Predictive model for survival in patients with gastric cancer
Background and aim: Gastric cancer is one of the most prevalent cancers in the world. Characterized by poor prognosis, it is a frequent cause of cancer in Iran. The aim of the study was to design a predictive model of survival time for patients suffering from gastric cancer. Methods: This was a h...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronic Physician
2017-12-01
|
| Series: | Electronic Physician |
| Subjects: | |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5843431/ |
| _version_ | 1818298558108925952 |
|---|---|
| author | Ladan Goshayeshi Benyamin Hoseini Zahra Yousefli Alireza Khooie Kobra Etminani Abbas Esmaeilzadeh Amin Golabpour |
| author_facet | Ladan Goshayeshi Benyamin Hoseini Zahra Yousefli Alireza Khooie Kobra Etminani Abbas Esmaeilzadeh Amin Golabpour |
| author_sort | Ladan Goshayeshi |
| collection | DOAJ |
| description | Background and aim: Gastric cancer is one of the most prevalent cancers in the world. Characterized by poor
prognosis, it is a frequent cause of cancer in Iran. The aim of the study was to design a predictive model of survival
time for patients suffering from gastric cancer.
Methods: This was a historical cohort conducted between 2011 and 2016. Study population were 277 patients
suffering from gastric cancer. Data were gathered from the Iranian Cancer Registry and the laboratory of Emam
Reza Hospital in Mashhad, Iran. Patients or their relatives underwent interviews where it was needed. Missing
values were imputed by data mining techniques. Fifteen factors were analyzed. Survival was addressed as a
dependent variable. Then, the predictive model was designed by combining both genetic algorithm and logistic
regression. Matlab 2014 software was used to combine them.
Results: Of the 277 patients, only survival of 80 patients was available whose data were used for designing the
predictive model. Mean ± SD of missing values for each patient was 4.43±1.41 combined predictive model
achieved 72.57% accuracy. Sex, birth year, age at diagnosis time, age at diagnosis time of patients’ family, family
history of gastric cancer, and family history of other gastrointestinal cancers were six parameters associated with
patient survival.
Conclusion: The study revealed that imputing missing values by data mining techniques have a good accuracy.
And it also revealed six parameters extracted by genetic algorithm effect on the survival of patients with gastric
cancer. Our combined predictive model, with a good accuracy, is appropriate to forecast the survival of patients
suffering from Gastric cancer. So, we suggest policy makers and specialists to apply it for prediction of patients’
survival. |
| first_indexed | 2024-12-13T04:37:14Z |
| format | Article |
| id | doaj.art-fe2d8bcc5f21416388d2e38dfef97dec |
| institution | Directory Open Access Journal |
| issn | 2008-5842 2008-5842 |
| language | English |
| last_indexed | 2024-12-13T04:37:14Z |
| publishDate | 2017-12-01 |
| publisher | Electronic Physician |
| record_format | Article |
| series | Electronic Physician |
| spelling | doaj.art-fe2d8bcc5f21416388d2e38dfef97dec2022-12-21T23:59:25ZengElectronic PhysicianElectronic Physician2008-58422008-58422017-12-019126035604210.19082/6035Predictive model for survival in patients with gastric cancerLadan GoshayeshiBenyamin HoseiniZahra YousefliAlireza KhooieKobra EtminaniAbbas EsmaeilzadehAmin GolabpourBackground and aim: Gastric cancer is one of the most prevalent cancers in the world. Characterized by poor prognosis, it is a frequent cause of cancer in Iran. The aim of the study was to design a predictive model of survival time for patients suffering from gastric cancer. Methods: This was a historical cohort conducted between 2011 and 2016. Study population were 277 patients suffering from gastric cancer. Data were gathered from the Iranian Cancer Registry and the laboratory of Emam Reza Hospital in Mashhad, Iran. Patients or their relatives underwent interviews where it was needed. Missing values were imputed by data mining techniques. Fifteen factors were analyzed. Survival was addressed as a dependent variable. Then, the predictive model was designed by combining both genetic algorithm and logistic regression. Matlab 2014 software was used to combine them. Results: Of the 277 patients, only survival of 80 patients was available whose data were used for designing the predictive model. Mean ± SD of missing values for each patient was 4.43±1.41 combined predictive model achieved 72.57% accuracy. Sex, birth year, age at diagnosis time, age at diagnosis time of patients’ family, family history of gastric cancer, and family history of other gastrointestinal cancers were six parameters associated with patient survival. Conclusion: The study revealed that imputing missing values by data mining techniques have a good accuracy. And it also revealed six parameters extracted by genetic algorithm effect on the survival of patients with gastric cancer. Our combined predictive model, with a good accuracy, is appropriate to forecast the survival of patients suffering from Gastric cancer. So, we suggest policy makers and specialists to apply it for prediction of patients’ survival.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5843431/Gastric CancerSurvivalMissing ValuePredictive Model |
| spellingShingle | Ladan Goshayeshi Benyamin Hoseini Zahra Yousefli Alireza Khooie Kobra Etminani Abbas Esmaeilzadeh Amin Golabpour Predictive model for survival in patients with gastric cancer Electronic Physician Gastric Cancer Survival Missing Value Predictive Model |
| title | Predictive model for survival in patients with gastric cancer |
| title_full | Predictive model for survival in patients with gastric cancer |
| title_fullStr | Predictive model for survival in patients with gastric cancer |
| title_full_unstemmed | Predictive model for survival in patients with gastric cancer |
| title_short | Predictive model for survival in patients with gastric cancer |
| title_sort | predictive model for survival in patients with gastric cancer |
| topic | Gastric Cancer Survival Missing Value Predictive Model |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5843431/ |
| work_keys_str_mv | AT ladangoshayeshi predictivemodelforsurvivalinpatientswithgastriccancer AT benyaminhoseini predictivemodelforsurvivalinpatientswithgastriccancer AT zahrayousefli predictivemodelforsurvivalinpatientswithgastriccancer AT alirezakhooie predictivemodelforsurvivalinpatientswithgastriccancer AT kobraetminani predictivemodelforsurvivalinpatientswithgastriccancer AT abbasesmaeilzadeh predictivemodelforsurvivalinpatientswithgastriccancer AT amingolabpour predictivemodelforsurvivalinpatientswithgastriccancer |