Clinical Factors Model Research Articles

Identification of texture MRI brain abnormalities on Fibromyalgia syndrome using interpretable machine learning models

To provide objective diagnostic markers for fibromyalgia symptoms (FMS) diagnosis, we have created interpretable extreme gradient boosting (XGBoost) models using radiomics to aid in the diagnosis of chronic pain (CP) and to develop nomogram models for diagnosing subgroups of FMS. A group of 54 patients with CP and 71 healthy controls was randomly separated into training and validation groups, using a 7:3 ratio. Radiomics features were extracted from grey-matter and white-matter in the filtered mwp0* image. The Mann-Whitney U test, Spearman’s rank correlation test, and least absolute shrinkage and selection operator (LASSO) were utilized to select features. An XGBoost model was created based on these features, and Shapley Additive exPlanations (SHAP) was used for personalization and visual interpretation. A nomogram was developed for the diagnosis of FMS subgroups, utilizing radiomics scores and clinical predictors. The efficacy of the nomogram was evaluated using the area under the receiver operating characteristic curve, while decision curve analysis was employed to evaluate its clinical efficacy. The XGBoost model displays stability in the training validation group, indicating lower overfitting of CP model. The nomogram model combined with the rad-score has a greater ability to distinguish between typical and sub-clinical than the clinical factor model alone. We developed and validated a CP diagnosis model by XGBoost and realized model visualization through SHAP. The rad-score obtained by machine learning was used to build a nomogram model that combines clinical scales to distinguish patients with typical and sub-clinical fibromyalgia.

Association of genetic ancestry with pre-eclampsia in multi-ethnic cohorts of pregnant women

ObjectivesMaternal self-reported ethnicity is recognised as a risk factor for pre-eclampsia in clinical screening tools and models. This study investigated whether ethnicity is acting as a proxy for genetic variants in this context. Study designA total of 436 women from multi-ethnic backgrounds recruited to two UK observational pregnancy hypertension cohort studies were genotyped. Genetically-computed individual ancestry estimates were calculated for each individual through comparison to the multi-ethnic 1000 Genomes reference panel genotypes. Regression models for pre-eclampsia using clinical risk factors including self-reported ethnicity with and without ancestry estimates were built and compared using Likelihood Ratio Tests (LRT). Main outcome measuresPre-eclampsia (early- and late-onset). ResultsIn these multi-ethnic cohorts (mean age 34.9 years; 41.3 % White, 34.2 % Black, 13.1 % Asian ethnic backgrounds; 82.6 % chronic hypertension), discrepancies between self-reported ethnicity and genetically-computed individual ancestry estimates were present in all ethnic groups, particularly minority groups. Genetically-computed pan-African ancestry percentage was associated with early-onset (< 34 weeks) pre-eclampsia in adjusted models (aOR 100 % vs 0 % African ancestry: 3.81, 95 % CI 1.04–14.14, p-value 0.044) independently of self-reported ethnicity and established clinical risk factors. Addition of genetically-computed African ancestry to a clinical risk factor model including self-reported ethnicity, improved model fit (Likelihood ratio test p-value 0.023). ConclusionsSelf-reported maternal ethnicity is an imperfect proxy for genetically-computed individual ancestry estimates, particularly in ethnic minority groups. Genetically-computed African ancestry percentage was associated with early-onset pre-eclampsia independently of self-reported maternal ethnicity. Well-powered studies in multi-ethnic cohorts are required to delineate the genetic contribution to pre-eclampsia.

A vision transformer-based deep transfer learning nomogram for predicting lymph node metastasis in lung adenocarcinoma.

Lymph node metastasis (LNM) plays a crucial role in the management of lung cancer; however, the ability of chest computed tomography (CT) imaging to detect LNM status is limited. This study aimed to develop and validate a vision transformer-based deep transfer learning nomogram for predicting LNM in lung adenocarcinoma patients using preoperative unenhanced chest CT imaging. This study included 528 patients with lung adenocarcinoma who were randomly divided into training and validation cohorts at a 7:3 ratio. The pretrained vision transformer (ViT) was utilized to extract deep transfer learning (DTL) feature, and logistic regression was employed to construct a ViT-based DTL model. Subsequently, the model was compared with six classical convolutional neural network (CNN) models. Finally, the ViT-based DTL signature was combined with independent clinical predictors to construct a ViT-based deep transfer learning nomogram (DTLN). The ViT-based DTL model showed good performance, with an area under the curve (AUC) of 0.821 (95% CI, 0.775-0.867) in the training cohort and 0.825 (95% CI, 0.758-0.891) in the validation cohort. The ViT-based DTL model demonstrated comparable performance to classical CNN models in predicting LNM, and the ViT-based DTL signature was then used to construct ViT-based DTLN with independent clinical predictors such as tumor maximum diameter, location, and density. The DTLN achieved the best predictive performance, with AUCs of 0.865 (95% CI, 0.827-0.903) and 0.894 (95% CI, 0845-0942), respectively, surpassing both the clinical factor model and the ViT-based DTL model (p<0.001). This study developed a new DTL model based on ViT to predict LNM status in lung adenocarcinoma patients and revealed that the performance of the ViT-based DTL model was comparable to that of classical CNN models, confirming that ViT was viable for deep learning tasks involving medical images. The ViT-based DTLN performed exceptionally well and can assist clinicians and radiologists in making accurate judgments and formulating appropriate treatment plans.

