Validation of biomarkers and clinical scores for the detection of uterine leiomyosarcoma: a case-control study with an update of pLMS

Abstract

Background: The diagnosis of rare uterine leiomyosarcoma (uLMS) remains a challenge given the high incidence rates of benign uterine tumors such as leiomyoma (LM). In the last decade, several clinical scores and blood serum markers have been proposed. The aim of this study is to validate and update the pLMS clinical scoring system, evaluating the accuracy of the scoring system by Zhang et al. and examining the discriminatory ability of blood markers such as serum lactate dehydrogenase (LDH), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR).

Methods: In a case-control study, 90 new uLMS from the DKSM consultation registry and 659 prospectively recruited LM cases from the Saarland University Hospital were used for validation. Welch's t-test and Hedges' g were used to evaluate blood markers and optimal thresholds and diagnostic odds ratios were calculated. Scoring systems were compared using receiver operating characteristics and proposed diagnostic cut-offs were reviewed. Missing values were imputed by random forest imputation to create the updated scoring system 'pLMS2' using penalized logistic regression based on the pooled data sets of 384 uLMS and 1485 LM.

Results: pLMS achieved an AUC of 0.97 on the validation data, but sensitivity and specificity varied at the proposed thresholds due to a shift in the score distributions. 43 uLMS and 578 LM were included in the comparison of pLMS with Zhang's scoring system, with pLMS being superior (AUC 0.960 vs 0.845). LDH, NLR, and PLR achieved a diagnostic odds ratios of 18.03, 8.64 and 4.81, respectively. pLMS2 is based on subscores for menopausal status interacting with age, tumor diameter, intermenstrual bleeding, hypermenorrhea, dysmenorrhea, postmenstrual bleeding, rapid tumor growth, and suspicious sonography.

Conclusions: Validation of the pLMS shows stable discriminatory ability as expressed by AUC, although caution should be taken with cut-off values, as sensitivity and specificity may vary. Data collection of the updated clinical score pLMS2 remains simple and convenient, with no additional cost. The proposed thresholds of 1.5 and 5.5 can be used as a guide to avoid unnecessary or inappropriate surgery and to make the use of further diagnostic measures cost-effective. LDH, NLR and PLR provide further evidence to differentiate uLMS from LM in conjunction with clinical data.

Keywords: Clinical score; Diagnostics; Lactate dehydrogenase; Leiomyoma; Neutrophil-to-lymphocyte-ratio; Platelet-to-lymphocyte-ratio; Uterine leiomyosarcoma.

Fig. 1

Flowchart of patient population and data flow for training and validation

Fig. 2

Continuous predictors of uterine leiomyosarcoma (uLMS) vs. leiomyoma (LM). Distributions are plotted with case numbers for: I Age; II Largest tumor diameter; III Serum lactate dehydrogenase; IV Platelet-to-lymphocyte ratio; V Neutrophil-to-lymphocyte ratio

Fig. 3

Receiver operating characteristic of pLMS applied to training and validation data. False positive (FPR) and true positive rates (TPR) vary at the proposed diagnostic thresholds at −3 and +1, although the AUC values do not differ

Fig. 4

Distribution of pLMS in the training and validation datasets. Tumor classification in the validation set is still good, but there is a slight shift in both, LM and LMS, towards higher scores can be seen. Threshold calibration may be required

Fig. 5

Comparison and correlation of the scoring systems by Zhang et al. and Köhler et al. (pLMS). Left: Absolute number of LM and uLMS at each Zhang score based on imputed data using predictive mean matching (PMM) with boxplots of pLMS. Right: ROC curves with DeLong confidence intervals for the AUC for pLMS and Zhang score based on PMM imputed data and random forest imputed data (RF). The labels indicate the diagnostic cut-off for the Zhang score

Fig. 6

Score distribution of the integer score system pLMS2 and LMS relative risk. Empirical relative risk is demonstrated at different prevalence rates, leading to proposed diagnostic thresholds of 1.5 and 5.5