A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context
Summary: Background: Diagnosing heparin-induced thrombocytopenia (HIT) at the bedside remains challenging, exposing a significant number of patients at risk of delayed diagnosis or overtreatment. We hypothesized that machine-learning algorithms could be utilized to develop a more accurate and user-...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589537022004746 |
| _version_ | 1811212251276771328 |
|---|---|
| author | Henning Nilius Adam Cuker Sigve Haug Christos Nakas Jan-Dirk Studt Dimitrios A. Tsakiris Andreas Greinacher Adriana Mendez Adrian Schmidt Walter A. Wuillemin Bernhard Gerber Johanna A. Kremer Hovinga Prakash Vishnu Lukas Graf Alexander Kashev Raphael Sznitman Tamam Bakchoul Michael Nagler |
| author_facet | Henning Nilius Adam Cuker Sigve Haug Christos Nakas Jan-Dirk Studt Dimitrios A. Tsakiris Andreas Greinacher Adriana Mendez Adrian Schmidt Walter A. Wuillemin Bernhard Gerber Johanna A. Kremer Hovinga Prakash Vishnu Lukas Graf Alexander Kashev Raphael Sznitman Tamam Bakchoul Michael Nagler |
| author_sort | Henning Nilius |
| collection | DOAJ |
| description | Summary: Background: Diagnosing heparin-induced thrombocytopenia (HIT) at the bedside remains challenging, exposing a significant number of patients at risk of delayed diagnosis or overtreatment. We hypothesized that machine-learning algorithms could be utilized to develop a more accurate and user-friendly diagnostic tool that integrates diverse clinical and laboratory information and accounts for complex interactions. Methods: We conducted a prospective cohort study including 1393 patients with suspected HIT between 2018 and 2021 from 10 study centers. Detailed clinical information and laboratory data were collected, and various immunoassays were conducted. The washed platelet heparin-induced platelet activation assay (HIPA) served as the reference standard. Findings: HIPA diagnosed HIT in 119 patients (prevalence 8.5%). The feature selection process in the training dataset (75% of patients) yielded the following predictor variables: (1) immunoassay test result, (2) platelet nadir, (3) unfractionated heparin use, (4) CRP, (5) timing of thrombocytopenia, and (6) other causes of thrombocytopenia. The best performing models were a support vector machine in case of the chemiluminescent immunoassay (CLIA) and the ELISA, as well as a gradient boosting machine in particle-gel immunoassay (PaGIA). In the validation dataset (25% of patients), the AUROC of all models was 0.99 (95% CI: 0.97, 1.00). Compared to the currently recommended diagnostic algorithm (4Ts score, immunoassay), the numbers of false-negative patients were reduced from 12 to 6 (−50.0%; ELISA), 9 to 3 (−66.7%, PaGIA) and 14 to 5 (−64.3%; CLIA). The numbers of false-positive individuals were reduced from 87 to 61 (−29.8%; ELISA), 200 to 63 (−68.5%; PaGIA) and increased from 50 to 63 (+29.0%) for the CLIA. Interpretation: Our user-friendly machine-learning algorithm for the diagnosis of HIT (https://toradi-hit.org) was substantially more accurate than the currently recommended diagnostic algorithm. It has the potential to reduce delayed diagnosis and overtreatment in clinical practice. Future studies shall validate this model in wider settings. Funding: Swiss National Science Foundation (SNSF), and International Society on Thrombosis and Haemostasis (ISTH). |
| first_indexed | 2024-04-12T05:25:54Z |
| format | Article |
| id | doaj.art-abfa12e6d5a74c3790cf25650e4523cd |
| institution | Directory Open Access Journal |
| issn | 2589-5370 |
| language | English |
| last_indexed | 2024-04-12T05:25:54Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj.art-abfa12e6d5a74c3790cf25650e4523cd2022-12-22T03:46:17ZengElsevierEClinicalMedicine2589-53702023-01-0155101745A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in contextHenning Nilius0Adam Cuker1Sigve Haug2Christos Nakas3Jan-Dirk Studt4Dimitrios A. Tsakiris5Andreas Greinacher6Adriana Mendez7Adrian Schmidt8Walter A. Wuillemin9Bernhard Gerber10Johanna A. Kremer Hovinga11Prakash Vishnu12Lukas Graf13Alexander Kashev14Raphael Sznitman15Tamam Bakchoul16Michael Nagler17Department of Clinical Chemistry, Inselspital, Bern University Hospital, University of Bern, Bern, SwitzerlandDepartment of Medicine and Department of Pathology and Laboratory Medicine, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USAMathematical Institute, University of Bern, Bern, Switzerland; Albert Einstein Center for Fundamental Physics and Laboratory for High Energy Physics, University of Bern, Bern, SwitzerlandDepartment of Clinical Chemistry, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland; Laboratory of Biometry, School of Agriculture, University of Thessaly, Volos, GreeceDivision of Medical Oncology and Hematology, University and University Hospital Zurich, Zurich, SwitzerlandDiagnostic Haematology, Basel University Hospital, Basel, SwitzerlandInstitut für Immunologie und Transfusionsmedizin, Universitätsmedizin Greifswald, Greifswald, GermanyDepartment of Laboratory Medicine, Kantonsspital Aarau, Aarau, SwitzerlandClinic of Medical Oncology and Hematology, Municipal Hospital Zurich Triemli, Zurich, SwitzerlandDivision of Hematology and Central Hematology Laboratory, Cantonal Hospital of Lucerne and University of Bern, SwitzerlandClinic of Hematology, Oncology Institute of Southern Switzerland, Bellinzona, SwitzerlandDepartment of Hematology and Central Hematology Laboratory, Inselspital, Bern University Hospital, University of Bern, Bern, SwitzerlandDivision of Hematology, CHI Franciscan Medical Group, Seattle, United StatesCantonal Hospital of St Gallen, SwitzerlandMathematical Institute, University of Bern, Bern, SwitzerlandARTORG Center for Biomedical Engineering Research, University of Bern, Bern, SwitzerlandCentre for Clinical Transfusion Medicine, University Hospital of Tübingen, Tübingen, GermanyDepartment of Clinical Chemistry, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland; Corresponding author. Inselspital, Bern University Hospital, University of Bern, 3010 Bern, Switzerland.Summary: Background: Diagnosing heparin-induced thrombocytopenia (HIT) at the bedside remains challenging, exposing a significant number of patients at risk of delayed diagnosis or