Combinations of Clinical Factors, CT Signs, Radiomics for Differentiating High-density Areas After Mechanical Thrombectomy in Patients with Acute Ischemic Stroke.

Clinically, hemorrhagic transformation (HT) after mechanical thrombectomy (MT) is a common complication. This study is aim to investigate the value of clinical factors, CT signs, and radiomics in the differential diagnosis of high-density areas (HDAs) in the brain after MT in patients with acute ischemic stroke with large vessel occlusion (AIS-LVO). A total of 156 eligible patients with AIS-LVO in Center Ⅰ from December 2015 to June 2023 were retrospectively enrolled and randomly divided into training (n=109) and internal validation (n=47) sets at a ratio of 7:3. The data of 63 patients in Center Ⅱ were collected as an external validation set. According to the diagnostic criteria, the patients in the three datasets were divided into a HT group and a non-HT group. The clinical and imaging data from Centers Ⅰ and Ⅱ were used to construct a clinical factor and CT-sign model, a radiomic model and a combined model by logistic regression (LR). Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic efficacy of each model in the three datasets. Clinical blood glucose (Glu) and the maximum cross-sectional area (Areamax) on CT were associated with the nature of the HDA according to multivariate LR analyses (P < 0.05). Among the three models, the combined model had the highest diagnostic efficiency, with area under the curve (AUC) values of 0.895, 0.882, and 0.820 in the three datasets, which were significantly greater than the AUC values of the radiomic model (0.887, 0.898, 0.798) and clinical factor and CT sign model (0.831, 0.744, 0.684). The combined model based on radiomics had the best performance, indicating that radiomic features can be used as imaging biomarkers to aid in the clinical judgment of the nature of HDA after MT. HDA =high-density area; HT =hemorrhagic transformation; MT =mechanical thrombectomy; AIS-LVO =acute ischemic stroke with large vessel occlusion; LR =logistic regression; AUC =area under the curve; ICE =iodine contrast extravasation; DECT =dual energy CT; IOM =iodine overlay map; VNC =virtual noncontrast; Glu =glucose; LASSO =least absolute shrinkage and selection operator; ICC =intraclass correlation coefficient; ROC =receiver operating characteristic; DCA =decision curve analysis.

A clinical-radiomics nomogram for the prediction of the risk of upper gastrointestinal bleeding in patients with decompensated cirrhosis.

To develop a model that integrates radiomics features and clinical factors to predict upper gastrointestinal bleeding (UGIB) in patients with decompensated cirrhosis. 104 decompensated cirrhosis patients with UGIB and 104 decompensated cirrhosis patients without UGIB were randomized according to a 7:3 ratio into a training cohort (n = 145) and a validation cohort (n = 63). Radiomics features of the abdominal skeletal muscle area (SMA) were extracted from the cross-sectional image at the largest level of the third lumbar vertebrae (L3) on the abdominal unenhanced multi-detector computer tomography (MDCT) images. Clinical-radiomics nomogram were constructed by combining a radiomics signature (Rad score) with clinical independent risk factors associated with UGIB. Nomogram performance was evaluated in calibration, discrimination, and clinical utility. The radiomics signature was built using 11 features. Plasma prothrombin time (PT), sarcopenia, and Rad score were independent predictors of the risk of UGIB in patients with decompensated cirrhosis. The clinical-radiomics nomogram performed well in both the training cohort (AUC, 0.902; 95% CI, 0.850-0.954) and the validation cohort (AUC, 0.858; 95% CI, 0.762-0.953) compared with the clinical factor model and the radiomics model and displayed excellent calibration in the training cohort. Decision curve analysis (DCA) demonstrated that the predictive efficacy of the clinical-radiomics nomogram model was superior to that of the clinical and radiomics model. Clinical-radiomics nomogram that combines clinical factors and radiomics features has demonstrated favorable predictive effects in predicting the occurrence of UGIB in patients with decompensated cirrhosis. This helps in early diagnosis and treatment of the disease, warranting further exploration and research.

Prognosis Prediction in Head and Neck Squamous Cell Carcinoma by Radiomics and Clinical Information.

