The Incidence of Esophageal Cancer in Iran: A Systematic Review and Meta-analysis

Design of risk prediction model for esophageal cancer based on machine learning approach

Background and aim

Esophageal cancer (EC) is a highly prevalent and progressive disease. Early prediction of EC risk in the population is crucial in preventing this disease and enhancing the overall health of individuals. So far, few studies have been conducted on predicting the EC risk based on the prediction models, and most of them focused on statistical methods. The ML approach obtained efficient predictive insights into the clinical domain. Therefore, this study aims to develop a risk prediction model for EC based on risk factors and by leveraging the ML approach to stratify the high-risk EC people and obtain efficient preventive purposes at the community level.

Material and methods

The current retrospective study was performed from 2018 to 2022 in Sari City based on 3256 EC and non-EC cases. The six selected algorithms, including Random Forest (RF), eXtreme Gradient Boosting (XG-Boost), Bagging, K-Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Artificial Neural Networks (ANNs), were used to develop the risk prediction model for EC and achieve the preventive purposes.

Results

Comparing the performance efficiency of algorithms revealed that the XG-Boost model gained the best predictability for EC risk with AU-ROC = 0.92 and AU-ROC-test = 0.889 for internal and validation states, respectively. Based on the XG-Boost, the factors, including sex, drinking hot liquids, fruit consumption, achalasia, and vegetable consumption, were considered the five top predictors of EC risk.

Conclusion

This study showed that the XG-Boost could provide insight into the early prediction of the EC risk for people and clinical providers to stratify the high-risk group of EC and achieve preventive measures based on modifying the risk factors associated with EC and other clinical solutions.

Prediction of five-year survival among esophageal cancer patients using machine learning

Background and aim

Considering the silent progression of esophageal cancer, the survival prediction of this disease is crucial in enhancing the quality of life of these patients globally. So far, no prediction solution has been introduced for the survival of EC in Iran based on the machine learning approach. So, this study aims to develop a prediction model for the five-year survival of EC based on the ML approach to promote clinical outcomes and various treatment and preventive plans.

Material and methods

In this retrospective study, we investigated the 1656 cases of survived and non-survived EC patients belonging to Imam Khomeini Hospital in Sari City from 2013 to 2020. The multivariable regression analysis was used to select the best predictors of five-year survival. We leveraged random forest, eXtreme Gradient Boosting, support vector machine, artificial neural networks, Bayesian networks, J-48 decision tree, and K-nearest neighborhood to develop the prediction models. To get the best model for predicting the five-year survival of EC, we compared them using the area under the receiver operator characteristics.

Results

The age at diagnosis, body mass index, smoking, obstruction, dysphagia, weight loss, lymphadenopathy, chemotherapy, radiotherapy, family history of EC, tumor stage, type of appearance, histological type, grade of differentiation, tumor location, tumor size, lymphatic invasion, vascular invasion, and platelet albumin ratio were considered as the best predictors associated with the five-year survival of EC based on the regression analysis. In this respect, the random forest with the area under the receiver operator characteristics of 0.95 was identified as a superior model.

Conclusion

The experimental results of the current study showed that the random forest could have a significant role in enhancing the quality of care in EC patients by increasing the effectiveness of follow-up and treatment measures introduced by care providers.

Global research trends of artificial intelligence applied in esophageal carcinoma: A bibliometric analysis (2000-2022) via CiteSpace and VOSviewer

Objective

Using visual bibliometric analysis, the application and development of artificial intelligence in clinical esophageal cancer are summarized, and the research progress, hotspots, and emerging trends of artificial intelligence are elucidated.

Methods

On April 7th, 2022, articles and reviews regarding the application of AI in esophageal cancer, published between 2000 and 2022 were chosen from the Web of Science Core Collection. To conduct co-authorship, co-citation, and co-occurrence analysis of countries, institutions, authors, references, and keywords in this field, VOSviewer (version 1.6.18), CiteSpace (version 5.8.R3), Microsoft Excel 2019, R 4.2, an online bibliometric platform (http://bibliometric.com/) and an online browser plugin (https://www.altmetric.com/) were used.

Results

A total of 918 papers were included, with 23,490 citations. 5,979 authors, 39,962 co-cited authors, and 42,992 co-cited papers were identified in the study. Most publications were from China (317). In terms of the H-index (45) and citations (9925), the United States topped the list. The journal “New England Journal of Medicine” of Medicine, General & Internal (IF = 91.25) published the most studies on this topic. The University of Amsterdam had the largest number of publications among all institutions. The past 22 years of research can be broadly divided into two periods. The 2000 to 2016 research period focused on the classification, identification and comparison of esophageal cancer. Recently (2017-2022), the application of artificial intelligence lies in endoscopy, diagnosis, and precision therapy, which have become the frontiers of this field. It is expected that closely esophageal cancer clinical measures based on big data analysis and related to precision will become the research hotspot in the future.

