Preoperative Clinical and Computed Tomography (CT)-Based Nomogram to Predict Oncologic Outcomes in Patients with Pancreatic Head Cancer Resected with Curative Intent: A Retrospective Study

Glucose-to-Lymphocyte Ratio (GLR) as an Independent Prognostic Factor in Patients with Resected Pancreatic Ductal Adenocarcinoma-Cohort Study

Background: We retrospectively evaluated the usefulness of an elevated glucose-to-lymphocyte ratio (GLR) as a sensitive prognostic biomarker of disease-specific survival in 338 patients who underwent surgical resection of pancreatic ductal adenocarcinoma (PDAC). Methods: The optimal GLR cutoff value was determined using the method of Contal and O'Quigley. Patient demographics, clinical information, and imaging data were analyzed to identify preoperative predictors of long-term survival outcomes. Results: Elevated GLR correlated significantly with aggressive tumor biologic behaviors, such as a high carbohydrate antigen (CA) 19-9 level (p = 0.003) and large tumor size (p = 0.011). Multivariate analysis identified (1) GLR > 92.72 [hazard ratio (HR) = 2.475, p < 0.001], (2) CA 19-9 level > 145.35 (HR = 1.577, p = 0.068), and (3) symptoms (p = 0.064) as independent predictors of long-term, cancer-specific survival. These three risk factors were used to group patients into groups 1 (0 factors), 2 (1-2 factors), and 3 (3 factors), which corresponded to significantly different 5-year overall survival rates (50.2%, 34.6%, and 11.7%, respectively; p < 0.001). Conclusions: An elevated preoperative GLR is associated with aggressive tumor characteristics and is an independent predictor of poor postoperative prognosis in patients with PDAC. Further prospective studies are required to verify these findings.

Preoperative prediction of disease-free survival in pancreatic ductal adenocarcinoma patients after R0 resection using contrast-enhanced CT and CA19-9

OBJECTIVES

To investigate the efficiency of a combination of preoperative contrast-enhanced computed tomography (CECT) and carbohydrate antigen 19-9 (CA19-9) in predicting disease-free survival (DFS) after R0 resection of pancreatic ductal adenocarcinoma (PDAC).

METHODS

A total of 138 PDAC patients who underwent curative R0 resection were retrospectively enrolled and allocated chronologically to training (n = 91, January 2014-July 2019) and validation cohorts (n = 47, August 2019-December 2020). Using univariable and multivariable Cox regression analyses, we constructed a preoperative clinicoradiographic model based on the combination of CECT features and serum CA19-9 concentrations, and validated it in the validation cohort. The prognostic performance was evaluated and compared with that of postoperative clinicopathological and tumor-node-metastasis (TNM) models. Kaplan-Meier analysis was conducted to verify the preoperative prognostic stratification performance of the proposed model.

RESULTS

The preoperative clinicoradiographic model included five independent prognostic factors (tumor diameter on CECT > 4 cm, extrapancreatic organ infiltration, CECT-reported lymph node metastasis, peripheral enhancement, and preoperative CA19-9 levels > 180 U/mL). It better predicted DFS than did the postoperative clinicopathological (C-index, 0.802 vs. 0.787; p < 0.05) and TNM (C-index, 0.802 vs. 0.711; p < 0.001) models in the validation cohort. Low-risk patients had significantly better DFS than patients at the high-risk, defined by the model preoperatively (p < 0.001, training cohort; p < 0.01, validation cohort).

CONCLUSIONS

The clinicoradiographic model, integrating preoperative CECT features and serum CA19-9 levels, helped preoperatively predict postsurgical DFS for PDAC and could facilitate clinical decision-making.

CLINICAL RELEVANCE STATEMENT

We constructed a simple model integrating clinical and radiological features for the prediction of disease-free survival after curative R0 resection in patients with pancreatic ductal adenocarcinoma; this novel model may facilitate preoperative identification of patients at high risk of recurrence and metastasis that may benefit from neoadjuvant treatments.

KEY POINTS

• Existing clinicopathological predictors for prognosis in pancreatic ductal adenocarcinoma (PDAC) patients who underwent R0 resection can only be ascertained postoperatively and do not allow preoperative prediction. • We constructed a clinicoradiographic model, using preoperative contrast-enhanced computed tomography (CECT) features and preoperative carbohydrate antigen 19-9 (CA19-9) levels, and presented it as a nomogram. • The presented model can predict disease-free survival (DFS) in patients with PDAC better than can postoperative clinicopathological or tumor-node-metastasis (TNM) models.

