Prediction model for spinal cord injury in spinal tuberculosis patients using multiple machine learning algorithms: a multicentric study

被引：6

作者：

Feng S. ^{[1
]}

Wang S. ^{[2
]}

Liu C. ^{[1
]}

Wu S. ^{[1
]}

Zhang B. ^{[1
,3
]}

Lu C. ^{[4
]}

Huang C. ^{[1
]}

Chen T. ^{[1
]}

Zhou C. ^{[1
]}

Zhu J. ^{[1
]}

Chen J. ^{[1
]}

Xue J. ^{[1
]}

Wei W. ^{[1
]}

Zhan X. ^{[1
]}

机构：

[1] Department of Spine and Osteopathy Ward, The First Affiliated Hospital of Guangxi Medical University, Guangxi, Nanning

[2] Department of Outpatient, General Hospital of Eastern Theater Command, Jiangsu, Nanjing

[3] Department of Spine Ward, Bei Jing Ji Shui Tan Hospital Gui Zhou Hospital, Guizhou, Guiyang

[4] Department of Spine and Osteopathy Ward, Bai Se People’s Hospital, Guangxi, Baise

来源：

Scientific Reports | / 14卷 / 1期

关键词：

Machine learning; Model deployment; Model interpretation; Predictive model; Spinal cord injury; Spinal tuberculosis;

D O I：

10.1038/s41598-024-56711-0

中图分类号：

学科分类号：

摘要：

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. © The Author(s) 2024.

引用

共 52 条

[21]

He J., Wang B., Tao J., Liu Q., Peng M., Xiong S., 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, (2023)

[22]

Obuchowski N.A., Bullen J.A., Receiver operating characteristic (ROC) curves: Review of methods with applications in diagnostic medicine, Phys. Med. Biol, 63, 7, (2018)

[23]

Li W., Guo Q., Plotting receiver operating characteristic and precision-recall curves from presence and background data, Ecol. Evol, 11, 15, pp. 10192-10206, (2021)

[24]

Vickers A.J., Elkin E.B., Decision curve analysis: A novel method for evaluating prediction models, Med. Decis. Mak, 26, 6, pp. 565-574, (2006)

[25]

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, pp. 107-114, (2018)

[26]

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, pp. 213-220, (2023)

[27]

Li J., Liu S., Hu Y., Zhu L., Mao Y., Liu J., 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, (2022)

[28]

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, pp. 15849-15854, (2019)

[29]

Peghin M., Rodriguez-Pardo D., Sanchez-Montalva A., Pellise F., Rivas A., Tortola T., Et al., The changing epidemiology of spinal tuberculosis: the influence of international immigration in Catalonia, 1993–2014, Epidemiol. Infect, 145, 10, pp. 2152-2160, (2017)

[30]

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, pp. 439-444, (2008)

← 1 2 3 4 5 6 →