derived from sub-regions clustered from individual's tumor by K-means method. The deep learning features were extracted based on 3D ResNet algorithm. Pearson correlation coefficient, T test and least absolute shrinkage and selection operator regression were used to select features. Support vector machine was applied to implement deep learning and habitat radiomics, respectively. Then, a combination model was developed integrating both sources of data. RESULTS: The combination model obtained a strong well-performance, achieving area under receiver operating characteristics curve of 0.865 (95% CI 0.772-0.931). The model significantly discerned high and low-risk patients, and exhibited a significant benefit in the clinical use. CONCLUSION: The integration of deep-leaning and habitat radiomics contributed to predicting response to immunotherapy in patients with NSCLC. The developed integration model may be used as potential tool for individual immunotherapy management.

Validación de test de flexión-relajación para definir un déficit lumbar con electrodos tetrapolares / Validation of the flexion-relaxation test to define a lumbar deficit with tetrapolar electrodes

Introducción y objetivo: Obtener un nuevo punto de corte (PC) para un test de flexión-relajación (FR) lumbar efectuado con electrodos (e.) tetrapolares, desde valores ya definidos con dispositivos bipolares.Materiales y métodosLa muestra del estudio consta de 47 pacientes en situación de incapacidad temporal por dolor lumbar (DL). Fueron evaluados mediante un test de dinamometría isométrica, una prueba cinemática y una valoración del fenómeno FR.Se plantean dos experimentos con curvas ROC. El primero, con 47 pacientes que efectuaron de modo consecutivo el test FR con ambos tipos de electrodos, utilizándose como variable de clasificación el punto de corte conocido para los e. bipolares (2,49uV). En el segundo, con los datos de la EMGs registrados con e. tetrapolares en 17 pacientes, se efectúa un test de DeLong que compara las 2 curvas ROC que construimos, por un lado, al clasificar la muestra desde pruebas de dinamometría y cinemática, y por el otro, al clasificarlos con los valores de la EMGs bipolar.ResultadosUn total de 34 pacientes completaron adecuadamente las valoraciones del primer experimento y 17 pacientes el segundo. El primer estudio arroja un punto de corte de 1,2uV, con un AUC del 87,7%; sensibilidad 84,2% y especificidad 80%. El segundo muestra un PC para los e. bipolares de 1,21uV (AUC 87,5%) y para los e. tetrapolares de 1,43 (AUC 82,5%) con un test de DeLong sin diferencias significativas entre ambas curvas (p>0,4065).ConclusionesLa metodología de validación con curvas ROC ha permitido obtener un nuevo PC para la prueba FR de modo práctico, simplemente simultaneando ambos test sobre el mismo grupo de pacientes hasta obtener una muestra significativa. (AU)

Introduction and objective: To obtain a new cut-off point (CP) for a lumbar flexion-relaxation (RF) test established with tetrapolar (e.) electrodes, from values already defined with bipolar devices.Materials and methodsThe study sample consists of 47 patients in a situation of temporary disability due to low back pain (DL). They were evaluated by means of an isometric dynamometry test, a kinematic test and an assessment of the FR phenomenon.Two experiments with ROC curves are proposed. The first, with 47 patients who consecutively performed the RF test with both types of electrodes, using the cut-off point (CP) known for the e. bipolar (2.49μV). In the second, with the EMG data recorded with e. tetrapolar in 17 patients, a DeLong test was performed that compares the 2 ROC curves that were constructed on the one hand, by classifying the sample from dynamometry and kinematic tests, and on the other, by classifying them with the bipolar EMG values.ResultsA total of 34 patients adequately completed the evaluations of the first experiment and 17 patients the second. The first study shows a cut-off point of 1.2μV, with an AUC of 87.7%; Sensitivity 84.2% and Specificity 80%. The second shows a PC for e. bipolars of 1.21μV (AUC 87.5%) and for e. tetrapolar values of 1.43 (AUC 82.5%) with a DeLong test without significant differences between both curves (p>0.4065).ConclusionsThe validation methodology with ROC curves has made it possible to obtain a new PC for the RF test in a practical way, simply by simultaneously performing both tests on the same group of patients until a significant sample is obtained. (AU)

Preoperative prediction of perineural invasion of rectal cancer based on a magnetic resonance imaging radiomics model: A dual-center study.