(1) Background: head and neck squamous cell carcinoma (HNSCC) is a common cancer whose prognosis is affected by its heterogeneous nature. We aim to predict 5-year overall survival in HNSCC radiotherapy (RT) patients by integrating radiomic and clinical information in machine-learning models; (2) Methods: HNSCC radiotherapy planning computed tomography (CT) images with RT structures were obtained from The Cancer Imaging Archive. Radiomic features and clinical data were independently analyzed by five machine-learning algorithms. The results were enhanced through a voted ensembled approach. Subsequently, a probability-weighted enhanced model (PWEM) was generated by incorporating both models; (3) Results: a total of 299 cases were included in the analysis. By receiver operating characteristic (ROC) curve analysis, PWEM achieved an area under the curve (AUC) of 0.86, which outperformed both radiomic and clinical factor models. Mean decrease accuracy, mean decrease Gini, and a chi-square test identified T stage, age, and disease site as the most important clinical factors in prognosis prediction; (4) Conclusions: our radiomic-clinical combined model revealed superior performance when compared to radiomic and clinical factor models alone. Further prospective research with a larger sample size is warranted to implement the model for clinical use.

Predicting Postoperative Speech Perception and Audiometric Thresholds Using Intracochlear Electrocochleography in Cochlear Implant Recipients.

Electrocochleography (ECochG) appears to offer the most accurate prediction of post-cochlear implant hearing outcomes. This may be related to its capacity to interrogate the health of underlying cochlear tissue. The four major components of ECochG (cochlear microphonic [CM], summating potential [SP], compound action potential [CAP], and auditory nerve neurophonic [ANN]) are generated by different cochlear tissue components. Analyzing characteristics of these components can reveal the state of hair and neural cell in a cochlea. There is limited evidence on the characteristics of intracochlear (IC) ECochG recordings measured across the array postinsertion but compared with extracochlear recordings has better signal to noise ratio and spatial specificity. The present study aimed to examine the relationship between ECochG components recorded from an IC approach and postoperative speech perception or audiometric thresholds. In 113 human subjects, responses to 500 Hz tone bursts were recorded at 11 IC electrodes across a 22-electrode cochlear implant array immediately following insertion. Responses to condensation and rarefaction stimuli were then subtracted from one another to emphasize the CM and added to one another to emphasize the SP, ANN, and CAP. Maximum amplitudes and extracochlear electrode locations were recorded for each of these ECochG components. These were added stepwise to a multi-factor generalized additive model to develop a best-fit model predictive model for pure-tone audiometric thresholds (PTA) and speech perception scores (speech recognition threshold [SRT] and consonant-vowel-consonant phoneme [CVC-P]) at 3- and 12-month postoperative timepoints. This best-fit model was tested against a generalized additive model using clinical factors alone (preoperative score, age, and gender) as a null model proxy. ECochG-factor models were superior to clinical factor models in predicting postoperative PTA, CVC-P, and SRT outcomes at both timepoints. Clinical factor models explained a moderate amount of PTA variance ( r2 = 45.9% at 3-month, 31.8% at 12-month, both p < 0.001) and smaller variances of CVC-P and SRT ( r2 range = 6 to 13.7%, p = 0.008 to 0.113). Age was not a significant predictive factor. ECochG models explained more variance at the 12-month timepoint ( r2 for PTA = 52.9%, CVC-P = 39.6%, SRT = 36.4%) compared with the 3-month one timepoint ( r2 for PTA = 49.4%, CVC-P = 26.5%, SRT = 22.3%). The ECochG model was based on three factors: maximum SP deflection amplitude, and electrode position of CM and SP peaks. Adding neural (ANN and/or CAP) factors to the model did not improve variance explanation. Large negative SP deflection was associated with poorer outcomes and a large positive SP deflection with better postoperative outcomes. Mid-array peaks of SP and CM were both associated with poorer outcomes. Postinsertion IC-ECochG recordings across the array can explain a moderate amount of postoperative speech perception and audiometric thresholds. Maximum SP deflection and its location across the array appear to have a significant predictive value which may reflect the underlying state of cochlear health.

