CT‑based radiomics of bowel wall at baseline predicts the efficacy of Ustekinumab at week 16 in patients with Crohn’s disease

CT‑based radiomics of bowel wall at baseline predicts the efficacy of Ustekinumab at week 16 in patients with Crohn’s disease | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article CT‑based radiomics of bowel wall at baseline predicts the efficacy of Ustekinumab at week 16 in patients with Crohn’s disease Minyi Guo, Yilin Guan, Siqi Hu, Qi Zhang, Jue Lin, Zhaoyuan Xu, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7441161/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Nov, 2025 Read the published version in Abdominal Radiology → Version 1 posted 9 You are reading this latest preprint version Abstract Objectives Ustekinumab is a biological treatment for Crohn's disease, but some patients do not respond. This study aimed to assess the role of radiomic techniques in predicting the treatment response by quantifying transmural inflammation in Crohn's disease. Materials and Methods A total of 296 patients (training cohort, n = 207; testing cohort, n = 89) were retrospectively recruited. Manual segmentation of 3D volumes of interest (VOIs) encompassing inflamed bowel wall segments was performed on arterial-phase CT enterography scans, from which radiomic features were extracted. Following feature dimensionality reduction via Pearson correlation filtering (threshold > 0.9) and recursive feature elimination, the least absolute shrinkage and selection operator (LASSO) logistic regression was utilized as a classifier to construct a radiomic signature. Subsequently, to leverage both radiomic and clinical information for optimal prediction, the radiomic signature was integrated with clinically accessible variables (C-reactive protein level, prior biologic exposure) to develop a model predicting UST efficacy at 16 weeks. The predictive performance was compared using the area under the curve (AUC) and calibration curve analysis. Clinical utility was assessed by decision curve analysis. Results The radiomic signature, based on 1,288 features, was an independent risk factor for Ustekinumab response, with area under the curve values of 0.819 in the training cohort and 0.791 in the testing cohort. An integrated model combining the radiomic signature, C-reactive protein levels, and prior biologics exposure achieved area under the curve values of 0.847 and 0.801, respectively. The model demonstrated good calibration and clinical benefit. Conclusions The baseline radiomic signature is a promising biomarker for predicting Ustekinumab treatment efficacy in Crohn's disease. Crohn's disease Ustekinumab CT‑based radiomics Treatment response Figures Figure 1 Figure 2 Figure 3 Introduction Crohn's disease (CD) is a chronic inflammatory bowel disease typically managed with corticosteroids, immunosuppressants, and biologics 1 . Ustekinumab (UST), a monoclonal antibody targeting IL-12/23p40, has recently been a commonly used biologic agent for treating CD 2 . Analysis of real-world data indicates that approximately 60% of patients achieve a pooled clinical response (CDAI-based) to UST therapy in the short term (8–14 weeks), while response rates are around 64% in both the medium term (16–24 weeks) and long term (48–52 weeks) 3 . Considering the high cost of UST and variable patient response, identifying those who will gain the most benefit is crucial. The European Crohn’s and Colitis Organization (ECCO) has emphasized the need to develop and validate predictive biomarkers to advance precision medicine in inflammatory bowel disease 4 . Current studies on predicting UST treatment response are limited in scope. The non-responsiveness to UST may be attributed to the high placebo effect and inadequate induction dosing; nevertheless, other potential risk factors have not yet been identified in prior research 2 , 5 . Clinical factors like age, gender, smoking, and disease characteristics such as duration and location show no correlation with treatment response 5 , 6 . Waljee et al. created random forest models from UNITI data to forecast treatment-induced remission, yet there's a shortage of medical imaging-based prediction studies 7 . Evaluating transmural inflammation through cross-sectional imaging techniques (Computed Tomography, Magnetic Resonance, ultrasound, etc.) is critical for understanding disease control, yet traditional scoring methods often rely on subjective interpretation 8 . Radiomics, which extracts high-dimensional features from imaging for tissue pathology, is widely used in oncology but is underutilized in inflammatory bowel disease research 9 , 10 . This study aims to quantify transmural inflammation in Crohn's disease through radiomic techniques, investigate its potential in predicting UST treatment response, and ultimately provide evidence for personalized medicine. Materials and Methods Patients Ethical approval for this single-center study was obtained from the Institutional Review Boards at hospital. Given the retrospective design, patient consent was waived. The study initially included 524 individuals diagnosed with CD, who received UST, treatment at our institution from January 2016 to July 2022. All enrolled patients received a standardized Ustekinumab induction regimen consisting of weight-based intravenous dosing (≈ 6 mg/kg) at Week 0 followed by subcutaneous 90 mg administration at Week 8. Crucially, treatment response was assessed at Week 16 immediately prior to the third scheduled dose, ensuring our evaluation exclusively captured induction-phase efficacy before any maintenance regimen could be initiated or modified. To ensure the validity of the study's outcomes, strict exclusion criteria were applied, disqualifying patients for the following reasons: 1) lack of baseline Computed Tomography Enterography (CTE) data or electronic medical records; 2) inadequate quality of CTE images; and 3) irregular injection schedules or optimized treatment regimens. Ultimately, a cohort of 296 CD patients was established, which was randomly divided into a training cohort (n = 207) and an independent testing cohort (n = 89) in a 7:3 ratio (Fig. 1 ). The distribution of baseline characteristics was largely consistent between the two cohorts (Supplementary Table 1). An experienced multidisciplinary team meticulously assessed disease activity in patients through clinical symptoms, laboratory indices, radiology, and endoscopies. Demographic and clinical data, including medication history, surgical interventions, follow-up duration, age, gender, height, weight, and smoking status, were carefully collected from electronic health records. Body Mass Index (BMI) was calculated using the standard formula: weight divided by height squared. Laboratory assessments included a complete blood count, with specific attention to neutrophil, lymphocyte, and platelet counts, as well as measurements of serum albumin, globulin, and C-reactive protein (CRP) levels. The location and behavior of Crohn's disease were classified according to the Montreal classification 11 . Outcomes and Definitions All enrolled patients received a standardized Ustekinumab induction regimen consisting of weight-based intravenous dosing (≈ 6 mg/kg) at Week 0 followed by subcutaneous 90 mg administration at Week 8. Considering the time-dependent nature of drug efficacy, it is clinically recommended that the effectiveness of UST be evaluated no earlier than the sixteenth week post-treatment initiation 12 . Given that our study is designed to predict the need for adjustments in pharmacotherapy (e.g., intensifying induction), we have adopted stricter response criteria. Treatment response to UST is defined as meeting all four criteria: clinical response, biochemical response, endoscopic response, and radiologic response: (1) clinical improvement, indicated by a Crohn’s Disease Activity Index (CDAI) score below 150 or a reduction of at least 70% from baseline values; (2) normalization of biomarkers, with a CRP level below 5 mg/L; (3) endoscopic data, if available, showing response with a decrease of at least 50% in the Simple Endoscopic Score for Crohn's Disease (SES-CD) or remission with an SES-CD score not exceeding 2; and (4) cross-sectional imaging demonstrating a reduction or resolution of inflamed bowel segments relative to baseline 13 , 14 . These evaluations are integral to the comprehensive assessment by the attending physician, guiding decisions on potential adjustments to the patient's therapeutic regimen. CTE image processing and radiomic feature extraction All patients underwent standardized CTE examinations (Supplementary Material 1) with the parameters summarized in Supplementary Table 2, and the original DICOM format images were exported for further analysis. The most recent CTE image prior to injection, obtained within three months during the arterial phase, was used for analysis due to its superior contrast 15 . The intestinal lesions were manually delineated by two radiologists (MY.G. and YL.G., with 8 and 5 years of experience, respectively) using the ITK-SNAP software (version 3.8.0; http://www.itksnap.org ). For the inflamed segments of the bowel, a 3D Volume of Interest (VOI) was semi-automatically segmented (Fig. 1 ). An inflamed bowel segment was defined based on abnormal enhancement or edema observed in CTE images 16 . The 3D VOIs were then selected as the input for feature extraction. The extraction of radiomic features was conducted using the flexible open-source platform PyRadiomics (version 3.7.6; https://www.python.org ). This radiomic quantification platform adheres to the Image Biomarker Standardization Initiative (IBSI), ensuring the standardization of both feature definitions and image processing protocols 17 , 18 . More detailed information regarding parameter settings for image processing, the radiomics procedure, and the extracted radiomic features is presented in Supplementary Material 2. Ultimately, a total of 1288 quantitative features were extracted from the VOI for further analysis. Feature selection and signature building Figure 1 illustrates the radiomics workflow. In the process of feature selection and signature development, we first standardized all radiomic features using the z-score method, parameterized from the training cohort, ensuring that each feature had a zero mean and a unit standard deviation. Subsequently, we performed dimensionality reduction by comparing features and removing those with a Pearson correlation coefficient exceeding 0.900, thereby eliminating redundancy and ensuring the independence of the retained features. Next, we used recursive feature elimination (RFE) to find the most important features. RFE is a method that uses a base model to train multiple times, removing the least significant features after each round. This improves the model's ability to generalize and reduces overfitting. According to the power calculation, the number of predictors should be no more than one-third of the smallest group in the training cohort, which here was non-responders with 67 participants 19 , 20 . Thus, we selected the top 20 features based on their highest rankings from the RFE process. To construct the RS, we used the LASSO logistic regression model as our classifier. This model, a variant of logistic regression, includes an L1 norm penalty in its loss function, constraining weights and promoting feature sparsity, enhancing interpretability. We conducted a 5-fold cross-validation on the training dataset to optimize hyperparameters like the number of features. Hyperparameters were chosen based on predefined performance criteria. Ultimately, we developed a RS reflecting the burden of transmural inflammation, serving as an independent predictor of treatment efficacy for UST. Construction of the RS‑clinical combined model Univariate analysis was conducted to preliminarily select significant clinical characteristics ( P < 0.10). Logistic regression was used to estimate odds ratios (OR) for candidate factors. A multivariable logistic regression model was developed, incorporating RS and clinical features. Backward elimination ( P < 0.10) and the Akaike Information Criterion (AIC) guided model refinement, ensuring selection of the most pertinent predictors and enhancing predictive power. Performance evaluation and Statistical Analysis Differences between UST responders and non-responders were analyzed using T-tests/Mann-Whitney U tests for continuous variables and Fisher’s/Chi-square tests for categorical variables. The radiomic model's performance was evaluated via ROC curve analysis, calculating AUC, accuracy, sensitivity, specificity, precision, recall, and F1 value, visualized by confusion matrices. The AUC of the RS and RS-clinical models was compared using the DeLong test, and calibration was assessed with calibration curves and the Hosmer-Lemeshow test. Performance metrics' 95% CIs were estimated with bootstrap resampling, and decision curve analysis evaluated the clinical utility of the combined model. Sample size considerations were calculated using MedCalc statistical software. All statistical analyses were conducted using R software (version 4.4.1) and Python (version 3.7.6), with a two-sided P < 0.05 considered indicative of statistical significance, except for the univariate analysis where P < 0.10 was applied. Results Baseline characteristics and demographics A total of 296 patients with CD treated with UST were retrospectively recruited and evenly divided into a training cohort (n = 207) and a testing cohort (n = 89), as outlined in Table 1 . An AUC-based estimation of sample size indicated that the sample size for training and validation in our study was adequate (Supplementary Material 3). The patient demographics were predominantly male in both cohorts, with 70% in the training cohort and 76% in the testing cohort (Supplementary Table 1). Clinical characteristics, including disease behavior, location, and the presence of fistulas, were comparable between responders and non-responders to UST across both cohorts, with no statistically significant differences observed (all P > 0.05). Notably, a majority of patients in both cohorts exhibited a Limberg score of 3 (a semiquantitative color Doppler ultrasound assessment of bowel wall vascularity in inflammatory bowel disease), indicating active inflammation; over 90% of the training cohort and a comparable proportion in the testing cohort presented such scores 21 . In the training cohort, approximately 32% of patients showed no response to UST at 16 weeks (n = 67), a proportion that was mirrored in the testing cohort (33%, n = 29). Prior exposure to biologics and key laboratory markers, such as CRP