Abstract
Objectives
To create a supervised machine learning algorithm aimed at predicting an optimal cerebrospinal fluid (CSF) dilution when determining virus specific antibody indices to reduce the need for repeated tests.
Methods
The CatBoost model was trained, optimized, and tested on a dataset with five input variables: albumin quotient, immunoglobulin G (IgG) in CSF, IgG quotient (QIgG), intrathecal synthesis (ITS) and limes quotient (LIM IgG). Albumin and IgG concentrations in CSF and serum were performed by immunonephelometry on Atellica NEPH 630 (Siemens Healthineers, Erlangen, Germany) and ITS and LIM IgG were calculated according to Reiber. Concentrations of IgG antibodies to measles, rubella, varicella zoster and herpes simplex 1/2 viruses were analysed in CSF and serum by ELISA (Euroimmun, Lübeck, Germany). Optimal CSF dilution was defined for each virus and used as a classification variable while the standard operating procedure was set to start at 2×-dilution of CSF.
Results
The dataset included 571 samples with the imbalanced distribution of the optimal CSF dilutions: 2× dilution n=440, 3× dilution n=109, 4× dilution n=22. The optimized CatBoost model achieved an area under the curve (AUC) score of 0.971, and a test accuracy of 0.900. The model falsely classified 14 (9.9 %) samples of the testing set but reduced the need for repeated testing compared to the standard protocol by 42 %. The output of the CatBoost model is mostly dependant on the QIgG, ITS and CSF IgG variables.
Conclusions
An accurate algorithm was achieved for predicting the optimal CSF dilution, which reduces the number of test repeats.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: Study concept and design: AT. Acquisition of data: AT, ZV, LJZ. Analysis and interpretation of data: AT, AŠ. Drafting the manuscript: AT, AŠ. Critical revision of the manuscript for important intellectual content: ZV, LJZ, DR. Administrative, technical, and material support: ZV, DR. The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
1. Carobene, A, Cabitza, F, Bernardini, S, Gopalan, R, Lennerz, JK, Weir, C, et al.. Where is laboratory medicine headed in the next decade? Partnership model for efficient integration and adoption of artificial intelligence into medical laboratories. Clin Chem Lab Med 2023;61:535–43. https://doi.org/10.1515/cclm-2022-1030.Search in Google Scholar PubMed
2. Rabbani, N, Kim, GYE, Suarez, CJ, Chen, JH. Applications of machine learning in routine laboratory medicine: current state and future directions. Clin Biochem 2022;103:1–7. https://doi.org/10.1016/j.clinbiochem.2022.02.011.Search in Google Scholar PubMed PubMed Central
3. Tsai, IJ, Shen, WC, Lee, CL, Wang, HD, Lin, CY. Machine learning in prediction of bladder cancer on clinical laboratory data. Diagnostics 2022;12:203. https://doi.org/10.3390/diagnostics12010203.Search in Google Scholar PubMed PubMed Central
4. Podnar, S, Kukar, M, Gunčar, G, Notar, M, Gošnjak, N, Notar, M. Diagnosing brain tumours by routine blood tests using machine learning. Sci Rep 2019;9:14481. https://doi.org/10.1038/s41598-019-51147-3.Search in Google Scholar PubMed PubMed Central
5. Cao, Y, Hu, ZD, Liu, XF, Deng, AM, Hu, CJ. An MLP classifier for prediction of HBV-induced liver cirrhosis using routinely available clinical parameters. Dis Markers 2013;35:653–60. https://doi.org/10.1155/2013/127962.Search in Google Scholar PubMed PubMed Central
6. Xiao, J, Ding, R, Xu, X, Guan, H, Feng, X, Sun, T, et al.. Comparison and development of machine learning tools in the prediction of chronic kidney disease progression. J Transl Med 2019;17:119. https://doi.org/10.1186/s12967-019-1860-0.Search in Google Scholar PubMed PubMed Central
7. Farrell, CJL, Giannoutsos, J. Machine learning models outperform manual result review for the identification of wrong blood in tube errors in complete blood count results. Int J Lab Hematol 2022;44:497–503. https://doi.org/10.1111/ijlh.13820.Search in Google Scholar PubMed
8. Rosenbaum, MW, Baron, JM. Using machine learning-based multianalyte delta checks to detect wrong blood in tube errors. Am J Clin Pathol 2018;150:555–66. https://doi.org/10.1093/ajcp/aqy085.Search in Google Scholar PubMed
9. Albahra, S, Gorbett, T, Robertson, S, D’Aleo, G, Kumar, SVS, Ockunzzi, S, et al.. Artificial intelligence and machine learning overview in pathology & laboratory medicine: a general review of data preprocessing and basic supervised concepts. Semin Diagn Pathol 2023;40:71–87. https://doi.org/10.1053/j.semdp.2023.02.002.Search in Google Scholar PubMed
10. Osterman, A, Böhm, S, Osterman, P. Accuracy, precision, and consistency of methods for pathogen-specific cerebrospinal fluid/serum Q-value calculation. J Immunol Methods 2020;477:112691. https://doi.org/10.1016/j.jim.2019.112691.Search in Google Scholar PubMed
11. Jarius, S, Eichhorn, P, Franciotta, D, Petereit, HF, Akman-Demir, G, Wick, M, et al.. The MRZ reaction as a highly specific marker of multiple sclerosis: re-evaluation and structured review of the literature. J Neurol 2017;264:453–66. https://doi.org/10.1007/s00415-016-8360-4.Search in Google Scholar PubMed
12. Reiber, H, Lange, P. Quantification of virus-specific antibodies in cerebrospinal fluid and serum: sensitive and specific detection of antibody synthesis in brain. Clin Chem 1991;37:1153–60. https://doi.org/10.1093/clinchem/37.7.1153.Search in Google Scholar
13. Doherty, CM, Forbes, RB. Diagnostic lumbar puncture. Ulster Med J 2014;83:93–102.Search in Google Scholar
14. Andersson, M, Alvarez-Cermeño, J, Bernardi, G, Cogato, I, Fredman, P, Frederiksen, J, et al.. Cerebrospinal fluid in the diagnosis of multiple sclerosis: a consensus report. J Neurol Neurosurg Psychiatry 1994;57:897–902. https://doi.org/10.1136/jnnp.57.8.897.Search in Google Scholar PubMed PubMed Central
15. Reiber, H. Flow rate of cerebrospinal fluid (CSF) — a concept common to normal blood-CSF barrier function and to dysfunction in neurological diseases. J Neurol Sci 1994;122:189–203. https://doi.org/10.1016/0022-510x(94)90298-4.Search in Google Scholar PubMed
16. Ibrahim, AA, Ridwan, RL, Muhammed, MM, Abdulaziz, RO, Saheed, GA. Comparison of the CatBoost classifier with other machine learning methods. Int J Adv Comput Sci Appl 2020;11:738–48. https://doi.org/10.14569/ijacsa.2020.0111190.Search in Google Scholar
17. Qi, J, Yang, R, Wang, P. Application of explainable machine learning based on Catboost in credit scoring. J Phys Conf 2021;1955:012039. https://doi.org/10.1088/1742-6596/1955/1/012039.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
