ISTH Congress Abstracts

Official abstracts site for the ISTH Congress

MENU 
  • Home
  • Congress Archive
    • ISTH 2022 Congress
    • ISTH 2021 Congress
    • ISTH 2020 Congress
  • Resources
  • Search

Diagnosing Heparin-induced Thrombocytopenia Using Machine Learning Algorithms: First Data of the TORADI-HIT Study

H. Nilius1, J.-D. Studt2, D.A. Tsakiris3, A. Greinacher4, A. Mendez5, A. Schmidt6, W.A. Wuillemin7, B. Gerber8, P. Vishnu9, L. Graf10, T. Bakchoul11, M. Nagler1

1University of Bern / University Institute of Clinical Chemistry, Bern, Switzerland, 2University and University Hospital Zurich / Division of Medical Oncology and Hematology, Zurich, Switzerland, 3Basel University Hospital / Diagnostic Haematology, Basel, Switzerland, 4Universitätsmedizin Greifswald / Institut für Immunologie und Transfusionsmedizin, Greifswald, Germany, 5Kantonsspital Aarau / Department of Laboratory Medicine, Aarau, Switzerland, 6City Hospital Waid and Triemli / Institute of Laboratory Medicine and Clinic of Medical Oncology and Hematology, Zurich, Switzerland, 7Cantonal Hospital of Lucerne and University of Bern / Division of Hematology and Central Hematology Laboratory, Lucerne, Switzerland, 8Oncology Institute of Southern Switzerland / Clinic of Hematology, Bellinzona, Switzerland, 9CHI Franciscan Medical Group / Division of Hematology, Seattle, United States, 10Cantonal Hospital of St Gallen, St Gallen, Switzerland, 11University Hospital of Tübingen / Centre for Clinical Transfusion Medicine, Tübingen, Germany

Abstract Number: PB0855

Meeting: ISTH 2021 Congress

Theme: Platelet Disorders, von Willebrand Disease and Thrombotic Microangiopathies » HIT

Background: Diagnosing heparin-induced thrombocytopenia (HIT) at the bedside is challenging, and current diagnostic algorithms expose patients to a considerable risk of overtreatment and delayed diagnosis.

Aims: We conducted a prospective multicenter study detailedly acquiring clinical and laboratory variables to assess the diagnostic performance of these variables and to develop an easy-to-apply clinical prediction model.

Methods: Consecutive patients with suspected HIT were included in 11 study centers and detailed clinical data were collected. Heparin-induced platelet activation assay (HIPA; reference standard) and various immunoassays were conducted at the central laboratory. Variables with a p-value < 0.05 for each level in a multivariable logistic regression were selected for the final model. Using 75% of the patients, logistic regression, penalized logistic regression, two random forest, and gradient boosting machine models were trained. The models were evaluated on the remaining 25% (validation set). The performance of the model with the best c-statistic was then compared to the current clinical practice.

Results: To date, we enrolled 1’182 patients with suspected HIT; the prevalence of HIT was 9.3%. Variables selected for the final model were: platelet nadir, use of unfractionated heparin, timing of thrombocytopenia, presence of other causes of thrombocytopenia, and immunoassay test result. Applied to the validation set and using an IgG-specific ELISA, the c-statistic of the random forest model was 98.8% (95% confidence interval [CI]: 97.7, 99.9), the sensitivity was 96.0% (95% CI: 79.6, 99.8) and the specificity 97.3% (95% CI: 93.0, 98.1). In contrast, the sensitivity of the currently recommended diagnostic algorithm was 80.0% (95% CI: 59.3, 93.2), and the specificity 89.1% (95% CI: 84.6, 92.6).

Conclusions: Using detailed clinical and laboratory data and machine-learning algorithms, we developed and validated an accurate clinical prediction model for the diagnosis of HIT. This model has the potential to relevantly reduce overtreatment and delayed diagnosis in clinical practice.

Diagnostic accuracy of a random-forest-based clinical prediction model in contrast to the currently recommended diagnostic algorithm. Proportions of false negatives, false positives, true positives, and true negatives are shown.

To cite this abstract in AMA style:

Nilius H, Studt J-, Tsakiris DA, Greinacher A, Mendez A, Schmidt A, Wuillemin WA, Gerber B, Vishnu P, Graf L, Bakchoul T, Nagler M. Diagnosing Heparin-induced Thrombocytopenia Using Machine Learning Algorithms: First Data of the TORADI-HIT Study [abstract]. Res Pract Thromb Haemost. 2021; 5 (Suppl 2). https://abstracts.isth.org/abstract/diagnosing-heparin-induced-thrombocytopenia-using-machine-learning-algorithms-first-data-of-the-toradi-hit-study/. Accessed September 22, 2023.

« Back to ISTH 2021 Congress

ISTH Congress Abstracts - https://abstracts.isth.org/abstract/diagnosing-heparin-induced-thrombocytopenia-using-machine-learning-algorithms-first-data-of-the-toradi-hit-study/

Simple Search

Supported By:

Takeda logo

ISTH 2022 Congress site

Visit the official web site for the ISTH 2022 Virtual Congress »

  • Help & Support
  • About Us
  • Cookies & Privacy
  • Wiley Job Network
  • Terms & Conditions
  • Advertisers & Agents
Copyright © 2023 John Wiley & Sons, Inc. All Rights Reserved.
Wiley