Predictors of von Willebrand disease diagnosis in individuals with borderline von Willebrand factor plasma levels

Early diagnosis of persons with von Willebrand disease using a machine learning algorithm and real-world data

BACKGROUND

Von Willebrand disease (VWD) is underdiagnosed, often delaying treatment. VWD claims coding is limited and includes no severity qualifiers; improved identification methods for VWD are needed. The aim of this study is to identify and characterize undiagnosed symptomatic persons with VWD in the US from medical insurance claims using predictive machine learning (ML) models.

RESEARCH DESIGN AND METHODS

Diagnosed and potentially undiagnosed VWD cohorts were defined using Komodo longitudinal US claims data (January 2015-March 2020). ML models were built using key characteristics predictive of VWD diagnosis from the diagnosed cohort. Two ML models predicted VWD diagnosis with the highest accuracy in females (random forest; 84%) and males (gradient boosting machine; 85%). Undiagnosed persons suspected to have VWD were identified using an 80% cutoff probability; profiles of key characteristics were constructed.

RESULTS

The trained ML models were applied to the undiagnosed cohort (28,463 females; 20,439 males) with suspected VWD. Fifty-two percent of undiagnosed females had heavy menstrual bleeding, a key pre-diagnosis symptom. Undiagnosed males tended to have more frequent medical procedures, hospitalizations, and emergency room visits compared with undiagnosed females.

CONCLUSIONS

ML algorithms successfully identified potentially undiagnosed symptomatic people with VWD, although many may remain undiagnosed and undertreated. External validation of the algorithms is recommended.

von Willebrand factor levels in the diagnosis of von Willebrand disease: a systematic review and meta-analysis

von Willebrand disease (VWD) is associated with significant morbidity as a result of excessive mucocutaneous bleeding. Early diagnosis and treatment are important to prevent and treat these symptoms. We systematically reviewed the accuracy of diagnostic tests using different cutoff values of von Willebrand factor antigen (VWF:Ag) and platelet-dependent von Willebrand factor (VWF) activity assays in the diagnosis of VWD. We searched Cochrane Central Register for Controlled Trials, MEDLINE, and Embase databases for eligible studies. We pooled estimates of sensitivity and specificity and reported patient-important outcomes when relevant. This review included 21 studies that evaluated VWD diagnosis. The results showed low certainty in the evidence for a net health benefit from reconsidering the diagnosis of VWD vs removing the disease diagnosis in patients with VWF levels that have normalized with age. For the diagnosis of type 1 VWD, VWF sequence variants were detected in 75% to 82% of patients with VWF:Ag < 0.30 IU/mL and in 44% to 60% of patients with VWF:Ag between 0.30 and 0.50 IU/mL. A sensitivity of 0.90 (95% confidence interval [CI], 0.83-0.94) and a specificity of 0.91 (95% CI, 0.76-0.97) were observed for a platelet-dependent VWF activity/VWF:Ag ratio < 0.7 in detecting type 2 VWD (moderate certainty in the test accuracy results). VWF:Ag and platelet-dependent activity are continuous variables that are associated with an increase in bleeding risk with decreasing levels. This systematic review shows that using a VWF activity/VWF:Ag ratio < 0.7 vs lower cutoff levels in patients with an abnormal initial VWD screen is more accurate for the diagnosis of type 2 VWD.

Von Willebrand Disease: Current Status of Diagnosis and Management

Von Willebrand disease (VWD) is a common bleeding disorder, affecting male and female individuals equally, that often manifests in mucosal bleeding. VWD can be secondary to a quantitative (Type 1 and Type 3) or qualitative (Type 2) defects in Von Willebrand factor (VWF). Initial testing includes VWF antigen, as well as a platelet binding assay to differentiate between qualitative and quantitative defects. Further subtyping requires additional testing and is needed to ensure appropriate treatment. Desmopressin, antifibrinolytics, hormonal treatments for heavy menstrual bleeding, and VWF concentrates are commonly used in the treatment of VWD.

ASH ISTH NHF WFH 2021 guidelines on the diagnosis of von Willebrand disease

BACKGROUND

von Willebrand disease (VWD) is the most common inherited bleeding disorder known in humans. Accurate and timely diagnosis presents numerous challenges.

OBJECTIVE

These evidence-based guidelines of the American Society of Hematology (ASH), the International Society on Thrombosis and Haemostasis (ISTH), the National Hemophilia Foundation (NHF), and the World Federation of Hemophilia (WFH) are intended to support patients, clinicians, and other health care professionals in their decisions about VWD diagnosis.

