An unsupervised learning approach to identify immunoglobulin utilization patterns using electronic health records.
electronic health records
immunoglobulin
unsupervised clustering
utilization patterns
Journal
Transfusion
ISSN: 1537-2995
Titre abrégé: Transfusion
Pays: United States
ID NLM: 0417360
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
revised:
20
08
2023
received:
22
06
2023
accepted:
20
09
2023
medline:
7
12
2023
pubmed:
20
10
2023
entrez:
20
10
2023
Statut:
ppublish
Résumé
Managing Canada's immunoglobulin (Ig) product resource allocation is challenging due to increasing demand, high expenditure, and global shortages. Detection of groups with high utilization rates can help with resource planning for Ig products. This study aims to uncover utilization subgroups among the Ig recipients using electronic health records (EHRs). The study included all Ig recipients (intravenous or subcutaneous) in Calgary from 2014 to 2020, and their EHR data, including blood inventory, recipient demographics, and laboratory test results, were analyzed. Patient clusters were derived based on patient characteristics and laboratory test data using K-means clustering. Clusters were interpreted using descriptive analyses and visualization techniques. Among 4112 recipients, six clusters were identified. Clusters 1 and 2 comprised 408 (9.9%) and 1272 (30.9%) patients, respectively, contributing to 62.2% and 27.1% of total Ig utilization. Cluster 3 included 1253 (30.5%) patients, with 86.4% of infusions administered in an inpatient setting. Cluster 4, comprising 1034 (25.1%) patients, had a median age of 4 years, while clusters 2-6 were adults with median ages of 46-60. Cluster 5 had 62 (1.5%) patients, with 77.3% infusions occurring in emergency departments. Cluster 6 contained 83 (2.0%) patients receiving subcutaneous Ig treatments. The results identified data-driven segmentations of patients with high Ig utilization rates and patients with high risk for short-term inpatient use. Our report is the first on EHR data-driven clustering of Ig utilization patterns. The findings hold the potential to inform demand forecasting and resource allocation decisions during shortages of Ig products.
Sections du résumé
BACKGROUND
BACKGROUND
Managing Canada's immunoglobulin (Ig) product resource allocation is challenging due to increasing demand, high expenditure, and global shortages. Detection of groups with high utilization rates can help with resource planning for Ig products. This study aims to uncover utilization subgroups among the Ig recipients using electronic health records (EHRs).
METHODS
METHODS
The study included all Ig recipients (intravenous or subcutaneous) in Calgary from 2014 to 2020, and their EHR data, including blood inventory, recipient demographics, and laboratory test results, were analyzed. Patient clusters were derived based on patient characteristics and laboratory test data using K-means clustering. Clusters were interpreted using descriptive analyses and visualization techniques.
RESULTS
RESULTS
Among 4112 recipients, six clusters were identified. Clusters 1 and 2 comprised 408 (9.9%) and 1272 (30.9%) patients, respectively, contributing to 62.2% and 27.1% of total Ig utilization. Cluster 3 included 1253 (30.5%) patients, with 86.4% of infusions administered in an inpatient setting. Cluster 4, comprising 1034 (25.1%) patients, had a median age of 4 years, while clusters 2-6 were adults with median ages of 46-60. Cluster 5 had 62 (1.5%) patients, with 77.3% infusions occurring in emergency departments. Cluster 6 contained 83 (2.0%) patients receiving subcutaneous Ig treatments.
CONCLUSION
CONCLUSIONS
The results identified data-driven segmentations of patients with high Ig utilization rates and patients with high risk for short-term inpatient use. Our report is the first on EHR data-driven clustering of Ig utilization patterns. The findings hold the potential to inform demand forecasting and resource allocation decisions during shortages of Ig products.
Substances chimiques
Immunoglobulins
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2234-2247Subventions
Organisme : Calgary Foundation
Organisme : Canadian Blood Services
Organisme : Mitacs
ID : IT28474
Organisme : Natural Sciences and Engineering Research Council of Canada
ID : RGPIN-2022-02999
Informations de copyright
© 2023 The Authors. Transfusion published by Wiley Periodicals LLC on behalf of AABB.
