DeLong Test Research Articles

Machine learning models for differential diagnosing HER2-low breast cancer: A radiomics approach.

To develop machine learning models based on preoperative dynamic enhanced magnetic resonance imaging (DCE-MRI) radiomics and to explore their potential prognostic value in the differential diagnosis of human epidermal growth factor receptor 2 (HER2)-low from HER2-positive breast cancer (BC). A total of 233 patients with pathologically confirmed invasive breast cancer admitted to our hospital between January 2018 and December 2022 were included in this retrospective analysis. Of these, 103 cases were diagnosed as HER2-positive and 130 cases were HER2 low-expression BC. The Synthetic Minority Oversampling Technique is employed to address the class imbalance problem. Patients were randomly split into a training set (163 cases) and a validation set (70 cases) in a 7:3 ratio. Radiomics features from DCE-MRI second-phase imaging were extracted. Z-score normalization was used to standardize the radiomics features, and Pearson's correlation coefficient and recursive feature elimination were used to explore the significant features. Prediction models were constructed using 6 machine learning algorithms: logistic regression, random forest, support vector machine, AdaBoost, decision tree, and auto-encoder. Receiver operating characteristic curves were constructed, and predictive models were evaluated according to the area under the curve (AUC), accuracy, sensitivity, and specificity. In the training set, the AUC, accuracy, sensitivity, and specificity of all models were 1.000. However, in the validation set, the auto-encoder model's AUC, accuracy, sensitivity, and specificity were 0.994, 0.976, 0.972, and 0.978, respectively. The remaining models' AUC, accuracy, sensitivity, and specificity were 1.000. The DeLong test showed no statistically significant differences between the machine learning models in the training and validation sets (Z = 0, P = 1). Our study investigated the feasibility of using DCE-MRI-based radiomics features to predict HER2-low BC. Certain radiomics features showed associations with HER2-low BC and may have predictive value. Machine learning prediction models developed using these radiomics features could be beneficial for distinguishing between HER2-low and HER2-positive BC. These noninvasive preoperative models have the potential to assist in clinical decision-making for HER2-low breast cancer, thereby advancing personalized clinical precision.

Association of body mass index-adjusted calf circumference with appendicular skeletal muscle mass and fall risk in older adults.

This study aims to evaluate the utility of body mass index (BMI)-adjusted calf circumference (CC) in estimating skeletal muscle mass and diagnosing sarcopenia, as well as its association with falls, a common adverse event in sarcopenia. This study used cross-sectional and longitudinal designs. The CC cut-off values and the diagnosis of sarcopenia were based on valid diagnostic criteria. BMI-adjusted CC was based on previous studies, with muscle mass measured by dual-energy X-ray absorptiometry. To evaluate the diagnostic performance of BMI-adjusted CC for low muscle mass and sarcopenia, receiver operating characteristic curves were generated, and the area under the curve (AUC) values were compared using DeLong's test. Over a 1year follow-up period, factors associated with falls were examined using logistic regression analysis. In the study of 901 older adults (77.6 ± 6.1years, 63.6% women), 38.1% of men and 42.1% of women had a BMI outside the 18.5-24.9kg/m2 range. BMI-adjusted CC significantly lowered the AUC values for diagnosing low skeletal muscle mass and sarcopenia in both sexes (P < 0.001). Longitudinal univariate logistic regression analysis in women revealed that unadjusted CC was not significantly associated with fall risk, whereas BMI-adjusted CC significantly reduced fall risk at higher values. However, this association was no longer present in the multivariate analysis. The utility of BMI-adjusted CC in assessing skeletal muscle mass was not confirmed. The potential value of BMI-adjusted CC has been suggested regarding falls. Further research is warranted to better elucidate these findings.

Development of a deep learning model for detecting lumbar vertebral fractures on CT images: An external validation

