1
|
Nikouline A, Feng J, Rudzicz F, Nathens A, Nolan B. Machine learning in the prediction of massive transfusion in trauma: a retrospective analysis as a proof-of-concept. Eur J Trauma Emerg Surg 2024:10.1007/s00068-023-02423-5. [PMID: 38265444 DOI: 10.1007/s00068-023-02423-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Accepted: 12/04/2023] [Indexed: 01/25/2024]
Abstract
PURPOSE Early administration and protocolization of massive hemorrhage protocols (MHP) has been associated with decreases in mortality, multiorgan system failure, and number of blood products used. Various prediction tools have been developed for the initiation of MHP, but no single tool has demonstrated strong prediction with early clinical data. We sought to develop a massive transfusion prediction model using machine learning and early clinical data. METHODS Using the National Trauma Data Bank from 2013 to 2018, we included severely injured trauma patients and extracted clinical features available from the pre-hospital and emergency department. We subsequently balanced our dataset and used the Boruta algorithm to determine feature selection. Massive transfusion was defined as five units at 4 h and ten units at 24 h. Six machine learning models were trained on the balanced dataset and tested on the original. RESULTS A total of 326,758 patients met our inclusion with 18,871 (5.8%) requiring massive transfusion. Emergency department models demonstrated strong performance characteristics with mean areas under the receiver-operating characteristic curve of 0.83. Extreme gradient boost modeling slightly outperformed and demonstrated adequate predictive performance with pre-hospital data only, as well as 4-h transfusion thresholds. CONCLUSIONS We demonstrate the use of machine learning in developing an accurate prediction model for massive transfusion in trauma patients using early clinical data. This research demonstrates the potential utility of artificial intelligence as a clinical decision support tool.
Collapse
Affiliation(s)
- Anton Nikouline
- Department of Emergency Medicine, London Health Sciences Centre, 800 Commissioners Road E, London, ON, N6A 5W9, Canada.
- Division of Critical Care and Emergency Medicine, Department of Medicine, Western University, London, ON, Canada.
| | - Jinyue Feng
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Vector Institute for Artificial Intelligence, Toronto, ON, Canada
| | - Frank Rudzicz
- Vector Institute for Artificial Intelligence, Toronto, ON, Canada
- Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada
| | - Avery Nathens
- Department of Surgery, Sunnybrook Health Sciences Center, Toronto, ON, Canada
- American College of Surgeons, Chicago, IL, USA
| | - Brodie Nolan
- Division of Emergency Medicine, Department of Medicine, University of Toronto, Toronto, ON, Canada
- International Centre for Surgical Safety, St. Michael's Hospital, Toronto, ON, Canada
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, ON, Canada
- Department of Emergency Medicine, St. Michael's Hospital, Toronto, ON, Canada
| |
Collapse
|
2
|
Maynard S, Farrington J, Alimam S, Evans H, Li K, Wong WK, Stanworth SJ. Machine learning in transfusion medicine: A scoping review. Transfusion 2024; 64:162-184. [PMID: 37950535 DOI: 10.1111/trf.17582] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 09/25/2023] [Accepted: 09/27/2023] [Indexed: 11/12/2023]
Affiliation(s)
- Suzanne Maynard
- Medical Sciences Division, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- NHSBT and Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Joseph Farrington
- Institute of Health Informatics, University College London, London, UK
| | - Samah Alimam
- Haematology Department, University College London Hospitals NHS Foundation Trust, London, UK
| | - Hayley Evans
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Kezhi Li
- Institute of Health Informatics, University College London, London, UK
| | - Wai Keong Wong
- Director of Digital, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
| | - Simon J Stanworth
- Medical Sciences Division, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- NIHR Blood and Transplant Research Unit in Data Driven Transfusion Practice, Nuffield Division of Clinical Laboratory Sciences, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
- NHSBT and Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| |
Collapse
|
3
|
Dion PM, Greene A, Beckett A, von Vopelius-Feldt J, Nolan B. A comparative analysis of current out-of-hospital transfusion protocols to expert recommendations. Resusc Plus 2023; 16:100498. [PMID: 38026143 PMCID: PMC10663952 DOI: 10.1016/j.resplu.2023.100498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Revised: 10/26/2023] [Accepted: 10/27/2023] [Indexed: 12/01/2023] Open
Abstract
Aim This study aimed to compare current out-of-hospital transfusion (OHT) protocols in Canadian civilian critical care transport organizations (CCTO) to expert recommendations and explore the variability and potential benefits of standardizing OHT practices across Canada. Methods A comprehensive cross-sectional study was conducted, encompassing all seven Canadian CCTOs that provide OHT. The study assessed adherence to expert recommendations and examined specific aspects of the transfusion process, such as indications for transfusion and cessation criteria. Results The study found an 89% adherence to expert recommendations for OHT among Canadian CCTOs. It highlighted a strong alignment between current practices and recommendations, possibly attributed to collaborative frameworks like the CAN-PATT network. However, notable variability and ambiguity were observed in transfusion indications and cessation criteria. The study also emphasized the potential benefits of standardizing OHT practices, such as improved policy formulation, better interpretation of emerging literature, and evaluation of OHT efficacy. Conclusion This cross-sectional study assessed how Canadian CCTOs implement OHT practices compared to expert-recommended practices. The findings underscore the importance of structured protocols in trauma management. Given the consistency in OHT protocol adoption and the comprehensive approach across CCTOs, there's a solid foundation for managing trauma patients in prehospital and transport settings across Canada. As OHT practices continue to evolve, sustained efforts are vital to refine, adapt, and elevate patient care standards in trauma management.
Collapse
Affiliation(s)
- Pierre-Marc Dion
- Faculty of Medicine, University of Ottawa, Ottawa, Ontario, Canada
- Canadian Forces Health Services, Canadian Armed Forces, Ottawa, Ontario, Canada
| | - Adam Greene
- Air Operations, British Columbia Emergency Health Services, British Columbia, Canada
- School of Medicine, Cardiff University, Cardiff, Wales, United Kingdom
| | - Andrew Beckett
- Canadian Forces Health Services, Canadian Armed Forces, Ottawa, Ontario, Canada
- Department of Surgery, St. Michael’s Hospital, Unity Health Toronto, Toronto, Ontario, Canada
- Department of Surgery, University of Toronto, Toronto, Ontario, Canada
- Li Ka Shing Knowledge Institute, Unity Health Toronto, Toronto, Ontario, Canada
| | - Johannes von Vopelius-Feldt
- Li Ka Shing Knowledge Institute, Unity Health Toronto, Toronto, Ontario, Canada
- Department of Emergency Medicine, St. Michael’s Hospital, Unity Health Toronto, Toronto, Ontario, Canada
- Division of Emergency Medicine, Department of Medicine, University of Toronto, Toronto, Ontario, Canada
- Ornge, Mississauga, Ontario, Canada
| | - Brodie Nolan
- Li Ka Shing Knowledge Institute, Unity Health Toronto, Toronto, Ontario, Canada
- Department of Emergency Medicine, St. Michael’s Hospital, Unity Health Toronto, Toronto, Ontario, Canada
- Division of Emergency Medicine, Department of Medicine, University of Toronto, Toronto, Ontario, Canada
- Ornge, Mississauga, Ontario, Canada
| |
Collapse
|