A novel nomogram integrating body composition and inflammatory-nutritional markers for predicting postoperative complications in patients with adhesive small bowel obstruction.

Background: Postoperative complications in adhesive small bowel obstruction (ASBO) significantly escalate healthcare costs and prolong hospital stays. This study endeavors to construct a nomogram that synergizes computed tomography (CT) body composition data with inflammatory-nutritional markers to forecast postoperative complications in ASBO. Methods: The study's internal cohort consisted of 190 ASBO patients recruited from October 2017 to November 2021, subsequently partitioned into training (n = 133) and internal validation (n = 57) groups at a 7:3 ratio. An additional external cohort comprised 52 patients. Body composition assessments were conducted at the third lumbar vertebral level utilizing CT images. Baseline characteristics alongside systemic inflammatory responses were meticulously documented. Through univariable and multivariable regression analyses, risk factors pertinent to postoperative complications were identified, culminating in the creation of a predictive nomogram. The nomogram's precision was appraised using the concordance index (C-index) and the area under the receiver operating characteristic (ROC) curve. Results: Postoperative complications were observed in 65 (48.87%), 26 (45.61%), and 22 (42.31%) patients across the three cohorts, respectively. Multivariate analysis revealed that nutrition risk score (NRS), intestinal strangulation, skeletal muscle index (SMI), subcutaneous fat index (SFI), neutrophil-lymphocyte ratio (NLR), and lymphocyte-monocyte ratio (LMR) were independently predictive of postoperative complications. These preoperative indicators were integral to the nomogram's formulation. The model, amalgamating body composition and inflammatory-nutritional indices, demonstrated superior performance: the internal training set exhibited a 0.878 AUC (95% CI, 0.802-0.954), 0.755 accuracy, and 0.625 sensitivity; the internal validation set displayed a 0.831 AUC (95% CI, 0.675-0.986), 0.818 accuracy, and 0.812 sensitivity. In the external cohort, the model yielded an AUC of 0.886 (95% CI, 0.799-0.974), 0.808 accuracy, and 0.909 sensitivity. Calibration curves affirmed a strong concordance between predicted outcomes and actual events. Decision curve analysis substantiated that the model could confer benefits on patients with ASBO. Conclusion: A rigorously developed and validated nomogram that incorporates body composition and inflammatory-nutritional indices proves to be a valuable tool for anticipating postoperative complications in ASBO patients, thus facilitating enhanced clinical decision-making.

Development of MRI-Based Deep Learning Signature for Prediction of Axillary Response After NAC in Breast Cancer.

RATIONALE AND OBJECTIVES: To develop a MRI-based deep learning signature for predicting axillary response after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients. MATERIALS AND METHODS: We enrolled 327 BC patients with axillary lymph node (ALN) metastases receiving axillary operations after NAC. The deep learning features were extracted by ResNet34, which was pretrained by a large, well-annotated dataset from ImageNet. Then we identified deep learning radiomics on magnetic resonance imaging with dynamic contrast enhancement (DCE-MRI) in predicting axillary response after NAC in BC patients. RESULTS: The extraction of 128 deep learning radiomics (DLR) features relied on the DCE-MRI for each patient. After the least absolute shrinkage and selection operator regression analysis, 13, 8, and 21 features remained from the pre-treatment, post-treatment, and combined DCE-MRI, respectively. The DLR signature established based on the combined DCE-MRI achieved good capacity in ALN response after NAC. The support vector machine achieved the best performance with an 0.99 area under the curve (AUC) of (95% confidence interval (CI), 0.98-1.00) and 0.83 (95% CI, 0.73-0.92) in the training and test sets, respectively. The LR model established with clinical parameters represented the best performance with 0.73 AUC (95% CI, 0.62-0.84), 0.73 sensitivity, 0.73 specificity, 0.63 PPV, and 0.81 NPV in the test set, respectively. Finally, the integration of radiomic signature and clinical signature resulted in establishing a predictive radiomic nomogram, with an AUC of 0.99 (95%CI, 0.99-1.00). CONCLUSION: In conclusion, our current study constructed a predictive nomogram through the deep learning method, demonstrating favorable performance in the training and test cohort. The present prognostic model furnishes a precise and objective foundation for directing the surgical strategy toward ALN management in BC patients receiving NAC.

Radiomic model based on magnetic resonance imaging for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer patients.

Purpose: To establish a model combining radiomic and clinicopathological factors based on magnetic resonance imaging to predict pathological complete response (pCR) after neoadjuvant chemotherapy in breast cancer patients. Method: MRI images and clinicopathologic data of 329 eligible breast cancer patients from the Affiliated Hospital of Qingdao University from August 2018 to August 2022 were included in this study. All patients received neoadjuvant chemotherapy (NAC), and imaging examinations were performed before and after NAC. A total of 329 patients were randomly allocated to a training set and a test set at a ratio of 7:3. We mainly studied the following three types of prediction models: radiomic models, clinical models, and clinical-radiomic models. All models were evaluated using subject operating characteristic curve analysis and area under the curve (AUC), decision curve analysis (DCA) and calibration curves. Results: The AUCs of the clinical prediction model, independent imaging model and clinical combined imaging model in the training set were 0.864 0.968 and 0.984, and those in the test set were 0.724, 0.754 and 0.877, respectively. According to DCA and calibration curves, the clinical-radiomic model showed good predictive performance in both the training set and the test set, and we found that we had developed a more concise clinical-radiomic nomogram. Conclusion: We have developed a clinical-radiomic model by integrating radiomic features and clinical factors to predict pCR after NAC in breast cancer patients, thereby contributing to the personalized treatment of patients.