ObjectiveTo develop and externally validate a binary classification model for lumbar vertebral body fractures based on CT images using deep learning methods. MethodsThis study involved data collection from two hospitals for AI model training and external validation. In Cohort A from Hospital 1, CT images from 248 patients, comprising 1508 vertebrae, revealed that 20.9% had fractures (315 vertebrae) and 79.1% were non-fractured (1193 vertebrae). In Cohort B from Hospital 2, CT images from 148 patients, comprising 887 vertebrae, indicated that 14.8% had fractures (131 vertebrae) and 85.2% were non-fractured (756 vertebrae). The AI model for lumbar spine fractures underwent two stages: vertebral body segmentation and fracture classification. The first stage utilized a 3D V-Net convolutional deep neural network, which produced a 3D segmentation map. From this map, region of each vertebra body were extracted and then input into the second stage of the algorithm. The second stage employed a 3D ResNet convolutional deep neural network to classify each proposed region as positive (fractured) or negative (not fractured). ResultsThe AI model’s accuracy for detecting vertebral fractures in Cohort A’s training set (n = 1199), validation set (n = 157), and test set (n = 152) was 100.0 %, 96.2 %, and 97.4 %, respectively. For Cohort B (n = 148), the accuracy was 96.3 %. The area under the receiver operating characteristic curve (AUC-ROC) values for the training, validation, and test sets of Cohort A, as well as Cohort B, and their 95 % confidence intervals (CIs) were as follows: 1.000 (1.000, 1.000), 0.978 (0.944, 1.000), 0.986 (0.969, 1.000), and 0.981 (0.970, 0.992). The area under the precision-recall curve (AUC-PR) values were 1.000 (0.996, 1.000), 0.964 (0.927, 0.985), 0.907 (0.924, 0.984), and 0.890 (0.846, 0.971), respectively. According to the DeLong test, there was no significant difference in the AUC-ROC values between the test set of Cohort A and Cohort B, both for the overall data and for each specific vertebral location (all P>0.05). ConclusionThe developed model demonstrates promising diagnostic accuracy and applicability for detecting lumbar vertebral fractures.

Peritumoral edema enhances MRI-based deep learning radiomic model for axillary lymph node metastasis burden prediction in breast cancer

To investigate whether peritumoral edema (PE) could enhance deep learning radiomic (DLR) model in predicting axillary lymph node metastasis (ALNM) burden in breast cancer. Invasive breast cancer patients with preoperative MRI were retrospectively enrolled and categorized into low (< 2 lymph nodes involved (LNs+)) and high (≥ 2 LNs+) burden groups based on surgical pathology. PE was evaluated on T2WI, and intra- and peri-tumoral radiomic features were extracted from MRI-visible tumors in DCE-MRI. Deep learning models were developed for LN burden prediction in the training cohort and validated in an independent cohort. The incremental value of PE was evaluated through receiver operating characteristic (ROC) analysis, confirming the improvement in the area under the curve (AUC) using the Delong test. This was complemented by net reclassification improvement (NRI) and integrated discrimination improvement (IDI) metrics. The deep learning combined model, incorporating PE with selected radiomic features, demonstrated significantly higher AUC values compared to the MRI model and the DLR model in the training cohort (n = 177) (AUC: 0.953 vs. 0.849 and 0.867, p < 0.05) and the validation cohort (n = 111) (AUC: 0.963 vs. 0.883 and 0.882, p < 0.05). The complementary analysis demonstrated that PE significantly enhances the prediction performance of the DLR model (Categorical NRI: 0.551, p < 0.001; IDI = 0.343, p < 0.001). These findings were confirmed in the validation cohort (Categorical NRI: 0.539, p < 0.001; IDI = 0.387, p < 0.001). PE improved preoperative ALNM burden prediction of DLR model, facilitating personalized axillary management in breast cancer patients.

Development and validation of a model predicting adrenal lipid-poor adenoma based on the minimum attenuation value from non-contrast CT: a dual-center retrospective study

ObjectiveThe early differentiation of adrenal lipid-poor adenomas from non-adenomas is a crucial step in reducing excessive examinations and treatments. This study seeks to construct an eXtreme Gradient Boosting (XGBoost) predictive model utilizing the minimum attenuation values (minAVs) from non-contrast CT (NCCT) scans to identify lipid-poor adenomas.Materials and methodsRetrospective analysis encompassed clinical data, minAVs, CT histogram (CTh), mean attenuation values (meanAVs), and lesion diameter from patients with pathologically or clinically confirmed adrenal lipid-poor adenomas across two medical institutions, juxtaposed with non-adenomas. Variable selection transpired in Institution A (training set), with XGBoost models established based on minAVs and CTh separately. Institution B (validation set) corroborated the diagnostic efficacy of the two models. Receiver operator characteristic (ROC) curve analysis, calibration curves, and Brier scores assessed the diagnostic performance and calibration of the models, with the Delong test gauging differences in the area under the curve (AUC) between models. SHapley Additive exPlanations (SHAP) values elucidated and visualized the models.ResultsThe training set comprised 136 adrenal lipid-poor adenomas and 126 non-adenomas, while the validation set included 46 and 40 instances, respectively. In the training set, there were substantial inter-group differences in minAVs, CTh, meanAVs, diameter, and body mass index (BMI) (p < 0.05 for all). The AUC for the minAV and CTh models were 0.912 (95% confidence interval [CI]: 0.866–0.957) and 0.916 (95% CI: 0.873–0.958), respectively. Both models exhibited good calibration, with Brier scores of 0.141 and 0.136. In the validation set, the AUCs were 0.871 (95% CI: 0.792–0.951) and 0.878 (95% CI: 0.794–0.962), with Brier scores of 0.156 and 0.165, respectively. The Delong test revealed no statistically significant differences in AUC between the models (p > 0.05 for both). SHAP value analysis for the minAV model suggested that minAVs had the highest absolute weight (AW) and negative contribution.ConclusionThe XGBoost predictive model based on minAVs demonstrates effective discrimination between adrenal lipid-poor adenomas and non-adenomas. The minAV variable is easily obtainable, and its diagnostic performance is comparable to that of the CTh model. This provides a basis for patient diagnosis and treatment plan selection.