Prediction of hypoattenuating leaflet thickening in patients undergoing transcatheter aortic valves replacement based on clinical factors and 4D-computed tomography morphological characteristics: A retrospective cross-sectional study

BackgroundThe rapid increase in the number of transcatheter aortic valve replacement (TAVR) procedures in China and worldwide has led to growing attention to hypoattenuating leaflet thickening (HALT) detected during follow-up by 4D-CT. It's reported that HALT may impact the durability of prosthetic valve. Early identification of these patients and timely deployment of anticoagulant therapy are therefore particularly important. MethodsWe retrospectively recruited 234 consecutive patients who underwent TAVR procedure in Fuwai Hospital. We collected clinical information and extracted morphological characteristics parameters of the transcatheter heart valve (THV) post TAVR procedure from 4D-CT. LASSO analysis was conducted to select important features. Three models were constructed, encapsulating clinical factors (Model 1), morphological characteristics parameters (Model 2), and all together (Model 3), to identify patients with HALT. Receiver operating characteristic (ROC) curves and decision curve analysis (DCA) were plotted to evaluate the discriminatory ability of models. A nomogram for HALT was developed and verified by bootstrap resampling. ResultsIn our study patients, Model 3 (AUC = 0.738) showed higher recognition effectiveness compared to Model 1 (AUC = 0.674, p = 0.032) and Model 2 (AUC = 0.675, p = 0.021). Internal bootstrap validation also showed that Model 3 had a statistical power similar to that of the initial stepwise model (AUC = 0.723 95%CI: 0.661–0.786). Overall, Model 3 was rated best for the identification of HALT in TAVR patients. ConclusionA comprehensive predictive model combining patient clinical factors with CT-based morphology parameters has superior efficacy in predicting the occurrence of HALT in TAVR patients.

Pre-PCI CT-FFR Predicts Target Vessel Failure After Stent Implantation.

To investigate the predictive value of coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) before percutaneous coronary intervention (PCI) to predict target vessel failure (TVF) after stent implantation. This retrospective study included 429 patients (429 vessels) who underwent PCI and stent implantation after CCTA within 3 months. All patients underwent coronary stent implantation between January 2012 and December 2019. A dedicated workstation (Syngo Via, Siemens) was used to analyze and measure the CT-FFR value. The cut-off values of pre-PCI CT-FFR for predicting TVF were defined as 0.80 and the value using the log-rank maximization method, respectively. The primary outcome was TVF, defined as a composite of cardiac death, target vessel myocardial infarction, and clinically driven target vessel revascularization (TVR), which was a secondary outcome. During a median 64.0 months follow-up, the cumulative incidence of TVF was 7.9% (34/429). The cutoff value of pre-PCI CT-FFR based on the log-rank maximization method was 0.74, which was the independent predictor for TVF [hazard ratio (HR): 2.61 (95% CI: 1.13, 6.02); P =0.024] and TVR [HR: 3.63 (95%CI: 1.25, 10.51); P =0.018]. Compared with the clinical risk factor model, pre-PCI CT-FFR significantly improved the reclassification ability for TVF [net reclassification improvement (NRI), 0.424, P <0.001; integrative discrimination index (IDI), 0.011, P =0.022]. Adding stent information to the prediction model resulted in an improvement in reclassification for the TVF (C statistics: 0.711, P =0.001; NRI: 0.494, P <0.001; IDI: 0.020, P =0.028). Pre-PCI CT-FFR ≤0.74 was an independent predictor for TVF or TVR, and integration of clinical, pre-PCI CT-FFR, and stent information models can provide a better risk stratification model in patients with stent implantation.

Are Radiomic Spleen Features Useful for Assessing the Response to Infliximab in Patients With Crohn's Disease? A Multicenter Study.

To develop and validate a radiomics nomogram for assessing the response of patients with Crohn's disease (CD) to infliximab. Radiomics features of the spleen were extracted from computed tomography enterography images of each patient's arterial phase. The feature selection process was performed using the least absolute shrinkage and selection operator algorithm, and a radiomics score was calculated based on the radiomics signature formula. Subsequently, the radiomic model and the clinical risk factor model were separately established based on the radiomics score and clinically significant features, respectively. The performance of both models was evaluated using receiver operating characteristic curves, decision curve analysis curves, and clinical impact curves. Among the 175 patients with CD, 105 exhibited a clinical response, and 60 exhibited clinical remission after receiving infliximab treatment. Our radiomic model, comprising 20 relevant features, demonstrated excellent predictive performance. The radiomic nomogram for predicting clinical response showed good calibration and discrimination in the training cohort (area under the curve [AUC] 0.909, 95% confidence interval [CI] 0.840-0.978), the validation cohort (AUC 0.954, 95% CI 0.889-1), and the external cohort (AUC = 0.902, 95% CI 0.83-0.974). Accordingly, the nomogram was also suitable for predicting clinical remission. Decision curve analysis and clinical impact curves highlighted the clinical utility of our nomogram. Our radiomics nomogram is a noninvasive predictive tool constructed from radiomic features of the spleen. It also demonstrated good predictive accuracy in evaluating CD patients' response to infliximab treatment. Multicenter validation provided high-level evidence for its clinical application.

Utility of CT Radiomics and Delta Radiomics for Survival Evaluation in Locally Advanced Nasopharyngeal Carcinoma with Concurrent Chemoradiotherapy.

