Prediction Model of Long-term Survival After Esophageal Cancer Surgery

Development and Validation of a Nomogram Model for the Risk of Cardiac Death in Patients Treated with Chemotherapy for Esophageal Cancer

The primary cause of mortality in esophageal cancer survivors is cardiac death. Early identification of cardiac mortality risk during chemotherapy for esophageal cancer is crucial for improving the prognosis. We developed and validated a nomogram model to identify patients with high cardiac mortality risk after chemotherapy for esophageal cancer for early screening and clinical decision-making. We randomly allocated 37,994 patients with chemotherapy-treated esophageal cancer into two groups using a 7:3 split ratio: model training (n = 26,598) and validation (n = 11,396). 5- and 10-year survival rates were used as endpoints for model training and validation. Decision curve analysis and the consistency index (C-index) were used to evaluate the model's net clinical advantage. Model performance was evaluated using receiver operating characteristic curves and computing the area under the curve (AUC). Kaplan-Meier survival analysis based on the prognostic index was performed. Patient risk was stratified according to the death probability. Age, surgery, sex, and year were most closely related to cardiac death and used to plot the nomograms. The C-index for the training and validation datasets were 0.669 and 0.698, respectively, indicating the nomogram's net clinical advantage in predicting cardiac death risk at 5 and 10 years. The 5- and 10-year AUCs were 0.753 and 0.772 for the training dataset and 0.778 and 0.789 for the validation dataset, respectively. The accuracy of the model in predicting cardiac death risk was moderate. This nomogram can identify patients at risk of cardiac death after chemotherapy for esophageal cancer at an early stage.

Integration of IDPC Clustering Analysis and Interpretable Machine Learning for Survival Risk Prediction of Patients with ESCC

Precise forecasting of survival risk plays a pivotal role in comprehending and predicting the prognosis of patients afflicted with esophageal squamous cell carcinoma (ESCC). The existing methods have the problems of insufficient fitting ability and poor interpretability. To address this issue, this work proposes a novel interpretable survival risk prediction method for ESCC patients based on extreme gradient boosting improved by whale optimization algorithm (WOA-XGBoost) and shapley additive explanations (SHAP). Given the imbalanced nature of the data set, the adaptive synthetic sampling (ADASYN) is first used to generate the samples with high survival risk. Then, an improved clustering by fast search and find of density peaks (IDPC) algorithm based on cosine distance and K nearest neighbors is used to cluster the patients. Next, the prediction model for each cluster is obtained by WOA-XGBoost and the constructed model is visualized with SHAP to uncover the factors hidden in the structured model and improve the interpretability of the black-box model. Finally, the effectiveness of the proposed scheme is demonstrated by analyzing the data collected from the First Affiliated Hospital of Zhengzhou University. The results of the analysis reveal that the proposed methodology exhibits superior performance, as indicated by the area under the receiver operating characteristic curve (AUROC) of 0.918 and accuracy of 0.881.

The Impact of Pretreatment Esophageal Stenosis on Survival of Esophageal Cancer Patients

BACKGROUND

Little is known about the survival impacts of pretreatment cancerous stenosis on patients with esophageal carcinoma (EC).

METHODS

The clinicopathologic characteristics of patients who underwent surgery for EC between January 2010 and December 2018 were retrospectively reviewed. Esophageal stenosis was defined as present when a thin endoscope could not be passed through the tumor site. The impacts of stenosis on overall survival (OS) and cancer-specific survival (CSS) were evaluated using Cox hazards analysis.

