본문 바로가기

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

  1. Seok, Hyeon Seok제1저자Chonnam Natl Univ, Interdisciplinary Program Biomed Engn, Yeosu, South Korea
  2. Choi, YunaUniv Ulsan, Coll Med, Asan Med Ctr, Dept Lab Med, 88 Olymp Ro 43 Gil, Seoul 680749, South Korea
  3. Yu, ShinaeInje Univ, Coll Med, Haeundae Paik Hosp, Dept Lab Med, Busan, South Korea
  4. 신경화Pusan Natl Univ Hosp, Dept Lab Med, Busan, South Korea
  5. Kim, Sollip교신저자Univ Ulsan, Coll Med, Asan Med Ctr, Dept Lab Med, 88 Olymp Ro 43 Gil, Seoul 680749, South Korea
  6. 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