Значение видео-уродинамического исследования в выборе метода лечения детей с нейрогенными дисфункциями мочевого пузыря

Video urodynamics is the standard for assessment of the lower urinary tract in children with neurogenic urinary disorders aiming to provide more information about the condition of the lower urinary tract v. retrograde urethrocystography. Video urodynamics parameters are used as possible indicators for choosing various surgical treatment options, however, all work is focused on adult patients, and data for the pediatric cohort were not available as yet. The purpose of this research was the evaluation of the role of video urodynamics and retrograde urethrocystography in the selection of effective conservative and surgical treatment of neurogenic urinary disorders in children. Materials and methods used: 112 patients aged 1,8 to 18 y/o with neurogenic urinary disorders were included in the study, of whom 101 were those who had been proven effectively treated with conservative M-cholinoblockers or had successfully undergone minimally invasive surgery as follows: intradetrusor injection of botulinum toxin (n=21), transurethral correction of VUR (n=17), simultaneous execution of two of these interventions (n=22). Based on the results of video urodynamic and cystographic examination of these patients with the CHAID technique, the classification trees were built in order to evaluate the effective treatment (conservative/surgical). Results: the median age of patients was 9,0 years [7,8-12,0]. The first classification tree containing the parameter “presence of VUR according to the results of retrograde cystography.” The sensitivity of the obtained model for the effectiveness of surgical treatment was 83,3% v. 73,2% for conservative treatment. The accuracy was 79,2%. The ROC-AUC value was 0,783. The second classification tree contained the maximum Pves value according to the results of the video urodynamics, presence of hyperactivity, presence of VUR. The sensitivity of the obtained model for the effectiveness of surgical treatment was 93,3% v. 97,6% for conservative treatment. The accuracy was 95,0%. The ROC-AUC value was 0,972. Comparison of ROC-AUC values by the Delong test revealed statistically significant differences between these binary classification metrics (p&lt;0.001). Conclusion: the parameters of video urodynamics have greater diagnostic accuracy in effective prediction of both conservative and surgical treatment methods compared to the retrograde urethrocystography.

Prediction of Length of Stay After Colorectal Surgery Using Intraoperative Risk Factors.

The primary objective of this study was to develop a length of stay (LOS) prediction model. Predicting the LOS is crucial for patient care, planning, managing expectations, and optimizing hospital resources. Prolonged LOS after colorectal surgery is largely influenced by complications, and an accurate prediction model could significantly benefit patient outcomes and healthcare efficiency. This study included patients who underwent colorectal surgery in 14 different hospitals between January 2016 and December 2020. Two distinct random forest models were developed: one solely based on preoperative variables (preoperative prediction model [PP model]) and the other incorporating both preoperative and intraoperative variables (intraoperative prediction model [IP model]). Both models underwent validation using 10-fold cross-validation. The discriminative power of the model was assessed using the area under the curve (AUC), and calibration was evaluated using a calibration curve. The 2 developed models were compared using DeLong test. A total of 2140 patients were included in the analysis. After internal validation, the PP model achieved an AUC of 0.75 (95% confidence interval [CI]: 0.73-0.77), and the IP model achieved an AUC of 0.84 (95% CI: 0.82-0.85). The difference in discrimination between the 2 models was statistically significant (DeLong test, P < 0.001). Both models exhibited good calibration. Incorporating intraoperative parameters enhances the accuracy of the predictive model for LOS after colorectal surgery. Improving LOS prediction can assist in managing the increasing number of patients and optimizing the allocation of healthcare resources.

HTFSMMA: Higher-Order Topological Guided Small Molecule-MicroRNA Associations Prediction.

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM-miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM-miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM-miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs.

Development and validation of a CT-based nomogram for accurate hepatocellular carcinoma detection in high risk patients.