BACKGROUND: Perineural invasion (PNI) has been used as an important pathological indicator and independent prognostic factor for patients with rectal cancer (RC). Preoperative prediction of PNI status is helpful for individualized treatment of RC. Recently, several radiomics studies have been used to predict the PNI status in RC, demonstrating a good predictive effect, but the results lacked generalizability. The preoperative prediction of PNI status is still challenging and needs further study. AIM: To establish and validate an optimal radiomics model for predicting PNI status preoperatively in RC patients. METHODS: This retrospective study enrolled 244 postoperative patients with pathologically confirmed RC from two independent centers. The patients underwent pre-operative high-resolution magnetic resonance imaging (MRI) between May 2019 and August 2022. Quantitative radiomics features were extracted and selected from oblique axial T2-weighted imaging (T2WI) and contrast-enhanced T1WI (T1CE) sequences. The radiomics signatures were constructed using logistic regression analysis and the predictive potential of various sequences was compared (T2WI, T1CE and T2WI + T1CE fusion sequences). A clinical-radiomics (CR) model was established by combining the radiomics features and clinical risk factors. The internal and external validation groups were used to validate the proposed models. The area under the receiver operating characteristic curve (AUC), DeLong test, net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration curve, and decision curve analysis (DCA) were used to evaluate the model performance. RESULTS: Among the radiomics models, the T2WI + T1CE fusion sequences model showed the best predictive performance, in the training and internal validation groups, the AUCs of the fusion sequence model were 0.839 [95% confidence interval (CI): 0.757-0.921] and 0.787 (95%CI: 0.650-0.923), which were higher than those of the T2WI and T1CE sequence models. The CR model constructed by combining clinical risk factors had the best predictive performance. In the training and internal and external validation groups, the AUCs of the CR model were 0.889 (95%CI: 0.824-0.954), 0.889 (95%CI: 0.803-0.976) and 0.894 (95%CI: 0.814-0.974). Delong test, NRI, and IDI showed that the CR model had significant differences from other models (P < 0.05). Calibration curves demonstrated good agreement, and DCA revealed significant benefits of the CR model. CONCLUSION: The CR model based on preoperative MRI radiomics features and clinical risk factors can preoperatively predict the PNI status of RC noninvasively, which facilitates individualized treatment of RC patients.

Dynamic Prediction of Mortality Using Longitudinally Measured Pediatric Sequential Organ Failure Assessment Scores: A Joint Modeling Approach.

OBJECTIVES: The pediatric Sequential Organ Failure Assessment (pSOFA) score was designed to track illness severity and predict mortality in critically ill children. Most commonly, pSOFA at a point in time is used to assess a static patient condition. However, this approach has a significant drawback because it fails to consider any changes in a patients' condition during their PICU stay and, especially, their response to initial critical care treatment. We aimed to evaluate the performance of longitudinal pSOFA scores for predicting mortality. DESIGN: Single-center, retrospective cohort study. SETTING: Quaternary 40-bed PICU. PATIENTS: All patients admitted to the PICU between 2015 and 2021 with at least 24 hours of ICU stay. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We calculated daily pSOFA scores up to 30 days, or until death or discharge from the PICU, if earlier. We used the joint longitudinal and time-to-event data model for the dynamic prediction of 30-day in-hospital mortality. The dataset, which included 9146 patients with a 30-day in-hospital mortality of 2.6%, was divided randomly into training (75%) and validation (25%) subsets, and subjected to 40 repeated stratified cross-validations. We used dynamic area under the curve (AUC) to evaluate the discriminative performance of the model. Compared with the admission-day pSOFA score, AUC for predicting mortality between days 5 and 30 was improved on average by 6.4% (95% CI, 6.3-6.6%) using longitudinal pSOFA scores from the first 3 days and 9.2% (95% CI, 9.0-9.5%) using scores from the first 5 days. CONCLUSIONS: Compared with admission-day pSOFA score, longitudinal pSOFA scores improved the accuracy of mortality prediction in PICU patients at a single center. The pSOFA score has the potential to be used dynamically for the evaluation of patient conditions.

Whole-orbit-based multiparametric assessment of disease activity of thyroid eye disease on Dixon MRI.

PURPOSE: This study aimed to explore the diagnostic value of whole-orbit-based multiparametric assessment on Dixon MRI for the evaluation of the thyroid eye disease (TED) activity. METHODS: The retrospective study enrolled patients diagnosed as TED and obtained their axial and coronal Dixon MRI scans. Multiparameters were assessed, including water fraction (WF), fat fraction (FF) of extraocular muscles (EOMs), orbital fat (OF), and lacrimal gland (LG). The thickness of OF and herniation of LG were also measured. Univariable and multivariable logistic regression was applied to construct prediction models based on single or multiple structures. Receiver operating characteristic (ROC) curve analysis was also implemented. RESULTS: Univariable logistic analysis revealed significant differences in water fraction (WF) of the superior rectus (P = 0.018), fat fraction (FF) of the medial rectus (P = 0.029), WF of OF (P = 0.004), and herniation of LG (P = 0.012) between the active and inactive TED phases. Multivariable logistic analysis and corresponding receiver operating characteristic curve (ROC) analysis of each structure attained the area under the curve (AUC) values of 0.774, 0.771, and 0.729 for EOMs, OF, and LG, respectively, while the combination of the four imaging parameters generated a final AUC of 0.909. CONCLUSIONS: Dixon MRI may be used for fine multiparametric assessment of multiple orbital structures. The whole-orbit-based model improves the diagnostic performance of TED activity evaluation.

