UMIN-ICDS Clinical Trial
| Unique ID issued by UMIN | UMIN000061679 |
|---|---|
| Receipt number | R000070576 |
| Scientific Title | Machine learning-based prediction of lymph node metastases for individualized surgical decision-making in older patients with gastric cancer: A retrospective simulation study compliant with TRIPOD+AI |
| Date of disclosure of the study information | 2026/05/25 |
| Last modified on | 2026/05/25 16:13:15 |
* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments
Basic information
Public title
Machine learning-based prediction of lymph node metastases for individualized surgical decision-making in older patients with gastric cancer: A retrospective simulation study compliant with TRIPOD+AI
Acronym
ML-based LNM prediction in GC
Scientific Title
Machine learning-based prediction of lymph node metastases for individualized surgical decision-making in older patients with gastric cancer: A retrospective simulation study compliant with TRIPOD+AI
Scientific Title:Acronym
ML-based LNM prediction in GC
Region
| Japan |
Condition
Condition
Gastric cancer
Classification by specialty
| Gastrointestinal surgery |
Classification by malignancy
Malignancy
Genomic information
NO
Objectives
Narrative objectives1
(1) to develop and temporally validate an LNM prediction model based on preoperative variables in patients aged >=70 years using six machine learning algorithms
(2) to quantify the oncological safety [negative predictive value (NPV), false-negative count] of a threshold-guided reduced-surgery strategy via retrospective simulation
(3) to perform a comprehensive evaluation of calibration, fairness, and uncertainty compliant with the TRIPOD+AI reporting guidelines
Basic objectives2
Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase
Assessment
Primary outcomes
the area under the receiver operating characteristic curve (ROC-AUC) and area under the precision-recall curve (PR-AUC) of the model
Key secondary outcomes
Base
Study type
Observational
Study design
Basic design
Randomization
Randomization unit
Blinding
Control
Stratification
Dynamic allocation
Institution consideration
Blocking
Concealment
Intervention
No. of arms
Purpose of intervention
Type of intervention
Interventions/Control_1
Interventions/Control_2
Interventions/Control_3
Interventions/Control_4
Interventions/Control_5
Interventions/Control_6
Interventions/Control_7
Interventions/Control_8
Interventions/Control_9
Interventions/Control_10
Eligibility
Age-lower limit
| 70 | years-old | <= |
Age-upper limit
| 100 | years-old | >= |
Gender
Male and Female
Key inclusion criteria
patients aged 70 years and above who underwent gastrectomies with lymph node dissections for gastric cancer between April 1995 and March 2025.
Key exclusion criteria
(i) neoadjuvant chemotherapy
(ii) distant metastases (M1)
Target sample size
1405
Research contact person
Name of lead principal investigator
| 1st name | Goshi |
| Middle name | |
| Last name | Fujimoto |
Organization
Kameda Medical Center
Division name
Gastroenterological Surgery
Zip code
296-0041
Address
929 Higashi-cho, Kamogawa City, Chiba Prefecture 296-8602, Japan
TEL
0470922211
g_chimera_7@yahoo.co.jp
Public contact
Name of contact person
| 1st name | Goshi |
| Middle name | |
| Last name | Fujimoto |
Organization
Kameda Medical Center
Division name
Gastroenterological Surgery
Zip code
296-0041
Address
929 Higashi-cho, Kamogawa City, Chiba Prefecture 296-8602, Japan
TEL
0470922211
Homepage URL
g_chimera_7@yahoo.co.jp
Sponsor or person
Institute
Kameda Medical Center
Institute
Department
Personal name
Goshi Fujimoto
Funding Source
Organization
None
Organization
Division
Category of Funding Organization
Other
Nationality of Funding Organization
Japan
Other related organizations
Co-sponsor
Name of secondary funder(s)
IRB Contact (For public release)
Organization
Kameda Medical Center
Address
929 Higashi-cho, Kamogawa City, Chiba Prefecture 296-8602, Japan
Tel
0470922211
g_chimera_7@yahoo.co.jp
Secondary IDs
Secondary IDs
NO
Study ID_1
Org. issuing International ID_1
Study ID_2
Org. issuing International ID_2
IND to MHLW
静岡県
Institutions
Institutions
Other administrative information
Date of disclosure of the study information
| 2026 | Year | 05 | Month | 25 | Day |
Related information
URL releasing protocol
Publication of results
Unpublished
Result
URL related to results and publications
Number of participants that the trial has enrolled
1405
Results
Results date posted
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
Participant flow
Adverse events
Outcome measures
Plan to share IPD
IPD sharing Plan description
Progress
Recruitment status
No longer recruiting
Date of protocol fixation
| 2026 | Year | 05 | Month | 18 | Day |
Date of IRB
| 2026 | Year | 05 | Month | 18 | Day |
Anticipated trial start date
| 2026 | Year | 05 | Month | 18 | Day |
Last follow-up date
| 2026 | Year | 12 | Month | 31 | Day |
Date of closure to data entry
Date trial data considered complete
Date analysis concluded
Other
Other related information
Final features are selected from the top-ranked features in LASSO and Random Forest. Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), CatBoost, and Multi-Layer Perceptron (MLP) are built after optimizing their hyperparameters.
Model evaluation is performed using Accuracy, Precision, Recall, F1 score, ROC-AUC, and PR-AUC. Calibration is quantitatively evaluated using a Calibration Plot, as well as the Brier Score, the expected-to-observed ratio, and the Hosmer-Lemeshow (HL) test.
Simulations of reduced surgery indications at thresholds of 5%, 10%, and 20% will be performed to calculate the negative predictive value (NPV, with 95% CI), number of false negatives, and rate of candidates for local resection. Decision Curve Analysis (DCA) will be performed using the method by Vickers et al. to calculate the net benefit.
SHAP (SHapley Additive Explanations) analysis will be performed on all models.
Management information
Registered date
| 2026 | Year | 05 | Month | 25 | Day |
Last modified on
| 2026 | Year | 05 | Month | 25 | Day |
Link to view the page
Value
https://center6.umin.ac.jp/cgi-open-bin/icdr_e/ctr_view.cgi?recptno=R000070576
