Using machine learning models to predict synchronous genitourinary cancers among gastrointestinal stromal tumor patients

被引:0
作者
Alghafees, Mohammad [1 ]
Seyam, Raouf M. [1 ]
Al-Hussain, Turki [2 ]
Amin, Tarek Mahmoud [3 ]
Altaweel, Waleed [1 ]
Sabbah, Belal Nedal [4 ]
Sabbah, Ahmad Nedal [4 ]
Almesned, Razan [1 ]
Alessa, Laila [1 ]
机构
[1] King Faisal Specialist Hosp & Res Ctr, Dept Urol, Riyadh, Saudi Arabia
[2] King Faisal Specialist Hosp & Res Ctr, Dept Pathol & Lab Med, Riyadh, Saudi Arabia
[3] King Faisal Specialist Hosp & Res Ctr, Oncol Ctr, Dept Surg Oncol, Riyadh, Saudi Arabia
[4] Alfaisal Univ, Coll Med, Riyadh, Saudi Arabia
关键词
Artificial intelligence; gastrointestinal oncology; gastrointestinal stromal tumors; genitourinary oncology; urologic oncology; urology;
D O I
10.4103/ua.ua_32_23
中图分类号
R5 [内科学]; R69 [泌尿科学(泌尿生殖系疾病)];
学科分类号
1002 ; 100201 ;
摘要
Objectives: Gastrointestinal stromal tumors (GISTs) can occur synchronously with other neoplasms, including the genitourinary (GU) system. Machine learning (ML) may be a valuable tool in predicting synchronous GU tumors in GIST patients, and thus improving prognosis. This study aims to evaluate the use of ML algorithms to predict synchronous GU tumors among GIST patients in a specialist research center in Saudi Arabia. Materials and Methods: We analyzed data from all patients with histopathologically confirmed GIST at our facility from 2003 to 2020. Patient files were reviewed for the presence of renal cell carcinoma, adrenal tumors, or other GU cancers. Three supervised ML algorithms were used: logistic regression, XGBoost Regressor, and random forests (RFs). A set of variables, including independent attributes, was entered into the models. Results: A total of 170 patients were included in the study, with 58.8% (n = 100) being male. The median age was 57 (range: 9-91) years. The majority of GISTs were gastric (60%, n = 102) with a spindle cell histology. The most common stage at diagnosis was T2 (27.6%, n = 47) and N0 (20%, n = 34). Six patients (3.5%) had synchronous GU tumors. The RF model achieved the highest accuracy with 97.1%. Conclusion: Our study suggests that the RF model is an effective tool for predicting synchronous GU tumors in GIST patients. Larger multicenter studies, utilizing more powerful algorithms such as deep learning and other artificial intelligence subsets, are necessary to further refine and improve these predictions.
引用
收藏
页码:94 / 97
页数:4
相关论文
共 15 条
[1]  
Bokhary RY, 2010, SAUDI MED J, V31, P437
[2]   A random forest classifier predicts recurrence risk in patients with ovarian cancer [J].
Cheng, Li ;
Li, Lin ;
Wang, Liling ;
Li, Xiaofang ;
Xing, Hui ;
Zhou, Jinting .
MOLECULAR MEDICINE REPORTS, 2018, 18 (03) :3289-3297
[3]   Gastrointestinal stromal tumour [J].
Joensuu, Heikki ;
Hohenberger, Peter ;
Corless, Christopher L. .
LANCET, 2013, 382 (9896) :973-983
[4]   The management of metastatic GIST: current standard and investigational therapeutics [J].
Kelly, Ciara M. ;
Sainz, Laura Gutierrez ;
Chi, Ping .
JOURNAL OF HEMATOLOGY & ONCOLOGY, 2021, 14 (01)
[5]   Machine learning-based random forest for predicting decreased quality of life in thyroid cancer patients after thyroidectomy [J].
Liu, Yong Hong ;
Jin, Jian ;
Liu, Yun Jiang .
SUPPORTIVE CARE IN CANCER, 2022, 30 (03) :2507-2513
[6]  
Mekni A, 2008, PATHOLOGICA, V100, P173
[7]   Development of Gene Expression-Based Random Forest Model for Predicting Neoadjuvant Chemotherapy Response in Triple-Negative Breast Cancer [J].
Park, Seongyong ;
Yi, Gwansu .
CANCERS, 2022, 14 (04)
[8]   Gastrointestinal stromal tumour [J].
Rubin, Brian P. ;
Heinrich, Michael C. ;
Corless, Christopher L. .
LANCET, 2007, 369 (9574) :1731-1741
[9]   Use of Artificial Intelligence in the Prediction of Malignant Potential of Gastric Gastrointestinal Stromal Tumors [J].
Seven, Gulseren ;
Silahtaroglu, Gokhan ;
Kochan, Koray ;
Ince, Ali Tuzun ;
Arici, Dilek Sema ;
Senturk, Hakan .
DIGESTIVE DISEASES AND SCIENCES, 2022, 67 (01) :273-281
[10]   Global epidemiology of gastrointestinal stromal tumours (GIST): A systematic review of population-based cohort studies [J].
Soreide, Kjetil ;
Sandvik, Oddvar M. ;
Soreide, Jon Arne ;
Giljaca, Vanja ;
Jureckova, Andrea ;
Bulusu, V. Ramesh .
CANCER EPIDEMIOLOGY, 2016, 40 :39-46