Differential Diagnosis of Tuberculosis and Sarcoidosis by Immunological Features Using Machine Learning
Diagnostics · 30.09.2024 · 14 (19) · 2188
DOI: 10.3390/diagnostics14192188 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 30.09.2024. Verfasst von Nikolay Osipov und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Computer Science, St. Petersburg State University, 199034 St. Petersburg, Russia. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Ministry of Science and Higher Education of the Russian Federation, State Assignment of the Institute of Experimental Medicine, Ministry of Science and Higher Education of the Russian Federation.
Abstract (Originalsprache)
Despite the achievements of modern medicine, tuberculosis remains one of the leading causes of mortality globally. The difficulties in differential diagnosis have particular relevance in the case of suspicion of tuberculosis with other granulomatous diseases. The most similar clinical and radiologic changes are sarcoidosis. The aim of this study is to apply mathematical modeling to determine diagnostically significant immunological parameters and an algorithm for the differential diagnosis of tuberculosis and sarcoidosis. Materials and methods: The serum samples of patients with sarcoidosis (SD) (n = 29), patients with pulmonary tuberculosis (TB) (n = 32) and the control group (n = 31) (healthy subjects) collected from 2017 to 2022 (the average age 43.4 ± 5.3 years) were examined. Circulating ‘polarized’ T-helper cell subsets were analyzed by multicolor flow cytometry. A symbolic regression method was used to find general mathematical relations between cell concentrations and diagnosis. The parameters of the selected model were finally fitted through multi-objective optimization applied to two conflicting indices: sensitivity to sarcoidosis and sensitivity to tuberculosis.
Results
The difference in Bm2 and CD5−CD27− concentrations was found to be more significant for the differential diagnosis of sarcoidosis and tuberculosis than any individual concentrations: the combined feature Bm2 − [CD5−CD27−] differentiates sarcoidosis and tuberculosis with p < 0.00001 and AUC = 0.823. An algorithm for differential diagnosis was developed. It is based on the linear model with two variables: the first variable is the difference Bm2 − [CD5−CD27−] mentioned above, and the second is the naïve-Tregs concentration. The algorithm uses the model twice and returns “dubious” in 26.7% of cases for patients with sarcoidosis and in 16.1% of cases for patients with tuberculosis. For the remaining patients with one of these two diagnoses, its sensitivity to sarcoidosis is 90.5%, and its sensitivity to tuberculosis is 88.5%.
Conclusions
A simple algorithm was developed that can distinguish, by certain immunological features, the cases in which sarcoidosis is likely to be present instead of tuberculosis. Such cases may be further investigated to rule out tuberculosis conclusively. The mathematical model underlying the algorithm is based on the analysis of “naive” T-regulatory cells and “naive” B-cells. This may be a promising approach for differential diagnosis between pulmonary sarcoidosis and pulmonary tuberculosis. The findings may be useful in the absence of clear differential diagnostic criteria between pulmonary tuberculosis and sarcoidosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics and Computer Science, St. Petersburg State University, 199034 St. Petersburg, Russia.
- Almazov National Medical Research Centre, 197341 St. Petersburg, Russia.
- St. Petersburg Department of Steklov Mathematical Institute of Russian Academy of Sciences, 191023 St. Petersburg, Russia.
- Department of Immunology, Institution of Experimental Medicine, 197376 St. Petersburg, Russia.
- Department of Pharmacology, Institute of Pharmacy, I.M. Sechenov First Moscow State Medical University, 119991 Moscow, Russia.
- Institute of Immunology, 115478 Moscow, Russia.
ORCID-Profile: Nikolay Osipov, Artem Rubinstein, Dmitry Kudlay, Anna Starshinova
Förderung
- the Ministry of Science and Higher Education of the Russian Federation
- State Assignment of the Institute of Experimental Medicine
- Ministry of Science and Higher Education of the Russian Federation
Zitieren
APA
Osipov, N., Kudryavtsev, I., Spelnikov, D., Rubinstein, A., Belyaeva, E., Kulpina, A., Kudlay, D., & Starshinova, A. (2024). Differential Diagnosis of Tuberculosis and Sarcoidosis by Immunological Features Using Machine Learning. Diagnostics, 14(19), 2188. https://doi.org/10.3390/diagnostics14192188
Vancouver
Osipov N, Kudryavtsev I, Spelnikov D, Rubinstein A, Belyaeva E, Kulpina A, et al. Differential Diagnosis of Tuberculosis and Sarcoidosis by Immunological Features Using Machine Learning. Diagnostics. 2024;14(19):2188. doi:10.3390/diagnostics14192188
BibTeX
@article{Osipov2024,
author = {Osipov, Nikolay and Kudryavtsev, Igor and Spelnikov, Dmitry and Rubinstein, Artem and Belyaeva, Ekaterina and Kulpina, Anastasia and Kudlay, Dmitry and Starshinova, Anna},
title = {Differential Diagnosis of Tuberculosis and Sarcoidosis by Immunological Features Using Machine Learning},
journal = {Diagnostics},
year = {2024},
volume = {14},
number = {19},
pages = {2188},
doi = {10.3390/diagnostics14192188}
}
EUVIMED