A high incidence rate of nasopharyngeal carcinoma (NPC) has been observed in Southeast Asia compared to other parts of the world. Radiomics is a computational tool to predict outcomes and may be used as a prognostic biomarker for advanced NPC treated with concurrent chemoradiotherapy. Recently, radiomic analysis of the peripheral tumor microenvironment (TME), which is the region surrounding the gross tumor volume (GTV), has shown prognostic usefulness. In this study, not only was gross tumor volume (GTVt) analyzed but also tumor peripheral regions (GTVp) were explored in terms of the TME concept. Both radiomic features and delta radiomic features were analyzed using CT images acquired in a routine radiotherapy process. A total of 50 patients with NPC stages III, IVA, and IVB were enrolled between September 2004 and February 2014. Survival models were built using Cox regression with clinical factors (i.e., gender, age, overall stage, T stage, N stage, and treatment dose) and radiomic features. Radiomic features were extracted from GTVt and GTVp. GTVp was created surrounding GTVt for TME consideration. Furthermore, delta radiomics, which is the longitudinal change in quantitative radiomic features, was utilized for analysis. Finally, C-index values were computed using leave-one-out cross-validation (LOOCV) to evaluate the performances of all prognosis models. Models were built for three different clinical outcomes, including overall survival (OS), local recurrence-free survival (LRFS), and progression-free survival (PFS). The range of the C-index in clinical factor models was (0.622, 0.729). All radiomics models, including delta radiomics models, were in the range of (0.718, 0.872). Among delta radiomics models, GTVt and GTVp were in the range of (0.833, 0.872) and (0.799, 0.834), respectively. Radiomic analysis on the proximal region surrounding the gross tumor volume of advanced NPC patients for survival outcome evaluation was investigated, and preliminary positive results were obtained. Radiomic models and delta radiomic models demonstrated performance that was either superior to or comparable with that of conventional clinical models.

Prediction of Ki-67 expression in bladder cancer based on CT radiomics nomogram.

This study aimed to create and validate a radiomics nomogram for non-invasive preoperative Ki-67 expression level prediction in patients with bladder cancer (BCa) using contrast-enhanced CT radiomics features. A retrospective analysis of 135 patients was conducted, 79 of whom had high levels of Ki-67 expression and 56 of whom had low levels. For the dimensionality reduction analysis, the best features were chosen using the least absolute shrinkage selection operator and one-way analysis of variance. Then, a radiomics nomogram was created using multiple logistic regression analysis based on radiomics features and clinical independent risk factors. The performance of the model was assessed using the Akaike information criterion (AIC) value, the area under the curve (AUC) value, accuracy, sensitivity, and specificity. The clinical usefulness of the model was assessed using decision curve analysis (DCA). Finally, to establish a radiomics nomogram, the best 5 features were chosen and integrated with the independent clinical risk factors (T stage) and Rad-score. This radiomics nomogram demonstrated significant correction and discriminating performance in both the training and validation sets, with an AUC of 0.836 and 0.887, respectively. This radiomics nomogram had the lowest AIC value (AIC = 103.16), which was considered to be the best model. When compared to clinical factor model and radiomics signature, DCA demonstrated the more value of the radiomics nomogram. Enhanced CT-based radiomics nomogram can better predict Ki-67 expression in BCa patients and can be used for prognosis assessment and clinical decision making.

CT-based whole lung radiomics nomogram: a tool for identifying the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease.

To evaluate the value of CT-based whole lung radiomics nomogram for identifying the risk of cardiovascular disease (CVD) in patients with chronic obstructive pulmonary disease (COPD). A total of 974 patients with COPD were divided into a training cohort (n = 402), an internal validation cohort (n = 172), and an external validation cohort (n = 400) from three hospitals. Clinical data and CT findings were analyzed. Radiomics features of whole lung were extracted from the non-contrast chest CT images. A radiomics signature was constructed with algorithms. Combined with the radiomics score and independent clinical factors, multivariate logistic regression analysis was used to establish a radiomics nomogram. ROC curve was used to analyze the prediction performance of the model. Age, weight, and GOLD were the independent clinical factors. A total of 1218 features were extracted and reduced to 15 features to build the radiomics signature. In the training cohort, the combined model (area under the curve [AUC], 0.731) showed better discrimination capability (p < 0.001) than the clinical factors model (AUC, 0.605). In the internal validation cohort, the combined model (AUC, 0.727) performed better (p = 0.032) than the clinical factors model (AUC, 0.629). In the external validation cohort, the combined model (AUC, 0.725) performed better (p < 0.001) than the clinical factors model (AUC, 0.690). Decision curve analysis demonstrated the radiomics nomogram outperformed the clinical factors model. The CT-based whole lung radiomics nomogram has the potential to identify the risk of CVD in patients with COPD. This study helps to identify cardiovascular disease risk in patients with chronic obstructive pulmonary disease on chest CT scans. •To investigate the value of CT-based whole lung radiomics features in identifying the risk of cardiovascular disease in chronic obstructive pulmonary disease patients. •The radiomics nomogram showed better performance than the clinical factors model to identify the risk of cardiovascular disease in patients with chronic obstructive pulmonary disease. •The radiomics nomogram demonstrated excellent performance in the training, internal validation, and external validation cohort (AUC, 0.731; AUC, 0.727; AUC, 0.725).