METHODS

ASH, ISTH, NHF, and WFH established a multidisciplinary guideline panel that included 4 patient representatives and was balanced to minimize potential bias from conflicts of interest. The Outcomes and Implementation Research Unit at the University of Kansas Medical Center (KUMC) supported the guideline-development process, including performing or updating systematic evidence reviews up to 8 January 2020. The panel prioritized clinical questions and outcomes according to their importance for clinicians and patients. The panel used the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach, including GRADE Evidence-to-Decision frameworks, to assess evidence and make recommendations, which were subsequently subject to public comment.

RESULTS

The panel agreed on 11 recommendations.

CONCLUSIONS

Key recommendations of these guidelines include the role of bleeding-assessment tools in the assessment of patients suspected of VWD, diagnostic assays and laboratory cutoffs for type 1 and type 2 VWD, how to approach a type 1 VWD patient with normalized levels over time, and the role of genetic testing vs phenotypic assays for types 2B and 2N. Future critical research priorities are also identified.

Utility of repeat testing in the evaluation for von Willebrand disease in pediatric patients

BACKGROUND

Von Willebrand disease (VWD) is the most common inherited bleeding disorder and is caused by quantitative and qualitative defects in von Willebrand factor (VWF). The laboratory diagnosis of VWD in pediatric patients is complicated by VWF interassay and intra-assay variability, stress-induced elevations in VWF levels, and a lack of significant bleeding history with which to correlate test results.

OBJECTIVE

Guidelines recommend repeat testing in patients with a high suspicion of VWD and unclear laboratory assay results; however, no studies have evaluated the utility of repeat VWF testing in pediatric patients.

METHODS

This retrospective single-center cohort study aimed to determine clinical variables associated with requiring more than one test to diagnose VWD and to establish a cutoff VWF value above which further testing is not informative.

RESULTS

Of 811 patients evaluated for a suspected bleeding disorder, 22.2% were diagnosed with VWD, with ~70% diagnosed on the first test. Patients with VWD were younger (5.8 vs. 8.5 years, P = .002) and more likely to have a family history of VWD (38% vs. 22%, P < .001) than those without VWD. Univariate analysis failed to identify any clinical variables that correlated with needing multiple tests for a VWD diagnosis. A cutoff of 100 IU/dL for VWF antigen or activity on the first test yielded negative predictive values >95%.

CONCLUSIONS

We demonstrate that the majority of pediatric patients had diagnostic VWF values on the first set of testing. Pediatric patients without a family history of VWD and VWF levels >100 IU/dL may not need further testing to rule out the diagnosis of VWD.

[Von Willebrand disease]

Von Willebrand factor is involved in primary hemostasis (adhesion of platelets to subendothelium and platelet aggregation) and acts as the carrier of coagulation factor VIII. Von Willebrand disease, resulting from a quantitative or qualitative defect of this factor, is the most frequent inherited bleeding disorder. It is mainly responsible for symptoms such as mucocutaneous bleeding and excessive bleeding after trauma or invasive procedures, but can also cause gastro-intestinal bleeding or hemarthrosis in the most severe forms of the disease. There are numerous causes of physiological variation of von Willebrand factor plasma levels which can be responsible for diagnostic difficulty or changes in symptoms over time. Diagnosis relies primarily on clinical symptoms but requires the use of several laboratory analyses: von Willebrand factor activity and antigen testing and factor VIII activity. More specialized assays allow classification of the disease in various types and subtypes which imply different management strategies (types 1, 2A, 2B, 2M, 2N, and 3). Treatment is based on desmopressin, responsible for an increase in plasma concentration of von Willebrand factor, and plasma-derived von Willebrand factor concentrates which can be combined with factor VIII.

Bleeding score in type 1 von Willebrand disease patients using the condensed MCMDM-1 vWD validated questionnaire

BACKGROUND

Assessment of the severity of bleeding symptom has led to the evolution of bleeding assessment tools which are now validated.

AIMS

To administer the condensed molecular and clinical markers for the diagnosis and management of type 1 von Willebrand disease VWD (MCMDM-1 vWD) questionnaire to the Omani type 1 vWD patients and correlate it with the laboratory parameters.

METHODS

Patients and controls were personally interviewed and the condensed MCMDM-1 vWD questionnaire administered by a single investigator. Bleeding score (BS) was calculated, based on the presence or absence of the bleeding symptoms according to a standard validated questionnaire in both the patients and the controls.