Construction of oxidative phosphorylation-related prognostic risk score model in uveal melanoma.

BACKGROUND: Uveal melanoma (UVM) is a malignant intraocular tumor in adults. Targeting genes related to oxidative phosphorylation (OXPHOS) may play a role in anti-tumor therapy. However, the clinical significance of oxidative phosphorylation in UVM is unclear. METHOD: The 134 OXPHOS-related genes were obtained from the KEGG pathway, the TCGA UVM dataset contained 80 samples, served as the training set, while GSE22138 and GSE39717 was used as the validation set. LASSO regression was carried out to identify OXPHOS-related prognostic genes. The coefficients obtained from Cox multivariate regression analysis were used to calculate a risk score, which facilitated the construction of a prognostic model. Kaplan-Meier survival analysis, logrank test and ROC curve using the time "timeROC" package were conducted. The immune cell frequency in low- and high-risk group was analyzed through Cibersort tool. The specific genomic alterations were analyzed by "maftools" R package. The differential expressed genes between low- or high-risk group were analyzed and performed Gene Ontology (GO) and GSEA. Finally, we verified the function of CYC1 in UVM by gene silencing in vitro. RESULTS: A total of 9 OXPHOS-related prognostic genes were identified, including NDUFB1, NDUFB8, ATP12A, NDUFA3, CYC1, COX6B1, ATP6V1G2, ATP4B and NDUFB4. The UVM prognostic risk model was constructed based on the 9 OXPHOS-related prognostic genes. The prognosis of patients in the high-risk group was poorer than low-risk group. Besides, the ROC curve demonstrated that the area under the curve of the model for predicting the 1 to 5-year survival rate of UVM patients were all more than 0.88. External validation in GSE22138 and GSE39717 dataset revealed that these 9 genes could also be utilized to evaluate and predict the overall survival of patients with UVM. The risk score levels related to immune cell frequency and specific genomic alterations. The DEGs between the low- and high- risk group were enriched in tumor OXPHOS and immune related pathway. In vitro experiments, CYC1 silencing significantly inhibited UVM cell proliferation and invasion, induced cell apoptosis. CONCLUSION: In sum, a prognostic risk score model based on oxidative phosphorylation-related genes in UVM was developed to enhance understanding of the disease. This prognostic risk score model may help to find potential therapeutic targets for UVM patients. CYC1 acts as an oncogene role in UVM.

Respiratory Rate Oxygenation (ROX) index as predictor of high flow nasal cannula in pediatric patients in pediatric intensive care unit.

BACKGROUND: High-flow nasal cannula (HFNC) is often used in pediatric populations with respiratory distress. In adults, the respiratory-rate oxygenation (ROX) index is used as a predictor of HFNC therapy; however, children have age-associated differences in respiratory rate, thus may not be applicable to children. This study aims to find the reliability of ROX index and modified P-ROX index as predictors of HFNC therapy failure in pediatric patients. METHODS: Subjects in this analytical cross-sectional study were taken from January 2023 until November 2023 in Cipto Mangunkusumo Hospital. Inclusion criteria are children aged 1 month to 18 years with respiratory distress and got HFNC therapy. Receiver operating characteristics (ROC) analysis was used to find mP-ROX index cutoff value as a predictor of HFNC failure. The area under curve (AUC) score of mP-ROX index was assessed at different time point. RESULTS: A total of 102 patients, with 70% of the population with pneumonia, were included in this study. There are significant differences in the ROX index between the successful and failed HFNC group therapy (p < 0.05). This study suggests that mP-ROX index is not useful as predictor of HFNC therapy in pediatrics. While ROX index < 5.52 at 60 min and < 5.68 at 90 min after HFNC initiation have a sensitivity of 90% and specificity of 71%, sensitivity of 78% and specificity of 76%, respectively. CONCLUSION: mP-ROX index is not useful as a predictor of HFNC therapy in pediatrics. Meanwhile, ROX index at 60 min and 90 min after initiation of HFNC is useful as a predictor of HFNC failure.