Références
Neunert C, Terrell DR, Arnold DM, Buchanan G, Cines DB, Cooper N, et al. American Society of Hematology 2019 guidelines for immune thrombocytopenia. Blood Adv. 2019;3(23):3829-3866. https://doi.org/10.1182/bloodadvances.2019000966
Arumugham VB, Rayi A. Intravenous immunoglobulin (IVIG) [Updated 2022 Jul 4]. StatPearls. Treasure Island, FL: StatPearls Publishing; 2022 Available from: https://www.ncbi.nlm.nih.gov/books/NBK554446/
Bonilla FA. Intravenous immunoglobulin: adverse reactions and management. J Allergy Clin Immunol. 2008;122:1238-1239. https://doi.org/10.1016/j.jaci.2008.08.033
Abolhassani H, Sadaghiani MS, Aghamohammadi A, Ochs HD, Rezaei N. Home-based subcutaneous immunoglobulin versus hospital-based intravenous immunoglobulin in treatment of primary antibody deficiencies: systematic review and meta analysis. J Clin Immunol. 2012;32(6):1180-1192. https://doi.org/10.1007/s10875-012-9720-1
Fu LW, Song C, Isaranuwatchai W, Betschel S. Home-based subcutaneous immunoglobulin therapy vs hospital-based intravenous immunoglobulin therapy: a prospective economic analysis. Ann Allergy Asthma Immunol. 2018;120(2):195-199. https://doi.org/10.1016/j.anai.2017.11.002
Perez EE, Orange JS, Bonilla F, Chinen J, Chinn IK, Dorsey M, et al. Update on the use of immunoglobulin in human disease: a review of evidence. J Allergy Clin Immunol. 2017;139(3):S1-S46. https://doi.org/10.1016/j.jaci.2016.09.023
Betschel SD, Warrington RJ, Schellenberg R. Clinical experience with Octagam® 10%, a solvent detergent virus inactivated intravenous immunoglobulin: a Canadian retrospective review of utilization. Allergy Asthma Clin Immunol. 2016;12(1):32. https://doi.org/10.1186/s13223-016-0138-9
Expert Panel on Immune Globulin Product Supply and Related Impacts in Canada. Protecting Access to Immune Globulins for Canadians. Government of Canada Publications, 2018. Available from: https://publications.gc.ca/collections/collection_2018/sc-hc/H22-4-12-2018-eng.pdf.
Gerth WC, Betschel SD, Zbrozek AS. Implications to payers of switch from hospital-based intravenous immunoglobulin to home-based subcutaneous immunoglobulin therapy in patients with primary and secondary immunodeficiencies in Canada. Allergy Asthma Clin Immunol. 2014;10(1):23. https://doi.org/10.1186/1710-1492-10-23
Office of the Auditor General of Ontario. Value-for-money audit: blood management and safety. 2020 Available from: https://www.auditor.on.ca/en/content/annualreports/arreports/en20/20VFM_02bloodmgmt.pdf. Last Accessed 05 June 05 2023
Canadian Blood Services. Annual report 2021-2022. 2022 Available from: https://www.blood.ca/sites/default/files/CBS_AR_2022_EN_Final.pdf
Canadian Blood Services. Plasma and immunoglobulin security of supply: risk-based decision-making analysis. 2022 Available from: https://www.blood.ca/sites/default/files/Plasma_and_Immunoglobulin_Security_of_Supply_-_RBDM_Analysis_2022_-_Public_Final.pdf
Pant S, Bagha R, McGill S. International plasma collection practices: project report. Canadian J Health Technol. 2021;1(12):1-38. https://doi.org/10.51731/cjht.2021.213
Prevot J, Jolles S. Global immunoglobulin supply: steaming towards the iceberg? Curr Opin Allergy Clin Immunol. 2020;20(6):557-564. https://doi.org/10.1097/aci.0000000000000696
Sher GD. Blueprint for greater security of immunoglobulins for patients in Canada. Lancet Haematol. 2022;9(11):e804-e805. https://doi.org/10.1016/s2352-3026(22)00317-9
U.S. Food and Drug Administration. Information About Immune Globulin (Human) Product Shortage. 2019 Available from: https://www.fda.gov/vaccines-blood-biologics/safety-availability-biologics/information-about-immune-globulin-human-product-shortage.