demonstrated significant differences between responders and non-responders in both cohorts. These findings underscore the potential predictive value of these markers in determining treatment outcomes with UST. Table 1 Baseline patient characteristics in training cohort and testing cohort Training cohort (n = 207) Testing cohort (n = 89) Characteristic Responders (n = 140) Non-responders (n = 67) P value Responders (n = 60) Non-responders (n = 29) P value Sex, n (%) 0.44 0.654 Male 95 (68%) 49 (73%) 45 (75%) 23 (79%) Female 45 (32%) 18 (27%) 15 (25%) 6 (21%) Age (years) 31.76 ± 10.51 31.21 ± 12.38 0.355 30.95 ± 10.17 30.86 ± 12.41 0.572 Disease Duration (years) 3.70 ± 3.55 3.85 ± 3.88 0.529 4.43 ± 4.45 3.60 ± 3.73 0.36 BMI (kg/m 2 ) 23.04 ± 4.41 19.57 ± 3.10 0.128 19.61 ± 4.26 19.01 ± 2.96 0.569 CRP (mg/L) 15.43 ± 26.89 26.70 ± 26.86 < 0.001* 22.72 ± 42.64 23.34 ± 28.43 0.027 * ALB (g/L) 38.78 ± 6.69 37.43 ± 5.82 0.113 39.12 ± 4.74 35.99 ± 5.39 0.01 * PLT (10 9 /L) 316.81 ± 106.60 339.70 ± 94.78 0.073 314.28 ± 85.32 331.97 ± 130.41 0.386 ESR (mm/h) 18.22 ± 20.65 28.70 ± 27.74 0.005* 18.97 ± 20.84 23.48 ± 18.60 0.213 Behavior, n (%) 0.23 0.903 B1 77 (55%) 40 (60%) 30 (50%) 15 (52%) B2 48 (34%) 16 (24%) 21 (35%) 11 (38%) B3 15 (11%) 11 (16%) 9 (15%) 3 (10%) Location, n (%) 0.19 0.216 L1 36 (26%) 10 (15%) 19 (32%) 8 (28%) L2 7 (5.0%) 5 (7.5%) 1 (1.7%) 3 (10%) L3 97 (69%) 52 (78%) 40 (67%) 18 (62%) L4, n (%) 0.778 0.678 No 129 (92%) 63 (94%) 56 (93%) 26 (90%) Yes 11 (7.9%) 4 (6.0%) 4 (6.7%) 3 (10%) Fistula, n (%) 0.496 0.029* No 74 (53%) 31 (46%) 34 (57%) 12 (41%) Simple 37 (26%) 23 (34%) 18 (30%) 6 (21%) Complex 29 (21%) 13 (19%) 8 (13%) 11 (38%) Bowel Surgery, n (%) 0.839 0.921 No 109 (78%) 53 (79%) 42 (70%) 20 (69%) Yes 31 (22%) 14 (21%) 18 (30%) 9 (31%) WBC (10 9 /L) 6.59 ± 2.48 7.87 ± 7.77 0.135 6.27 ± 1.97 6.64 ± 2.14 0.467 RBC (10 12 /L) 4.47 ± 0.74 4.45 ± 0.69 0.787 4.68 ± 0.69 4.56 ± 0.63 0.514 Hb (g/L) 120.28 ± 25.57 116.91 ± 25.02 0.254 125.50 ± 19.51 116.03 ± 23.86 0.094 HCT (L/L) 0.67 ± 3.43 0.37 ± 0.06 0.474 0.99 ± 4.61 0.51 ± 0.75 0.266 Smoking History, n (%) 0.577 0.157 No 117 (84%) 58 (87%) 51 (85%) 28 (97%) Yes 23 (16%) 9 (13%) 9 (15%) 1 (3.4%) ASA Treatment History, n (%) 0.974 0.501 No 54 (39%) 26 (39%) 23 (38%) 9 (31%) Yes 86 (61%) 41 (61%) 37 (62%) 20 (69%) Steroid Treatment History, n (%) 0.969 No 79 (56%) 38 (57%) 37 (62%) 15 (52%) Yes 61 (44%) 29 (43%) 23 (38%) 14 (48%) Immunosuppressive Treatment History, n (%) 0.341 0.301 0.301 No 62 (44%) 27 (40%) 21 (35%) 7 (24%) Yes 78 (56%) 40 (60%) 39 (65%) 22 (76%) Prior Biologics Exposure, n (%) 0.027* 0.03 * No 65 (46%) 24 (36%) 33 (55%) 8 (28%) anti -TNF 48 (34%) 33 (49%) 19 (32%) 12 (41%) VDZ 13 (9.3%) 5 (7.5%) 5 (8.3%) 3 (10%) anti -TNF + VDZ 14 (10%) 5 (7.5%) 3 (5.0%) 6 (21%) Limberg Degree, n (%) 0.326 0.711 1 1 (0.7%) 0 (0%) 1 (1.7%) 0 (0%) 2 14 (10%) 5 (7.5%) 6 (10%) 1 (3.4%) 3 94 (67%) 46 (69%) 39 (65%) 22 (76%) 4 31 (22%) 16 (24%) 14 (23%) 6 (21%) CDAI 224 ± 81 238 ± 63 0.325 225 ± 64 264 ± 92 0.683 SES-CD 15 ± 6 19 ± 4 0.155 17 ± 3 15 ± 7 0.224 * Statistical significance is indicated by P < 0.05. Abbreviations: BMI, Body Mass Index; CRP, C-reactive Protein; ALB, Albumin; PLT, Platelet Count; ESR, Erythrocyte Sedimentation Rate; WBC, White Blood Cell; RBC, Red Blood Cell; Hb, Hemoglobin; HCT, Hematocrit; ASA, Aminosalicylic Acid; anti-TNF, anti-Tumor Necrosis Factor; VDZ, Vedolizumab; CDAI, Crohn’s Disease Activity Index; SES-CD, Simple Endoscopic Score for Crohn Disease. Radiomic signature building A total of 1,288 radiomic features were extracted from manually delineated VOIs on CT images. Following dimensionality reduction based on PCC, 918 features from inflamed bowel segments were selected. Ranking these features through RFE, the top 20 features from inflamed lesions were chosen. Utilizing LASSO logistic regression, this was further refined to 16 potential predictors (Supplementary Figure). The selected features and their coefficients and interpretation listed in Supplementary Table 3. A heatmap of PCC correlation coefficients for each retained feature is also presented in Supplementary Figure. The RS yielded AUCs of 0.819 (95% CI, 0.759–0.878) in the training cohort and 0.791 (95% CI, 0.698–0.885) in the testing cohort (Fig. 2 ). The confusion matrix visualizes the discriminative power of the RS, with related metrics such as accuracy, sensitivity, specificity, precision, recall, and F1 value presented in Table 2 . The calibration curves for both cohorts, as depicted in Fig. 2 , indicated good calibration of the RS, and the non-significant Hosmer–Lemeshow test results ( P > 0.05) for both cohorts confirmed a satisfactory model fit. Table 2 Prediction performance of the RS and RS-clinical combined model Index Training cohort Testing cohort RS Combined model RS Combined model Accuracy 0.705 0.797 0.730 0.840 Sensitivity 0.851 0.924 0.683 0.927 Specificity 0.636 0.574 0.828 0.654 Precision 0.899 0.812 0.891 0.810 Recall 0.636 0.791 0.683 0.850 F1 value 0.745 AUC (95% CI) 0.819 (0.759–0.878) 0.847 (0.790–0.904) 0.791 (0.698–0.885) 0.801 (0.702–0.899) P value < 0.001 < 0.001 < 0.005 < 0.005 Abbreviations: RS, radiomic signature; AUC, Area Under the Curve; CI, Confidence Interval. Construction of RS‑clinical combined model Based on the results of variance analysis between positive (responders) and negative (non-responders) samples, along with clinical experience (Table 1 ), we conducted univariate regression analysis for each clinical variable, including the RS, which may serve as a potential predictive factor. As shown in Table 3 , the results indicated that RS, CRP, ESR, disease location, and prior biologics exposure were potential predictive factors (threshold P < 0.10). Further multivariate logistic regression analysis using a backward elimination method demonstrated that RS (OR 5.23, 95% CI [2.98–9.17], P < 0.001) and prior anti-TNF (anti-Tumor Necrosis Factor) exposure (OR 0.42, 95% CI [0.18–0.96], P = 0.041) were independent predictive factors ( P < 0.05). Following the principle of minimum AIC (AIC = 191.45), the final model retained three predictive factors: RS, CRP, and prior biologics exposure. The formula for calculating the response probability is as follows: Table 3 Univariable and multivariable logistic regression for predicting Ustekinumab response in training cohort Variables Univariable Multivariable Final model OR (95% CI) P value OR (95% CI) P value OR (95% CI) P value RS 4.74 (2.80–8.02) < 0.001* 5.23 (2.98–9.17) < 0.001 ** 5.32 (3.04–9.31) < 0.001 ** Sex (Male vs Female) 1.29 (0.68–2.46) 0.441 Age 1.00 (0.98–1.03) 0.736 Disease Duration 0.99 (0.91–1.07) 0.776 BMI 1.01 (0.98–1.03) 0.624 CRP 0.99 (0.97-1.00) 0.009* 0.99 (0.97-1.00) 0.173 0.98 (0.97–0.99) 0.006 ** ALB 1.04 (0.99–1.09) 0.159 PLT 1.00 (1.00–1.00) 0.137 ESR 0.98 (0.97–0.99) 0.004* 0.99 (0.97–1.01) 0.253 Behavior B1 - B2 1.56 (0.79–3.08) 0.203 B3 0.71 (0.30–1.69) 0.436 Location L1 L2 0.39 (0.10–1.49) 0.169 0.70 (0.13–3.81) 0.677 L3 0.52 (0.24–1.13) 0.097* 0.89 (0.35–2.31) 0.818 Fistula No Simple 0.67 (0.35–1.31) 0.247 Complex 0.93 (0.43–2.03) 0.864 Bowel Surgery (Yes vs No) 1.08 (0.53–2.19) 0.839 WBC 0.93 (0.84–1.03) 0.177 RBC 1.03 (0.69–1.54) 0.876 Hb 1.01 (0.99–1.02) 0.372 HCT 2.97 (0.03-269.03) 0.636 Smoking History (Yes vs No) 0.79 (0.34–1.81) 0.578 ASA Treatment History (Yes vs No) 0.99 (0.54–1.80) 0.974 Steroid Treatment History (Yes vs No) 0.99 (0.55–1.78) 0.969 Immunosuppressive Treatment History (Yes vs No) 1.18 (0.65–2.13) 0.588 Prior Biologics Exposure No anti-TNF 0.54 (0.28–1.02) 0.059* 0.42 (0.18–0.96) 0.041 ** 0.40 (0.18–0.89) 0.026 ** VDZ 0.96 (0.31–2.98) 0.944 1.79 (0.43–7.40) 0.420 1.69 (0.42–6.76) 0.461 anti-TNF + VDZ 1.03 (0.34–3.18) 0.954 1.50 (0.34–6.53) 0.592 1.47 (0.34–6.37) 0.605 * In univariable analysis, P value < 0.1 was considered statistically significant. ** In multivariate analysis, P value < 0.05 was considered statistically significant. Abbreviations: RS, Radiomic Signature; BMI, Body Mass Index; CRP, C-reactive Protein; ALB, Albumin; PLT, Platelet Count; ESR, Erythrocyte Sedimentation Rate; WBC, White Blood Cell; RBC, Red Blood Cell; Hb, Hemoglobin; HCT, Hematocrit; ASA, Aminosalicylic Acid; anti-TNF, anti-Tumor Necrosis Factor; VDZ, Vedolizumab. $$\:\text{P}\text{r}\text{e}\text{d}\text{i}\text{c}\text{t}\text{e}\text{d}\:\text{p}\text{r}\text{o}\text{b}\text{a}\text{b}\text{i}\text{l}\text{i}\text{t}\text{y}=\frac{1}{1+{e}^{-f\left(x\right)}}$$ $$\:f\left(x\right)=\:\left(1.670\:\times\:\:RS\right)-\left(0.018\times\:\:CRP\:in\:mg/L\right)-\:0.918\:\times\:\left(\text{0,1}\right)\left(anti\_TNF\:vs\:no\:biologics\:exposure\right)+0.523\times\:\left(\text{0,1}\right)\left(VDZ\:vs\:no\:biologics\:exposure\right)+0.387\:\times\:\left(\text{0,1}\right)\left(anti\_TNF+VDZ\:vs\:no\:biologics\:exposure\right)$$ Figure 3 illustrates the superior discriminative power of the RS-clinical combined model between responders and non-responders, achieving an AUC of 0.847 (95% CI, 0.790–0.904) in the training cohort, surpassing the RS model alone (AUC = 0.819; 95% CI, 0.759–0.878) as detailed in Table 2 . Consistent results were observed in the testing cohort, with an AUC of 0.801 (95% CI, 0.702–0.899). The RS-clinical combined model demonstrated significantly enhanced predictive performance for UST efficacy compared to the clinical model alone in the training ( P = 0.006), but not in the testing cohort ( P = 0.034), as determined by the DeLong test. The calibration curves indicated good agreement between predicted probabilities and observed outcomes in both cohorts, further supported by nonsignificant P values from the Hosmer-Lemeshow test (0.904 and 0.950), suggesting strong calibration power. The confusion matrix visualized the performance of the combined model across both datasets. The decision curve analysis (Fig. 3 ) revealed that, at nearly all threshold levels, the combined model offered the greatest net benefit over no clinical decision-making or the RS alone, underscoring its utility as a superior tool for informing clinical decisions. Discussion Previous clinical trials have established UST as an essential treatment option for CD patients who have failed prior anti-TNF and vedolizumab (VDZ) therapies 2 . Like other biologics, UST's response varies among patients, with unclear non-response factors. Our study identified an RS based on intestinal inflammation as an independent predictor of UST response at 16 weeks, with improved prediction when combined with clinical factors. This lays a foundation for informed clinical treatment decisions. To our knowledge, our study cohort is the largest sample size reported to date in a real-world clinical dataset (total n = 296). Unlike clinical trials, in routine clinical practice, biologic efficacy assessment is more comprehensive than in trials, involving symptoms, imaging, endoscopy, and labs, guided by a specialized team. UST optimization strategies, like dosage and injection timing, are based on these assessments 22 . Given the pan-gastrointestinal distribution of CD lesions, it is logical that the quantification of inflamed intestinal segments is a potential approach to quantify the inflammatory burden. Consequently, we extracted radiomic features from the entire inflamed intestinal segment. As hypothesized, the RS demonstrated strong discriminative performance, with AUC values of 0.819 in the training cohort and 0.791 in the testing cohort, and calibration performance, as indicated by a Hosmer-Lemeshow test where P > 0.05, surpassing previously reported study models and predictive factors 7 . By incorporating clinical factors, the comprehensive model not only exhibited excellent discriminative power, with an AUC of 0.847, but also displayed satisfactory calibration performance, indicated by a Hosmer-Lemeshow test where P > 0.05. These promising results were corroborated in an independent testing cohort, which reported an AUC of 0.801. The clinical decision curve further highlighted the clinical utility of the model. Compared to previous studies on the use of radiomic analysis in CD, which have focused on predicting the efficacy of infliximab (IFX) and diagnosing the disease, our study aligns with prior research in the areas of segmentation, feature extraction and reduction, focusing mainly on texture features 15 , 23 – 25 . However, when compared with several studies on IFX efficacy prediction, the categories of retained features, the number of features, and the optimal classifiers used varied 15 , 26 , 27 .Different biologics target various sites with distinct molecular and histological heterogeneities, affecting feature predictive importance. Additionally, the high number of radiomic features relative to sample size makes RS construction heavily reliant on machine learning methods, impacting model stability and generalizability. We observed that in previous multicenter studies on IFX efficacy prediction (with cohorts of three or more), the radiomic models retained more features and frequently employed non-linear classifiers such as support vector machines 15 , 23 . Notably, CD lesions consist of multiple independent segments, leading to increased heterogeneity when analyzed collectively, unlike continuous lesions like tumors. Addressing overfitting and ensuring model generalizability is challenging for both oncological and non-oncological diseases. Treating CD lesions from different locations separately for feature extraction increases the feature count, which in turn necessitates larger sample sizes and the use of advanced analysis techniques. Despite concerns about overfitting and stability, radiomics remains a valuable clinical biomarker. The adage "images are more than pictures but data" holds true, underscoring the value of radiomic analysis in extracting meaningful information from medical images to support clinical decision-making and patient management 10 , 28 . Beyond the construction of the RS, our analysis of baseline clinical factors for UST treatment differs from previous reports 6 . First, CRP is a widely used and accessible marker for CD inflammation, predicts responses to anti-TNF, VDZ, and UST treatments, aligning with our results 6 . Notably, CRP levels are affected by factors like disease activity and infections, fluctuate widely. Thus, guidelines increasingly advocate fecal calprotectin for assessing CD inflammation due to its higher specificity 29 , 30 . However, due to health insurance limitations, fecal calprotectin testing isn't performed at our center. There were differences in biologic exposure between UST responders and non-responders ( P < 0.05). Univariate analysis showed prior anti-TNF monotherapy was associated with UST efficacy, which