Development and validation of a generalizable M-protein screening model using routine laboratory indicators: a multicenter retrospective study.

Background

Early detection of plasma cell disorders (PCDs) remains challenging due to limited accessibility of gold standard diagnostic methods. This study aimed to develop a simple M-protein screening model using routine laboratory indicators for clinical laboratories.

Methods

A total of 5217 participants from three Chinese hospitals were enrolled. The derivation cohort (n = 3019) was randomly divided into training and internal validation cohorts. Two external validation cohorts (n = 1747 and n = 451) were included. M-protein positivity was rigorously defined by SPE combined with IFE. Demographic data and routine laboratory blood parameters were collected for model development. Eight machine learning algorithms-Logistic regression (LR), k-nearest neighbors classifier, decision tree classifier, random forest classifier, AdaBoost classifier, linear discriminant analysis, quadratic discriminant analysis, and multilayer perceptron classifier-were used to construct M-protein screening models.

Results

Eight M-protein screening models were established, incorporating indicators including sex, age, total protein, albumin, albumin/globulin ratio, and hemoglobin. Based on a comprehensive evaluation of models' performance and generalization ability, the LR model was identified as the optimal model, with an AUC of 0.843. A five-tier risk stratification was established based on predicted probabilities (P): ≤15.0%, 15.0-40.0%, 40.0-70.0%, 70.0-90.0%, and ≥ 90.0%. The model's performance in the internal validation cohort and two external validation cohorts also met expectations, with AUCs of 0.843, 0.801, and 0.800, respectively.

Conclusion

We developed and validated a practical M-protein screening model based on routine laboratory indicators. The LR model demonstrated robust predictive ability and offers an accessible tool to facilitate early identification of individuals at high risk of M-protein, thereby supporting early diagnosis of clinically relevant PCDs, particularly in resource-limited primary healthcare settings.