Radiomic nomogram for discriminating parotid pleomorphic adenoma from parotid adenolymphoma based on grayscale ultrasonography.

To differentiate parotid pleomorphic adenoma (PA) from adenolymphoma (AL) using radiomics of grayscale ultrasonography in combination with clinical features. This retrospective study aimed to analyze the clinical and radiographic characteristics of 162 cases from December 2019 to March 2023. The study population consisted of a training cohort of 113 patients and a validation cohort of 49 patients. Grayscale ultrasonography was processed using ITP-Snap software and Python to delineate regions of interest (ROIs) and extract radiomic features. Univariate analysis, Spearman's correlation, greedy recursive elimination strategy, and least absolute shrinkage and selection operator (LASSO) correlation were employed to select relevant radiographic features. Subsequently, eight machine learning methods (LR, SVM, KNN, RandomForest, ExtraTrees, XGBoost, LightGBM, and MLP) were employed to build a quantitative radiomic model using the selected features. A radiomic nomogram was developed through the utilization of multivariate logistic regression analysis, integrating both clinical and radiomic data. The accuracy of the nomogram was assessed using receiver operating characteristic (ROC) curve analysis, calibration, decision curve analysis (DCA), and the Hosmer-Lemeshow test. To differentiate PA from AL, the radiomic model using SVM showed optimal discriminatory ability (accuracy = 0.929 and 0.857, sensitivity = 0.946 and 0.800, specificity = 0.921 and 0.897, positive predictive value = 0.854 and 0.842, and negative predictive value = 0.972 and 0.867 in the training and validation cohorts, respectively). A nomogram incorporating rad-Signature and clinical features achieved an area under the ROC curve (AUC) of 0.983 (95% confidence interval [CI]: 0.965-1) and 0.910 (95% CI: 0.830-0.990) in the training and validation cohorts, respectively. Decision curve analysis showed that the nomogram and radiomic model outperformed the clinical-factor model in terms of clinical usefulness. A nomogram based on grayscale ultrasonic radiomics and clinical features served as a non-invasive tool capable of differentiating PA and AL.

A nomogram model combining computed tomography-based radiomics and Krebs von den Lungen-6 for identifying low-risk rheumatoid arthritis-associated interstitial lung disease.

Quantitatively assess the severity and predict the mortality of interstitial lung disease (ILD) associated with Rheumatoid arthritis (RA) was a challenge for clinicians. This study aimed to construct a radiomics nomogram based on chest computed tomography (CT) imaging by using the ILD-GAP (gender, age, and pulmonary physiology) index system for clinical management. Chest CT images of patients with RA-ILD were retrospectively analyzed and staged using the ILD-GAP index system. The balanced dataset was then divided into training and testing cohorts at a 7:3 ratio. A clinical factor model was created using demographic and serum analysis data, and a radiomics signature was developed from radiomics features extracted from the CT images. Combined with the radiomics signature and independent clinical factors, a nomogram model was established based on the Rad-score and clinical factors. The model capabilities were measured by operating characteristic curves, calibration curves and decision curves analyses. A total of 177 patients were divided into two groups (Group I, n = 107; Group II, n = 63). Krebs von den Lungen-6, and nineteen radiomics features were used to build the nomogram, which showed favorable calibration and discrimination in the training cohort [AUC, 0.948 (95% CI: 0.910-0.986)] and the testing validation cohort [AUC, 0.923 (95% CI: 0.853-0.993)]. Decision curve analysis demonstrated that the nomogram performed well in terms of clinical usefulness. The CT-based radiomics nomogram model achieved favorable efficacy in predicting low-risk RA-ILD patients.

Non-contrast computed tomography-based radiomics for staging of connective tissue disease-associated interstitial lung disease.

