Highly accurate and explainable detection of specimen mix-up using a machine learning model
The DOI matches its Crossref record; 8 of the 9 references it cites were found in a registry or an index.
Abstract
Background: Delta check is widely used for detecting specimen mix-ups. Owing to the inadequate specificity and sparseness of the absolute incidence of mix-ups, the positive predictive value (PPV) of delta check is considerably low as it is labor consuming to identify true mix-up errors among a large number of false alerts. To overcome this problem, we developed a new accurate detection model through machine learning. Methods: Inspired by delta check, we decided to conduct comparisons with the past examinations and broaden the time range. Fifteen common items were selected from complete blood cell counts and biochemical tests. We considered examinations in which ≥11 among the 15 items were measured simultaneously in our hospital; we created individual partial time-series data of the consecutive examinations with a sliding window size of 4. The last examinations of the partial time-series data were shuffled to generate artificial mix-up cases. After splitting the dataset into development and validation sets, we allowed a gradient-boosting-decision-tree (GBDT) model to learn using the development set to detect whether the last examination results of the partial time-series data were artificial mixed-up results. The model’s performance was evaluated on the validation set. Results: The area under the receiver operating characteristic curve (ROC AUC) of our model was 0.9983 (bootstrap confidence interval [bsCI]: 0.9983–0.9985). Conclusions: The GBDT model was more effective in detecting specimen mix-up. The improved accuracy will enable more facilities to perform more efficient and centralized mix-up detection, leading to improved patient safety.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Mitani et al. developed a gradient-boosting-decision-tree (GBDT) model to effectively detect specimen mix-ups [27].”
From Machine learning-based clinical decision support using laboratory data (2024) · cites this paper as [27]
In the citing paper
“The model achieved an outstanding AUC of 0.998, showcasing its efficacy in accurately identifying mix-up occurrences.”
From Machine learning-based clinical decision support using laboratory data (2024) · cites this paper as [27]
In the citing paper
“Nonetheless, it is worth mentioning that this study was limited to a simulation-based approach and lacked external validation [27]”
From Machine learning-based clinical decision support using laboratory data (2024) · cites this paper as [27]
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“The weighted averages of the differences were calculated as indices for specimen mix-up (wCDI) [6].”
MethodXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 6×
“The missing values were managed by the default setting of XGBoost, wherein which branch to follow with the missing value is also learned on every node.”
MethodInfluentialConsistent Individualized Feature Attribution for Tree Ensembles
Lundberg, S. M., Erion, G. G., & Lee, S.-I. (2018) · arXiv · doi:10.48550/arxiv.1802.03888 · Cited by 1,430 · cited 1×
“With an XGBoost model, the output can be explained by the SHAP values calculated using the TreeSHAP algorithm [9].”
MethodPreanalytical quality improvement: from dream to reality
Lippi, G., Chance, J. J., Church, S., Dazzi, P., Fontana, R., Giavarina, D., Grankvist, K., Huisman, W., Kouri, T., Palicka, V., et al. (2011) · Clinical Chemistry and Laboratory Medicine · doi:10.1515/cclm.2011.600 · Cited by 388 · cited 2×
“A rigorous “zero-tolerance” policy of rejecting any potentially mislabeled or misidentified specimen has been proposed [1].”
BackgroundCauses, consequences, detection, and prevention of identification errors in laboratory diagnostics
Lippi, G., Blanckaert, N., Bonini, P., Green, S., Kitchen, S., Palicka, V., Vassault, A. J., Mattiuzzi, C., & Plebani, M. (2009) · Clinical Chemistry and Laboratory Medicine · doi:10.1515/cclm.2009.045 · Cited by 167 · cited 1×
“0%, and the estimates might be negatively biased because most identification errors might go undetected [1, 2].”
BackgroundSimundic, A.-M., Church, S., Cornes, M. P., Grankvist, K., Lippi, G., Nybo, M., Nikolac, N., van Dongen-Lases, E., Eker, P., Kovalevskaya, S., et al. (2015) · Clinical Chemistry and Laboratory Medicine (CCLM) · doi:10.1515/cclm-2014-1053 · Cited by 95 · cited 1×
“Although there are some guidelines for a phlebotomy procedure to reduce these errors, the compliance level was found to be unacceptably low as in the identification procedure [3].”
