Development and validation of a machine learning-based nomogram for predicting HLA-B27 expression

Abstract

Background: HLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.

Methods: This study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.

Results: Six factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.

Conclusion: To conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.

Keywords: HLA-B27; Immunological diseases; Machine learning algorithms; Nomogram; Prediction model.

Fig. 1

Heatmap showing associations of diverse involved variables are shown

Fig. 2

Randomforest screening variables. a The 30 most vital elements measured based on the 2 random forest algorithms including “IncNodePurity” and “%IncMSE”. b This perfect regression impact is acquired through maintaining 20 vital variables following 10-fold cross-validation

Fig. 3

Cross-validation was used for the LASSO coefficient profiles and optimum penalty parameter lambda for factors. a LASSO regression for dependent variables. b 24 significantly different variables in cases with HLA-B27 positivity relative to negativity

Fig. 4

Thirty factors were chosen to be diagnostic models using SVM-RFE calculation

Fig. 5

Selected variable intersection based on LASSO, SVM-RFE as well as Random forest

Fig. 6

AUCs for selected variable intersection

Fig. 7

The HLA-B27 model for training cohort. a HLA-B27 probability predicted by the nomogram. b Calibration curves for prediction of HLA-B27 probability. c Nomogram AUC based on HLA-B27 diagnostic model. d Decision curve analysis showing HLA-B27 model

Fig. 8

Validation cohort. a The AUC value of HLA-B27 diagnostic model in the validation cohort. b Calibration curves of HLA-B27 model for validation set

Fig. 9

The AUC value for ALB/GLB of validation set