It is of significance to assess the severity and predict the mortality of patients with connective tissue disease-associated interstitial lung disease (CTD-ILD). In this double-center retrospective study, we developed and validated a radiomics nomogram for clinical management by using the ILD-GAP (gender, age, and pulmonary physiology) index system. Patients with CTD-ILD were staged using the ILD-GAP index system. A clinical factor model was built by demographics and CT features, and a radiomics signature was developed using radiomics features extracted from CT images. Combined with the radiomics signature and independent clinical factors, a radiomics nomogram was constructed and evaluated by the area under the curve (AUC) from receiver operating characteristic (ROC) analyses. The models were externally validated in dataset 2 to evaluate the model generalization ability using ROC analysis. A total of 245 patients from two clinical centers (dataset 1, n = 202; dataset 2, n = 43) were screened. Pack-years of smoking, traction bronchiectasis, and nine radiomics features were used to build the radiomics nomogram, which showed favorable calibration and discrimination in the training cohort {AUC, 0.887 [95% confidence interval (CI): 0.827-0.940]}, the internal validation cohort [AUC, 0.885 (95% CI: 0.816-0.922)], and the external validation cohort [AUC, 0.85 (95% CI: 0.720-0.919)]. Decision curve analysis demonstrated that the nomogram outperformed the clinical factor model and radiomics signature in terms of clinical usefulness. The CT-based radiomics nomogram showed favorable efficacy in predicting individual ILD-GAP stages.

ROLE OF THE WOMAC SCORES IN PREOPERATIVE DECISION-MAKING AND ANALYSIS OF KNEE REPLACEMENT FOR KNEE OSTEOARTHRITIS PATIENTS

Objective: Knee replacement (KR) is a widely accepted procedure for end-stage knee arthritis. Patients’ subjective perception of knee joint symptoms is an important factor in their decision to undergo knee replacement. This paper mainly studies the correlation between knee joint symptoms and knee replacement, aimed to establish the corresponding preoperative decision-making model. Methods: 122 knee arthritis patients were included from the knee arthritis database FNIH OAI, of which 61 had knee arthroplasty and 61 without knee arthroplasty. First, WOMAC score was used to quantitatively evaluate the knee joint symptoms of patients; then the correlation between clinical risk factors, single WOMAC score and knee replacement was analyzed. Then K-means cluster analysis was used to divide the multidimensional WOMAC score into different groups of knee arthritis symptoms’ severity. Finally, based on the retained clinical risk factors and WOMAC cluster variables, the clinical models, WOMAC scoring model and clinical +WOMAC scoring model were constructed, respectively, and compared. Results: Age and BMI were significant risk factors for knee replacement ([Formula: see text]), which could be used to construct the clinical model. There was no significant correlation between any single WOMAC score and knee replacement ([Formula: see text]). The cluster variable of WOMAC score obtained by cluster analysis was significantly correlated with knee replacement ([Formula: see text]). Based on the above risk factors, we established the Age+BMI, Cluster and Age+BMI+Cluster models, respectively. The comparison results showed that the Age+BMI+Cluster model ([Formula: see text]) showed the highest predictive value for knee replacement, and the corresponding nomogram also showed good predictive consistency; the performance of Cluster model ([Formula: see text]) was the second. The pure clinical risk factor model Age+BMI showed the worst predictive performance ([Formula: see text]). Conclusion: This paper analyzed the correlation between patients’ subjective perception of knee arthritis symptoms and the final knee replacement, and constructed a new biomarker based on the WOMAC score. After analysis and modeling, this marker could be used to predict knee replacement. The constructed Age+BMI+Cluster nomogram could be used for personalized assessment of the risk of knee replacement.

A Novel Magnetic Resonance Imaging-Based Radiomics and Clinical Predictive Model for the Regrowth of Postoperative Residual Tumor in Non-Functioning Pituitary Neuroendocrine Tumor.

Background and Objectives: To develop a novel magnetic resonance imaging (MRI)-based radiomics-clinical risk stratification model to predict the regrowth of postoperative residual tumors in patients with non-functioning pituitary neuroendocrine tumors (NF-PitNETs). Materials and Methods: We retrospectively enrolled 114 patients diagnosed as NF-PitNET with postoperative residual tumors after the first operation, and the diameter of the tumors was greater than 10 mm. Univariate and multivariate analyses were conducted to identify independent clinical risk factors. We identified the optimal sequence to generate an appropriate radiomic score (Rscore) that combined pre- and postoperative radiomic features. Three models were established by logistic regression analysis that combined clinical risk factors and radiomic features (Model 1), single clinical risk factors (Model 2) and single radiomic features (Model 3). The models' predictive performances were evaluated using receiver operator characteristic (ROC) curve analysis and area under curve (AUC) values. A nomogram was developed and evaluated using decision curve analysis. Results: Knosp classification and preoperative tumor volume doubling time (TVDT) were high-risk factors (p < 0.05) with odds ratios (ORs) of 2.255 and 0.173. T1WI&T1CE had a higher AUC value (0.954) and generated an Rscore. Ultimately, the AUC of Model 1 {0.929 [95% Confidence interval (CI), 0.865-0.993]} was superior to Model 2 [0.811 (95% CI, 0.704-0.918)] and Model 3 [0.844 (95% CI, 0.748-0.941)] in the training set, which were 0.882 (95% CI, 0.735-1.000), 0.834 (95% CI, 0.676-0.992) and 0.763 (95% CI, 0.569-0.958) in the test set, respectively. Conclusions: We trained a novel radiomics-clinical predictive model for identifying patients with NF-PitNETs at increased risk of postoperative residual tumor regrowth. This model may help optimize individualized and stratified clinical treatment decisions.

