A machine learning PROGRAM to identify COVID-19 and other diseases from hematology data.

Autor: Gladding PA; Department of Cardiology, Waitematā District Health Board, Auckland, New Zealand., Ayar Z; Clinical Information Services, Waitematā District Health Board, Auckland, New Zealand., Smith K; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Patel P; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Pearce J; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Puwakdandawa S; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Tarrant D; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Atkinson J; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., McChlery E; Clinical laboratory, Waitematā District Health Board, Auckland, New Zealand., Hanna M; Department of Hematology, Waitematā District Health Board, Auckland, New Zealand., Gow N; Department of Infectious diseases, Waitematā District Health Board, Auckland, New Zealand., Bhally H; Department of Infectious diseases, Waitematā District Health Board, Auckland, New Zealand., Read K; Department of Infectious diseases, Waitematā District Health Board, Auckland, New Zealand., Jayathissa P; Institute for Innovation & Improvement (i3), Waitematā District Health Board, Auckland, New Zealand., Wallace J; Institute for Innovation & Improvement (i3), Waitematā District Health Board, Auckland, New Zealand., Norton S; Nanix Ltd, Dunedin, New Zealand., Kasabov N; Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology, Auckland, New Zealand., Calude CS; School of Computer Science, University of Auckland, Auckland, New Zealand., Steel D; Sysmex New Zealand Ltd, Auckland, New Zealand., Mckenzie C; Sysmex New Zealand Ltd, Auckland, New Zealand.
Jazyk: angličtina
Zdroj: Future science OA [Future Sci OA] 2021 Jun 12; Vol. 7 (7), pp. FSO733. Date of Electronic Publication: 2021 Jun 12 (Print Publication: 2021).
DOI: 10.2144/fsoa-2020-0207
Abstrakt: Aim: We propose a method for screening full blood count metadata for evidence of communicable and noncommunicable diseases using machine learning (ML).
Materials & Methods: High dimensional hematology metadata was extracted over an 11-month period from Sysmex hematology analyzers from 43,761 patients. Predictive models for age, sex and individuality were developed to demonstrate the personalized nature of hematology data. Both numeric and raw flow cytometry data were used for both supervised and unsupervised ML to predict the presence of pneumonia, urinary tract infection and COVID-19. Heart failure was used as an objective to prove method generalizability.
Results: Chronological age was predicted by a deep neural network with R 2 : 0.59; mean absolute error: 12; sex with AUROC: 0.83, phi: 0.47; individuality with 99.7% accuracy, phi: 0.97; pneumonia with AUROC: 0.74, sensitivity 58%, specificity 79%, 95% CI: 0.73-0.75, p < 0.0001; urinary tract infection AUROC: 0.68, sensitivity 52%, specificity 79%, 95% CI: 0.67-0.68, p < 0.0001; COVID-19 AUROC: 0.8, sensitivity 82%, specificity 75%, 95% CI: 0.79-0.8, p = 0.0006; and heart failure area under the receiver operator curve (AUROC): 0.78, sensitivity 72%, specificity 72%, 95% CI: 0.77-0.78; p < 0.0001.
Conclusion: ML applied to hematology data could predict communicable and noncommunicable diseases, both at local and global levels.
Competing Interests: Financial & competing interests disclosure D Steele and C McKenzie are employees of Sysmex Corporation. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed. No writing assistance was utilized in the production of this manuscript.
(© 2021 The authors.)
Databáze: MEDLINE