RESULTS

Of the 496 EC patients in this study, 51 (10.3 %) had pretreatment esophageal stenosis. Stenosis was associated with lower body mass index (P < 0.001) and higher pStage (P < 0.001). The 3-year OS rate for the patients with stenosis was significantly poorer than for the patients without stenosis (40.2 % vs 69.6 %; hazard ratio [HR], 2.19; P < 0.001). The survival outcomes, especially CSS, for the patients with stenosis were significantly poorer than for the patients without stenosis for both pStage II-III (P = 0.009) and pStage IV (P = 0.006) disease. The OS and CSS curves were well stratified by the presence of stenosis even in early-stage (pStage II) patients (P = 0.04 and P < 0.01, respectively). Multivariable analysis showed esophageal stenosis, pStage III-IV disease, and non-curative resection to be independently associated with poor OS (HR, 1.61; P = 0.02) and poor CSS (HR,1.67; P = 0.02). Higher pStage was an independent predictor of poor CSS for patients without stenosis, but not for those with stenosis.

CONCLUSIONS

Esophageal carcinoma patients with pretreatment stenosis had significantly poorer survival outcomes, especially poorer CSS, than those without stenosis in both early- and advanced-stage diseases.

Prediction of conditional survival in esophageal cancer in a population-based cohort study

BACKGROUND

The authors aimed to produce a prediction model for survival at any given date after surgery for esophageal cancer (conditional survival), which has not been done previously.

MATERIALS AND METHODS

Using joint density functions, the authors developed and validated a prediction model for all-cause and disease-specific mortality after surgery with esophagectomy, for esophageal cancer, conditional on postsurgery survival time. The model performance was assessed by the area under the receiver operating characteristic curve (AUC) and risk calibration, with internal cross-validation. The derivation cohort was a nationwide Swedish population-based cohort of 1027 patients treated in 1987-2010, with follow-up throughout 2016. This validation cohort was another Swedish population-based cohort of 558 patients treated in 2011-2013, with follow-up throughout 2018.

RESULTS

The model predictors were age, sex, education, tumor histology, chemo(radio)therapy, tumor stage, resection margin status, and reoperation. The medians of AUC after internal cross-validation in the derivation cohort were 0.74 (95% CI: 0.69-0.78) for 3-year all-cause mortality, 0.76 (95% CI: 0.72-0.79) for 5-year all-cause mortality, 0.74 (95% CI: 0.70-0.78) for 3-year disease-specific mortality, and 0.75 (95% CI: 0.72-0.79) for 5-year disease-specific mortality. The corresponding AUC values in the validation cohort ranged from 0.71 to 0.73. The model showed good agreement between observed and predicted risks. Complete results for conditional survival any given date between 1 and 5 years of surgery are available from an interactive web-tool: https://sites.google.com/view/pcsec/home .

CONCLUSION

This novel prediction model provided accurate estimates of conditional survival any time after esophageal cancer surgery. The web-tool may help guide postoperative treatment and follow-up.

Longer interval between neoadjuvant chemoradiotherapy and surgery is associated with improved pathological response, but does not accurately estimate survival in patients with resectable esophageal cancer

Neoadjuvant chemoradiotherapy (nCRT) has been shown to reduce tumor burden and achieve tumor regression in patients with esophageal cancer (ESC). However, the most beneficial time interval between the administration of nCRT and surgery remains unclear. Therefore, the aim of the present study was to explore the association of the duration of time between nCRT and surgery with the prognosis of patients with ESC. Patients with ESC who received nCRT following surgical resection (n=161) were reviewed and divided into the prolonged time interval group (time interval ≥66 days) and the short time interval group (time interval <66 days), according to the median value. Subsequent analysis revealed that the prolonged time interval group achieved a higher pathological complete response (pCR) rate compared with the short time interval group (49.4 vs. 26.3%; P=0.003). Furthermore, multivariate logistic regression analysis showed that it was possible to independently estimate a higher pCR rate based on a prolonged time interval (odds ratio, 2.131; P=0.042). However, no association between a prolonged time interval and disease-free survival (DFS) was detected using Kaplan-Meier curves (P=0.252) or multivariate Cox regression (P=0.607) analyses. Similarly, no association was identified between a prolonged time interval and overall survival (OS; P=0.946) based on Kaplan-Meier curve analysis, and subsequent multivariate Cox regression analyses showed that the time interval also failed to independently estimate OS (P=0.581). Moreover, female sex (P=0.001) and a radiation dose ≥40 Gy (P=0.039) served as independent factors associated with a higher pCR rate, and the pCR rate was an independent predictor of favorable DFS (P=0.002) and OS (P=0.015) rates. In conclusion, the present study revealed that a prolonged time interval from nCRT to surgery was associated with a higher pCR rate, but it failed to estimate the survival profile of patients with ESC.

