Identification of spinal tuberculosis subphenotypes using routine clinical data: a study based on unsupervised machine learning

Abstract

Objective: The identification of spinal tuberculosis subphenotypes is an integral component of precision medicine. However, we lack proper study models to identify subphenotypes in patients with spinal tuberculosis. Here we identified possible subphenotypes of spinal tuberculosis and compared their clinical results.

Methods: A total of 422 patients with spinal tuberculosis who received surgical treatment were enrolled. Clustering analysis was performed using the K-means clustering algorithm and the routinely available clinical data collected from patients within 24 h after admission. Finally, the differences in clinical characteristics, surgical efficacy, and postoperative complications among the subphenotypes were compared.

Results: Two subphenotypes of spinal tuberculosis were identified. Laboratory examination results revealed that the levels of more than one inflammatory index in cluster 2 were higher than those in cluster 1. In terms of disease severity, Cluster 2 showed a higher Oswestry Disability Index (ODI), a higher visual analysis scale (VAS) score, and a lower Japanese Orthopedic Association (JOA) score. In addition, in terms of postoperative outcomes, cluster 2 patients were more prone to complications, especially wound infections, and had a longer hospital stay.

Conclusion: K-means clustering analysis based on conventional available clinical data can rapidly identify two subtypes of spinal tuberculosis with different clinical results. We believe this finding will help clinicians to rapidly and easily identify the subtypes of spinal tuberculosis at the bedside and become the cornerstone of individualized treatment strategies.

Keywords: K-means; Spinal tuberculosis; cluster analysis; heterogeneity; machine learning.

Figure 1.

The process of K-means cluster analysis. (A) The correlation matrix. (B) The ordered dissimilarity matrix. (C) Optimal clustering number of the K-means clustering algorithm was determined by Silhouette coefficient (SC). (D) Scatter plots of patients’clinical data. Scatter points on the graph represent each patient, and the K-means clustering algorithm divides patients into two clusters.

Figure 2.

The radar chart of preoperative variables of spinal tuberculosis patients in two clusters. The K-means clustering algorithm normalized preoperative variables were compared between two clusters. Spoke lengths represent the average of each variable after the K-means clustering algorithm is normalized. Significance levels are presented with asterisks. **p-value < 0.01, ***p-value < 0.001.

Figure 3.

Comparison of disease severity between two clusters of spinal tuberculosis patients. (A) The differences in ODI scores between two clusters. (B) The differences in JOA scores between two clusters. (C) The differences in VAS scores between two clusters. *p-value < 0.05, ***p-value < 0.001.

Figure 4.

Correlation analysis between preoperative variables and disease severity. (A) Correlation between ODI score and preoperative variables. (B) Correlation between JOA score and preoperative variables. (C) Correlation between VAS score and preoperative variables.

Figure 5.

The radar chart of postoperative variables of spinal tuberculosis patients in two clusters. The K-means clustering algorithm normalized postoperative variables and were compared between two clusters. Spoke lengths represent the average of each variable after the K-means clustering algorithm is normalized. Significance levels are presented with asterisks. *p-value < 0.05, **p-value < 0.01.