Prediction of postoperative recurrence in resectable pancreatic body/tail adenocarcinoma: a novel risk stratification approach using a CT-based nomogram

OBJECTIVES

To identify prognostic CT features that predict recurrence in patients with resectable pancreatic body/tail adenocarcinoma (PBTA) and construct a CT-based nomogram for preoperative risk stratification.

METHODS

A total of 258 patients with resectable PBTA who underwent upfront surgery were retrospectively enrolled (development cohort, n = 172; validation cohort, n = 86), and their clinical and CT features were analyzed. Stepwise Cox proportional hazard analysis was performed to identify prognostic features and construct a predictive nomogram for recurrence-free survival (RFS). The prognostic performance of the CT-based nomogram was validated and compared to the 8th American Joint Committee on Cancer (AJCC) pathological staging system.

RESULTS

In the development cohort, the following five CT features for predicting recurrence were identified to construct the nomogram: tumor density in the venous phase, tumor necrosis, adjacent organ invasion, splenic vein invasion, and superior mesenteric vein/portal vein abutment. In the validation cohort, the CT-based nomogram showed a concordance index of 0.65 (95% confidence interval: 0.58-0.73), which was higher than the 8th AJCC staging system. The area under the curves of the nomogram for predicting recurrence at 0.5, 1, and 2 years were 0.66, 0.71, and 0.72, respectively. Patients were categorized into high- and low-risk groups with 1-year recurrence probabilities of 0.73 and 0.43, respectively.

CONCLUSIONS

The proposed nomogram provided accurate recurrence risk stratification for patients with resectable PBTA in a preoperative setting and may be used to facilitate clinical decision-making.

CLINICAL RELEVANCE STATEMENT

The proposed CT-based nomogram, based on easily available CT features, may serve as an effective and convenient tool for stratifying further the recurrence risk of patients with pancreatic body/tail adenocarcinoma.

KEY POINTS

• The CT-based nomogram, incorporating five commonly used CT features, successfully preoperatively stratified patients with resectable PBTA into distinct prognosis groups. • Tumor density in the venous phase, tumor necrosis, splenic vein invasion, adjacent organ invasion, and superior mesenteric vein/portal vein abutment were associated with RFS in patients with resectable PBTA. • The CT-based nomogram exhibited better predictive performance for recurrence than the 8th AJCC staging system.

Development and Validation of a Nomogram for Preoperative Prediction of Early Recurrence after Upfront Surgery in Pancreatic Ductal Adenocarcinoma by Integrating Deep Learning and Radiological Variables

Around 80% of pancreatic ductal adenocarcinoma (PDAC) patients experience recurrence after curative resection. We aimed to develop a deep-learning model based on preoperative CT images to predict early recurrence (recurrence within 12 months) in PDAC patients. The retrospective study included 435 patients with PDAC from two independent centers. A modified 3D-ResNet18 network was used for a deep learning model construction. A nomogram was constructed by incorporating deep learning model outputs and independent preoperative radiological predictors. The deep learning model provided the area under the receiver operating curve (AUC) values of 0.836, 0.736, and 0.720 in the development, internal, and external validation datasets for early recurrence prediction, respectively. Multivariate logistic analysis revealed that higher deep learning model outputs (odds ratio [OR]: 1.675; 95% CI: 1.467, 1.950; p < 0.001), cN1/2 stage (OR: 1.964; 95% CI: 1.036, 3.774; p = 0.040), and arterial involvement (OR: 2.207; 95% CI: 1.043, 4.873; p = 0.043) were independent risk factors associated with early recurrence and were used to build an integrated nomogram. The nomogram yielded AUC values of 0.855, 0.752, and 0.741 in the development, internal, and external validation datasets. In conclusion, the proposed nomogram may help predict early recurrence in PDAC patients.

Transcriptomic Profiling Identifies an Exosomal microRNA Signature for Predicting Recurrence Following Surgery in Patients With Pancreatic Ductal Adenocarcinoma

OBJECTIVE

We performed genome-wide expression profiling to develop an exosomal miRNA panel for predicting recurrence following surgery in patients with PDAC.

SUMMARY OF BACKGROUND DATA

Pretreatment risk stratification is essential for offering individualized treatments to patients with PDAC, but predicting recurrence following surgery remains clinically challenging.