A clinical prognostic model for patients with esophageal squamous cell carcinoma based on circulating tumor DNA mutation features

Background

Few predictive models have included circulating tumor DNA (ctDNA) indicators to predict prognosis of esophageal squamous cell carcinoma (ESCC) patients. Here, we aimed to explore whether ctDNA can be used as a predictive biomarker in nomogram models to predict the prognosis of patients with ESCC.

Methods

We included 57 patients who underwent surgery and completed a 5-year follow-up. With next-generation sequencing, a 61-gene panel was used to evaluate plasma cell-free DNA and white blood cell genomic DNA from patients with ESCC. We analyzed the relationship between the mutation features of ctDNA and the prognosis of patients with ESCC, identified candidate risk predictors by Cox analysis, and developed nomogram models to predict the 2- and 5-year disease-free survival (DFS) and overall survival (OS). The area under the curve of the receiver operating characteristic (ROC) curve, concordance index (C-index), calibration plot, and integrated discrimination improvement (IDI) were used to evaluate the performance of the nomogram model. The model was compared with the traditional tumor-nodes-metastasis (TNM) staging system.

Results

The ROC curve showed that the average mutant allele frequency (MAF) of ctDNA variants and the number of ctDNA variants were potential biomarkers for predicting the prognosis of patients with ESCC. The predictors included in the models were common candidate predictors of ESCC, such as lymph node stage, angiolymphatic invasion, drinking history, and ctDNA characteristics. The calibration curve demonstrated consistency between the observed and predicted results. Moreover, our nomogram models showed clear prognostic superiority over the traditional TNM staging system (based on C-index, 2-year DFS: 0.82 vs. 0.64; 5-year DFS: 0.78 vs. 0.65; 2-year OS: 0.80 vs. 0.66; 5-year OS: 0.77 vs. 0.66; based on IDI, 2-year DFS: 0.33, p <0.001; 5-year DFS: 0.18, p = 0.04; 2-year OS: 0.28, p <0.001; 5-year OS: 0.15, p = 0.04). The comprehensive scores of the nomogram models could be used to stratify patients with ESCC.

Conclusions

The novel nomogram incorporating ctDNA features may help predict the prognosis of patients with resectable ESCC. This model can potentially be used to guide the postoperative management of ESCC patients in the future, such as adjuvant therapy and follow-up.

Machine learning applications in upper gastrointestinal cancer surgery: a systematic review

BACKGROUND

Machine learning (ML) has seen an increase in application, and is an important element of a digital evolution. The role of ML within upper gastrointestinal surgery for malignancies has not been evaluated properly in the literature. Therefore, this systematic review aims to provide a comprehensive overview of ML applications within upper gastrointestinal surgery for malignancies.

METHODS

A systematic search was performed in PubMed, EMBASE, Cochrane, and Web of Science. Studies were only included when they described machine learning in upper gastrointestinal surgery for malignancies. The Cochrane risk-of-bias tool was used to determine the methodological quality of studies. The accuracy and area under the curve were evaluated, representing the predictive performances of ML models.

RESULTS

From a total of 1821 articles, 27 studies met the inclusion criteria. Most studies received a moderate risk-of-bias score. The majority of these studies focused on neural networks (n = 9), multiple machine learning (n = 8), and random forests (n = 3). Remaining studies involved radiomics (n = 3), support vector machines (n = 3), and decision trees (n = 1). Purposes of ML included predominantly prediction of metastasis, detection of risk factors, prediction of survival, and prediction of postoperative complications. Other purposes were predictions of TNM staging, chemotherapy response, tumor resectability, and optimal therapy.