To establish and validate a CT-based nomogram for accurately detecting HCC in patients at high risk for the disease. A total of 223 patients were divided into training (n=161) and validation (n=62) cohorts between January of 2017 and May of 2022. Logistic analysis was performed, and clinical model and radiological model were developed separately. Finally, a nomogram was established based on clinical and radiological features. All models were evaluated using the area under the curve (AUC). DeLong's test was used to evaluate the differences among these models. In the multivariate analysis, gender (p = 0.014), increased Alpha-fetoprotein (AFP) (p = 0.017), non-rim arterial phase hyperenhancement (APHE) (p = 0.011), washout (p = 0.011), and enhancing capsule (p = 0.001) were the independent differential predictors of HCC. A nomogram was formed with well-fitted calibration curves based on these five factors. The area under the curve (AUC) of the nomogram in the training and validation cohorts was 0.961(95%CI: 0.935~0.986) and 0.979 (95% CI: 0.949~1), respectively. The nomogram outperformed the clinical and the radiological models in training and validation cohorts. The nomogram incorporating clinical and CT features can be a simple and reliable tool for detecting HCC and achieving risk stratification in patients at high risk for HCC.

External validation of different predictive scores for symptomatic intracranial hemorrhage after intravenous thrombolysis in Asian stroke patients

ObjectiveThis study aimed to externally validate different predictive scores for symptomatic intracranial hemorrhage (SICH) after intravenous thrombolysis (IVT), with a particular focus on their predictive abilities in Asian stroke patients. MethodsWe retrospectively enrolled stroke patients who received a standard dose of alteplase within 4.5 hours from symptom onset at the First Affiliated Hospital of Dalian Medical University from July 2010 to August 2023. SICH was defined as the hemorrhagic transformation detected on the head CT scan completed within 48 h post-IVT, accompanied by a clinical deterioration of at least a 4-point increase in NIHSS score. Predictive abilities of the HAT, MSS, SEDAN, SPAN-100, and GRASPS scores were tested. Discrimination and calibration were performed using the area under the receiver operating characteristic curve (ROC-AUC), DeLong test, and Hosmer-Lemeshow (H-L) goodness-of-fit test. ResultsThe study included 1007 stroke patients, of whom 31 (3.08 %) developed SICH. ROC-AUCs for predicting SICH were: 0.796 (95 %CI: 0.726–0.866) for the GRASPS score, 0.724 (95 %CI: 0.644–0.804) for the MSS score, 0.715 (95 %CI: 0.619–0.811) for the SEDAN score, 0.714 (95 %CI: 0.611–0.817) for the HAT score, and 0.605 (95 %CI: 0.491–0.720) for the SPAN-100 score (all P < 0.05). DeLong tests showed that the GRASPS score demonstrated significantly better discrimination than the MSS score (P = 0.010), the SEDAN score (P = 0.009), the HAT score (P = 0.049), and the SPAN-100 score (P = 0.000). H-L tests indicated good calibrations which were ranked HAT > SEDAN > MSS > SPAN-100 > GRASPS scores. ConclusionThe GRASPS score showed reasonable predictive ability for SICH, indicating its potential utility for Asian stroke patients receiving IVT.

Gadolinium Enhanced T2 FLAIR is an Imaging Biomarker of Radiation Necrosis and Tumor Progression in Patients with Brain Metastases.

Differentiating radiation necrosis (RN) from tumor progression (TP) after radiotherapy for brain metastases is an important clinical problem requiring advanced imaging techniques which may not be widely available and are challenging to perform at multiple time points. The ability to leverage conventional MRI for this problem, could have meaningful clinical impact. The purpose of this study was to explore contrast enhanced T2 FLAIR (T2FLAIRc) as a new imaging biomarker of RN and TP. This single-institution retrospective study included patients with treated brain metastases undergoing DSC-MRI between January 2021 and June 2023. Reference standard assessment was based on histopathology or serial follow-up including results of DSC-MRI for a minimum of 6 months from the first DSC-MRI. The index test was implemented as part of the institutional brain tumor MRI protocol and preceded the first DSC-MRI. T2FLAIRc and gadolinium enhanced T1 MPRAGE (T1c) signal were normalized against normal brain parenchyma and expressed as z-score. Mean signal intensity of enhancing disease for RN and TP groups were compared using unpaired t-test. Receiver operator characteristic (ROC) curves and area under the ROC curve (AUC) were derived by bootstrapping. DeLong test was used to compare AUC. 56 participants (mean age, 62 years +/-12.7 [SD]; 39 females); 28 RN, 28 TP were evaluated. The index MRI was performed on average 73 days +/-34 [SD] before the first DSC-MRI. Significantly higher z-scores were found for RN using T2FLAIRc (8.3 versus 5.8, p<0.001) and T1c (4.1 versus 3.5, p=0.02). AUC for T2FLAIRc (0.83, 95% CI, 0.72-0.92) was greater than T1c (0.70, 95% CI, 0.560.83) (p = 0.04). The AUC of DSC derived rCBV (0.82, 95% CI, 0.70-0.93) was not significantly different from T2FLAIRc (p = 0.9). A higher normalized T1c and T2FLAIRc signal intensity was found for RN. In a univariable test, mean T2FLAIRc signal intensity of enhancing voxels showed good discrimination performance for distinguishing RN from TP. The results of this work demonstrate the potential of T2FLAIRc as an imaging biomarker in the work-up of RN in patients with brain metastases. AUC = area under the receiver operating characteristic curve; RN = radiation necrosis; ROC = receiver operating characteristic; SRS = stereotactic radiosurgery; T1c = contrast enhanced T1; T2FLAIRc = contrast enhanced T2 FLAIR; TP = tumor progression.