was confirmed by multivariate analysis as an independent predictor. VDZ was retained in the final regression model, either alone or with anti-TNF ( P > 0.05). Interestingly, both had positive regression coefficients (0.523 and 0.327), suggesting that VDZ exposure in both forms could enhance the UST response rate and serve as a protective factor. Considering that both had P -values > 0.05 in both univariate and multivariate logistic regression analyses, this interpretation should be approached with caution and requires further clinical data for validation. Compared to anti-TNF, VDZ targets the integrin α4β7, offering gut selectivity, which prompts further consideration of the biologics selection sequence in CD treatment 31 . After analyzing clinical factors, our radiomic-clinical combined model achieved an AUC of 0.847, with all data readily obtainable in routine clinical practice. In conclusion, our radiomic-clinical nomogram provides a comprehensive method to forecast UST therapy outcomes in CD patients, helping clinicians assess treatment risks versus benefits. Our study has several limitations. First, despite a large cohort of CD patients with CTE data, our retrospective, single-centered study may have introduced bias. Second, lacking external validation and long-term efficacy data necessitates further research, including multi-institutional, prospective studies with extended follow-up. Third, our model is based on CTE, not MRE, raising concerns about ionizing radiation. However, CTE has advantages in assessing baseline CD, effectively identifying complex abdominal complications, reducing technical complexity, and examination time, increasing accessibility. Moreover, low-dose CT scanners can mitigate radiation risks. Fourth, Manual or semi-automatic segmentation of computed tomographic enterography (CTE) images constitutes a labor-intensive process demanding specialized radiological expertise, which may impede widespread clinical implementation. This persistent methodological bottleneck currently affects numerous radiomics models. Future development of deep learning algorithms for automated segmentation promises enhanced efficiency and reproducibility of segmentation protocols. In summary, we have developed a CTE-based radiomic-clinical combined model to predict UST treatment efficacy in CD patients, facilitating early optimization of therapy. Further large-scale studies with long-term follow-up are warranted to validate these imaging biomarkers. Declarations Conflicts of interest The authors declare that they have no competing interests. Funding: This study was supported by the Taikang Science Fund for Young Scholars. Author Contribution Conceptualization: Yingkui Zhong Data curation: Minyi Guo, Yilin Guan, Siqi Hu, Qi Zhang, Jue Lin, Zhaoyuan Xu, Huibo Wu, Jiayin Yao Formal analysis: Yingkui Zhong Funding acquisition: Yingkui Zhong Methodology: Jiayin Yao, Yingkui Zhong Project administration: Minyi Guo Software: Minyi Guo, Yingkui Zhong Supervision: Yilin Guan, Siqi Hu Visualization: Yilin Guan, Siqi Hu Writing-original draft: Minyi Guo Writing-review & editing: Min Zhi, Jiayin Yao, Yingkui Zhong Data availability statement: The datasets generated or analyzed during the study are available from the corresponding author on reasonable request. References Dolinger M, Torres J, Vermeire S. Crohn's disease. Lancet . 2024; 403: 1177–91. Feagan BG, Sandborn WJ, Gasink C, et al. Ustekinumab as Induction and Maintenance Therapy for Crohn's Disease. N Engl J Med . 2016; 375: 1946–60. Rubín de Célix C, Chaparro M, Gisbert JP. Real-World Evidence of the Effectiveness and Safety of Ustekinumab for the Treatment of Crohn's Disease: Systematic Review and Meta-Analysis of Observational Studies. J Clin Med . 2022; 11. Torres J, Bonovas S, Doherty G, et al. ECCO Guidelines on Therapeutics in Crohn's Disease: Medical Treatment. J Crohns Colitis . 2020; 14: 4–22. Lorenzo González L, Valdés Delgado T, Vázquez Morón JM, et al. Ustekinumab in Crohn's disease: real-world outcomes and predictors of response. Rev Esp Enferm Dig . 2022; 114: 272–9. Gisbert JP, Chaparro M. Predictors of Primary Response to Biologic Treatment [Anti-TNF, Vedolizumab, and Ustekinumab] in Patients With Inflammatory Bowel Disease: From Basic Science to Clinical Practice. J Crohns Colitis . 2020; 14: 694–709. Waljee AK, Wallace BI, Cohen-Mekelburg S, et al. Development and Validation of Machine Learning Models in Prediction of Remission in Patients With Moderate to Severe Crohn Disease. JAMA Network Open . 2019; 2: e193721-e. Rimola J, Torres J, Kumar S, Taylor SA, Kucharzik T. Recent advances in clinical practice: advances in cross-sectional imaging in inflammatory bowel disease. Gut . 2022; 71: 2587–97. Tariq R, Dilmaghani S. Machine Learning and Radiomics: Changing the Horizon of Crohn's Disease Assessment. Inflamm Bowel Dis . 2024; 30: 1919–21. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology . 2015; 278: 563–77. Silverberg MS, Satsangi J, Ahmad T, et al. Toward an integrated clinical, molecular and serological classification of inflammatory bowel disease: report of a Working Party of the 2005 Montreal World Congress of Gastroenterology. Can J Gastroenterol . 2005; 19 Suppl A: 5a-36a. Yang H, Li B, Guo Q, et al. Systematic review with meta-analysis: loss of response and requirement of ustekinumab dose escalation in inflammatory bowel diseases. Aliment Pharmacol Ther . 2022; 55: 764–77. Ma C, Hussein IM, Al-Abbar YJ, et al. Heterogeneity in Definitions of Efficacy and Safety Endpoints for Clinical Trials of Crohn's Disease: A Systematic Review. Clin Gastroenterol Hepatol . 2018; 16: 1407-19.e22. Hallé E, Azahaf M, Duveau N, et al. Radiological Response Is Associated with Better Outcomes and Should Be Considered a Therapeutic Target in Crohn’s Disease. Dig Dis Sci . 2019. Wang Y, Luo Z, Zhou Z, et al. CT-based radiomics signature of visceral adipose tissue and bowel lesions for identifying patients with Crohn's disease resistant to infliximab. Insights Imaging . 2024; 15: 28. Bruining DH, Zimmermann EM, Loftus EV, Sandborn WJ, Sauer CG, Strong SA. Consensus Recommendations for Evaluation, Interpretation, and Utilization of Computed Tomography and Magnetic Resonance Enterography in Patients With Small Bowel Crohn's Disease. Gastroenterology . 2018; 154: 1172–94. Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology . 2020; 295: 328–38. van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Research . 2017; 77: e104-e7. Vittinghoff E, McCulloch CE. Relaxing the rule of ten events per variable in logistic and Cox regression. Am J Epidemiol . 2007; 165: 710–8. van Smeden M, de Groot JA, Moons KG, et al. No rationale for 1 variable per 10 events criterion for binary logistic regression analysis. BMC Med Res Methodol . 2016; 16: 163. Limberg B, Osswald B. Diagnosis and differential diagnosis of ulcerative colitis and Crohn's disease by hydrocolonic sonography. Am J Gastroenterol . 1994; 89: 1051–7. Meserve J, Ma C, Dulai PS, Jairath V, Singh S. Effectiveness of Reinduction and/or Dose Escalation of Ustekinumab in Crohn's Disease: A Systematic Review and Meta-analysis. Clin Gastroenterol Hepatol . 2022; 20: 2728-40.e1. Li X, Zhong Y, Yuan C, et al. Identifying patients with Crohn's disease at high risk of primary nonresponse to infliximab using a radiomic-clinical model. International Journal of Intelligent Systems . 2022; 37: 11853–70. Chen Y, Li H, Feng J, Suo S, Feng Q, Shen J. A Novel Radiomics Nomogram for the Prediction of Secondary Loss of Response to Infliximab in Crohn's Disease. J Inflamm Res . 2021; 14: 2731–40. Zhu C, Yu Y, Wang S, et al. A Novel Clinical Radiomics Nomogram to Identify Crohn's Disease from Intestinal Tuberculosis. J Inflamm Res . 2021; 14: 6511–21. Zhu C, Wang X, Wang S, et al. Development and validation of a clinical radiomics nomogram to predict secondary loss of response to infliximab in Crohn's disease patients. Heliyon . 2023; 9: e14594. Song F, Ma M, Zeng S, et al. CT enterography-based radiomics combined with body composition to predict infliximab treatment failure in Crohn's disease. Radiol Med . 2024; 129: 175–87. Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer . 2012; 48: 441–6. Ma C, Battat R, Parker CE, Khanna R, Jairath V, Feagan BG. Update on C-reactive protein and fecal calprotectin: are they accurate measures of disease activity in Crohn's disease? Expert Rev Gastroenterol Hepatol . 2019; 13: 319–30. Maaser C, Sturm A, Vavricka SR, et al. ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications. J Crohns Colitis . 2019; 13: 144–64. Jovani M, Danese S. Vedolizumab for the treatment of IBD: a selective therapeutic approach targeting pathogenic a4b7 cells. Curr Drug Targets . 2013; 14: 1433 Additional Declarations No competing interests reported. Supplementary Files Supplementarymaterials.docx Cite Share Download PDF Status: Published Journal Publication published 24 Nov, 2025 Read the published version in Abdominal Radiology → Version 1 posted Editorial decision: Revision requested 06 Sep, 2025 Reviews received at journal 06 Sep, 2025 Reviews received at journal 03 Sep, 2025 Reviewers agreed at journal 27 Aug, 2025 Reviewers agreed at journal 27 Aug, 2025 Reviewers invited by journal 26 Aug, 2025 Editor assigned by journal 25 Aug, 2025 Submission checks completed at journal 25 Aug, 2025 First submitted to journal 23 Aug, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7441161","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":506383196,"identity":"8ec1232b-a9d2-47d7-9ce6-5d43951bb3ad","order_by":0,"name":"Minyi Guo","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Minyi","middleName":"","lastName":"Guo","suffix":""},{"id":506383197,"identity":"a14c591e-b8d4-4e18-8628-77d97d238b90","order_by":1,"name":"Yilin Guan","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yilin","middleName":"","lastName":"Guan","suffix":""},{"id":506383198,"identity":"3febb5e7-6627-4726-adf3-ba32405eec36","order_by":2,"name":"Siqi Hu","email":"","orcid":"","institution":"Third Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Siqi","middleName":"","lastName":"Hu","suffix":""},{"id":506383199,"identity":"ca5303ae-07e3-40cc-9dda-3bdabdddfff2","order_by":3,"name":"Qi Zhang","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Zhang","suffix":""},{"id":506383200,"identity":"196a1f20-b552-4647-8ae0-d776f6ff31f6","order_by":4,"name":"Jue Lin","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jue","middleName":"","lastName":"Lin","suffix":""},{"id":506383201,"identity":"cc4ec622-be9a-4462-9089-499f0961bf88","order_by":5,"name":"Zhaoyuan Xu","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Zhaoyuan","middleName":"","lastName":"Xu","suffix":""},{"id":506383202,"identity":"5fd6f1e0-4d2d-430c-a10a-bf245be7ae2a","order_by":6,"name":"Huibo Wu","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Huibo","middleName":"","lastName":"Wu","suffix":""},{"id":506383203,"identity":"1a5a759f-59a9-47d6-a7d4-6acdf8f3824f","order_by":7,"name":"Min Zhi","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Zhi","suffix":""},{"id":506383204,"identity":"990e1449-ae07-4388-9bec-1a8535d256d7","order_by":8,"name":"Jiayin Yao","email":"","orcid":"","institution":"Sixth Affiliated Hospital of Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jiayin","middleName":"","lastName":"Yao","suffix":""},{"id":506383205,"identity":"ce852b41-d2af-42a0-aa13-c94ab6123126","order_by":9,"name":"Yingkui Zhong","email":"data:image/png;base64,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","orcid":"","institution":"Shenzhen Qianhai Taikang Hospital","correspondingAuthor":true,"prefix":"","firstName":"Yingkui","middleName":"","lastName":"Zhong","suffix":""}],"badges":[],"createdAt":"2025-08-23 12:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7441161/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7441161/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00261-025-05247-6","type":"published","date":"2025-11-24T15:58:46+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":90541780,"identity":"4559f181-8816-466a-9316-2adb9bb7fff4","added_by":"auto","created_at":"2025-09-03 23:57:56","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":8001877,"visible":true,"origin":"","legend":"\u003cp\u003eThe study flowchart (Left) and\u003cstrong\u003e \u003c/strong\u003ethe radiomic workflow (Right) are illustrated. (\u003cem\u003eCD\u003c/em\u003e Crohn’s Disease; \u003cem\u003eCTE\u003c/em\u003e CT Enterography.)\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-7441161/v1/f6d8fe09d11911d5b38e8ad8.png"},{"id":90542643,"identity":"02a4b567-006b-4184-9be0-6ad9c391bdfb","added_by":"auto","created_at":"2025-09-04 00:05:56","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1433927,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of the radiomic signature is illustrated. \u003cstrong\u003e2A:\u003c/strong\u003e Receiver operator characteristic curve analyses of the radiomic signature are shown to compare their predictive performance in training and testing cohorts. 2B: Calibration curves of the nomogram in the training and testing cohorts are shown. The calibration curve delineates the concordance between the predicted probabilities and the observed outcomes. The diagonal gray dashed line signifies perfect calibration, whereas the solid line portrays the accuracy of the radiomic signature. The calibration is considered more accurate as the solid line approaches the dashed line. Area under the curve refers to the area under the curve. 2C, 2D: Confusion matrices of the training and testing cohorts, respectively. The top-left cell in each matrix represents the true negatives, indicating the number of patients correctly identified as non-responders by the model. The top-right cell shows the false negatives, which are the patients incorrectly labelled as non-responders. The bottom-left cell indicates the false positives, representing the number of patients incorrectly identified as responders. Finally, the bottom-right cell denotes the true positives, which are the patients correctly identified as responders by the model. AUC = area under curve; CI = confidence interval.\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-7441161/v1/78c6075f290c09e9d2eff5e9.png"},{"id":90541783,"identity":"4243fcab-20c6-4ac0-a609-65e0c8083d0b","added_by":"auto","created_at":"2025-09-03 23:57:56","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":2688453,"visible":true,"origin":"","legend":"\u003cp\u003eThe performance of the radiomic signature-clinical combined model is illustrated. 3A: Receiver operator characteristic curve analyses of the radiomic signature-clinical combined model are shown to compare their predictive performance in training and testing cohorts. 