Machine learning-based delta check method for detecting misidentification errors in tumor marker tests
- 문서 유형
- 연구출판물 · 학술지 논문
- 등재
- SCIEScopus
- 저널 순위
- JCR Q1Scopus Q1
- 저널
- CLINICAL CHEMISTRY AND LABORATORY MEDICINE62(7) · pp.1421 · 2024
- 피인용
- Web of Science 10Scopus 10
- FWCI (Scopus)
- 1.26
- JCR IF
- JCR 2023 3.8
- ISSN
- 1434-6621
저자
- Seok, Hyeon Seok제1저자Chonnam Natl Univ, Interdisciplinary Program Biomed Engn, Yeosu, South Korea
- Choi, YunaUniv Ulsan, Coll Med, Asan Med Ctr, Dept Lab Med, 88 Olymp Ro 43 Gil, Seoul 680749, South Korea
- Yu, ShinaeInje Univ, Coll Med, Haeundae Paik Hosp, Dept Lab Med, Busan, South Korea
- 신경화Pusan Natl Univ Hosp, Dept Lab Med, Busan, South Korea
- Kim, Sollip교신저자Univ Ulsan, Coll Med, Asan Med Ctr, Dept Lab Med, 88 Olymp Ro 43 Gil, Seoul 680749, South Korea
- Shin, Hangsik교신저자Univ Ulsan, Coll Med, Asan Med Ctr, Dept Digital Med, 88 Olymp Ro 43 Gil, Seoul 05505, South Korea
초록
Misidentification errors in tumor marker tests can lead to serious diagnostic and treatment errors. This study aims to develop a method for detecting these errors using a machine learning (ML)-based delta check approach, overcoming limitations of conventional methods. We analyzed five tumor marker test results: alpha-fetoprotein (AFP), cancer antigen 19-9 (CA19-9), cancer antigen 125 (CA125), carcinoembryonic antigen (CEA), and prostate-specific antigen (PSA). A total of 246,261 records were used in the analysis. Of these, 179,929 records were used for model training and 66,332 records for performance evaluation. We developed a misidentification error detection model based on the random forest (RF) and deep neural network (DNN) methods. We performed an in silico simulation with 1 % random sample shuffling. The performance of the developed models was evaluated and compared to conventional delta check methods such as delta percent change (DPC), absolute DPC (absDPC), and reference change values (RCV). The DNN model outperformed the RF, DPC, absDPC, and RCV methods in detecting sample misidentification errors. It achieved balanced accuracies of 0.828, 0.842, 0.792, 0.818, and 0.833 for AFP, CA19-9, CA125, CEA, and PSA, respectively. Although the RF method performed better than DPC and absDPC, it showed similar or lower performance compared to RCV. Our research results demonstrate that an ML-based delta check method can more effectively detect sample misidentification errors compared to conventional delta check methods. In particular, the DNN model demonstrated superior and stable detection performance compared to the RF, DPC, absDPC, and RCV methods.
키워드
artificial intelligenceautoverificationdeep neural networkdelta checkmachine learningtumor markers
식별자
- Scopus EID
- 2-s2.0-85180084944
- WoS UID
- 001126642900001



로그인
연구물 목록으로