Radiomics nomogram based on CT radiomics features and clinical factors for prediction of Ki-67 expression and prognosis in clear cell renal cell carcinoma: a two-center study

ObjectivesTo develop and validate a radiomics nomogram combining radiomics features and clinical factors for preoperative evaluation of Ki-67 expression status and prognostic prediction in clear cell renal cell carcinoma (ccRCC).MethodsTwo medical centers of 185 ccRCC patients were included, and each of them formed a training group (n = 130) and a validation group (n = 55). The independent predictor of Ki-67 expression status was identified by univariate and multivariate regression, and radiomics features were extracted from the preoperative CT images. The maximum relevance minimum redundancy (mRMR) and the least absolute shrinkage and selection operator algorithm (LASSO) were used to identify the radiomics features that were most relevant for high Ki-67 expression. Subsequently, clinical model, radiomics signature (RS), and radiomics nomogram were established. The performance for prediction of Ki-67 expression status was validated using area under curve (AUC), calibration curve, Delong test, decision curve analysis (DCA). Prognostic prediction was assessed by survival curve and concordance index (C-index).ResultsTumour size was the only independent predictor of Ki-67 expression status. Five radiomics features were finally identified to construct the RS (AUC: training group, 0.821; validation group, 0.799). The radiomics nomogram achieved a higher AUC (training group, 0.841; validation group, 0.814) and clinical net benefit. Besides, the radiomics nomogram provided a highest C-index (training group, 0.841; validation group, 0.820) in predicting prognosis for ccRCC patients.ConclusionsThe radiomics nomogram can accurately predict the Ki-67 expression status and exhibit a great capacity for prognostic prediction in patients with ccRCC and may provide value for tailoring personalized treatment strategies and facilitating comprehensive clinical monitoring for ccRCC patients.

The combined application of oligoclonal bands in cerebrospinal fluid and IgG intrathecal synthesis indicators and biochemical markers in the diagnosis of multiple sclerosis

Objective: To establish and verify a diagnostic model for distinguishing multiple sclerosis (MS) from other neurological diseases with similar symptoms by usingcerebrospinal fluid oligoclonal band (CSF-OCB)combined with IgG intrathecal synthesis indicators and biochemical markers. Methods: Multiple sclerosis (MS) patients admitted to the Neurology Department of Beijing Tiantan Hospital affiliated with Capital Medical University from January 2014 to December 2022 were selected as the case group, while patients with similar neurological symptoms were selected as the control group. Using the case-control study design, a retrospective analysis was conducted on the detection of age, gender, oligoclonal bands in cerebrospinal fluid, IgG intrathecal synthesis indicators and biochemical indicators for all study subjects. The differential diagnosis model was determined by the multiple logistic regression analysis, and the receiver operating characteristic (ROC) curve was used to analyze the diagnostic efficiency of the differential diagnosis model for neurological diseases with similar symptoms to MS and other conditions. Results: This study included 167 patients in the case group and 335 patients in the control group, of which 128 patients in the case group and 265 patients in the control group were used to construct the model, and 39 patients in the case group and 70 patients in the control group were used for model validation. The differential diagnostic model constructed by a multivariate logistic regression model was Y=0.871×CSF-OCB-0.051×CSFprotein-0.231×CSFchloride+1.183×gender-0.036×LDH+35.770. The model showed that the area under the curve, sensitivity and specificity were respectively 0.916, 87.3% and 87.6%. The Delong test results showed that the diagnostic efficacy of the model was significantly different from OCB, IgG intrathecal synthesis indicators, and OCB combined with IgG intrathecal synthesis indicators (P<0.05). The new model validation showed that the actual diagnostic consistency rate for the MS group was 84.6%, while the actual diagnostic consistency rate for the control group was 90.0%. Conclusion: This study combines OCB, IgG intrathecal synthesis indicators, and biochemical indicators to establish a diagnostic prediction model for neurological diseases with similar clinical symptoms in MS. This model may have good differential diagnostic value and can better assist clinical diagnosis in the early stages of disease progression in MS patients.