METHODS

We analyzed 210 plasma and serum specimens from 4 cohorts of PDAC patients. Using a discovery cohort (n = 25), we performed genome-wide sequencing to identify candidate exosomal miRNAs (exo-miRNAs). Subsequently, we trained and validated the predictive performance of the exo-miRNAs in two clinical cohorts (training cohort: n = 82, validation cohort: n = 57) without neoadjuvant therapy (NAT), followed by a post-NAT clinical cohort (n = 46) as additional validation.

RESULTS

We performed exo-miRNA expression profiling in plasma specimens obtained before any treatment in a discovery cohort. Subsequently we optimized and trained a 6-exo-miRNA risk-prediction model, which robustly discriminated patients with recurrence [area under the curve (AUC): 0.81, 95% confidence interval (CI): 0.70-0.89] and relapse-free survival (RFS, P < 0.01) in the training cohort. The identified exo-miRNA panel was successfully validated in an independent validation cohort (AUC: 0.78, 95% CI: 0.65- 0.88, RFS: P < 0.01), where it exhibited comparable performance in the post-NAT cohort (AUC: 0.72, 95% CI: 0.57-0.85, RFS: P < 0.01) and emerged as an independent predictor for RFS (hazard ratio: 2.84, 95% CI: 1.30-6.20).

CONCLUSIONS

We identified a novel, noninvasive exo-miRNA signature that robustly predicts recurrence following surgery in patients with PDAC; highlighting its potential clinical impact for optimized patient selection and improved individualized treatment strategies.

Perioperative risk of pancreatic head resection-nomogram-based prediction of severe postoperative complications as a decisional aid for clinical practice

PURPOSE

To develop nomograms for pre- and early-postoperative risk assessment of patients undergoing pancreatic head resection.

METHODS

Clinical data from 956 patients were collected in a prospectively maintained database. A test (n = 772) and a validation cohort (n = 184) were randomly generated. Uni- and multi-variate analysis and nomogram construction were performed to predict severe postoperative complications (Clavien-Dindo Grades III-V) in the test cohort. External validation was performed with the validation cohort.

RESULTS

We identified ASA score, indication for surgery, body mass index (BMI), preoperative white blood cell (WBC) count, and preoperative alkaline phosphatase as preoperative factors associated with an increased perioperative risk for complications. Additionally to ASA score, BMI, indication for surgery, and the preoperative alkaline phosphatase, the following postoperative parameters were identified as risk factors in the early postoperative setting: the need for intraoperative blood transfusion, operation time, maximum WBC on postoperative day (POD) 1-3, and maximum serum amylase on POD 1-3. Two nomograms were developed on the basis of these risk factors and showed accurate risk estimation for severe postoperative complications (ROC-AUC-values for Grades III-V-preoperative nomogram: 0.673 (95%, CI: 0.626-0.721); postoperative nomogram: 0.734 (95%, CI: 0.691-0.778); each p ≤ 0.001). Validation yielded ROC-AUC-values for Grades III-V-preoperative nomogram of 0.676 (95%, CI: 0.586-0.766) and postoperative nomogram of 0.677 (95%, CI: 0.591-0.762); each p = 0.001.

CONCLUSION

Easy-to-use nomograms for risk estimation in the pre- and early-postoperative setting were developed. Accurate risk estimation can support the decisional process, especially for IPMN-patients with an increased perioperative risk.

Preoperative recurrence prediction in pancreatic ductal adenocarcinoma after radical resection using radiomics of diagnostic computed tomography

BACKGROUND

The high recurrence rate after radical resection of pancreatic ductal adenocarcinoma (PDAC) leads to its poor prognosis. We aimed to develop a model to preoperatively predict the risk of recurrence based on computed tomography (CT) radiomics and multiple clinical parameters.

METHODS

Datasets were retrospectively collected and analysed of 220 PDAC patients who underwent contrast-enhanced computed tomography (CE-CT) and received radical resection at 3 institutions in China between 2013 and 2017, with 153 from one institution as a training set, the remaining 67 as a validation set. For each patient, CT radiomics features were extracted from intratumoral and peritumoral regions to establish intratumoral, peritumoral and combined radiomics models using artificial neural network (ANN) algorithm. By incorporating clinical factors, radiomics-clinical nomograms were finally built by multivariable logistic regression analysis to predict 1- and 2-year recurrence risk.

