Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a multicentric study.
Machine learning
Model deployment
Model interpretation
Predictive model
Spinal cord injury
Spinal tuberculosis
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
02 Apr 2024
02 Apr 2024
Historique:
received:
29
11
2023
accepted:
09
03
2024
medline:
3
4
2024
pubmed:
3
4
2024
entrez:
2
4
2024
Statut:
epublish
Résumé
Spinal cord injury (SCI) is a prevalent and serious complication among patients with spinal tuberculosis (STB) that can lead to motor and sensory impairment and potentially paraplegia. This research aims to identify factors associated with SCI in STB patients and to develop a clinically significant predictive model. Clinical data from STB patients at a single hospital were collected and divided into training and validation sets. Univariate analysis was employed to screen clinical indicators in the training set. Multiple machine learning (ML) algorithms were utilized to establish predictive models. Model performance was evaluated and compared using receiver operating characteristic (ROC) curves, area under the curve (AUC), calibration curve analysis, decision curve analysis (DCA), and precision-recall (PR) curves. The optimal model was determined, and a prospective cohort from two other hospitals served as a testing set to assess its accuracy. Model interpretation and variable importance ranking were conducted using the DALEX R package. The model was deployed on the web by using the Shiny app. Ten clinical characteristics were utilized for the model. The random forest (RF) model emerged as the optimal choice based on the AUC, PRs, calibration curve analysis, and DCA, achieving a test set AUC of 0.816. Additionally, MONO was identified as the primary predictor of SCI in STB patients through variable importance ranking. The RF predictive model provides an efficient and swift approach for predicting SCI in STB patients.
Identifiants
pubmed: 38565845
doi: 10.1038/s41598-024-56711-0
pii: 10.1038/s41598-024-56711-0
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7691Informations de copyright
© 2024. The Author(s).
Références
Chakaya, J. et al. Global tuberculosis report 2020—Reflections on the global TB burden, treatment and prevention efforts. Int. J. Infect. Dis. 113(Suppl 1), S7–S12 (2021).
pubmed: 33716195
pmcid: 8433257
doi: 10.1016/j.ijid.2021.02.107
Furin, J., Cox, H. & Pai, M. Tuberculosis. Lancet 393(10181), 1642–1656 (2019).
pubmed: 30904262
doi: 10.1016/S0140-6736(19)30308-3
Dunn, R. N. & Ben, H. M. Spinal tuberculosis: Review of current management. Bone Jt. J. 100-B(4), 425–31 (2018).
doi: 10.1302/0301-620X.100B4.BJJ-2017-1040.R1
Jain, A. K., Rajasekaran, S., Jaggi, K. R. & Myneedu, V. P. Tuberculosis of the Spine. J. Bone Jt. Surg. Am. 102(7), 617–628 (2020).
doi: 10.2106/JBJS.19.00001
Garcia-Rodriguez, J. F. et al. Extrapulmonary tuberculosis: Epidemiology and risk factors. Enferm. Infecc. Microbiol. Clin. 29(7), 502–509 (2011).
pubmed: 21570159
doi: 10.1016/j.eimc.2011.03.005
Khanna, K. & Sabharwal, S. Spinal tuberculosis: A comprehensive review for the modern spine surgeon. Spine J. 19(11), 1858–1870 (2019).
pubmed: 31102727
doi: 10.1016/j.spinee.2019.05.002
Kim, J.-H. et al. Delayed diagnosis of extrapulmonary tuberculosis presenting as fever of unknown origin in an intermediate-burden country. BMC Infect. Dis. https://doi.org/10.1186/s12879-018-3349-5 (2018).
doi: 10.1186/s12879-018-3349-5
pubmed: 30587154
pmcid: 6307147
Gilpin, C., Korobitsyn, A., Migliori, G. B., Raviglione, M. C. & Weyer, K. The World Health Organization standards for tuberculosis care and management. Eur. Respir. J. 51(3), 1800098 (2018).
pubmed: 29567724
doi: 10.1183/13993003.00098-2018
Margraf, J. T. Science-driven atomistic machine learning. Angew. Chem. Int. Ed. Engl. 62(26), e202219170 (2023).
