scholarly journals Application of Data Mining for the Prediction of Mortality and Occurrence of Complications for Gastric Cancer Patients

Entropy ◽  
2019 ◽  
Vol 21 (12) ◽  
pp. 1163 ◽  
Author(s):  
Cristiana Neto ◽  
Maria Brito ◽  
Vítor Lopes ◽  
Hugo Peixoto ◽  
António Abelha ◽  
...  

The development of malign cells that can grow in any part of the stomach, known as gastric cancer, is one of the most common causes of death worldwide. In order to increase the survival rate in patients with this condition, it is essential to improve the decision-making process leading to a better and more efficient selection of treatment strategies. Nowadays, with the large amount of information present in hospital institutions, it is possible to use data mining algorithms to improve the healthcare delivery. Thus, this study, using the CRISP methodology, aims to predict not only the mortality associated with this disease, but also the occurrence of any complication following surgery. A set of classification models were tested and compared in order to improve the prediction accuracy. The study showed that, on one hand, the J48 algorithm using oversampling is the best technique to predict the mortality in gastric cancer patients, with an accuracy of approximately 74%. On the other hand, the rain forest algorithm using oversampling presents the best results when predicting the possible occurrence of complications among gastric cancer patients after their in-hospital stays, with an accuracy of approximately 83%.

Life ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1304
Author(s):  
Evangelos Koustas ◽  
Eleni-Myrto Trifylli ◽  
Panagiotis Sarantis ◽  
Nikolaos I. Kontolatis ◽  
Christos Damaskos ◽  
...  

Gastric cancer is the fifth most common malignancy and the third leading cause of cancer-related death worldwide. The three entirely variable entities have distinct epidemiology, molecular characteristics, prognosis, and strategies for clinical management. However, many gastric tumors appear to be resistant to current chemotherapeutic agents. Moreover, a significant number of gastric cancer patients, with a lack of optimal treatment strategies, have reduced survival. In recent years, multiple research data have highlighted the importance of autophagy, an essential catabolic process of cytoplasmic component digestion, in cancer. The role of autophagy as a tumor suppressor or tumor promoter mechanism remains controversial. The multistep nature of the autophagy process offers a wide array of targetable points for designing novel chemotherapeutic strategies. The purpose of this review is to summarize the current knowledge regarding the interplay between gastric cancer development and the autophagy process and decipher the role of autophagy in this kind of cancer. A plethora of different agents that direct or indirect target autophagy may be a novel therapeutic approach for gastric cancer patients.


2018 ◽  
Vol 36 (4_suppl) ◽  
pp. 123-123
Author(s):  
Magdalena Mydlowska ◽  
Sebastian Rybski ◽  
Zuzanna Guzel ◽  
Katarzyna Kokoszyńska ◽  
Lucjan Wyrwicz

123 Background: In the western world gastric cancer patients are either treated with peri-operative chemotherapy or adjuvant chemoradiation and no direct comparisons of these two treatment strategies are available. In our referral gastric cancer center (MSCMCC) we have changed in January 2013 the treatment protocol from adjuvant chemoradiation (like in INT-0116 study) to peri-operative chemotherapy (ECF or CF regimen). Here we report the updated results of single institution indirect comparison of two treatment strategies in the treatment of gastric cancer patients. Methods: 139 consecutive pts who underwent gastrectomy between 2009-2015 treated at MSCMCC were identified in a cohort manner (2009-2012 radiochemotherapy: 60 pts; 2013-2015- peri-operative chemotherapy: 79 pts). The patients’ clinical characteristics were collected from medical records. All patients were followed for relapse and survival with median observation time of 57 and 17 months for chemoradiation and peri-operative chemotherapy respectively. Results: The patients’ characteristics were similar in two groups including, age, sex, ECOG status and Lauren-classification types. DFS was similar in both arms with 47% of patients in radiochemotherapy and 63% of peri-operative chemotherapy patients without relapse at 2 years cut-off (p=0.17). OS was not significantly different between the groups (p=0.783). The toxicity profile was similar in two cohorts, with only leukopenia reported more often in the chemoradiation group (grade 3-4: 43.3% vs 12.3%. p<0.001) and low platelet count (grade 3-4: 6.7% vs 3.7%; p=0.19).There was a trend for excessive mucositis (p=0.067) and diarrhea (p=0.051) in the chemoradiation group. Vomiting more often observed in the peri-operative chemotherapy group (grade 3-4: 29.6% vs 13.3%, p=0.032). Notable, no differences were reported for neutropenia, fatigue and weigth loss. Conclusions: This indirect comparison suggests that results of two modalities are similar in terms of RFS. Further follow up is needed to assess the impact on survival. The toxicity profile favours the peri-operative chemotherapy.


Sign in / Sign up

Export Citation Format

Share Document