Conclusions

An increasing number of scholars are devoted to artificial intelligence-related esophageal cancer research. The research field of artificial intelligence in esophageal cancer has entered a new stage. In the future, there is a need to continue to strengthen cooperation between countries and institutions. Improving the diagnostic accuracy of esophageal imaging, big data-based treatment and prognosis prediction through deep learning technology will be the continuing focus of research. The application of AI in esophageal cancer still has many challenges to overcome before it can be utilized.

Dietary risk factors for esophageal cancer based on World Health Organization regions

OBJECTIVES

Esophageal cancer (EC) has become one of the most alarming cancers in the world. There are significant differences in incidence and risk factors associated with the two most common histological subtypes of EC, esophageal squamous cell carcinoma and esophageal adenocarcinoma, between regions. This systematic review was undertaken to analyze dietary risk factors specific to EC and its two subtypes based on World Health Organization regions.

METHODS

A systematic search of five databases (Global Health, Google Scholar, PubMed, Scopus, and Web of Science) for the past 5 y (2015-2020) was conducted from March 2020 to July 2020. Titles and abstracts were screened to determine the primary inclusion eligibility, followed by an examination of the full-text articles. Finally, 59 articles were reviewed to identify EC risk factors and compare these by region. Data were extracted using a table developed by the research team. Risk factors found in >50% of regions were highlighted.

RESULTS

The study identified some major dietary risk factors for EC that were previously reported, as well as some uncommon dietary risk factors, such as salty foods and beverages, unpiped drinking water, sugar-related factors (e.g., sweet intake), and foods with high glycemic index.

CONCLUSIONS

EC risk factors extend beyond those previously identified. Targeting all EC risk factors by region will assist the World Health Organization and other health agencies in providing a tailored, culturally appropriate response to effectively reduce the incidence and prevalence of EC within a region.

National and Subnational Cancer Incidence for 22 Cancer Groups, 2000 to 2016: A Study Based on Cancer Registration Data of Iran

BACKGROUND

Cancer is an increasing public health concern, and detailed knowledge of the cancer incidence is required for developing effective cancer control plans. The objective of this study is to present the cancer incidence of 22 cancer groups in Iran and all 31 provinces of the country from 2000 to 2016, for both sexes across different age groups.

METHOD

To study the national and provincial cancer incidence in Iran, we extracted data from the Cancer Project, which collects the Iranian cancer registry data and visualizes it in the VIZIT data visualization system. The methodology and statistical analysis that is used in this study follow the cancer project study protocol. Joinpoint analysis was performed to calculate the average annual percent change of the crude rates and age-standardized rates from 2000 to 2016.

RESULTS

Cancer incidence was 126,982 patients in 2016, and the crude rate (CR) of cancer in both sexes and all ages was 155 per 100,000 people. Cancer incidence approximately doubled between 2000 and 2016; however, the age-standardized rate (ASR) had a less drastic increase. The most incident cancers in 2016 were breast, skin, and colorectal cancers; however, the ranking of cancer groups by incidence was different in different age and sex groups and provinces. Some cancers exhibited a unique distribution pattern in the country with high-incidence local areas. Discussion. The study showed that cancer incidence, crude rate, and age-standardized rate (ASR) in Iran had increased in 2000-2016 with vast heterogeneity by cancer type, province, and sex. Moreover, it was shown that the crude rate of cancer in Iran was much less than the global cancer crude rate. Providing such data helps to allocate resources and develop effective national cancer control plans appropriately.

Clinical, epidemiological, and diagnostic characteristics of esophageal carcinoma in a Pakistani population

BACKGROUND

Esophageal cancer ranks eighth among the most prevalent cancers globally and is the sixth leading cause of mortality from malignancy worldwide; it is the 7th most prevalent malignancy in males and the 6th most prevalent malignancy in females. In Pakistan, the incidence is 4.1 per 100 000 with the province of Baluchistan having the greatest incidence.

OBJECTIVE

Report trends and characteristics of esophageal cancer in Pakistan over the past 10 years.

DESIGN

Cross-sectional, retrospective review of medical records.

SETTING

Tertiary care hospital.

PATIENTS AND METHODS

The study included all patients admitted with a diagnosis of esophageal carcinoma with a mass lesion or luminal narrowing. The records were for the period from January 2011 to September 2020.

MAIN OUTCOME MEASURES

Gender, histopathological types/differentiation along with clinical/laboratory findings.