3B: Calibration curves of the radiomic signature-clinical combined model in the training and testing cohorts are shown. 3C, 3D: Confusion matrices of the training and testing cohorts, respectively. 3E, 3F: Decision curve analyses comparing the net benefit of the radiomic signature-clinical combined model are shown. The net benefit was plotted versus the threshold probability. The combined model provides greater benefits compared to a no-decision scenario across the entire range of threshold probabilities. AUC = area under curve; CI = confidence interval.\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-7441161/v1/e330eb3c1cc49ef3086be592.png"},{"id":97178674,"identity":"d55d3b7d-6715-4280-abcd-4aca1dc250ca","added_by":"auto","created_at":"2025-12-01 16:12:31","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12786140,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7441161/v1/12607b69-1358-4867-a2e9-82f8de2b1260.pdf"},{"id":90541776,"identity":"a2104523-626d-4404-a8e7-280823a98b25","added_by":"auto","created_at":"2025-09-03 23:57:56","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":817658,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementarymaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7441161/v1/47be4a0f9d60492416758048.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"CT‑based radiomics of bowel wall at baseline predicts the efficacy of Ustekinumab at week 16 in patients with Crohn’s disease","fulltext":[{"header":"Introduction","content":"\u003cp\u003eCrohn's disease (CD) is a chronic inflammatory bowel disease typically managed with corticosteroids, immunosuppressants, and biologics\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Ustekinumab (UST), a monoclonal antibody targeting IL-12/23p40, has recently been a commonly used biologic agent for treating CD\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. Analysis of real-world data indicates that approximately 60% of patients achieve a pooled clinical response (CDAI-based) to UST therapy in the short term (8\u0026ndash;14 weeks), while response rates are around 64% in both the medium term (16\u0026ndash;24 weeks) and long term (48\u0026ndash;52 weeks)\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e. Considering the high cost of UST and variable patient response, identifying those who will gain the most benefit is crucial.\u003c/p\u003e\u003cp\u003eThe European Crohn\u0026rsquo;s and Colitis Organization (ECCO) has emphasized the need to develop and validate predictive biomarkers to advance precision medicine in inflammatory bowel disease\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. Current studies on predicting UST treatment response are limited in scope. The non-responsiveness to UST may be attributed to the high placebo effect and inadequate induction dosing; nevertheless, other potential risk factors have not yet been identified in prior research\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e. Clinical factors like age, gender, smoking, and disease characteristics such as duration and location show no correlation with treatment response\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eWaljee et al. created random forest models from UNITI data to forecast treatment-induced remission, yet there's a shortage of medical imaging-based prediction studies\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. Evaluating transmural inflammation through cross-sectional imaging techniques (Computed Tomography, Magnetic Resonance, ultrasound, etc.) is critical for understanding disease control, yet traditional scoring methods often rely on subjective interpretation\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eRadiomics, which extracts high-dimensional features from imaging for tissue pathology, is widely used in oncology but is underutilized in inflammatory bowel disease research\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. This study aims to quantify transmural inflammation in Crohn's disease through radiomic techniques, investigate its potential in predicting UST treatment response, and ultimately provide evidence for personalized medicine.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003ePatients\u003c/h2\u003e\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003cp\u003efor this single-center study was obtained from the Institutional Review Boards at hospital. Given the retrospective design, patient consent was waived. The study initially included 524 individuals diagnosed with CD, who received UST, treatment at our institution from January 2016 to July 2022. All enrolled patients received a standardized Ustekinumab induction regimen consisting of weight-based intravenous dosing (\u0026asymp;\u0026thinsp;6 mg/kg) at Week 0 followed by subcutaneous 90 mg administration at Week 8. Crucially, treatment response was assessed at Week 16 immediately prior to the third scheduled dose, ensuring our evaluation exclusively captured induction-phase efficacy before any maintenance regimen could be initiated or modified. To ensure the validity of the study's outcomes, strict exclusion criteria were applied, disqualifying patients for the following reasons: 1) lack of baseline Computed Tomography Enterography (CTE) data or electronic medical records; 2) inadequate quality of CTE images; and 3) irregular injection schedules or optimized treatment regimens. Ultimately, a cohort of 296 CD patients was established, which was randomly divided into a training cohort (n\u0026thinsp;=\u0026thinsp;207) and an independent testing cohort (n\u0026thinsp;=\u0026thinsp;89) in a 7:3 ratio (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The distribution of baseline characteristics was largely consistent between the two cohorts (Supplementary Table\u0026nbsp;1).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/p\u003e\u003cp\u003eAn experienced multidisciplinary team meticulously assessed disease activity in patients through clinical symptoms, laboratory indices, radiology, and endoscopies. Demographic and clinical data, including medication history, surgical interventions, follow-up duration, age, gender, height, weight, and smoking status, were carefully collected from electronic health records. Body Mass Index (BMI) was calculated using the standard formula: weight divided by height squared. Laboratory assessments included a complete blood count, with specific attention to neutrophil, lymphocyte, and platelet counts, as well as measurements of serum albumin, globulin, and C-reactive protein (CRP) levels. The location and behavior of Crohn's disease were classified according to the Montreal classification\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eOutcomes and Definitions\u003c/h3\u003e\n\u003cp\u003eAll enrolled patients received a standardized Ustekinumab induction regimen consisting of weight-based intravenous dosing (\u0026asymp;\u0026thinsp;6 mg/kg) at Week 0 followed by subcutaneous 90 mg administration at Week 8. Considering the time-dependent nature of drug efficacy, it is clinically recommended that the effectiveness of UST be evaluated no earlier than the sixteenth week post-treatment initiation\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. Given that our study is designed to predict the need for adjustments in pharmacotherapy (e.g., intensifying induction), we have adopted stricter response criteria. Treatment response to UST is defined as meeting all four criteria: clinical response, biochemical response, endoscopic response, and radiologic response: (1) clinical improvement, indicated by a Crohn\u0026rsquo;s Disease Activity Index (CDAI) score below 150 or a reduction of at least 70% from baseline values; (2) normalization of biomarkers, with a CRP level below 5 mg/L; (3) endoscopic data, if available, showing response with a decrease of at least 50% in the Simple Endoscopic Score for Crohn's Disease (SES-CD) or remission with an SES-CD score not exceeding 2; and (4) cross-sectional imaging demonstrating a reduction or resolution of inflamed bowel segments relative to baseline\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e. These evaluations are integral to the comprehensive assessment by the attending physician, guiding decisions on potential adjustments to the patient's therapeutic regimen.\u003c/p\u003e\n\u003ch3\u003eCTE image processing and radiomic feature extraction\u003c/h3\u003e\n\u003cp\u003eAll patients underwent standardized CTE examinations (Supplementary Material 1) with the parameters summarized in Supplementary Table\u0026nbsp;2, and the original DICOM format images were exported for further analysis. The most recent CTE image prior to injection, obtained within three months during the arterial phase, was used for analysis due to its superior contrast\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. The intestinal lesions were manually delineated by two radiologists (MY.G. and YL.G., with 8 and 5 years of experience, respectively) using the ITK-SNAP software (version 3.8.0; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.itksnap.org\u003c/span\u003e\u003cspan address=\"http://www.itksnap.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). For the inflamed segments of the bowel, a 3D Volume of Interest (VOI) was semi-automatically segmented (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). An inflamed bowel segment was defined based on abnormal enhancement or edema observed in CTE images\u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e. The 3D VOIs were then selected as the input for feature extraction.\u003c/p\u003e\u003cp\u003eThe extraction of radiomic features was conducted using the flexible open-source platform PyRadiomics (version 3.7.6; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.python.org\u003c/span\u003e\u003cspan address=\"https://www.python.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). This radiomic quantification platform adheres to the Image Biomarker Standardization Initiative (IBSI), ensuring the standardization of both feature definitions and image processing protocols\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. More detailed information regarding parameter settings for image processing, the radiomics procedure, and the extracted radiomic features is presented in Supplementary Material 2. Ultimately, a total of 1288 quantitative features were extracted from the VOI for further analysis.\u003c/p\u003e\n\u003ch3\u003eFeature selection and signature building\u003c/h3\u003e\n\u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates the radiomics workflow. In the process of feature selection and signature development, we first standardized all radiomic features using the z-score method, parameterized from the training cohort, ensuring that each feature had a zero mean and a unit standard deviation. Subsequently, we performed dimensionality reduction by comparing features and removing those with a Pearson correlation coefficient exceeding 0.900, thereby eliminating redundancy and ensuring the independence of the retained features.\u003c/p\u003e\u003cp\u003eNext, we used recursive feature elimination (RFE) to find the most important features. RFE is a method that uses a base model to train multiple times, removing the least significant features after each round. This improves the model's ability to generalize and reduces overfitting. According to the power calculation, the number of predictors should be no more than one-third of the smallest group in the training cohort, which here was non-responders with 67 participants\u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e. Thus, we selected the top 20 features based on their highest rankings from the RFE process.\u003c/p\u003e\u003cp\u003eTo construct the RS, we used the LASSO logistic regression model as our classifier. This model, a variant of logistic regression, includes an L1 norm penalty in its loss function, constraining weights and promoting feature sparsity, enhancing interpretability. We conducted a 5-fold cross-validation on the training dataset to optimize hyperparameters like the number of features. Hyperparameters were chosen based on predefined performance criteria. Ultimately, we developed a RS reflecting the burden of transmural inflammation, serving as an independent predictor of treatment efficacy for UST.\u003c/p\u003e\n\u003ch3\u003eConstruction of the RS‑clinical combined model\u003c/h3\u003e\n\u003cp\u003eUnivariate analysis was conducted to preliminarily select significant clinical characteristics (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.10). Logistic regression was used to estimate odds ratios (OR) for candidate factors. A multivariable logistic regression model was developed, incorporating RS and clinical features. Backward elimination (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.10) and the Akaike Information Criterion (AIC) guided model refinement, ensuring selection of the most pertinent predictors and enhancing predictive power.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003ePerformance evaluation and Statistical Analysis\u003c/h2\u003e\u003cp\u003eDifferences between UST responders and non-responders were analyzed using T-tests/Mann-Whitney U tests for continuous variables and Fisher\u0026rsquo;s/Chi-square tests for categorical variables. The radiomic model's performance was evaluated via ROC curve analysis, calculating AUC, accuracy, sensitivity, specificity, precision, recall, and F1 value, visualized by confusion matrices. The AUC of the RS and RS-clinical models was compared using the DeLong test, and calibration was assessed with calibration curves and the Hosmer-Lemeshow test. Performance metrics' 95% CIs were estimated with bootstrap resampling, and decision curve analysis evaluated the clinical utility of the combined model.\u003c/p\u003e\u003cp\u003eSample size considerations were calculated using MedCalc statistical software. All statistical analyses were conducted using R software (version 4.4.1) and Python (version 3.7.6), with a two-sided \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered indicative of statistical significance, except for the univariate analysis where \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.10 was applied.