Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography
Background: Recurrent hemarthrosis and resultant hemophilic arthropathy are significant causes of morbidity in persons with hemophilia, despite the marked evolution of hemophilia care. Prevention, timely diagnosis, and treatment of bleeding episodes are key. However, a physical examination or a pati...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-11-01
|
| Series: | Research and Practice in Thrombosis and Haemostasis |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2475037924002978 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850101172348649472 |
|---|---|
| author | Pascal N. Tyrrell María Teresa Alvarez-Román Nihal Bakeer Brigitte Brand-Staufer Victor Jiménez-Yuste Susan Kras Carlo Martinoli Mauro Mendez Azusa Nagao Margareth Ozelo Janaina B.S. Ricciardi Marek Zak Johannes Roth |
| author_facet | Pascal N. Tyrrell María Teresa Alvarez-Román Nihal Bakeer Brigitte Brand-Staufer Victor Jiménez-Yuste Susan Kras Carlo Martinoli Mauro Mendez Azusa Nagao Margareth Ozelo Janaina B.S. Ricciardi Marek Zak Johannes Roth |
| author_sort | Pascal N. Tyrrell |
| collection | DOAJ |
| description | Background: Recurrent hemarthrosis and resultant hemophilic arthropathy are significant causes of morbidity in persons with hemophilia, despite the marked evolution of hemophilia care. Prevention, timely diagnosis, and treatment of bleeding episodes are key. However, a physical examination or a patient’s assessment of musculoskeletal pain may not accurately identify a joint bleed. This difficulty is compounded as hemophilic arthropathy progresses. Objectives: Our system aims to utilize artificial intelligence and ultrasonography (US; point-of-care and handheld) to enable providers, and ultimately patients, to detect joint bleeds at the bedside and at home. We aimed to develop and assess the reliability of artificial intelligence algorithms in detecting and segmenting synovial recess distension (SRD; an indicator of disease activity) on US images of adult and pediatric knee, elbow, and ankle joints. Methods: A total of 12,145 joint exams, comprising 61,501 US images from 7 international healthcare centers, were collected. The dataset included healthy participants and adult and pediatric persons with hemophilia, with and without SRD. Images were manually labeled by 2 experts and used to train binary convolutional neural network classifiers and segmentation models. Metrics to evaluate performance included accuracy, sensitivity, specificity, and area under the curve. Results: The algorithms exhibited high performance across all joints and all cohorts. Specifically, the knee model showed an accuracy of 97%, sensitivity of 96%, specificity of 97%, and an area under the curve of 0.97 in SRD. High Dice coefficients (80%-85%) were achieved in segmentation tasks across all joints. Conclusion: This technology could assist with the early detection and management of hemarthrosis in hemophilia. |
| format | Article |
| id | doaj-art-440f6e72aba9460bb30369f251523faf |
| institution | DOAJ |
| issn | 2475-0379 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Research and Practice in Thrombosis and Haemostasis |
| spelling | doaj-art-440f6e72aba9460bb30369f251523faf2025-08-20T02:40:07ZengElsevierResearch and Practice in Thrombosis and Haemostasis2475-03792024-11-018810260210.1016/j.rpth.2024.102602Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonographyPascal N. Tyrrell0María Teresa Alvarez-Román1Nihal Bakeer2Brigitte Brand-Staufer3Victor Jiménez-Yuste4Susan Kras5Carlo Martinoli6Mauro Mendez7Azusa Nagao8Margareth Ozelo9Janaina B.S. Ricciardi10Marek Zak11Johannes Roth12Department of Medical Imaging, University of Toronto, Toronto, Ontario, Canada; Institute of Medical Science, University of Toronto, Toronto, Canada; Department of Statistical Sciences, University of Toronto, Toronto, Canada; Correspondence Pascal N. Tyrrell, Department of Medical Imaging, University of Toronto, Toronto, ON M5T 1W7, Canada.Hematology Department, Hospital Universitario La Paz-IdiPaz, Autónoma University, Madrid, SpainIndiana Hemophilia & Thrombosis Center, Indianapolis, Indiana, USA; Children’s Hospital of Philadelphia, Pennsylvania, USANovo Nordisk Healthcare, Zürich SwitzerlandHematology Department, Hospital Universitario La Paz-IdiPaz, Autónoma University, Madrid, SpainMohawk College, Institute for Applied Health Sciences, McMaster University, Hamilton, Ontario, CanadaDepartment of Health Sciences, University of Genoa, Genova, Italy; IRCCS Ospedale