pubmed: 36896758
doi: 10.1002/anie.202219170
Srinivas, S. & Young, A. J. Machine learning and artificial intelligence in surgical research. Surg. Clin. N. Am. 103(2), 299–316 (2023).
pubmed: 36948720
doi: 10.1016/j.suc.2022.11.002
Ota, R. & Yamashita, F. Application of machine learning techniques to the analysis and prediction of drug pharmacokinetics. J. Control Release 352, 961–969 (2022).
pubmed: 36370876
doi: 10.1016/j.jconrel.2022.11.014
Guo, T. & Li, X. Machine learning for predicting phenotype from genotype and environment. Curr. Opin. Biotechnol. 79, 102853 (2023).
pubmed: 36463837
doi: 10.1016/j.copbio.2022.102853
Mondal, P. P. et al. Review on machine learning-based bioprocess optimization, monitoring, and control systems. Bioresour. Technol. 370, 128523 (2023).
pubmed: 36565820
doi: 10.1016/j.biortech.2022.128523
Duan, S. et al. Accurate differentiation of spinal tuberculosis and spinal metastases using MR-based deep learning algorithms. Infect. Drug Resist. 16, 4325–4334 (2023).
pubmed: 37424672
pmcid: 10329448
doi: 10.2147/IDR.S417663
Li, Z. et al. Computer-aided diagnosis of spinal tuberculosis from CT images based on deep learning with multimodal feature fusion. Front. Microbiol. 13, 823324 (2022).
pubmed: 35283815
pmcid: 8905347
doi: 10.3389/fmicb.2022.823324
Zhou, C. et al. MMP9 and STAT1 are biomarkers of the change in immune infiltration after anti-tuberculosis therapy, and the immune status can identify patients with spinal tuberculosis. Int. Immunopharmacol. 116, 109588 (2023).
pubmed: 36773569
doi: 10.1016/j.intimp.2022.109588
Wu, S. et al. Proteomic analysis to identification of hypoxia related markers in spinal tuberculosis: A study based on weighted gene co-expression network analysis and machine learning. BMC Med. Genom. 16(1), 142 (2023).
doi: 10.1186/s12920-023-01566-z
Chen, L. et al. Mechanism of COVID-19-related proteins in spinal tuberculosis: Immune dysregulation. Front. Immunol. 13, 882651 (2022).
pubmed: 35720320
pmcid: 9202521
doi: 10.3389/fimmu.2022.882651
Borislavov, L., Nedyalkova, M., Tadjer, A., Aydemir, O. & Romanova, J. Machine learning-based screening for potential singlet fission chromophores: The challenge of imbalanced data sets. J. Phys. Chem. Lett. 14(45), 10103–10112 (2023).
pubmed: 37921710
doi: 10.1021/acs.jpclett.3c02365
Jiang, X. & Xu, C. Deep learning and machine learning with grid search to predict later occurrence of breast cancer metastasis using clinical data. J. Clin. Med. 11(19), 5772 (2022).
pubmed: 36233640
pmcid: 9570670
doi: 10.3390/jcm11195772
He, J. et al. Accurate classification of pulmonary nodules by a combined model of clinical, imaging, and cell-free DNA methylation biomarkers: A model development and external validation study. Lancet Digit Health https://doi.org/10.1016/S2589-7500(23)00125-5 (2023).
doi: 10.1016/S2589-7500(23)00125-5
pubmed: 38065778
Obuchowski, N. A. & Bullen, J. A. Receiver operating characteristic (ROC) curves: Review of methods with applications in diagnostic medicine. Phys. Med. Biol. 63(7), 07TR1 (2018).
doi: 10.1088/1361-6560/aab4b1
Li, W. & Guo, Q. Plotting receiver operating characteristic and precision-recall curves from presence and background data. Ecol. Evol. 11(15), 10192–10206 (2021).
pubmed: 34367569
pmcid: 8328458
doi: 10.1002/ece3.7826
Vickers, A. J. & Elkin, E. B. Decision curve analysis: A novel method for evaluating prediction models. Med. Decis. Mak. 26(6), 565–574 (2006).