FINDINGS

The developed radiomics model integrating intratumoral and peritumoral radiomics features was superior to the conventionally constructed model merely using intratumoral radiomics features. Further, radiomics-clinical nomograms outperformed other models in predicting 1-year recurrence with an area under the receiver operating characteristic curve (AUROC) of 0.916 (95%CI, 0.860-0.955) in the training set and 0.764 (95%CI, 0.644-0.859) in the validation set, and 2-year recurrence with an AUROC of 0.872 (95%CI: 0.809-0.921) in the training set and 0.773 (95%CI, 0.654-0.866) in the validation set.

INTERPRETATION

This study has developed and externally validated a radiomics-clinical nomogram integrating intra- and peritumoral CT radiomics signature as well as clinical factors to predict the recurrence risk of PDAC after radical resection, which will facilitate optimized and individualized treatment strategies.

FUNDING

This work was supported by the National Key R&D Program of China [grant number: 2018YFE0114800], the General Program of National Natural Science Foundation of China [grant number: 81772562, 2017; 81871351, 2018], the Fundamental Research Funds for the Central Universities [grant number: 2021FZZX005-08], and Zhejiang Provincial Key Projects of Technology Research [grant number: WKJ-ZJ-2033].

Multi-institutional development and external validation of machine learning-based models to predict relapse risk of pancreatic ductal adenocarcinoma after radical resection

BACKGROUND

Surgical resection is the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC) and the survival of patients after radical resection is closely related to relapse. We aimed to develop models to predict the risk of relapse using machine learning methods based on multiple clinical parameters.

METHODS

Data were collected and analysed of 262 PDAC patients who underwent radical resection at 3 institutions between 2013 and 2017, with 183 from one institution as a training set, 79 from the other 2 institution as a validation set. We developed and compared several predictive models to predict 1- and 2-year relapse risk using machine learning approaches.

RESULTS

Machine learning techniques were superior to conventional regression-based analyses in predicting risk of relapse of PDAC after radical resection. Among them, the random forest (RF) outperformed other methods in the training set. The highest accuracy and area under the receiver operating characteristic curve (AUROC) for predicting 1-year relapse risk with RF were 78.4% and 0.834, respectively, and for 2-year relapse risk were 95.1% and 0.998. However, the support vector machine (SVM) model showed better performance than the others for predicting 1-year relapse risk in the validation set. And the k neighbor algorithm (KNN) model achieved the highest accuracy and AUROC for predicting 2-year relapse risk.

CONCLUSIONS

By machine learning, this study has developed and validated comprehensive models integrating clinicopathological characteristics to predict the relapse risk of PDAC after radical resection which will guide the development of personalized surveillance programs after surgery.

Applying a radiomics-based strategy to preoperatively predict lymph node metastasis in the resectable pancreatic ductal adenocarcinoma

PURPOSE

This retrospective study is designed to develop a Radiomics-based strategy for preoperatively predicting lymph node (LN) status in the resectable pancreatic ductal adenocarcinoma (PDAC) patients.

METHODS

Eighty-five patients with histopathological confirmed PDAC are included, of which 35 are LN metastasis positive and 50 are LN metastasis negative. Initially, 1,124 radiomics features are computed from CT images of each patient. After a series of feature selection, a Radiomics logistic regression (LOG) model is developed. Subsequently, the predictive efficiency of the model is validated using a leave-one-out cross-validation method. The model performance is evaluated on discrimination and compared with the conventional CT evaluation method based on subjective CT image features.

RESULTS

Radiomics LOG model is developed based on eight most related radiomics features. Remarkable differences are demonstrated between patients with LN metastasis positive and LN metastasis negative in Radiomics LOG scores namely, 0.535±1.307 (mean±standard deviation) vs. -1.514±1.800 (mean±standard deviation) with p < 0.001. Radiomics LOG model shows significantly higher predictive efficiency compared to the conventional evaluation method of LN status in which areas under ROC curves are AUC = 0.841 with 95% confidence interval (CI: 0.758∼0.925) vs. AUC = 0.682 with (95% CI: 0.566∼0.798). Leave-one-out cross validation indicates that the Radiomics LOG model correctly classifies 70.3% cases, while the conventional CT evaluation method only correctly classifies 57.0% cases.

CONCLUSION

A radiomics-based strategy provides an individualized LN status evaluation in PDAC patients, which may help clinicians implement an optimal personalized patient treatment.