Policlinico San Martino, Genova, ItalyDepartment of Health Sciences, University of Genoa, Genova, ItalyDepartment of Blood Coagulation, Ogikubo Hospital, Tokyo, JapanHemocentro UNICAMP, University of Campinas, Campinas, BrazilHemocentro UNICAMP, University of Campinas, Campinas, BrazilNovo Nordisk A/S, Søborg, DenmarkChildren’s Hospital of Central Switzerland, Luzern, Switzerland; Johannes Roth, Children’s Hospital of Central Switzerland, Spitalstrasse, 6004 Luzern, Switzerland.Background: Recurrent hemarthrosis and resultant hemophilic arthropathy are significant causes of morbidity in persons with hemophilia, despite the marked evolution of hemophilia care. Prevention, timely diagnosis, and treatment of bleeding episodes are key. However, a physical examination or a patient’s assessment of musculoskeletal pain may not accurately identify a joint bleed. This difficulty is compounded as hemophilic arthropathy progresses. Objectives: Our system aims to utilize artificial intelligence and ultrasonography (US; point-of-care and handheld) to enable providers, and ultimately patients, to detect joint bleeds at the bedside and at home. We aimed to develop and assess the reliability of artificial intelligence algorithms in detecting and segmenting synovial recess distension (SRD; an indicator of disease activity) on US images of adult and pediatric knee, elbow, and ankle joints. Methods: A total of 12,145 joint exams, comprising 61,501 US images from 7 international healthcare centers, were collected. The dataset included healthy participants and adult and pediatric persons with hemophilia, with and without SRD. Images were manually labeled by 2 experts and used to train binary convolutional neural network classifiers and segmentation models. Metrics to evaluate performance included accuracy, sensitivity, specificity, and area under the curve. Results: The algorithms exhibited high performance across all joints and all cohorts. Specifically, the knee model showed an accuracy of 97%, sensitivity of 96%, specificity of 97%, and an area under the curve of 0.97 in SRD. High Dice coefficients (80%-85%) were achieved in segmentation tasks across all joints. Conclusion: This technology could assist with the early detection and management of hemarthrosis in hemophilia.http://www.sciencedirect.com/science/article/pii/S2475037924002978artificial intelligencehemarthrosishemophiliajointultrasonography |
| spellingShingle | Pascal N. Tyrrell María Teresa Alvarez-Román Nihal Bakeer Brigitte Brand-Staufer Victor Jiménez-Yuste Susan Kras Carlo Martinoli Mauro Mendez Azusa Nagao Margareth Ozelo Janaina B.S. Ricciardi Marek Zak Johannes Roth Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography Research and Practice in Thrombosis and Haemostasis artificial intelligence hemarthrosis hemophilia joint ultrasonography |
| title | Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography |
| title_full | Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography |
| title_fullStr | Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography |
| title_full_unstemmed | Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography |
| title_short | Utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point-of-care ultrasonography |
| title_sort | utilizing artificial intelligence for the detection of hemarthrosis in hemophilia using point of care ultrasonography |
| topic | artificial intelligence hemarthrosis hemophilia joint ultrasonography |
| url | http://www.sciencedirect.com/science/article/pii/S2475037924002978 |
| work_keys_str_mv | AT pascalntyrrell utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT mariateresaalvarezroman utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT nihalbakeer utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT brigittebrandstaufer utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT victorjimenezyuste utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT susankras utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT carlomartinoli utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT mauromendez utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT azusanagao utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT margarethozelo utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT janainabsricciardi utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT marekzak utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography AT johannesroth utilizingartificialintelligenceforthedetectionofhemarthrosisinhemophiliausingpointofcareultrasonography |