Artificial Intelligence in Pediatric Blood Transfusion during Anesthesia: A Scoping Review
,
Abstract
Background: Transfusion is a vital process, but incorrect injection can cause harm. In the field of children's blood transfusion under anesthesia, the use of artificial intelligence (AI) and machine learning (ML) is regarded as innovative tools that enhance patient safety levels. This article examines and reviews the scoping literature on the use of artificial intelligence in pediatric blood transfusions during anesthesia, with the aim of identifying solutions, challenges, and future opportunities in this field.
Methods: The study, conducted from early 2024 to May 2024, aimed to evaluate the effectiveness of artificial intelligence (AI) and machine learning (ML) in predicting blood transfusion needs and bleeding risks in pediatric anesthesia. Relevant keywords, including artificial intelligence, machine learning, predictive model, neural network, predictive algorithm, blood transfusion, children, pediatric, neonates, anesthesia, surgery, and operation, were extracted from the Medical Subject Headings (MeSH). A comprehensive search strategy was independently implemented in Web of Science, PubMed, Scopus, and Google Scholar databases
Results: The search strategy initially identified 260 articles. After a systematic screening process, 60 duplicate articles were excluded. Subsequently, careful screening of titles, abstracts, and full texts eliminated an additional 195 articles, resulting in a final selection of 5 relevant English-language articles. Based on these studies, factors such as the type of surgery, the machine learning models used, decreases in hemoglobin and hematocrit levels before surgery, prolonged surgery, as well as the young age and low weight of pediatric patients, were identified as indicators of the increased risk of blood transfusion during surgery and anesthesia.
Conclusion: Based on the findings of the studies, artificial intelligence (AI) and machine learning (ML) have shown significant advancements in pediatric blood transfusion under anesthesia. This technology offers notable benefits, including high accuracy in predicting transfusion requirements and the ability to make timely decisions in critical situations. However, despite these advancements, further research is warranted to comprehensively understand the advantages and limitations of AI in the field of pediatric blood transfusion during anesthesia.
[2] Cifuentes J, Yao Y, Yan M, Zheng B. Blood transfusion prediction using restricted Boltzmann machines. Comput Methods Biomech Biomed Engin. 2020;23(9):510-7.
[3] Angthong C, Rungrattanawilai N, Pundee C. Artificial intelligence assistance in deciding management strategies for polytrauma and trauma patients. Pol Przegl Chir. 2023;96(0):114-7.
[4] Feng Y, Xu Z, Sun X, Wang D, Yu Y. Machine learning for predicting preoperative red blood cell demand. J Transfus Med. 2021;31(4):262-70.
[5] Tao J, Qian B, Zhang A, Liu X, Mao P. Investigation and analysis of rationality of 900 cases of clinical blood transfusion. Chin J Blood Transfus. 2017:805-7.
[6] Sadana D, Pratzer A, Scher LJ, Saag HS, Adler N, Volpicelli FM, et al. Promoting high-value practice by reducing unnecessary transfusions with a patient blood management program. JAMA Intern Med. 2018;178(1):116-22.
[7] Meier JM, Tschoellitsch T. Artificial intelligence and machine learning in patient blood management: a scoping review. Anesth Analg. 2022;135(3):524-31.
[8] Dupuis C, Michelet D, Hilly J, Diallo T, Vidal C, Delivet H, et al. Predictive factors for homologous transfusion during paediatric scoliosis surgery. Anaesth Crit Care Pain Med. 2015;34(6):327-32.
[9] Vassal O, Desgranges FP, Tosetti S, Burgal S, Dailler F, Javouhey E, et al. Risk factors for intraoperative allogeneic blood transfusion during craniotomy for brain tumor removal in children. Paediatr Anaesth. 2016;26(2):199-206.
[10] Sherrod BA, Baker DK, Gilbert SR. Blood transfusion incidence, risk factors, and associated complications in surgical treatment of hip dysplasia. J Pediatr Orthop. 2018;38(4):208-16.
[11] Alassaf N, Reitsma JB. Development of a prediction model for allogenic blood transfusion in children undergoing surgery for developmental dysplasia of the hip. Technol Health Care. 2019;27(3):327-34.
[12] Jalali A, Lonsdale H, Zamora LV, Ahumada L, Nguyen ATH, Rehman M, et al. Machine Learning Applied to Registry Data: Development of a Patient-Specific Prediction Model for Blood Transfusion Requirements During Craniofacial Surgery Using the Pediatric Craniofacial Perioperative Registry Dataset. Anesth Analg. 2021;132(1):160-71.
[13] Karišik M. Perioperative Blood Transfusion in Pediatrics. J Anesth. 2023;31.
[14] Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337-40.
[15] Sendak MP, D’Arcy J, Kashyap S, Gao M, Nichols M, Corey K, et al. A path for translation of machine learning products into healthcare delivery. EMJ Innov. 2020; 10:19-00172.
[16] Feng J, Phillips RV, Malenica I, Bishara A, Hubbard AE, Celi LA, et al. Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare. NPJ digi Med. 2022;5(1):66.
[17] Amrollahi F, Shashikumar SP, Holder AL, Nemati S. Leveraging clinical data across healthcare institutions for continual learning of predictive risk models. Sci Rep. 2022;12(1):8380.
| Files | ||
| Issue | Article in Press |
|
| Section | Research Article(s) | |
| Keywords | ||
| Artificial intelligence machine learning blood transfusion anesthesia pediatrics | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