overtreatment. We hypothesized that machine-learning algorithms could be utilized to develop a more accurate and user-friendly diagnostic tool that integrates diverse clinical and laboratory information and accounts for complex interactions. Methods: We conducted a prospective cohort study including 1393 patients with suspected HIT between 2018 and 2021 from 10 study centers. Detailed clinical information and laboratory data were collected, and various immunoassays were conducted. The washed platelet heparin-induced platelet activation assay (HIPA) served as the reference standard. Findings: HIPA diagnosed HIT in 119 patients (prevalence 8.5%). The feature selection process in the training dataset (75% of patients) yielded the following predictor variables: (1) immunoassay test result, (2) platelet nadir, (3) unfractionated heparin use, (4) CRP, (5) timing of thrombocytopenia, and (6) other causes of thrombocytopenia. The best performing models were a support vector machine in case of the chemiluminescent immunoassay (CLIA) and the ELISA, as well as a gradient boosting machine in particle-gel immunoassay (PaGIA). In the validation dataset (25% of patients), the AUROC of all models was 0.99 (95% CI: 0.97, 1.00). Compared to the currently recommended diagnostic algorithm (4Ts score, immunoassay), the numbers of false-negative patients were reduced from 12 to 6 (−50.0%; ELISA), 9 to 3 (−66.7%, PaGIA) and 14 to 5 (−64.3%; CLIA). The numbers of false-positive individuals were reduced from 87 to 61 (−29.8%; ELISA), 200 to 63 (−68.5%; PaGIA) and increased from 50 to 63 (+29.0%) for the CLIA. Interpretation: Our user-friendly machine-learning algorithm for the diagnosis of HIT (https://toradi-hit.org) was substantially more accurate than the currently recommended diagnostic algorithm. It has the potential to reduce delayed diagnosis and overtreatment in clinical practice. Future studies shall validate this model in wider settings. Funding: Swiss National Science Foundation (SNSF), and International Society on Thrombosis and Haemostasis (ISTH).http://www.sciencedirect.com/science/article/pii/S2589537022004746HeparinLow-molecular-weightThrombocytopeniaAnticoagulantsPlatelet countHeparin-induced thrombocytopenia |
| spellingShingle | Henning Nilius Adam Cuker Sigve Haug Christos Nakas Jan-Dirk Studt Dimitrios A. Tsakiris Andreas Greinacher Adriana Mendez Adrian Schmidt Walter A. Wuillemin Bernhard Gerber Johanna A. Kremer Hovinga Prakash Vishnu Lukas Graf Alexander Kashev Raphael Sznitman Tamam Bakchoul Michael Nagler A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context EClinicalMedicine Heparin Low-molecular-weight Thrombocytopenia Anticoagulants Platelet count Heparin-induced thrombocytopenia |
| title | A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context |
| title_full | A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context |
| title_fullStr | A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context |
| title_full_unstemmed | A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context |
| title_short | A machine-learning model for reducing misdiagnosis in heparin-induced thrombocytopenia: A prospective, multicenter, observational studyResearch in context |
| title_sort | machine learning model for reducing misdiagnosis in heparin induced thrombocytopenia a prospective multicenter observational studyresearch in context |
| topic | Heparin Low-molecular-weight Thrombocytopenia Anticoagulants Platelet count Heparin-induced thrombocytopenia |
| url | http://www.sciencedirect.com/science/article/pii/S2589537022004746 |
| work_keys_str_mv | AT henningnilius amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adamcuker amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT sigvehaug amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT christosnakas amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT jandirkstudt amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT dimitriosatsakiris amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT andreasgreinacher amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adrianamendez amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adrianschmidt amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT walterawuillemin amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT bernhardgerber amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT johannaakremerhovinga amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT prakashvishnu amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT lukasgraf amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT alexanderkashev amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT raphaelsznitman amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT tamambakchoul amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT michaelnagler amachinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT henningnilius machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adamcuker machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT sigvehaug machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT christosnakas machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT jandirkstudt machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT dimitriosatsakiris machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT andreasgreinacher machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adrianamendez machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT adrianschmidt machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT walterawuillemin machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT bernhardgerber machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT johannaakremerhovinga machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT prakashvishnu machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT lukasgraf machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT alexanderkashev machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT raphaelsznitman machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT tamambakchoul machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext AT michaelnagler machinelearningmodelforreducingmisdiagnosisinheparininducedthrombocytopeniaaprospectivemulticenterobservationalstudyresearchincontext |