CONCLUSIONS

Machine Learning algorithms seem to contribute to the prediction of postoperative complications and the course of disease after upper gastrointestinal surgery for malignancies. However, due to the retrospective character of ML studies, these results require trials or prospective studies to validate this application of ML.

Efficacy and safety of camrelizumab in combination with neoadjuvant chemotherapy for ESCC and its impact on esophagectomy

Background

Esophageal squamous cell carcinoma (ESCC) is the most common type of esophageal cancer in China. The use of neoadjuvant immunotherapy for the treatment of ESCC is gradually increasing. Camrelizumab is one such immune checkpoint inhibitor (ICI) used for treatment. In this retrospective study, we explored the efficacy, safety, and short-term perioperative prognosis of camrelizumab in combination with neoadjuvant chemotherapy for ESCC.

Materials and Methods

A total of 254 Chinese patients with ESCC were enrolled in the study; 48 received camrelizumab in combination with neoadjuvant chemotherapy (C-NC group), and 206 received neoadjuvant chemotherapy (NC group). All patients underwent surgery after the completion of 2 cycles of neoadjuvant therapy.

Results

Twenty patients (20/48, 41.7%) in the C-NC group and 22 patients (22/206, 10.7%) in the NC group achieved a pathologic complete response (pCR) (p<0.001). Twenty-nine patients (29/48, 60.4%) in the C-NC group and 56 patients (56/206, 27.2%) in the NC group achieved major pathologic remission (MPR) (p<0.001). There was a lower incidence of myelosuppression during neoadjuvant therapy in patients in the C-NC group (33/48, 68.8%) than in the NC group (174/206, 84.5%, p=0.012). The total incidence of adverse reactions during neoadjuvant therapy was also lower in the C-NC group (37/48, 77.1%) than in the NC group (189/206, 91.7%, p=0.003). Patients in the C-NC group had more lymph nodes cleared during surgery than those in the NC group (34 vs.30, p<0.001). The logistic model showed that the treatment regimen, age, and presence of lymph node metastasis were influential factors for achieving a pCR in these patients (p<0.001). Regarding other adverse events and surgery-related data, there were no significant differences observed between the two groups.

Conclusion

Camrelizumab in combination with neoadjuvant chemotherapy is an efficacious neoadjuvant regimen with an acceptable safety profile and does not increase the difficulty of surgery or the incidence of complications. A pCR is more likely to be achieved in patients treated with camrelizumab in combination with neoadjuvant chemotherapy, in younger patients, or in those without lymph node metastases.

Convolutional neural network-based artificial intelligence for the diagnosis of early esophageal cancer based on endoscopic images: A meta-analysis

BACKGROUND

Early screening and treatment of esophageal cancer (EC) is particularly important for the survival and prognosis of patients. However, early EC is difficult to diagnose by a routine endoscopic examination. Therefore, convolutional neural network (CNN)-based artificial intelligence (AI) has become a very promising method in the diagnosis of early EC using endoscopic images. The aim of this study was to evaluate the diagnostic performance of CNN-based AI for detecting early EC based on endoscopic images.

METHODS

A comprehensive search was performed to identify relevant English articles concerning CNN-based AI in the diagnosis of early EC based on endoscopic images (from the date of database establishment to April 2022). The pooled sensitivity (SEN), pooled specificity (SPE), positive likelihood ratio (LR+), negative likelihood ratio (LR-), diagnostic odds ratio (DOR) with 95% confidence interval (CI), summary receiver operating characteristic (SROC) curve, and area under the curve (AUC) for the accuracy of CNN-based AI in the diagnosis of early EC based on endoscopic images were calculated. We used the I² test to assess heterogeneity and investigated the source of heterogeneity by performing meta-regression analysis. Publication bias was assessed using Deeks' funnel plot asymmetry test.