BackgroundAutoverification of test results in the core clinical laboratory
Randell, E. W., Yenice, S., Wamono, A. A. K., & Orth, M. (2019) · Clinical Biochemistry · doi:10.1016/j.clinbiochem.2019.08.002 · Cited by 65
Yamashita, T., Ichihara, K., & Miyamoto, A. (2013) · Clinical Chemistry and Laboratory Medicine (CCLM) · doi:10.1515/cclm-2012-0752 · Cited by 19
Cited by
Barbado, A., Corcho, Ó., & Benjamins, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116100 · Cited by 77
“…model for binary classi-fication (even though anomaly detection models provide an output heavily imbalanced) Shapely values for explaining anomalies also appear at [25], where the SHAP algorithm is used to generate feature relevance explanations in order to explain what contributes specimen mix-up.”
MethodMachine learning-based clinical decision support using laboratory data
Çubukçu, H. C., Topcu, D. İ., & Yenice, S. (2024) · Clinical Chemistry and Laboratory Medicine (CCLM) · doi:10.1515/cclm-2023-1037 · Cited by 66
“None-theless, it is worth mentioning that this study was limited to a simulation-based approach and lacked external validation [27].”
BackgroundRecent evolutions of machine learning applications in clinical laboratory medicine
Bruyne, S. D., Speeckaert, M. M., Biesen, W. V., & Delanghe, J. (2020) · Critical Reviews in Clinical Laboratory Sciences · doi:10.1080/10408363.2020.1828811 · Cited by 60
“A comparable study [31] developed a GBDT model based on 15 lab parameters (complete blood cell counts and biochemical tests) and found an AUROC of 0.998 and PPV of 43.5% (error prevalence 0.1%, sensitivity 90”
BackgroundMethodInfluentialGu, Y., Zhang, D., & Bao, Z. (2021) · Journal of Petroleum Science and Engineering · doi:10.1016/j.petrol.2021.108350 · Cited by 54
Cadamuro, J. (2021) · Diagnostics · doi:10.3390/diagnostics11081399 · Cited by 47
“, who aimed to overcome the routinely used delta-check method to detect preanalytical specimen mix-up [64].”
Method
Metadata
- Authors
- Mitani, T., Doi, S., Yokota, S., Imai, T., & Ohe, K.
- Affiliations
- The University of Tokyo (JP)
- University of Tokyo Hospital (JP)
- Corresponding author
- Mitani, Tomohiro
- Venue
- Clinical Chemistry and Laboratory Medicine (CCLM)
- Publisher
- Walter de Gruyter GmbH
- Published
- 2019-09-12
- Volume
- 58
- Issue
- 3
- Pages
- 375-383
- ISSN
- 1434-6621 (ISSN-L)
- 1437-4331
- OpenAlex
- W3004936589
- Cited by
- 25
- References
- 9
- Citations by year
- 2026: 1 · 2025: 7 · 2024: 2 · 2023: 5 · 2022: 5 · 2021: 3 · 2020: 2
- FWCI
- 1.71
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Clinical Chemistry and Laboratory Medicine (CCLM) (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Health Professions › Medical Laboratory Technology › Clinical Laboratory Practices and Quality Control
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- delta check, gradient boosting decision tree, time series comparison, complete blood cell count, biochemical tests, patient safety, explainable machine learning
- MeSH terms
- Machine Learning, Humans, Specimen Handling, Artifacts
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Highly accurate and explainable detection of specimen mix-up using a machine learning model. https://app.cochat.ai/papers/10.1515/cclm-2019-0534
- The paper
- Mitani, T., Doi, S., Yokota, S., Imai, T., & Ohe, K. (2020). Highly accurate and explainable detection of specimen mix-up using a machine learning model. Clinical Chemistry and Laboratory Medicine (CCLM). https://doi.org/10.1515/cclm-2019-0534
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.