SAMPLE SIZE

1009 with a mean (standard deviation) age of 49.3 (14.2) and a median (interquartile range of 50 (22) years (443 males and 566 females with age of 51.0 [20] years and 47.9 [23.8] years, respectively). The male-to-female ratio was 1:1.2.

RESULTS

Most patients (82.7%) had squamous cell carcinomas with a male-to-female ratio of 1:2; the remainder had adenocarcinomas with a male-to-female ratio of 4:1 (P<.001). Dysphagia, weight loss, and vomiting were the most prevalent symptoms. More adenocarcinoma masses were located distally compared with squamous cell carcinomas (P=.030), lesions were most likely to be ulcerated (P=.910). Luminal narrowing was slightly more frequent in squamous cell carcinoma (P=.215), thickening was more prominently circumferential in the adenocarcinomas. In squamous cell carcinoma, the most common variant was moderately differentiated while moderate to poorly differentiated variants were more common in adenocarcinoma. In the survival analysis, squamous cell carcinoma (P=.014 vs adenocarcinoma), particularly the well-differentiated type (P=.018 vs other variants), projected a better prognosis.

CONCLUSION

Our study reports the most recent trends of esophageal carcinoma in this region.

LIMITATIONS

Lack of metastatic workup, TNM staging, and mode of treatment, along with the overlapping pattern of histological variants.

CONFLICT OF INTEREST

None.

Effects of medical nutrition therapy compared with general nutritional advice on nutritional status and nutrition-related complications in esophageal cancer patients receiving concurrent chemoradiation: A randomized controlled trial

OBJECTIVE: The purpose of this randomized controlled trial study was to assess the effects of medical nutrition therapy (MNT) compared with general nutritional advice (NA) on nutritional status in esophageal cancer (EC) patients during Chemoradiation (CRT). METHOD: The sample includes one hundred newly diagnosed patients with EC. The MNT group received individualized nutritional therapy. The NA group received general nutritional advice at the beginning of the participation. Patient-Generated- Subjective Global Assessment (PG-SGA), anthropometric indices, body composition, dietary intake, laboratory tests, and nutrition-related complications were assessed. RESULTS: Forty-nine cases were in the MNT group. The MNT group had significantly more favorable energy (26.4±14.1 vs. 18.2±11.2 kcal/kgw.day) and protein (1±0.6 vs. 0.7±0.4 g/kgw.day) intake than the NA group at the final evaluation. The PG-SGA score diminished but not significantly in both groups (11±6 vs. 12±6). As compared to the NA group, patients in the MNT group experienced more frequently no weight loss (21% vs. 11%) or mild weight loss (40% vs 35%) during the treatment. Meanwhile, moderate weight loss was more frequently observed in the NA group (26% vs. 44%). In the MNT group, those with severe weight loss had not proper adherence to the nutritional protocol. Mid-upper arm circumference, body composition, laboratory tests, physical performance, and nutrition-related complications were not significantly different between the two groups. CONCLUSION: As compared to general NA, MNT improved energy and macronutrients intake in patients with EC undergoing CRT which resulted in less severe weight loss and potentially better nutritional status.

Trends in Mortality Rates for Gastrointestinal Cancers in Fars Province, Iran (2005-2015)

PURPOSE

In Iran, cancers are the third leading cause of death, and gastrointestinal cancers are the primary cause of mortality among all the cancers. This study aimed to determine the trend of crude and age-standardized mortality rates (ASMR) for different types of gastrointestinal cancers over an 11-year period in Fars province (Iran).

METHODS

In this study, all the mortality data for gastrointestinal cancers were derived from the Electronic Death Registration System (EDRS) between 2005 and 2015. Subsequently, we calculated the crude and age-standardized mortality rates (ASMR) and their trends for different types of gastrointestinal cancers based on age groups and gender over the study period.

RESULTS

A total of 6547 deaths from gastrointestinal cancers were identified, with an average age of 66.0 ± 16.4 years. The crude and age-standardized mortality rates for gastrointestinal cancers were respectively 10.9 and 15.0 per 100,000 population in 2005 which significantly increased to 17.4 and 19.4 per 100,000 population in 2015 (P < 0.001). The ASMR for colon, pancreatic, and oral cancers showed an increasing trend; for small intestine cancers, a decreasing trend; and for esophageal, gastric, rectal, and hepatobiliary cancers displayed an almost constant trend.

CONCLUSIONS

Our study shows a higher ASMR and an increasing trend of gastrointestinal cancers in Fars province. Prevention and early diagnosis programs with screening techniques should be implemented to control the mortality rate of gastrointestinal cancers in the future.