RESULTS

Seven studies met the eligibility criteria. The SEN and SPE were 0.90 (95% confidence interval [CI]: 0.82-0.94) and 0.91 (95% CI: 0.79-0.96), respectively. The LR+ of the malignant ultrasonic features was 9.8 (95% CI: 3.8-24.8) and the LR- was 0.11 (95% CI: 0.06-0.21), revealing that CNN-based AI exhibited an excellent ability to confirm or exclude early EC on endoscopic images. Additionally, SROC curves showed that the AUC of the CNN-based AI in the diagnosis of early EC based on endoscopic images was 0.95 (95% CI: 0.93-0.97), demonstrating that CNN-based AI has good diagnostic value for early EC based on endoscopic images.

CONCLUSIONS

Based on our meta-analysis, CNN-based AI is an excellent diagnostic tool with high sensitivity, specificity, and AUC in the diagnosis of early EC based on endoscopic images.

Patient and public involvement in oesophageal cancer survivorship research

BACKGROUND

Good clinical research is often conducted in close collaboration between patients, the public, and researchers. Few studies have reported the development of patient and public involvement (PPI) in research outside the United States and the United Kingdom, and for patients with more aggressive cancers. The study aimed to describe and evaluate the development of PPI in oesophageal cancer survivorship research in Sweden by the use of a framework to support the process.

METHODS

Oesophageal cancer survivors were recruited to a PPI research collaboration at Karolinska Institutet, Sweden. The development process was supported by the use of a framework for PPI, 'Patient and service user engagement in research'. Insights, benefits, and challenges of the process were described and discussed among the collaborators.

RESULTS

The collaboration resulted in joint publications with a more patient- and family-focussed perspective. It also contributed to the development of information folders about survivorship after oesophageal cancer surgery and national conference arrangements for patients, their families, healthcare workers, and researchers. Since the PPI contributors were represented in patient organisations and care programmes, the dissemination of research results increased. Their contributions were highly valued by the researchers, but also revealed some challenges. The use of a structured framework contributed to support and facilitated the process of establishing PPI in research collaboration.

CONCLUSIONS

A genuine interest in establishing PPI in research and an understanding and respect for the patients' expertise in providing a unique inside perspective was imperative for a successful collaboration. Research focus should not only be on mortality and reductions in daily life, but also on positive outcomes. Using a framework supports development and avoids pitfalls of PPI collaboration.

PATIENT AND PUBLIC CONTRIBUTION

Patient partners were equal collaborators in all aspects of the study.

Pan-immune-inflammation Value and Prognosis in Patients With Esophageal Cancer

Mini-abstract

The pan-immune-inflammation value was associated with clinical outcomes and tumor-infiltrating lymphocytes in 866 esophageal cancers. Systemic immune competence may influence patient prognosis through local immune response.

Objective

To examine the relationship between the pan-immune-inflammation value (PIV), tumor immunity, and clinical outcomes in 866 patients with esophageal cancer.

Background

The PIV, calculated from all immune-inflammatory cells in the peripheral blood count, is a recently proposed marker for clinical outcomes in some types of cancers. Nonetheless, the prognostic significance of PIV in esophageal cancer remains unclear.

Methods

In the derivation cohort (n = 433), we set the optimal cutoff value using a time-dependent receiver operating characteristic (ROC) curve. In the validation cohort (n = 433), the relationships between the PIV, tumor-infiltrating lymphocytes (TILs), CD8 expression by immunohistochemical staining, and patient prognosis were examined.

Results

The area under the ROC curve for the PIV at 5 years was 0.631 in the derivation cohort. The validation cohort, divided into PIV-low cases (n = 223) and PIV-high cases (n = 210), showed significantly worse overall survival (log-rank P = 0.0065; hazard ratio [HR]: 1.48; 95% confidence interval [CI]: 1.12-1.98; P < 0.001; multivariate HR: 1.41; 95% CI: 1.05-1.90; P = 0.023). The prognostic effect of the PIV was not significantly modified by any clinical characteristics (P for interaction > 0.05). The PIV-high cases were significantly associated with a low TIL status (P < 0.001) and low CD8-positive cell counts (P = 0.011).