Evaluation of Large-Scale Proteomics for Prediction of Cardiovascular Events

Whether protein risk scores derived from a single plasma sample could be useful for risk assessment for atherosclerotic cardiovascular disease (ASCVD), in conjunction with clinical risk factors and polygenic risk scores, is uncertain. To develop protein risk scores for ASCVD risk prediction and compare them to clinical risk factors and polygenic risk scores in primary and secondary event populations. The primary analysis was a retrospective study of primary events among 13 540 individuals in Iceland (aged 40-75 years) with proteomics data and no history of major ASCVD events at recruitment (study duration, August 23, 2000 until October 26, 2006; follow-up through 2018). We also analyzed a secondary event population from a randomized, double-blind lipid-lowering clinical trial (2013-2016), consisting of individuals with stable ASCVD receiving statin therapy and for whom proteomic data were available for 6791 individuals. Protein risk scores (based on 4963 plasma protein levels and developed in a training set in the primary event population); polygenic risk scores for coronary artery disease and stroke; and clinical risk factors that included age, sex, statin use, hypertension treatment, type 2 diabetes, body mass index, and smoking status at the time of plasma sampling. Outcomes were composites of myocardial infarction, stroke, and coronary heart disease death or cardiovascular death. Performance was evaluated using Cox survival models and measures of discrimination and reclassification that accounted for the competing risk of non-ASCVD death. In the primary event population test set (4018 individuals [59.0% women]; 465 events; median follow-up, 15.8 years), the protein risk score had a hazard ratio (HR) of 1.93 per SD (95% CI, 1.75 to 2.13). Addition of protein risk score and polygenic risk scores significantly increased the C index when added to a clinical risk factor model (C index change, 0.022 [95% CI, 0.007 to 0.038]). Addition of the protein risk score alone to a clinical risk factor model also led to a significantly increased C index (difference, 0.014 [95% CI, 0.002 to 0.028]). Among White individuals in the secondary event population (6307 participants; 432 events; median follow-up, 2.2 years), the protein risk score had an HR of 1.62 per SD (95% CI, 1.48 to 1.79) and significantly increased C index when added to a clinical risk factor model (C index change, 0.026 [95% CI, 0.011 to 0.042]). The protein risk score was significantly associated with major adverse cardiovascular events among individuals of African and Asian ancestries in the secondary event population. A protein risk score was significantly associated with ASCVD events in primary and secondary event populations. When added to clinical risk factors, the protein risk score and polygenic risk score both provided statistically significant but modest improvement in discrimination.

Identification of vulnerable carotid plaque with CT-based radiomics nomogram

To develop and validate a radiomics nomogram for identifying high-risk carotid plaques on computed tomography (CT) angiography (CTA). A total of 280 patients with symptomatic (n=131) and asymptomatic (n=139) carotid plaques were divided into a training set (n=135), validation set (n=58), and external test set (n=87). Radiomic features were extracted from CTA images. A radiomics model was constructed based on selected features and a radiomics score (rad-score) was calculated. A clinical factor model was constructed by demographics and CT findings. A radiomics nomogram combining independent clinical factors and the rad-score was constructed. The diagnostic performance of three models was evaluated and validated by region of characteristic curves. Calcification and maximum plaque thickness were the independent clinical factors. Twenty-four features were used to build the radiomics signature. In the validation set, the nomogram (area under the curve [AUC], 0.977; 95% CI, 0.899-0.999) performed better (p=0.017 and p=0.031) than the clinical factor model (AUC, 0.862; 95% CI, 0.746-0.938) and radiomics signature (AUC, 0.944; 95% CI, 0.850-0.987). In external test set, the nomogram (AUC, 0.952; 95% CI, 0.884-0.987) and radiomics signature (AUC, 0.932; 95% CI, 0.857-0.975) showed better discrimination capability (p=0.002 and p=0.037) than clinical factor model (AUC, 0.818; 95% CI, 0.721-0.892). The CT-based nomogram showed satisfactory performance in identification of high-risk plaques in carotid arteries, and it may serve as a potential non-invasive tool to identify carotid plaque vulnerability and risk stratification.