doi: 10.1177/0272989X06295361
Fenlon, C., O’Grady, L., Doherty, M. L. & Dunnion, J. A discussion of calibration techniques for evaluating binary and categorical predictive models. Prev. Vet. Med. 149, 107–114 (2018).
pubmed: 29290291
doi: 10.1016/j.prevetmed.2017.11.018
Scodari, B. T., Chacko, S., Matsumura, R. & Jacobson, N. C. Using machine learning to forecast symptom changes among subclinical depression patients receiving stepped care or usual care. J. Affect. Disord. 340, 213–220 (2023).
pubmed: 37541599
doi: 10.1016/j.jad.2023.08.004
Li, J. et al. Predicting mortality in intensive care unit patients with heart failure using an interpretable machine learning model: Retrospective cohort study. J. Med. Internet Res. 24(8), e38082 (2022).
pubmed: 35943767
pmcid: 9399880
doi: 10.2196/38082
Belkin, M., Hsu, D., Ma, S. & Mandal, S. Reconciling modern machine-learning practice and the classical bias-variance trade-off. Proc. Natl. Acad. Sci. U. S. A. 116(32), 15849–15854 (2019).
pubmed: 31341078
pmcid: 6689936
doi: 10.1073/pnas.1903070116
Peghin, M. et al. The changing epidemiology of spinal tuberculosis: the influence of international immigration in Catalonia, 1993–2014. Epidemiol. Infect. 145(10), 2152–2160 (2017).
pubmed: 28516818
pmcid: 9203422
doi: 10.1017/S0950268817000863
Chen, S. H., Lin, W. C., Lee, C. H. & Chou, W. Y. Spontaneous infective spondylitis and mycotic aneurysm: Incidence, risk factors, outcome and management experience. Eur. Spine J. 17(3), 439–444 (2008).
pubmed: 18046585
doi: 10.1007/s00586-007-0551-3
Xu, G. et al. Proteomic analysis reveals critical molecular mechanisms involved in the macrophage anti-spinal tuberculosis process. Tuberculosis (Edinb.) 126, 102039 (2021).
pubmed: 33316736
doi: 10.1016/j.tube.2020.102039
Sun, Z., Pang, X., Wang, X. & Zeng, H. Differential expression analysis of miRNAs in macrophage-derived exosomes in the tuberculosis-infected bone microenvironment. Front. Microbiol. 14, 1236012 (2023).
pubmed: 37601387
pmcid: 10435735
doi: 10.3389/fmicb.2023.1236012
Yao, Y. et al. Identification of spinal tuberculosis subphenotypes using routine clinical data: A study based on unsupervised machine learning. Ann. Med. 55(2), 2249004 (2023).
pubmed: 37611242
pmcid: 10448834
doi: 10.1080/07853890.2023.2249004
Yang, L. et al. Monocyte-to-lymphocyte ratio is associated with 28-day mortality in patients with acute respiratory distress syndrome: A retrospective study. J. Intensive Care https://doi.org/10.1186/s40560-021-00564-6 (2021).
doi: 10.1186/s40560-021-00564-6
pubmed: 34663479
pmcid: 8522140
Muller, B. L. et al. Inflammatory and immunogenetic markers in correlation with pulmonary tuberculosis. J. Bras. Pneumol. 39(6), 719–727 (2013).
pubmed: 24473766
pmcid: 4075896
doi: 10.1590/S1806-37132013000600011
Kim, J. H. et al. Prognostic factors for unfavourable outcomes of patients with spinal tuberculosis in a country with an intermediate tuberculosis burden: A multicentre cohort study. Bone Jt. J. 101(12), 1542–9 (2019).
doi: 10.1302/0301-620X.101B12.BJJ-2019-0558.R1
Tang, L. et al. Clinical features and outcomes of spinal tuberculosis in central China. Infect. Drug Resist. 15, 6641–6650 (2022).