Conclusions

The PIV was associated with clinical outcomes in esophageal cancer, supporting its role as a prognostic biomarker. Considering the relationship between the PIV and TILs, systemic immune competence may influence patient prognosis through a local immune response.

Dispositional optimism and all-cause mortality after esophageal cancer surgery: a nationwide population-based cohort study

PURPOSE

To examine the association between dispositional optimism and all-cause mortality after esophageal cancer surgery and whether pathological tumor stage and the COVID-19 pandemic modified this association.

METHODS

This nationwide, population-based prospective cohort study included 335 patients undergoing esophageal cancer surgery in Sweden between January 1, 2013, and December 31, 2019. Dispositional optimism was measured 1 year post-surgery using Life Orientation Test-Revised (LOT-R). A higher LOT-R sum score represents higher dispositional optimism. Mortality information was obtained from the Swedish Register of the Total Population. All patients were followed up until death or until December 31, 2020, whichever occurred first. Cox regression with adjustments for confounders was used.

RESULTS

The median follow-up was 20.8 months, during which 125 (37.3%) patients died. Among the included 335 patients, 219 (65.4%) patients had tumor pathologically staged Tis-II, and 300 (89.6%) patients entered the cohort before the COVID-19 pandemic. Both tumor stage and the COVID-19 pandemic were effect modifiers. For each unit increase in LOT-R sum score, the risk of all-cause mortality decreased by 11% (HR 0.89, 95% CI 0.81 to 0.98) among patients with tumor staged Tis-II before the COVID-19 pandemic. This association was non-significant in patients with tumor staged III-IV (HR 0.99, 95% CI 0.92 to 1.07) and during the COVID-19 pandemic (HR 1.08, 95% CI 0.94 to 1.25).

CONCLUSION

Assessing dispositional optimism may help predict postoperative survival, especially for patients with early and intermediate esophageal cancer. Increasing dispositional optimism might be a potential intervention target to improve survival after esophageal cancer surgery.

Development and external validation of a COVID-19 mortality risk prediction algorithm: a multicentre retrospective cohort study

OBJECTIVE

This study aimed to develop and externally validate a COVID-19 mortality risk prediction algorithm.

DESIGN

Retrospective cohort study.

SETTING

Five designated tertiary hospitals for COVID-19 in Hubei province, China.

PARTICIPANTS

We routinely collected medical data of 1364 confirmed adult patients with COVID-19 between 8 January and 19 March 2020. Among them, 1088 patients from two designated hospitals in Wuhan were used to develop the prognostic model, and 276 patients from three hospitals outside Wuhan were used for external validation. All patients were followed up for a maximal of 60 days after the diagnosis of COVID-19.

METHODS

The model discrimination was assessed by the area under the receiver operating characteristic curve (AUC) and Somers' D test, and calibration was examined by the calibration plot. Decision curve analysis was conducted.

MAIN OUTCOME MEASURES

The primary outcome was all-cause mortality within 60 days after the diagnosis of COVID-19.

RESULTS

The full model included seven predictors of age, respiratory failure, white cell count, lymphocytes, platelets, D-dimer and lactate dehydrogenase. The simple model contained five indicators of age, respiratory failure, coronary heart disease, renal failure and heart failure. After cross-validation, the AUC statistics based on derivation cohort were 0.96 (95% CI, 0.96 to 0.97) for the full model and 0.92 (95% CI, 0.89 to 0.95) for the simple model. The AUC statistics based on the external validation cohort were 0.97 (95% CI, 0.96 to 0.98) for the full model and 0.88 (95% CI, 0.80 to 0.96) for the simple model. Good calibration accuracy of these two models was found in the derivation and validation cohort.

CONCLUSION

The prediction models showed good model performance in identifying patients with COVID-19 with a high risk of death in 60 days. It may be useful for acute risk classification.

WEB CALCULATOR

We provided a freely accessible web calculator (https://www.whuyijia.com/).