RESULTS

The median age of the patient cohort was 27 (range, 7-49) years with 60.87% of females. The median time to administer condensed MCMDM-1 BS questionnaire was 11 minutes (interquartile range-IQR;7,16). Overall, bleeding from the oral cavity was the most predominant symptom (63%). The median BS was 5 (IQR;1,8) although individual scores ranged between 0 and 29. However, there was no statistically significant difference in BS between genders (males: median 4; IQR 1,6 and females: median 5, IQR 1,10) (P > .05, Kruskal-Wallis test) The Spearman's correlation value of BS was weak with FVIII:C levels and von Willebrand Ristocetin co-factor activity; very weak with von Willebrand Antigen level, and moderate with vonWillebrand Collagen Binding activity being -0.29, -0.28, -0.14 and -0.43, respectively.

CONCLUSION

The BS reflects the severity of bleeding among the vWD patients. Although the BS was abnormal, it did not correlate significantly with the surrogate laboratory parameters [P > .05].

Bleeding score in Type 1 von Willebrand disease patients using the ISTH-BAT questionnaire

BACKGROUND

Bleeding assessment tools have evolved in the last decade to standardize the assessment of the severity of bleeding symptom in a consistent way. In 2010, the International Society on Thrombosis and Hemostasis-Bleeding Assessment Tool (ISTH-BAT) was developed and validated.

AIMS

Our aim was to administer ISTH-BAT questionnaire to the Omani patients with type 1 VWD and obtain the bleeding score (BS). We also studied the severity of their bleeding symptoms and correlated it with the BS as well as with the laboratory parameters.

METHODS

Forty-eight type I VWD index cases and 52 normal subjects were interviewed and the ISTH-BAT questionnaire administered. The BS was calculated based on a history of bleeding symptoms from 12 different sites according to the standard ISTH-BAT questionnaire. Laboratory parameters were obtained from patient's medical records.

RESULTS

The mean age of this cohort was 27 years (range, 6-49) with 60% being females. The median time to administer this questionnaire was 10 minutes with an interquartile range (IQR) from 8 to 17 minutes. Overall, the median BS was 7 (IQR; 2,11) although individual scores ranged between 0 and 36. The BS was negatively correlated with VWF: Ag, VWF: RCo, and VWF: CB and the Spearman's correlation coefficient "rho" was, respectively, -0.15, -0.08, and -0.22.

CONCLUSION

The ISTH-BAT BS is designed to reflect the severity of bleeding. Our results demonstrate the inherent variability of this bleeding pattern. We also found that the ISTH-BAT BS significantly correlated with VWF: Ag and VWF: CB.

Diagnosing von Willebrand disease: genetic analysis

Investigation of a patient with possible von Willebrand disease (VWD) includes a range of phenotypic analyses. Often, this is sufficient to discern disease type, and this will suggest relevant treatment. However, for some patients, phenotypic analysis does not sufficiently explain the patient's disorder, and for this group, genetic analysis can aid diagnosis of disease type. Polymerase chain reaction and Sanger sequencing have been mainstays of genetic analysis for several years. More recently, next-generation sequencing has become available, with the advantage that several genes can be simultaneously analyzed where necessary, eg, for discrimination of possible type 2N VWD or mild hemophilia A. Additionally, several techniques can now identify deletions/duplications of an exon or more that result in VWD including multiplex ligation-dependent probe amplification and microarray analysis. Algorithms based on next-generation sequencing data can also identify missing or duplicated regions. These newer techniques enable causative von Willebrand factor defects to be identified in more patients than previously, aiding in a specific VWD diagnosis. Genetic analysis can also be helpful in the discrimination between type 2B and platelet-type VWD and in prenatal diagnosis for families with type 3.

Current controversies in the diagnosis and management of von Willebrand disease

Von Willebrand disease (VWD) is the most common inherited bleeding disorder in the world. The spectrum of VWD spans quantitative and qualitative deficiencies of von Willebrand factor (VWF), a platelet adhesive protein. It manifests primarily as mucocutaneous bleeding, but severely affected patients may suffer soft tissue bleeding and hemarthroses. There is disagreement in the multiple guidelines published regarding diagnosis, especially of type 1 VWD, which also remains the most opaque with respect to molecular characterization. Treatment with desmopressin (DDAVP) is most effective in type 1 VWD, but regimens are not standardized. It is not clear which type 2 VWD patients with qualitative deficiencies can be treated with DDAVP and which ones should receive VWF concentrates. No guidelines stipulate which patients might benefit from prophylactic VWF infusions and how they should be dosed. These are some current controversies in VWD that are discussed in this review.