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003eBaseline characteristics and demographics\u003c/h2\u003e\u003cp\u003eA total of 296 patients with CD treated with UST were retrospectively recruited and evenly divided into a training cohort (n\u0026thinsp;=\u0026thinsp;207) and a testing cohort (n\u0026thinsp;=\u0026thinsp;89), as outlined in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. An AUC-based estimation of sample size indicated that the sample size for training and validation in our study was adequate (Supplementary Material 3). The patient demographics were predominantly male in both cohorts, with 70% in the training cohort and 76% in the testing cohort (Supplementary Table\u0026nbsp;1). Clinical characteristics, including disease behavior, location, and the presence of fistulas, were comparable between responders and non-responders to UST across both cohorts, with no statistically significant differences observed (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Notably, a majority of patients in both cohorts exhibited a Limberg score of 3 (a semiquantitative color Doppler ultrasound assessment of bowel wall vascularity in inflammatory bowel disease), indicating active inflammation; over 90% of the training cohort and a comparable proportion in the testing cohort presented such scores\u003csup\u003e\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e. In the training cohort, approximately 32% of patients showed no response to UST at 16 weeks (n\u0026thinsp;=\u0026thinsp;67), a proportion that was mirrored in the testing cohort (33%, n\u0026thinsp;=\u0026thinsp;29). Prior exposure to biologics and key laboratory markers, such as CRP demonstrated significant differences between responders and non-responders in both cohorts. These findings underscore the potential predictive value of these markers in determining treatment outcomes with UST.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBaseline patient characteristics in training cohort and testing cohort\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e\u003cp\u003eTraining cohort (n\u0026thinsp;=\u0026thinsp;207)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c7\" namest=\"c5\"\u003e\u003cp\u003eTesting cohort (n\u0026thinsp;=\u0026thinsp;89)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCharacteristic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eResponders\u003c/p\u003e\u003cp\u003e(n\u0026thinsp;=\u0026thinsp;140)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNon-responders\u003c/p\u003e\u003cp\u003e(n\u0026thinsp;=\u0026thinsp;67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eResponders\u003c/p\u003e\u003cp\u003e(n\u0026thinsp;=\u0026thinsp;60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNon-responders\u003c/p\u003e\u003cp\u003e(n\u0026thinsp;=\u0026thinsp;29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSex, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.654\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e95 (68%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e49 (73%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e45 (75%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e23 (79%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e45 (32%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e18 (27%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e15 (25%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e31.76\u0026thinsp;\u0026plusmn;\u0026thinsp;10.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31.21\u0026thinsp;\u0026plusmn;\u0026thinsp;12.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.355\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30.95\u0026thinsp;\u0026plusmn;\u0026thinsp;10.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e30.86\u0026thinsp;\u0026plusmn;\u0026thinsp;12.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.572\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDisease Duration (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3.70\u0026thinsp;\u0026plusmn;\u0026thinsp;3.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e3.85\u0026thinsp;\u0026plusmn;\u0026thinsp;3.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.529\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.43\u0026thinsp;\u0026plusmn;\u0026thinsp;4.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3.60\u0026thinsp;\u0026plusmn;\u0026thinsp;3.73\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.36\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI (kg/m\u003csup\u003e2\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23.04\u0026thinsp;\u0026plusmn;\u0026thinsp;4.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19.57\u0026thinsp;\u0026plusmn;\u0026thinsp;3.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19.61\u0026thinsp;\u0026plusmn;\u0026thinsp;4.26\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e19.01\u0026thinsp;\u0026plusmn;\u0026thinsp;2.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.569\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCRP (mg/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e15.43\u0026thinsp;\u0026plusmn;\u0026thinsp;26.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e26.70\u0026thinsp;\u0026plusmn;\u0026thinsp;26.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e22.72\u0026thinsp;\u0026plusmn;\u0026thinsp;42.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e23.34\u0026thinsp;\u0026plusmn;\u0026thinsp;28.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.027\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eALB (g/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e38.78\u0026thinsp;\u0026plusmn;\u0026thinsp;6.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e37.43\u0026thinsp;\u0026plusmn;\u0026thinsp;5.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.113\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e39.12\u0026thinsp;\u0026plusmn;\u0026thinsp;4.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e35.99\u0026thinsp;\u0026plusmn;\u0026thinsp;5.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.01\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePLT (10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e316.81\u0026thinsp;\u0026plusmn;\u0026thinsp;106.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e339.70\u0026thinsp;\u0026plusmn;\u0026thinsp;94.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.073\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e314.28\u0026thinsp;\u0026plusmn;\u0026thinsp;85.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e331.97\u0026thinsp;\u0026plusmn;\u0026thinsp;130.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.386\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eESR (mm/h)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e18.22\u0026thinsp;\u0026plusmn;\u0026thinsp;20.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e28.70\u0026thinsp;\u0026plusmn;\u0026thinsp;27.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.005*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18.97\u0026thinsp;\u0026plusmn;\u0026thinsp;20.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e23.48\u0026thinsp;\u0026plusmn;\u0026thinsp;18.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.213\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBehavior, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.903\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e77 (55%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e40 (60%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30 (50%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15 (52%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e48 (34%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e16 (24%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e21 (35%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e11 (38%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e15 (11%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e11 (16%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e9 (15%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLocation, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.216\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e36 (26%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e10 (15%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19 (32%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e8 (28%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e7 (5.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5 (7.5%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1 (1.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e97 (69%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e52 (78%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e40 (67%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e18 (62%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u003cp\u003eL4, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.778\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.678\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e129 (92%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e63 (94%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e56 (93%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e26 (90%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e11 (7.9%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4 (6.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4 (6.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFistula, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.496\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.029*\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e74 (53%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31 (46%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e34 (57%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12 (41%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSimple\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e37 (26%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e23 (34%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18 (30%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eComplex\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e29 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e13 (19%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e8 (13%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e11 (38%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBowel Surgery, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.839\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.921\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e109 (78%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e53 (79%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e42 (70%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e20 (69%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e31 (22%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e14 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18 (30%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e9 (31%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWBC (10\u003csup\u003e9\u003c/sup\u003e/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e6.59\u0026thinsp;\u0026plusmn;\u0026thinsp;2.48\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7.87\u0026thinsp;\u0026plusmn;\u0026thinsp;7.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.135\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e6.27\u0026thinsp;\u0026plusmn;\u0026thinsp;1.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6.64\u0026thinsp;\u0026plusmn;\u0026thinsp;2.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.467\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRBC (10\u003csup\u003e12\u003c/sup\u003e/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4.47\u0026thinsp;\u0026plusmn;\u0026thinsp;0.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4.45\u0026thinsp;\u0026plusmn;\u0026thinsp;0.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.787\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.68\u0026thinsp;\u0026plusmn;\u0026thinsp;0.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e4.56\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.514\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHb (g/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e120.28\u0026thinsp;\u0026plusmn;\u0026thinsp;25.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e116.91\u0026thinsp;\u0026plusmn;\u0026thinsp;25.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.254\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e125.50\u0026thinsp;\u0026plusmn;\u0026thinsp;19.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e116.03\u0026thinsp;\u0026plusmn;\u0026thinsp;23.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.094\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHCT (L/L)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.67\u0026thinsp;\u0026plusmn;\u0026thinsp;3.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.37\u0026thinsp;\u0026plusmn;\u0026thinsp;0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.474\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.99\u0026thinsp;\u0026plusmn;\u0026thinsp;4.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.51\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.266\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoking History, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.577\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.157\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e117 (84%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e58 (87%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e51 (85%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e28 (97%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23 (16%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e9 (13%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e9 (15%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1 (3.4%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eASA Treatment History, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.974\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.501\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e54 (39%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e26 (39%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23 (38%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e9 (31%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e86 (61%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e41 (61%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e37 (62%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e20 (69%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSteroid Treatment History, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.969\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e79 (56%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e38 (57%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e37 (62%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15 (52%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e61 (44%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e29 (43%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23 (38%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e14 (48%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImmunosuppressive Treatment History, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.341\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.301\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.301\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e62 (44%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e27 (40%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e21 (35%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e7 (24%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e78 (56%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e40 (60%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e39 (65%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e22 (76%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrior Biologics Exposure, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.027*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.03\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e65 (46%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e24 (36%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e33 (55%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e8 (28%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eanti -TNF\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e48 (34%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e33 (49%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19 (32%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12 (41%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVDZ\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e13 (9.