Washout-parametric imaging with Sonazoid for enhanced differentiation of focal liver lesions.

The study aimed to compare the diagnostic performance of washout-parametric imaging (WOPI) with that of conventional contrast-enhanced ultrasound (cCEUS) in differentiating focal liver lesions (FLLs). A total of 181 FLLs were imaged with contrast-enhanced ultrasound using Sonazoid, and the recordings were captured for 10 minutes in a prospective setting. WOPI was constructed from three images, depicting the arterial phase (peak enhancement), the early portal venous phase (1-minute post-injection), and the vasculo-Kupffer phase (5 or 10 minutes post-injection). The intensity variations in these images were color-coded and superimposed to produce a single image representing the washout timing across the lesions. From the 181 FLLs, 30 hepatocellular carcinomas (HCCs), 30 non-HCC malignancies, and 30 benign lesions were randomly selected for an observer study. Both techniques (cCEUS and WOPI) were evaluated by four off-site readers. They classified each lesion as benign or malignant using a continuous rating scale, with the endpoints representing "definitely benign" and "definitely malignant." The diagnostic performance of cCEUS and WOPI was compared using the area under the receiver operating characteristic curve (AUC) with the DeLong test. Interobserver agreement was assessed using the intraclass correlation coefficient (ICC). The difference in average AUC values between WOPI and cCEUS was 0.0062 (95% confidence interval, -0.0161 to 0.0285), indicating no significant difference between techniques. The interobserver agreement was higher for WOPI (ICC, 0.77) than cCEUS (ICC, 0.67). The diagnostic performance of WOPI is comparable to that of cCEUS in differentiating FLLs, with superior interobserver agreement.

The incremental value of left ventricular energy loss in predicting adverse events in chronic kidney disease patients with preserved ejection fraction

BackgroundVector flow mapping (VFM) is a new echocardiographic technology that can effectively evaluate systolic and diastolic hemodynamic function. However, little is known about the prognostic value of VFM-related parameters. In this paper we aimed to investigate whether left ventricular energy loss (EL) parameters as assessed by VFM enhance prediction of adverse events in patients with chronic kidney disease with preserved ejection fraction. MethodsOne hundred thirty-nine prospectively recruited patients (66% male, 58% on dialysis) with CKD stage 3–5 with normal left ventricular ejection fraction (LVEF) made up the study cohort. Global longitudinal strain (GLS) was calculated using 2-dimensional speckle tracking, and the LV EL during one cardiac cycle for each period was measured using VFM technology. Participants were followed for 4.17 ± 1.58 years for the primary end point of overall mortality and major adverse cardiovascular events (MACE). ResultsForty-five (32%) patients had a primary endpoint event. The EL during each period especially during the ejection stage (Ej-EL) was significantly higher in patients with adverse events than in those without, meanwhile the LV GLS were lower. The Ej-EL (HR: 1.11; 95% CI: 1.06–1.15) and LV GLS (HR: 0.87; 95% CI: 0.81–0.94) (all P < .001) were independent predictors for the primary end point. Increased Ej-EL (≥6.13, 10−3 J/m s) and impaired GLS (<15.52, %) were associated with a higher risk of overall mortality death and MACE (log rank χ2 = 26.94, 7.19; P < .001, =0.007), and DeLong tests showed that Ej-EL (AUC = 0.823) has a slight advantage in predicting adverse events compared to GLS (AUC = 0.681). Furthermore, the addition of Ej-EL to a model with conventional parameters did more to improve the model's discrimination compared to GLS. ConclusionsIncreased Ej-EL as determined by VFM is associated with a higher risk of overall death and MACE in CKD patients with preserved EF.

Fat-suppression T2 relaxation time and water fraction predict response to intravenous glucocorticoid therapy for thyroid-associated ophthalmopathy.

