Developing a prediction model based on MRI for pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer

2019 ◽  
Vol 44 (9) ◽  
pp. 2978-2987 ◽  
Author(s):  
Lijuan Wan ◽  
Chongda Zhang ◽  
Qing Zhao ◽  
Yankai Meng ◽  
Shuangmei Zou ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Prediction Model ◽  
Pathological Complete Response ◽  
Locally Advanced ◽  
Neoadjuvant Chemoradiotherapy ◽  
Complete Response ◽  
Advanced Rectal Cancer ◽  
Locally Advanced Rectal Cancer ◽  
Model Based

scholarly journals Machine Learning for Predicting Pathological Complete Response in Patients with Locally Advanced Rectal Cancer after Neoadjuvant Chemoradiotherapy

2020 ◽  
Author(s):  
Chun-Ming Huang ◽  
Ming-Yii Huang ◽  
Ching-Wen Huang ◽  
Hsiang-Lin Tsai ◽  
Wei-Chih Su ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Pathological Complete Response ◽  
Locally Advanced ◽  
Neoadjuvant Chemoradiotherapy ◽  
Complete Response ◽  
Advanced Rectal Cancer ◽  
Locally Advanced Rectal Cancer ◽  
Support Vector ◽  
Ann Model ◽  
Data Set

Abstract BACKGROUND For patients with locally advanced rectal cancer (LARC), achieving pathological complete response (pCR) after neoadjuvant chemoradiotherapy (CRT) results in best prognosis. So far, no reliable prediction model has been available. We aim to evaluate the performance of an artificial neural network (ANN) model in the prediction of pCR in patients with LARC. METHODS Predictive accuracy was compared between the ANN, k-earest neighbor (KNN), support vector machines (SVM), naïve Bayes classifier (NBC), and multiple logistic regression (MLR) models. RESULTS A total of 236 patients with LARC were used to compare the forecasting models. We trained the model with an estimation data set, and evaluated model performance with a validation data set. The ANN model significantly outperformed the KNN, SVM, NBC, and MLR models in predicting pCR. Our results revealed that post-CRT carcinoembryonic antigen was the most influential predictor of pCR, followed by intervals between CRT and surgery, chemotherapy regimens, clinical nodal stage, and clinical tumor stage. CONCLUSIONS Compared with conventional prediction models, the ANN model was more accurate in the prediction of pCR. The predictors of pCR can be used to identify which patients with LARC can benefit from watch-and-wait approaches.

scholarly journals Predictive Value of FOLFOX-Based Regimen, Long Interval, Hemoglobin Levels and Clinical Negative Nodal Status, and Postchemoradiotherapy CEA Levels for Pathological Complete Response in Patients with Locally Advanced Rectal Cancer after Neoadjuvant Chemoradiotherapy

2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Chun-Ming Huang ◽  
Ching-Wen Huang ◽  
Cheng-Jen Ma ◽  
Yung-Sung Yeh ◽  
Wei-Chih Su ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Pathological Complete Response ◽  
Locally Advanced ◽  
Neoadjuvant Chemoradiotherapy ◽  
Radical Resection ◽  
Complete Response ◽  
Advanced Rectal Cancer ◽  
Locally Advanced Rectal Cancer ◽  
Multimodality Therapy ◽  
Good Agreement

We aimed to identify predictors of a pathological complete response (pCR) in patients with locally advanced rectal cancer (LARC) following a multimodality therapy. We retrospectively reviewed 236 patients with LARC treated with neoadjuvant chemoradiotherapy (CRT) followed by radical resection from January 2011 to December 2017. Patients were administered CRT, which comprised radiotherapy and chemotherapy with an oxaliplatin plus 5-fluorouracil- or fluoropyrimidine-based regimen. Clinical factors were correlated with treatment response. The multivariate logistic regression revealed that a negative nodal stage (odds ratio (OR) = 3.2, P=0.0135), a high hemoglobin level (>10 g/dL) during neoadjuvant CRT (OR = 3.067, P=0.0125), an oxaliplatin-containing neoadjuvant CRT (OR = 5.385, P=0.0044), a long interval (>8 weeks) between radiotherapy and surgery (OR = 1.135, P=0.0469), and a post-CRT CEA ≤2 ng/mL (OR = 2.891, P=0.0233) were the independent predictors of increased pCR rates. The prediction nomogram was developed according to the above independent variables. The concordance index was 0.74, and the calibration curve showed good agreement. In summary, negative nodal stages, high hemoglobin levels during treatment, oxaliplatin-containing neoadjuvant therapy, a long radiotherapy-surgery interval (>8 weeks), and post-CRT CEA levels ≤2 ng/mL were favorable predictors of a pCR. This prediction nomogram might be crucial for patients with LARC undergoing a multimodality therapy.

Sign in / Sign up

Export Citation Format

Share Document