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5 (7.5%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e5 (8.3%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eanti -TNF\u0026thinsp;+\u0026thinsp;VDZ\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e14 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5 (7.5%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e3 (5.0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLimberg Degree, n (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.326\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.711\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1 (0.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1 (1.7%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0 (0%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e14 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5 (7.5%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e6 (10%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1 (3.4%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e94 (67%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e46 (69%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e39 (65%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e22 (76%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e31 (22%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e16 (24%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14 (23%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6 (21%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCDAI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e224\u0026thinsp;\u0026plusmn;\u0026thinsp;81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e238\u0026thinsp;\u0026plusmn;\u0026thinsp;63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.325\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e225\u0026thinsp;\u0026plusmn;\u0026thinsp;64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e264\u0026thinsp;\u0026plusmn;\u0026thinsp;92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.683\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSES-CD\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e15\u0026thinsp;\u0026plusmn;\u0026thinsp;6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19\u0026thinsp;\u0026plusmn;\u0026thinsp;4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.155\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e17\u0026thinsp;\u0026plusmn;\u0026thinsp;3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15\u0026thinsp;\u0026plusmn;\u0026thinsp;7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.224\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003csup\u003e*\u003c/sup\u003e Statistical significance is indicated by \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003cp\u003eAbbreviations: BMI, Body Mass Index; CRP, C-reactive Protein; ALB, Albumin; PLT, Platelet Count; ESR, Erythrocyte Sedimentation Rate; WBC, White Blood Cell; RBC, Red Blood Cell; Hb, Hemoglobin; HCT, Hematocrit; ASA, Aminosalicylic\u0026nbsp;Acid; anti-TNF, anti-Tumor Necrosis Factor; VDZ, Vedolizumab; CDAI, Crohn\u0026rsquo;s Disease Activity Index; SES-CD, Simple Endoscopic Score for Crohn Disease.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eRadiomic signature building\u003c/h2\u003e\u003cp\u003eA total of 1,288 radiomic features were extracted from manually delineated VOIs on CT images. Following dimensionality reduction based on PCC, 918 features from inflamed bowel segments were selected. Ranking these features through RFE, the top 20 features from inflamed lesions were chosen. Utilizing LASSO logistic regression, this was further refined to 16 potential predictors (Supplementary Figure). The selected features and their coefficients and interpretation listed in Supplementary Table\u0026nbsp;3. A heatmap of PCC correlation coefficients for each retained feature is also presented in Supplementary Figure. The RS yielded AUCs of 0.819 (95% CI, 0.759\u0026ndash;0.878) in the training cohort and 0.791 (95% CI, 0.698\u0026ndash;0.885) in the testing cohort (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The confusion matrix visualizes the discriminative power of the RS, with related metrics such as accuracy, sensitivity, specificity, precision, recall, and F1 value presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The calibration curves for both cohorts, as depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, indicated good calibration of the RS, and the non-significant Hosmer\u0026ndash;Lemeshow test results (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05) for both cohorts confirmed a satisfactory model fit.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePrediction performance of the RS and RS-clinical combined model\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eIndex\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eTraining cohort\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eTesting cohort\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRS\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCombined model\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRS\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCombined model\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.705\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.797\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.730\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.840\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.851\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.924\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.683\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.927\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.636\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.574\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.828\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.654\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.899\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.812\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.891\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.810\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRecall\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.636\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.791\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.683\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.850\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eF1 value\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.745\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAUC\u003c/p\u003e\u003cp\u003e(95% CI)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.819\u003c/p\u003e\u003cp\u003e(0.759\u0026ndash;0.878)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.847\u003c/p\u003e\u003cp\u003e(0.790\u0026ndash;0.904)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.791\u003c/p\u003e\u003cp\u003e(0.698\u0026ndash;0.885)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.801\u003c/p\u003e\u003cp\u003e(0.702\u0026ndash;0.899)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.005\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003eAbbreviations: RS, radiomic signature; AUC, Area Under the Curve; CI, Confidence Interval.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eConstruction of RS‑clinical combined model\u003c/h2\u003e\u003cp\u003eBased on the results of variance analysis between positive (responders) and negative (non-responders) samples, along with clinical experience (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e), we conducted univariate regression analysis for each clinical variable, including the RS, which may serve as a potential predictive factor. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, the results indicated that RS, CRP, ESR, disease location, and prior biologics exposure were potential predictive factors (threshold \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.10). Further multivariate logistic regression analysis using a backward elimination method demonstrated that RS (OR 5.23, 95% CI [2.98\u0026ndash;9.17], \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and prior anti-TNF (anti-Tumor Necrosis Factor) exposure (OR 0.42, 95% CI [0.18\u0026ndash;0.96], \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.041) were independent predictive factors (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Following the principle of minimum AIC (AIC\u0026thinsp;=\u0026thinsp;191.45), the final model retained three predictive factors: RS, CRP, and prior biologics exposure. The formula for calculating the response probability is as follows:\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eUnivariable and multivariable logistic regression for predicting Ustekinumab response in training cohort\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eVariables\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eUnivariable\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eMultivariable\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003eFinal model\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOR (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eOR (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eOR (95% CI)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4.74 (2.80\u0026ndash;8.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e5.23 (2.98\u0026ndash;9.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e5.32 (3.04\u0026ndash;9.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSex (Male vs Female)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.29 (0.68\u0026ndash;2.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.441\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.98\u0026ndash;1.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.736\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDisease Duration\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.99 (0.91\u0026ndash;1.07)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.776\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.01 (0.98\u0026ndash;1.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.624\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCRP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.99 (0.97-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.009*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99 (0.97-1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98 (0.97\u0026ndash;0.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.006\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eALB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.04 (0.99\u0026ndash;1.09)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePLT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.00 (1.00\u0026ndash;1.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.137\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eESR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.98 (0.97\u0026ndash;0.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.004*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99 (0.97\u0026ndash;1.01)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.253\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBehavior\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.56 (0.79\u0026ndash;3.08)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.203\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eB3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.71 (0.30\u0026ndash;1.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.436\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLocation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.39 (0.10\u0026ndash;1.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.169\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.70 (0.13\u0026ndash;3.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.677\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eL3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.52 (0.24\u0026ndash;1.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.097*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.89 (0.35\u0026ndash;2.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.818\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFistula\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSimple\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.67 (0.35\u0026ndash;1.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.247\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eComplex\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.93 (0.43\u0026ndash;2.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.864\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBowel Surgery\u003c/p\u003e\u003cp\u003e(Yes vs No)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.08 (0.53\u0026ndash;2.