To investigate the value of fat-suppression (FS) T2 relaxation time (T2RT) derived from FS T2 mapping and water fraction (WF) derived from T2 IDEAL to predict the treatment response to intravenous glucocorticoids (IVGC) in patients with thyroid-associated ophthalmopathy (TAO) based on texture analysis. In this study, 89 patients clinically diagnosed with active and moderate-to-severe TAO were enroled (responsive group, 48 patients; unresponsive group, 41 patients). The baseline clinical characteristics and texture features were compared between the two groups. Multivariate analysis was performed to identify the independent predictors of treatment response to IVGC. ROC analysis and the DeLong test were used to assess and compare the predictive performance of different models. The responsive group exhibited significantly shorter disease duration and higher 90th percentile of FS T2RT and kurtosis of WF in the extraocular muscle (EOM) and 95th percentile of WF in the orbital fat (OF) than the unresponsive group. Model 2 (disease duration + WF; AUC, 0.816) and model 3 (disease duration + FS T2RT + WF; AUC, 0.823) demonstrated superior predictive efficacy compared to model 1 (disease duration + FS T2RT; AUC, 0.756), while there was no significant difference between models 2 and 3. The orbital tissues of responders exhibited more oedema and heterogeneity. Furthermore, OF is as valuable as EOM for assessing the therapeutic efficacy of IVGC. Finally, WF derived from T2 IDEAL processed by texture analysis can provide valuable information for predicting the treatment response to IVGC in patients with active and moderate-to-severe TAO. The texture features of FS T2RT and WF are different between responders and non-responders, which can be the predictive tool for treatment response to IVGC. Texture analysis can be used for predicting response to IVGC in TAO patients. TAO patients responsive to IVGC show more oedema and heterogeneity in the orbital tissues. WF from T2 IDEAL is a tool to predict the therapeutic response of TAO.

Comparing Frailty Indices for Risk Stratification in Urologic Oncology: Which Index to Choose?

ObjectiveTo compare the predictive ability of the modified Frailty Index (mFI) and the revised Risk Analysis Index (RAI-Rev) for perioperative outcomes in patients undergoing major urologic oncologic surgery, aiming to identify the optimal frailty screening tool for surgical risk stratification. MethodsNSQIP was queried to identify patients undergoing radical prostatectomy, partial or radical nephrectomy, or radical cystectomy between 2013-2017. We investigated the association of mFI and RAI-Rev with the following 30-day perioperative outcomes using multivariable logistic regression: major complications, Clavien grade ≥4 complications, non-home discharge, 30-day readmission, and all-cause mortality. Receiver-operating characteristic curve analysis compared the predictive performances of the two frailty instruments, with differences between the C-statistics assessed using DeLong's test. ResultsAmong 101,739 patients, 30-day major complication rates varied from 2.40% in prostatectomy to 26.86% in cystectomy, non-home discharge rates ranged from 1.92% to 13.54%, and mortality rates were between 0.16% and 1.43%. RAI-Rev showed higher discriminatory ability for mortality (C-statistic: 0.688-0.798) and non-home discharge (C-statistic: 0.638-0.734) compared to mFI (C-statistic: 0.594-0.677 and 0.593-0.639, respectively). Both frailty indices had similar discriminatory ability for major perioperative complications (C-statistic: 0.531-0.607). DeLong's test confirmed statistically significant differences in C-statistics between RAI-Rev and mFI for mortality (p<0.001) and non-home discharge (p<0.001) across all surgical cohorts. ConclusionRAI-Rev may have greater utility as a frailty prognostic tool than mFI among patients undergoing major urologic surgery. Prospective studies and clinical trials exploring frailty should consider these results during trial design.

A Comprehensive Model Outperformed the Single Radiomics Model in Noninvasively Predicting the HER2 Status in Patients with Breast Cancer

This study aimed to develop predictive models based on conventional magnetic resonance imaging (cMRI) and radiomics features for predicting human epidermal growth factor receptor 2 (HER2) status of breast cancer (BC) and compare their performance. A total of 287 patients with invasive BC in our hospital were retrospectively analyzed. All patients underwent preoperative breast MRI consisting of fat-suppressed T2-weighted imaging, axial dynamic contrast-enhanced MRI, and diffusion-weighted imaging sequences. From these sequences, radiomics features were derived. Three distinct models were established utilizing cMRI features, radiomics features, and a comprehensive model that amalgamated both. The predictive capabilities of these models were assessed using the receiver operating characteristic curve analysis. The comparative performance was then determined through the DeLong test and net reclassification improvement (NRI). In a randomized split, the 287 patients with BC were allotted to either training (234; 46 HER2-zero, 107 HER2-low, 81 HER2-positive) or test (53; 8 HER2-zero, 27 HER2-low, 18 HER2-positive) at an 8:2 ratio. The mean area under the curve (AUCs) for cMRI, radiomics, and comprehensive models predicting HER2 status were 0.705, 0.819, and 0.859 in training set and 0.639, 0.797, and 0.842 in test set, respectively. DeLong's test indicated that the combined model's AUC surpassed the radiomics model significantly (p<0.05). NRI analysis verified superiority of the combined model over the radiomics for BC HER2 prediction (NRI 25.0) in the test set. The comprehensive model based on the combination of cMRI and radiomics features outperformed the single radiomics model in noninvasively predicting the three-tiered HER2 status in patients with BC.

