دوره 14، شماره 3 - ( 2-1402 )
جلد 14 شماره 3 صفحات 533-526 |
برگشت به فهرست نسخه ها
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Farzaneh F, Jafari Ashtiani A, Hashemi M M, Hosseini M S, Arab M, Ashrafganjoei T et al . Endometrial cancer in women with abnormal uterine bleeding: Data mining classification methods. Caspian J Intern Med 2023; 14 (3) :526-533
URL: http://caspjim.com/article-1-3525-fa.html
URL: http://caspjim.com/article-1-3525-fa.html
Endometrial cancer in women with abnormal uterine bleeding: Data mining classification methods. . 1402; 14 (3) :526-533
چکیده: (1257 مشاهده)
Background: Over the last decade, artificial intelligence in medicine has been growing. Since endometrial cancer can be treated with early diagnosis, finding a non-invasive method for screening patients, especially high-risk ones, could have a particular value. Regarding the importance of this issue, we aimed to investigate the risk factors related to endometrial cancer and find a tool to predict it using machine learning.
Methods: In this cross-sectional study, 972 patients with abnormal uterine bleeding from January 2016 to January 2021 were studied, and the essential characteristics of each patient, along with the findings of curettage pathology, were analyzed using statistical methods and machine learning algorithms, including artificial neural networks, classification and regression trees, support vector machine, and logistic regression.
Results: Out of 972 patients with a mean age of 45.77 ± 10.70 years, 920 patients had benign pathology, and 52 patients had endometrial cancer. In terms of endometrial cancer prediction, the logistic regression model had the best performance (sensitivity of 100% and 98%, specificity of 98.83% and 98.7%, for trained and test data sets respectively,) followed by the classification and regression trees model.
Conclusion: Based on the results, artificial intelligence-based algorithms can be applied as a non-invasive screening method for predicting endometrial cancer.
Methods: In this cross-sectional study, 972 patients with abnormal uterine bleeding from January 2016 to January 2021 were studied, and the essential characteristics of each patient, along with the findings of curettage pathology, were analyzed using statistical methods and machine learning algorithms, including artificial neural networks, classification and regression trees, support vector machine, and logistic regression.
Results: Out of 972 patients with a mean age of 45.77 ± 10.70 years, 920 patients had benign pathology, and 52 patients had endometrial cancer. In terms of endometrial cancer prediction, the logistic regression model had the best performance (sensitivity of 100% and 98%, specificity of 98.83% and 98.7%, for trained and test data sets respectively,) followed by the classification and regression trees model.
Conclusion: Based on the results, artificial intelligence-based algorithms can be applied as a non-invasive screening method for predicting endometrial cancer.
نوع مطالعه: Original Article |
موضوع مقاله:
Obstetrics & Gynicology
دریافت: 1401/3/26 | پذیرش: 1401/5/23 | انتشار: 1402/2/19
دریافت: 1401/3/26 | پذیرش: 1401/5/23 | انتشار: 1402/2/19
| بازنشر اطلاعات | |
 |
این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است. |