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.839\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWBC\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.93 (0.84\u0026ndash;1.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.177\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRBC\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.03 (0.69\u0026ndash;1.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.876\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHb\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.01 (0.99\u0026ndash;1.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.372\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHCT\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.97 (0.03-269.03)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.636\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoking History\u003c/p\u003e\u003cp\u003e(Yes vs No)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.79 (0.34\u0026ndash;1.81)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.578\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eASA Treatment History\u003c/p\u003e\u003cp\u003e(Yes vs No)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.99 (0.54\u0026ndash;1.80)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.974\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSteroid Treatment History\u003c/p\u003e\u003cp\u003e(Yes vs No)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.99 (0.55\u0026ndash;1.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.969\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eImmunosuppressive Treatment History\u003c/p\u003e\u003cp\u003e(Yes vs No)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.18 (0.65\u0026ndash;2.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.588\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrior Biologics Exposure\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eanti-TNF\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.54 (0.28\u0026ndash;1.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.059*\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.42 (0.18\u0026ndash;0.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.041\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.40 (0.18\u0026ndash;0.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.026\u003csup\u003e**\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVDZ\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.96 (0.31\u0026ndash;2.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.944\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.79 (0.43\u0026ndash;7.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.420\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.69 (0.42\u0026ndash;6.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.461\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eanti-TNF\u0026thinsp;+\u0026thinsp;VDZ\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.03 (0.34\u0026ndash;3.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.954\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.50 (0.34\u0026ndash;6.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.592\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.47 (0.34\u0026ndash;6.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.605\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003e\u003csup\u003e*\u003c/sup\u003e In univariable analysis, \u003cem\u003eP\u003c/em\u003e value\u0026thinsp;\u0026lt;\u0026thinsp;0.1 was considered statistically significant.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003e\u003csup\u003e**\u003c/sup\u003e In multivariate analysis, \u003cem\u003eP\u003c/em\u003e value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003eAbbreviations: RS, Radiomic Signature; BMI, Body Mass Index; CRP, C-reactive Protein; ALB, Albumin; PLT, Platelet Count; ESR, Erythrocyte Sedimentation Rate; WBC, White Blood Cell; RBC, Red Blood Cell; Hb, Hemoglobin; HCT, Hematocrit; ASA, Aminosalicylic Acid; anti-TNF, anti-Tumor Necrosis Factor; VDZ, Vedolizumab.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equa\" name=\"EquationSource\"\u003e\n$$\\:\\text{P}\\text{r}\\text{e}\\text{d}\\text{i}\\text{c}\\text{t}\\text{e}\\text{d}\\:\\text{p}\\text{r}\\text{o}\\text{b}\\text{a}\\text{b}\\text{i}\\text{l}\\text{i}\\text{t}\\text{y}=\\frac{1}{1+{e}^{-f\\left(x\\right)}}$$\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equb\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equb\" name=\"EquationSource\"\u003e\n$$\\:f\\left(x\\right)=\\:\\left(1.670\\:\\times\\:\\:RS\\right)-\\left(0.018\\times\\:\\:CRP\\:in\\:mg/L\\right)-\\:0.918\\:\\times\\:\\left(\\text{0,1}\\right)\\left(anti\\_TNF\\:vs\\:no\\:biologics\\:exposure\\right)+0.523\\times\\:\\left(\\text{0,1}\\right)\\left(VDZ\\:vs\\:no\\:biologics\\:exposure\\right)+0.387\\:\\times\\:\\left(\\text{0,1}\\right)\\left(anti\\_TNF+VDZ\\:vs\\:no\\:biologics\\:exposure\\right)$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e illustrates the superior discriminative power of the RS-clinical combined model between responders and non-responders, achieving an AUC of 0.847 (95% CI, 0.790\u0026ndash;0.904) in the training cohort, surpassing the RS model alone (AUC\u0026thinsp;=\u0026thinsp;0.819; 95% CI, 0.759\u0026ndash;0.878) as detailed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Consistent results were observed in the testing cohort, with an AUC of 0.801 (95% CI, 0.702\u0026ndash;0.899). The RS-clinical combined model demonstrated significantly enhanced predictive performance for UST efficacy compared to the clinical model alone in the training (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.006), but not in the testing cohort (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.034), as determined by the DeLong test. The calibration curves indicated good agreement between predicted probabilities and observed outcomes in both cohorts, further supported by nonsignificant \u003cem\u003eP\u003c/em\u003e values from the Hosmer-Lemeshow test (0.904 and 0.950), suggesting strong calibration power. The confusion matrix visualized the performance of the combined model across both datasets. The decision curve analysis (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e) revealed that, at nearly all threshold levels, the combined model offered the greatest net benefit over no clinical decision-making or the RS alone, underscoring its utility as a superior tool for informing clinical decisions.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003ePrevious clinical trials have established UST as an essential treatment option for CD patients who have failed prior anti-TNF and vedolizumab (VDZ) therapies\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. Like other biologics, UST's response varies among patients, with unclear non-response factors. Our study identified an RS based on intestinal inflammation as an independent predictor of UST response at 16 weeks, with improved prediction when combined with clinical factors. This lays a foundation for informed clinical treatment decisions.\u003c/p\u003e\u003cp\u003eTo our knowledge, our study cohort is the largest sample size reported to date in a real-world clinical dataset (total n\u0026thinsp;=\u0026thinsp;296). Unlike clinical trials, in routine clinical practice, biologic efficacy assessment is more comprehensive than in trials, involving symptoms, imaging, endoscopy, and labs, guided by a specialized team. UST optimization strategies, like dosage and injection timing, are based on these assessments\u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u003c/sup\u003e. Given the pan-gastrointestinal distribution of CD lesions, it is logical that the quantification of inflamed intestinal segments is a potential approach to quantify the inflammatory burden. Consequently, we extracted radiomic features from the entire inflamed intestinal segment. As hypothesized, the RS demonstrated strong discriminative performance, with AUC values of 0.819 in the training cohort and 0.791 in the testing cohort, and calibration performance, as indicated by a Hosmer-Lemeshow test where \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05, surpassing previously reported study models and predictive factors\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. By incorporating clinical factors, the comprehensive model not only exhibited excellent discriminative power, with an AUC of 0.847, but also displayed satisfactory calibration performance, indicated by a Hosmer-Lemeshow test where \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05. These promising results were corroborated in an independent testing cohort, which reported an AUC of 0.801. The clinical decision curve further highlighted the clinical utility of the model.\u003c/p\u003e\u003cp\u003eCompared to previous studies on the use of radiomic analysis in CD, which have focused on predicting the efficacy of infliximab (IFX) and diagnosing the disease, our study aligns with prior research in the areas of segmentation, feature extraction and reduction, focusing mainly on texture features\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan additionalcitationids=\"CR24\" citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e. However, when compared with several studies on IFX efficacy prediction, the categories of retained features, the number of features, and the optimal classifiers used varied\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e\u003c/sup\u003e.Different biologics target various sites with distinct molecular and histological heterogeneities, affecting feature predictive importance. Additionally, the high number of radiomic features relative to sample size makes RS construction heavily reliant on machine learning methods, impacting model stability and generalizability. We observed that in previous multicenter studies on IFX efficacy prediction (with cohorts of three or more), the radiomic models retained more features and frequently employed non-linear classifiers such as support vector machines\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e. Notably, CD lesions consist of multiple independent segments, leading to increased heterogeneity when analyzed collectively, unlike continuous lesions like tumors. Addressing overfitting and ensuring model generalizability is challenging for both oncological and non-oncological diseases. Treating CD lesions from different locations separately for feature extraction increases the feature count, which in turn necessitates larger sample sizes and the use of advanced analysis techniques. Despite concerns about overfitting and stability, radiomics remains a valuable clinical biomarker. The adage \"images are more than pictures but data\" holds true, underscoring the value of radiomic analysis in extracting meaningful information from medical images to support clinical decision-making and patient management\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eBeyond the construction of the RS, our analysis of baseline clinical factors for UST treatment differs from previous reports\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. First, CRP is a widely used and accessible marker for CD inflammation, predicts responses to anti-TNF, VDZ, and UST treatments, aligning with our results\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. Notably, CRP levels are affected by factors like disease activity and infections, fluctuate widely. Thus, guidelines increasingly advocate fecal calprotectin for assessing CD inflammation due to its higher specificity\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e, \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. However, due to health insurance limitations, fecal calprotectin testing isn't performed at our center. There were differences in biologic exposure between UST responders and non-responders (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Univariate analysis showed prior anti-TNF monotherapy was associated with UST efficacy, which was confirmed by multivariate analysis as an independent predictor. VDZ was retained in the final regression model, either alone or with anti-TNF (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Interestingly, both had positive regression coefficients (0.523 and 0.327), suggesting that VDZ exposure in both forms could enhance the UST response rate and serve as a protective factor. Considering that both had \u003cem\u003eP\u003c/em\u003e-values\u0026thinsp;\u0026gt;\u0026thinsp;0.05 in both univariate and multivariate logistic regression analyses, this interpretation should be approached with caution and requires further clinical data for validation. Compared to anti-TNF, VDZ targets the integrin α4β7, offering gut selectivity, which prompts further consideration of the biologics selection sequence in CD treatment\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. After analyzing clinical factors, our radiomic-clinical combined model achieved an AUC of 0.847, with all data readily obtainable in routine clinical practice. In conclusion, our radiomic-clinical nomogram provides a comprehensive method to forecast UST therapy outcomes in CD patients, helping clinicians assess treatment risks versus benefits.\u003c/p\u003e\u003cp\u003eOur study has several limitations. First, despite a large cohort of CD patients with CTE data, our retrospective, single-centered study may have introduced bias. Second, lacking external validation and long-term efficacy data necessitates further research, including multi-institutional, prospective studies with extended follow-up. Third, our model is based on CTE, not MRE, raising concerns about ionizing radiation. However, CTE has advantages in assessing baseline CD, effectively identifying complex abdominal complications, reducing technical complexity, and examination time, increasing accessibility. Moreover, low-dose CT scanners can mitigate radiation risks. Fourth, Manual or semi-automatic segmentation of computed tomographic enterography (CTE) images constitutes a labor-intensive process demanding specialized radiological expertise, which may impede widespread clinical implementation. This persistent methodological bottleneck currently affects numerous radiomics models. Future development of deep learning algorithms for automated segmentation promises enhanced efficiency and reproducibility of segmentation protocols.\u003c/p\u003e\u003cp\u003eIn summary, we have developed a CTE-based radiomic-clinical combined model to predict UST treatment efficacy in CD patients, facilitating early optimization of therapy. Further large-scale studies with long-term follow-up are warranted to validate these imaging biomarkers.