Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study

Abstract BackgroundInsufficient participant enrollment is a major factor responsible for clinical trial failure. ObjectiveWe formulated a machine learning (ML)–based framework using clinical laboratory parameters to identify participants eligible for enrollment in...

Full description

Saved in:
Bibliographic Details
Main Authors: Byungeun Shon, Sook Jin Seong, Eun Jung Choi, Mi-Ri Gwon, Hae Won Lee, Jaechan Park, Ho-Young Chung, Sungmoon Jeong, Young-Ran Yoon
Format: Article
Language:English
Published: JMIR Publications 2025-05-01
Series:JMIR AI
Online Access:https://ai.jmir.org/2025/1/e64845
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427716370071552
author Byungeun Shon
Sook Jin Seong
Eun Jung Choi
Mi-Ri Gwon
Hae Won Lee
Jaechan Park
Ho-Young Chung
Sungmoon Jeong
Young-Ran Yoon
author_facet Byungeun Shon
Sook Jin Seong
Eun Jung Choi
Mi-Ri Gwon
Hae Won Lee
Jaechan Park
Ho-Young Chung
Sungmoon Jeong
Young-Ran Yoon
author_sort Byungeun Shon
collection DOAJ
description Abstract BackgroundInsufficient participant enrollment is a major factor responsible for clinical trial failure. ObjectiveWe formulated a machine learning (ML)–based framework using clinical laboratory parameters to identify participants eligible for enrollment in a bioequivalence study. MethodsWe acquired records of 11,592 patients with gastric cancer from the electronic medical records of Kyungpook National University Hospital in Korea. The ML model was developed using 8 clinical laboratory parameters, including complete blood count and liver and kidney function tests, along with the dates of acquisition. Two datasets were collected: (1) a training dataset to design an ML-based candidate selection method and (2) a test dataset to evaluate the performance of the proposed method. The generalization performance of the ML-based method was confirmed using the F1 ResultsThe weighted ensemble model achieved strong performance with an F1 ConclusionsThe proposed ML-based framework using clinical laboratory parameters can be used to identify patients eligible for a clinical trial, enabling faster participant enrollment.
format Article
id doaj-art-ad54543faa9949bd81fa183edd17decc
institution Kabale University
issn 2817-1705
language English
publishDate 2025-05-01
publisher JMIR Publications
record_format Article
series JMIR AI
spelling doaj-art-ad54543faa9949bd81fa183edd17decc2025-08-20T03:28:55ZengJMIR PublicationsJMIR AI2817-17052025-05-014e64845e6484510.2196/64845Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation StudyByungeun Shonhttp://orcid.org/0000-0001-5161-2398Sook Jin Seonghttp://orcid.org/0000-0001-8872-3796Eun Jung Choihttp://orcid.org/0000-0003-1881-9869Mi-Ri Gwonhttp://orcid.org/0000-0001-5703-1615Hae Won Leehttp://orcid.org/0000-0001-7299-5332Jaechan Parkhttp://orcid.org/0000-0001-7572-3260Ho-Young Chunghttp://orcid.org/0000-0001-7264-0865Sungmoon Jeonghttp://orcid.org/0000-0002-4579-3150Young-Ran Yoonhttp://orcid.org/0000-0003-2166-7579 Abstract BackgroundInsufficient participant enrollment is a major factor responsible for clinical trial failure. ObjectiveWe formulated a machine learning (ML)–based framework using clinical laboratory parameters to identify participants eligible for enrollment in a bioequivalence study. MethodsWe acquired records of 11,592 patients with gastric cancer from the electronic medical records of Kyungpook National University Hospital in Korea. The ML model was developed using 8 clinical laboratory parameters, including complete blood count and liver and kidney function tests, along with the dates of acquisition. Two datasets were collected: (1) a training dataset to design an ML-based candidate selection method and (2) a test dataset to evaluate the performance of the proposed method. The generalization performance of the ML-based method was confirmed using the F1 ResultsThe weighted ensemble model achieved strong performance with an F1 ConclusionsThe proposed ML-based framework using clinical laboratory parameters can be used to identify patients eligible for a clinical trial, enabling faster participant enrollment.https://ai.jmir.org/2025/1/e64845
spellingShingle Byungeun Shon
Sook Jin Seong
Eun Jung Choi
Mi-Ri Gwon
Hae Won Lee
Jaechan Park
Ho-Young Chung
Sungmoon Jeong
Young-Ran Yoon
Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
JMIR AI
title Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
title_full Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
title_fullStr Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
title_full_unstemmed Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
title_short Clinical Laboratory Parameter–Driven Machine Learning for Participant Selection in Bioequivalence Studies Among Patients With Gastric Cancer: Framework Development and Validation Study
title_sort clinical laboratory parameter driven machine learning for participant selection in bioequivalence studies among patients with gastric cancer framework development and validation study
url https://ai.jmir.org/2025/1/e64845
work_keys_str_mv AT byungeunshon clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT sookjinseong clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT eunjungchoi clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT mirigwon clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT haewonlee clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT jaechanpark clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT hoyoungchung clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT sungmoonjeong clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy
AT youngranyoon clinicallaboratoryparameterdrivenmachinelearningforparticipantselectioninbioequivalencestudiesamongpatientswithgastriccancerframeworkdevelopmentandvalidationstudy