Real-world performance of plasma p-tau181 in a heterogeneous memory clinic cohort.

In light of clinical trials and disease-modifying therapies, an early identification of patients at-risk of developing Alzheimer's disease (AD) is crucial. Blood-based biomarkers have shown promising results regarding the in vivo detection of the earliest neuropathological changes in AD. Herein, we investigated the ability of plasma p-tau181 to act as a prescreening marker for amyloid positivity in a heterogeneous memory clinic-based cohort. In this retrospective cross-sectional study, we included a total of 115 patients along the clinical AD continuum (mild cognitive impairment [MCI] due to AD, n = 62, probable AD dementia, n = 53). Based on their biomarker status, they were stratified into an amyloid-positive (Aβ+, n = 88) or amyloid-negative cohort (Aβ-, n = 27). Plasma and CSF p-tau181 concentrations were quantified using an ultrasensitive single-molecule array (SIMOA©). Furthermore, age- and sex-adjusted receiver operating characteristic (ROC) curves were calculated and the area under the curve (AUC) of each model was compared using DeLong's test for correlated AUC curves. The median (interquartile range [IQR]) concentration of plasma p-tau181 was significantly higher in Aβ+ patients (3.6 pg/mL [2.5-4.6]), compared with Aβ- patients (1.7 pg/mL [1.2-1.9], p < 0.001). Regarding the distinction between Aβ+ and Aβ- patients and the prediction of amyloid positivity, a high diagnostic accuracy for plasma p-tau181 with an AUC of 0.89 (95% CI = 0.82-0.95) was calculated. Adding the risk factors, age and APOE4, to the model did not significantly improve its performance. Our findings demonstrate that plasma p-tau181 could be a noninvasive and feasible prescreening marker for amyloid positivity in a heterogeneous clinical AD cohort and therefore help in identifying those who would benefit from more invasive assessment of amyloid pathology.

Development and Validation of a Deep Learning Algorithm for Differentiation of Choroidal Nevi from Small Melanoma in Fundus Photographs

To develop and validate a deep learning algorithm capable of differentiating small choroidal melanomas from nevi. Retrospective multicenter cohort study. A total of 802 images from 688 patients diagnosed with choroidal nevi or melanoma. Wide field and standard field fundus photographs were collected from patients diagnosed with choroidal nevi or melanoma by ocular oncologists during clinical examinations. A lesion was classified as a nevus if it was followed for at least 5 years without being rediagnosed as melanoma. A neural network optimized for image classification was trained and validated on cohorts of 495 and 168 images and subsequently tested on independent sets of 86 and 53 images. Area under the curve (AUC) in receiver operating characteristic analysis for differentiating small choroidal melanomas from nevi. The algorithm achieved an AUC of 0.88 in both test cohorts, outperforming ophthalmologists using the Mushroom shape, Orange pigment, Large size, Enlargement, and Subretinal fluid (AUC 0.77) and To Find Small Ocular Melanoma Using Helpful Hints Daily (AUC 0.67) risk factors (DeLong's test, P<0.001). The algorithm performed equally well for wide field and standard field photos (AUC 0.89 for both when analyzed separately). Using an optimal operating point of 0.63 (on a scale from 0.00 to 1.00) determined from the training and validation datasets, the algorithm achieved 100% sensitivity and 74% specificity in the first test cohort (F-score 0.72), and 80% sensitivity and 81% specificity in the second (F-score 0.71), which consisted of images from external clinics nationwide. It outperformed 12 ophthalmologists in sensitivity (Mann-Whitney U, P=0.006) but not specificity (P=0.54). The algorithm showed higher sensitivity than both resident and consultant ophthalmologists (Dunn's test, P=0.04 and P=0.006, respectively) but not ocular oncologists (P>0.99, all P values Bonferroni corrected). This study develops and validates a deep learning algorithm for differentiating small choroidal melanomas from nevi, matching or surpassing the discriminatory performance of experienced human ophthalmologists. Further research will aim to validate its utility in clinical settings. Financial DisclosuresProprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.