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003ch2\u003eConflicts of interest\u003c/h2\u003e\u003cp\u003e The authors declare that they have no competing interests.\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding:\u003c/h2\u003e\u003cp\u003eThis study was supported by the Taikang Science Fund for Young Scholars.\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eConceptualization: Yingkui Zhong Data curation: Minyi Guo, Yilin Guan, Siqi Hu, Qi Zhang, Jue Lin, Zhaoyuan Xu, Huibo Wu, Jiayin Yao Formal analysis: Yingkui Zhong Funding acquisition: Yingkui Zhong Methodology: Jiayin Yao, Yingkui Zhong Project administration: Minyi Guo Software: Minyi Guo, Yingkui Zhong Supervision: Yilin Guan, Siqi Hu Visualization: Yilin Guan, Siqi Hu Writing-original draft: Minyi Guo Writing-review \u0026amp; editing: Min Zhi, Jiayin Yao, Yingkui Zhong\u003c/p\u003e\u003ch2\u003eData availability statement:\u003c/h2\u003e\u003cp\u003eThe datasets generated or analyzed during the study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eDolinger M, Torres J, Vermeire S. Crohn's disease. \u003cem\u003eLancet\u003c/em\u003e. 2024; 403: 1177\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFeagan BG, Sandborn WJ, Gasink C, \u003cem\u003eet al.\u003c/em\u003e Ustekinumab as Induction and Maintenance Therapy for Crohn's Disease. \u003cem\u003eN Engl J Med\u003c/em\u003e. 2016; 375: 1946\u0026ndash;60.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRub\u0026iacute;n de C\u0026eacute;lix C, Chaparro M, Gisbert JP. Real-World Evidence of the Effectiveness and Safety of Ustekinumab for the Treatment of Crohn's Disease: Systematic Review and Meta-Analysis of Observational Studies. \u003cem\u003eJ Clin Med\u003c/em\u003e. 2022; 11.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTorres J, Bonovas S, Doherty G, \u003cem\u003eet al.\u003c/em\u003e ECCO Guidelines on Therapeutics in Crohn's Disease: Medical Treatment. \u003cem\u003eJ Crohns Colitis\u003c/em\u003e. 2020; 14: 4\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLorenzo Gonz\u0026aacute;lez L, Vald\u0026eacute;s Delgado T, V\u0026aacute;zquez Mor\u0026oacute;n JM, \u003cem\u003eet al.\u003c/em\u003e Ustekinumab in Crohn's disease: real-world outcomes and predictors of response. \u003cem\u003eRev Esp Enferm Dig\u003c/em\u003e. 2022; 114: 272\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGisbert JP, Chaparro M. Predictors of Primary Response to Biologic Treatment [Anti-TNF, Vedolizumab, and Ustekinumab] in Patients With Inflammatory Bowel Disease: From Basic Science to Clinical Practice. \u003cem\u003eJ Crohns Colitis\u003c/em\u003e. 2020; 14: 694\u0026ndash;709.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWaljee AK, Wallace BI, Cohen-Mekelburg S, \u003cem\u003eet al.\u003c/em\u003e Development and Validation of Machine Learning Models in Prediction of Remission in Patients With Moderate to Severe Crohn Disease. \u003cem\u003eJAMA Network Open\u003c/em\u003e. 2019; 2: e193721-e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRimola J, Torres J, Kumar S, Taylor SA, Kucharzik T. Recent advances in clinical practice: advances in cross-sectional imaging in inflammatory bowel disease. \u003cem\u003eGut\u003c/em\u003e. 2022; 71: 2587\u0026ndash;97.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTariq R, Dilmaghani S. Machine Learning and Radiomics: Changing the Horizon of Crohn's Disease Assessment. \u003cem\u003eInflamm Bowel Dis\u003c/em\u003e. 2024; 30: 1919\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. \u003cem\u003eRadiology\u003c/em\u003e. 2015; 278: 563\u0026ndash;77.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSilverberg MS, Satsangi J, Ahmad T, \u003cem\u003eet al.\u003c/em\u003e Toward an integrated clinical, molecular and serological classification of inflammatory bowel disease: report of a Working Party of the 2005 Montreal World Congress of Gastroenterology. \u003cem\u003eCan J Gastroenterol\u003c/em\u003e. 2005; 19 Suppl A: 5a-36a.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang H, Li B, Guo Q, \u003cem\u003eet al.\u003c/em\u003e Systematic review with meta-analysis: loss of response and requirement of ustekinumab dose escalation in inflammatory bowel diseases. \u003cem\u003eAliment Pharmacol Ther\u003c/em\u003e. 2022; 55: 764\u0026ndash;77.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMa C, Hussein IM, Al-Abbar YJ, \u003cem\u003eet al.\u003c/em\u003e Heterogeneity in Definitions of Efficacy and Safety Endpoints for Clinical Trials of Crohn's Disease: A Systematic Review. \u003cem\u003eClin Gastroenterol Hepatol\u003c/em\u003e. 2018; 16: 1407-19.e22.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHall\u0026eacute; E, Azahaf M, Duveau N, \u003cem\u003eet al.\u003c/em\u003e Radiological Response Is Associated with Better Outcomes and Should Be Considered a Therapeutic Target in Crohn\u0026rsquo;s Disease. \u003cem\u003eDig Dis Sci\u003c/em\u003e. 2019.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang Y, Luo Z, Zhou Z, \u003cem\u003eet al.\u003c/em\u003e CT-based radiomics signature of visceral adipose tissue and bowel lesions for identifying patients with Crohn's disease resistant to infliximab. \u003cem\u003eInsights Imaging\u003c/em\u003e. 2024; 15: 28.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBruining DH, Zimmermann EM, Loftus EV, Sandborn WJ, Sauer CG, Strong SA. Consensus Recommendations for Evaluation, Interpretation, and Utilization of Computed Tomography and Magnetic Resonance Enterography in Patients With Small Bowel Crohn's Disease. \u003cem\u003eGastroenterology\u003c/em\u003e. 2018; 154: 1172\u0026ndash;94.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZwanenburg A, Valli\u0026egrave;res M, Abdalah MA, \u003cem\u003eet al.\u003c/em\u003e The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. \u003cem\u003eRadiology\u003c/em\u003e. 2020; 295: 328\u0026ndash;38.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Griethuysen JJM, Fedorov A, Parmar C, \u003cem\u003eet al.\u003c/em\u003e Computational Radiomics System to Decode the Radiographic Phenotype. \u003cem\u003eCancer Research\u003c/em\u003e. 2017; 77: e104-e7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVittinghoff E, McCulloch CE. Relaxing the rule of ten events per variable in logistic and Cox regression. \u003cem\u003eAm J Epidemiol\u003c/em\u003e. 2007; 165: 710\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Smeden M, de Groot JA, Moons KG, \u003cem\u003eet al.\u003c/em\u003e No rationale for 1 variable per 10 events criterion for binary logistic regression analysis. \u003cem\u003eBMC Med Res Methodol\u003c/em\u003e. 2016; 16: 163.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLimberg B, Osswald B. Diagnosis and differential diagnosis of ulcerative colitis and Crohn's disease by hydrocolonic sonography. \u003cem\u003eAm J Gastroenterol\u003c/em\u003e. 1994; 89: 1051\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMeserve J, Ma C, Dulai PS, Jairath V, Singh S. Effectiveness of Reinduction and/or Dose Escalation of Ustekinumab in Crohn's Disease: A Systematic Review and Meta-analysis. \u003cem\u003eClin Gastroenterol Hepatol\u003c/em\u003e. 2022; 20: 2728-40.e1.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi X, Zhong Y, Yuan C, \u003cem\u003eet al.\u003c/em\u003e Identifying patients with Crohn's disease at high risk of primary nonresponse to infliximab using a radiomic-clinical model. \u003cem\u003eInternational Journal of Intelligent Systems\u003c/em\u003e. 2022; 37: 11853\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChen Y, Li H, Feng J, Suo S, Feng Q, Shen J. A Novel Radiomics Nomogram for the Prediction of Secondary Loss of Response to Infliximab in Crohn's Disease. \u003cem\u003eJ Inflamm Res\u003c/em\u003e. 2021; 14: 2731\u0026ndash;40.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhu C, Yu Y, Wang S, \u003cem\u003eet al.\u003c/em\u003e A Novel Clinical Radiomics Nomogram to Identify Crohn's Disease from Intestinal Tuberculosis. \u003cem\u003eJ Inflamm Res\u003c/em\u003e. 2021; 14: 6511\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhu C, Wang X, Wang S, \u003cem\u003eet al.\u003c/em\u003e Development and validation of a clinical radiomics nomogram to predict secondary loss of response to infliximab in Crohn's disease patients. \u003cem\u003eHeliyon\u003c/em\u003e. 2023; 9: e14594.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSong F, Ma M, Zeng S, \u003cem\u003eet al.\u003c/em\u003e CT enterography-based radiomics combined with body composition to predict infliximab treatment failure in Crohn's disease. \u003cem\u003eRadiol Med\u003c/em\u003e. 2024; 129: 175\u0026ndash;87.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLambin P, Rios-Velazquez E, Leijenaar R, \u003cem\u003eet al.\u003c/em\u003e Radiomics: extracting more information from medical images using advanced feature analysis. \u003cem\u003eEur J Cancer\u003c/em\u003e. 2012; 48: 441\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMa C, Battat R, Parker CE, Khanna R, Jairath V, Feagan BG. Update on C-reactive protein and fecal calprotectin: are they accurate measures of disease activity in Crohn's disease? \u003cem\u003eExpert Rev Gastroenterol Hepatol\u003c/em\u003e. 2019; 13: 319\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMaaser C, Sturm A, Vavricka SR, \u003cem\u003eet al.\u003c/em\u003e ECCO-ESGAR Guideline for Diagnostic Assessment in IBD Part 1: Initial diagnosis, monitoring of known IBD, detection of complications. \u003cem\u003eJ Crohns Colitis\u003c/em\u003e. 2019; 13: 144\u0026ndash;64.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJovani M, Danese S. Vedolizumab for the treatment of IBD: a selective therapeutic approach targeting pathogenic a4b7 cells. \u003cem\u003eCurr Drug Targets\u003c/em\u003e. 2013; 14: 1433\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"abdominal-radiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aima","sideBox":"Learn more about [Abdominal Radiology](http://link.springer.com/journal/261)","snPcode":"261","submissionUrl":"https://submission.springernature.com/new-submission/261/3","title":"Abdominal Radiology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Crohn's disease, Ustekinumab, CT‑based radiomics, Treatment response","lastPublishedDoi":"10.21203/rs.3.rs-7441161/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7441161/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eObjectives\u003c/h2\u003e\u003cp\u003eUstekinumab is a biological treatment for Crohn's disease, but some patients do not respond. This study aimed to assess the role of radiomic techniques in predicting the treatment response by quantifying transmural inflammation in Crohn's disease.\u003c/p\u003e\u003ch2\u003eMaterials and Methods\u003c/h2\u003e\u003cp\u003eA total of 296 patients (training cohort, n\u0026thinsp;=\u0026thinsp;207; testing cohort, n\u0026thinsp;=\u0026thinsp;89) were retrospectively recruited. Manual segmentation of 3D volumes of interest (VOIs) encompassing inflamed bowel wall segments was performed on arterial-phase CT enterography scans, from which radiomic features were extracted. Following feature dimensionality reduction via Pearson correlation filtering (threshold\u0026thinsp;\u0026gt;\u0026thinsp;0.9) and recursive feature elimination, the least absolute shrinkage and selection operator (LASSO) logistic regression was utilized as a classifier to construct a radiomic signature. Subsequently, to leverage both radiomic and clinical information for optimal prediction, the radiomic signature was integrated with clinically accessible variables (C-reactive protein level, prior biologic exposure) to develop a model predicting UST efficacy at 16 weeks. The predictive performance was compared using the area under the curve (AUC) and calibration curve analysis. Clinical utility was assessed by decision curve analysis.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThe radiomic signature, based on 1,288 features, was an independent risk factor for Ustekinumab response, with area under the curve values of 0.819 in the training cohort and 0.791 in the testing cohort. An integrated model combining the radiomic signature, C-reactive protein levels, and prior biologics exposure achieved area under the curve values of 0.847 and 0.801, respectively. The model demonstrated good calibration and clinical benefit.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eThe baseline radiomic signature is a promising biomarker for predicting Ustekinumab treatment efficacy in Crohn's disease.\u003c/p\u003e","manuscriptTitle":"CT‑based radiomics of bowel wall at baseline predicts the efficacy of Ustekinumab at week 16 in patients with Crohn’s disease","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-03 23:57:51","doi":"10.21203/rs.3.rs-7441161/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-07T02:57:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-07T01:49:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-03T17:07:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"178784561871391478801106019658926489322","date":"2025-08-27T12:30:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34451082574210494491078448248222844808","date":"2025-08-27T04:03:51+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-27T03:42:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-26T02:29:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-26T02:28:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Abdominal Radiology","date":"2025-08-23T11:59:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"abdominal-radiology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"aima","sideBox":"Learn more about [Abdominal Radiology](http://link.springer.com/journal/261)","snPcode":"261","submissionUrl":"https://submission.springernature.com/new-submission/261/3","title":"Abdominal Radiology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d82be76b-ac2e-4df2-ad61-c0d436f99b3b","owner":[],"postedDate":"September 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-01T16:05:21+00:00","versionOfRecord":{"articleIdentity":"rs-7441161","link":"https://doi.org/10.1007/s00261-025-05247-6","journal":{"identity":"abdominal-radiology","isVorOnly":false,"title":"Abdominal Radiology"},"publishedOn":"2025-11-24 15:58:46","publishedOnDateReadable":"November 24th, 2025"},"versionCreatedAt":"2025-09-03 23:57:51","video":"","vorDoi":"10.1007/s00261-025-05247-6","vorDoiUrl":"https://doi.org/10.1007/s00261-025-05247-6","workflowStages":[]},"version":"v1","identity":"rs-7441161","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7441161","identity":"rs-7441161","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}