Solís-Díez G, Turu-Pedrola M, Roig-Izquierdo M, Zara C, Vallano A, Pontes C. Dealing with immunoglobulin shortages: a rationalization plan from evidence-based and data collection. Front Public Health. 2022;10:893770. https://doi.org/10.3389/fpubh.2022.893770
Saeys Y, Inza I, Larrañaga P. A review of feature selection techniques in bioinformatics. Bioinformatics (Oxford, England). 2007;23(19):2507-2517. https://doi.org/10.1093/bioinformatics/btm344
Koçak B. Key concepts, common pitfalls, and best practices in artificial intelligence and machine learning: focus on radiomics. Diagn Interv Radiol. 2022;28(5):450-462. https://doi.org/10.5152/dir.2022.211297
Zhang Z, Castelló A. Principal components analysis in clinical studies. Ann Transl Med. 2017;5(17):351. https://doi.org/10.21037/atm.2017.07.12
Gewers FL, Ferreira GR, de Arruda HF, Silva FN, Comin CH, Amancio DR, et al. Principal component analysis: a natural approach to data exploration. ACM Comput Surv. 2021;54(4):1-34. https://doi.org/10.1145/3447755
Cui M. Introduction to the K-means clustering algorithm based on the elbow method. Geosci Remote Sens. 2020;3:9-16. Available from: https://www.clausiuspress.com/article/592.html
R Core Team. R: A language and environment for statistical computing [Internet]. Vienna, Austria: R foundation for statistical computing. 2022. Available from: https://www.R-project.org
Wang Y, Zhao Y, Therneau TM, Atkinson EJ, Tafti AP, Zhang N, et al. Unsupervised machine learning for the discovery of latent disease clusters and patient subgroups using electronic health records. J Biomed Inform. 2020;102:103364. https://doi.org/10.1016/j.jbi.2019.103364
Qu H, Shewchuk RM, Richman J, Andreae LJ, Safford MM. Identifying patient profiles for developing tailored diabetes self-management interventions: a latent class cluster analysis. Risk management and healthcare. Foreign Policy. 2022;15:1055-1063. https://doi.org/10.2147/RMHP.S355470
Home-based subcutaneous infusion of immunoglobulin for primary and secondary Immunodeficiencies: a health technology assessment. Ontario Health Technol Assess Ser. 2017;17(16):1-86.
Ritchie B, Martins KJB, Tran DT, Blain H, Richer L, Klarenbach SW. Economic impact of self-administered subcutaneous versus clinic-administered intravenous immunoglobulin G therapy in Alberta, Canada: a population-based cohort study. Allergy Asthma Clin Immunol. 2022;18(1):99. https://doi.org/10.1186/s13223-022-00735-6
Kobrynski L. Subcutaneous immunoglobulin therapy: a new option for patients with primary immunodeficiency diseases. Biol Theory. 2012;6:277-287. https://doi.org/10.2147/BTT.S25188
Borte M, Krivan G, Derfalvi B, Marodi L, Harrer T, Jolles S, et al. Efficacy, safety, tolerability and pharmacokinetics of a novel human immune globulin subcutaneous, 20%: a phase 2/3 study in Europe in patients with primary immunodeficiencies. Clin Exp Immunol. 2017;187(1):146-159. https://doi.org/10.1111/cei.12866
Jolles S, Sewell WA, Misbah SA. Clinical uses of intravenous immunoglobulin. Clin Exp Immunol. 2005;142(1):1-11. https://doi.org/10.1111/j.1365-2249.2005.02834.x
Ikotun AM, Ezugwu AE, Abualigah L, Abuhaija B, Heming J. K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data. Inform Sci. 2023;622:178-210. https://doi.org/10.1016/j.ins.2022.11.139
Ronan T, Qi Z, Naegle KM. Avoiding common pitfalls when clustering biological data. Sci Signal. 2016;9(432):re6. https://doi.org/10.1126/scisignal.aad1932
Dridi S. Unsupervised learning-a systematic literature review. OSF Preprints. 2021. https://doi.org/10.31219/osf.io/kpqr6
Armstrong RA. When to use the Bonferroni correction. Ophthal Physiol Opt J Br Coll Ophthal Opt (Optometr). 2014;34(5):502-508. https://doi.org/10.1111/opo.12131
Colquhoun D. An investigation of the false discovery rate and the misinterpretation of p-values. Royal Society open. Science. 2014;1(3):140216. https://doi.org/10.1098/rsos.140216