Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer
Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analy...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gastroenterology Council for Gut and Liver
2025-01-01
|
| Series: | Gut and Liver |
| Subjects: | |
| Online Access: | http://gutnliver.org/journal/view.html?doi=10.5009/gnl240273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536147847643136 |
|---|---|
| author | Ji Eun Baek Hahn Yi Seung Wook Hong Subin Song Ji Young Lee Sung Wook Hwang Sang Hyoung Park Dong-Hoon Yang Byong Duk Ye Seung-Jae Myung Suk-Kyun Yang Namkug Kim Jeong-Sik Byeon |
| author_facet | Ji Eun Baek Hahn Yi Seung Wook Hong Subin Song Ji Young Lee Sung Wook Hwang Sang Hyoung Park Dong-Hoon Yang Byong Duk Ye Seung-Jae Myung Suk-Kyun Yang Namkug Kim Jeong-Sik Byeon |
| author_sort | Ji Eun Baek |
| collection | DOAJ |
| description | Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions: AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method. |
| format | Article |
| id | doaj-art-ffb8a345172c4bc290ab876046a1a97f |
| institution | Kabale University |
| issn | 1976-2283 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Gastroenterology Council for Gut and Liver |
| record_format | Article |
| series | Gut and Liver |
| spelling | doaj-art-ffb8a345172c4bc290ab876046a1a97f2025-01-15T00:51:13ZengGastroenterology Council for Gut and LiverGut and Liver1976-22832025-01-01191697610.5009/gnl240273gnl240273Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal CancerJi Eun Baek0Hahn Yi1Seung Wook Hong2Subin Song3Ji Young Lee4Sung Wook Hwang5Sang Hyoung Park6Dong-Hoon Yang7Byong Duk Ye8Seung-Jae Myung9Suk-Kyun Yang10Namkug Kim11Jeong-Sik Byeon12Department of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaHealth Screening and Promotion Center, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaDepartment of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, KoreaBackground/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions: AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.http://gutnliver.org/journal/view.html?doi=10.5009/gnl240273artificial intelligence; t1 colorectal cancer; lymph node metastasis |
| spellingShingle | Ji Eun Baek Hahn Yi Seung Wook Hong Subin Song Ji Young Lee Sung Wook Hwang Sang Hyoung Park Dong-Hoon Yang Byong Duk Ye Seung-Jae Myung Suk-Kyun Yang Namkug Kim Jeong-Sik Byeon Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer Gut and Liver artificial intelligence; t1 colorectal cancer; lymph node metastasis |
| title | Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer |
| title_full | Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer |
| title_fullStr | Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer |
| title_full_unstemmed | Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer |
| title_short | Artificial Intelligence Models May Aid in Predicting Lymph Node Metastasis in Patients with T1 Colorectal Cancer |
| title_sort | artificial intelligence models may aid in predicting lymph node metastasis in patients with t1 colorectal cancer |
| topic | artificial intelligence; t1 colorectal cancer; lymph node metastasis |
| url | http://gutnliver.org/journal/view.html?doi=10.5009/gnl240273 |
| work_keys_str_mv | AT jieunbaek artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT hahnyi artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT seungwookhong artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT subinsong artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT jiyounglee artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT sungwookhwang artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT sanghyoungpark artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT donghoonyang artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT byongdukye artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT seungjaemyung artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT sukkyunyang artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT namkugkim artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer AT jeongsikbyeon artificialintelligencemodelsmayaidinpredictinglymphnodemetastasisinpatientswitht1colorectalcancer |