pubmed: 36386413
pmcid: 9664916
doi: 10.2147/IDR.S384442
Huang, Y., Wu, R., Xia, Q., Liu, L. & Feng, G. Prognostic values of geriatric nutrition risk index on elderly patients after spinal tuberculosis surgery. Front. Nutr. 10, 1229427 (2023).
pubmed: 37614748
pmcid: 10442490
doi: 10.3389/fnut.2023.1229427
Chen, L. et al. Monocyte-to-lymphocyte ratio was an independent factor of the severity of spinal tuberculosis. Oxid. Med. Cell Longev. 2022, 7340330 (2022).
pubmed: 35633888
pmcid: 9142277
Luo, M. et al. Monocyte at diagnosis as a prognosis biomarker in tuberculosis patients with anemia. Front. Med. (Lausanne) 10, 1141949 (2023).
pubmed: 37351072
doi: 10.3389/fmed.2023.1141949
Nonaka, M. et al. Risk factors for clinical progression in patients with pulmonary Mycobacterium avium complex disease without culture-positive sputum: A single-center, retrospective study. Eur. J. Med. Res. 28(1), 186 (2023).
pubmed: 37291649
pmcid: 10249251
doi: 10.1186/s40001-023-01152-0
Trovato, F. M. et al. Lysophosphatidylcholines modulate immunoregulatory checkpoints in peripheral monocytes and are associated with mortality in people with acute liver failure. J. Hepatol. 78(3), 558–573 (2023).
pubmed: 36370949
doi: 10.1016/j.jhep.2022.10.031
Orchanian, S. B. & Lodoen, M. B. Monocytes as primary defenders against Toxoplasma gondii infection. Trends Parasitol. 39(10), 837–849 (2023).
pubmed: 37633758
doi: 10.1016/j.pt.2023.07.007
Hou, P. et al. Macrophage polarization and metabolism in atherosclerosis. Cell Death Dis. 14(10), 691 (2023).
pubmed: 37863894
pmcid: 10589261
doi: 10.1038/s41419-023-06206-z
Meidaninikjeh, S. et al. Monocytes and macrophages in COVID-19: Friends and foes. Life Sci. 269, 119010 (2021).
pubmed: 33454368
pmcid: 7834345
doi: 10.1016/j.lfs.2020.119010
Sia, J. K. & Rengarajan, J. Immunology of Mycobacterium tuberculosis infections. Microbiol. Spectr. https://doi.org/10.1128/microbiolspec.GPP3-0022-2018 (2019).
doi: 10.1128/microbiolspec.GPP3-0022-2018
pubmed: 31298204
Liang, T. et al. STAT1 and CXCL10 involve in M1 macrophage polarization that may affect osteolysis and bone remodeling in extrapulmonary tuberculosis. Gene 809, 146040 (2022).
pubmed: 34710525
doi: 10.1016/j.gene.2021.146040
Galbusera, F., Casaroli, G. & Bassani, T. Artificial intelligence and machine learning in spine research. JOR Spine 2(1), e1044 (2019).
pubmed: 31463458
pmcid: 6686793
doi: 10.1002/jsp2.1044
Garrett, B. L. & Rudin, C. Interpretable algorithmic forensics. Proc. Natl. Acad. Sci. U. S. A. 120(41), e2301842120 (2023).
pubmed: 37782786
pmcid: 10576126
doi: 10.1073/pnas.2301842120
van der Velden, B. H. M., Kuijf, H. J., Gilhuijs, K. G. A. & Viergever, M. A. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med. Image Anal. 79, 102470 (2022).
pubmed: 35576821
doi: 10.1016/j.media.2022.102470
Zhang, C. et al. A deep learning image data augmentation method for single tumor segmentation. Front. Oncol. 12, 782988 (2022).
pubmed: 35237511
pmcid: 8882602
doi: 10.3389/fonc.2022.782988
Cheung, T. H. & Yeung, D. Y. A survey of automated data augmentation for image classification: Learning to compose, mix, and generate. IEEE Trans. Neural Netw. Learn. Syst. https://doi.org/10.1109/TNNLS.2023.3282258 (2023).
doi: 10.1109/TNNLS.2023.3282258
pubmed: 37566497