Literature DB >> 33872186

Using Unsupervised Machine Learning to Identify Age- and Sex-Independent Severity Subgroups among COVID-19 Patients in the Emergency Department.

Julián Benito-León1, Mª Dolores Del Castillo2, Alberto Estirado3, Ritwik Ghosh4, Souvik Dubey5, J Ignacio Serrano2.   

Abstract

BACKGROUND: Early detection and intervention are the key factors for improving outcomes in the 2019 coronavirus infectious disease (COVID-19). Objective: Our aim was to identify severity subgroups (clusters) among COVID-19 patients, based exclusively on clinical data and standard laboratory tests, obtained during the assessment in the emergency department.
OBJECTIVE: Our aim was to identify severity subgroups (clusters) among COVID-19 patients, based exclusively on clinical data and standard laboratory tests, obtained during the assessment in the emergency department.
METHODS: We applied unsupervised machine learning to a dataset of 853 COVID-19 patients from HM hospitals in Madrid (Spain). Age and sex were not considered while building the clusters as these variables could introduce biases in machine learning algorithms and raise ethical implications or discriminations in triage protocols.
RESULTS: From 850 clinical and laboratory variables, four tests, the serum levels of aspartate transaminase (AST), lactate dehydrogenase (LDH) and C-reactive protein (CRP), and the number of neutrophils, were enough to segregate the entire patient pool into three separate clusters. Further, the percentage of monocytes and lymphocytes and the levels of alanine transaminase (ALT) distinguished the cluster 3 from the other two clusters. The highest mortality rate and the highest levels of AST, ALT, LDH, CRP and number of neutrophils, and low percentage of monocytes and lymphocytes, characterized the cluster 1. The cluster 2 included patients with a moderate mortality rate and medium levels of the previous laboratory tests. The lowest mortality rate and the lowest levels of AST, ALT, LDH, CRP and number of neutrophils, and the highest percentage of monocytes and lymphocytes, characterized the cluster 3. An online cluster assignment tool can be found at https://g-nec.car.upm-csic.es/COVID19-severity-group-assessment/.
CONCLUSIONS: A few standard laboratory tests, deemed available in all emergency departments, have shown far discriminative power for characterization of severity subgroups among COVID-19 patients.

Entities:  

Year:  2021        PMID: 33872186     DOI: 10.2196/25988

Source DB:  PubMed          Journal:  J Med Internet Res        ISSN: 1438-8871            Impact factor:   5.428


  2 in total

1.  Investigating phenotypes of pulmonary COVID-19 recovery: A longitudinal observational prospective multicenter trial.

Authors:  Thomas Sonnweber; Piotr Tymoszuk; Sabina Sahanic; Anna Boehm; Alex Pizzini; Anna Luger; Christoph Schwabl; Manfred Nairz; Philipp Grubwieser; Katharina Kurz; Sabine Koppelstätter; Magdalena Aichner; Bernhard Puchner; Alexander Egger; Gregor Hoermann; Ewald Wöll; Günter Weiss; Gerlig Widmann; Ivan Tancevski; Judith Löffler-Ragg
Journal:  Elife       Date:  2022-02-08       Impact factor: 8.140

2.  Machine learning-based clustering in cervical spondylotic myelopathy patients to identify heterogeneous clinical characteristics.

Authors:  Chenxing Zhou; ShengSheng Huang; Tuo Liang; Jie Jiang; Jiarui Chen; Tianyou Chen; Liyi Chen; Xuhua Sun; Jichong Zhu; Shaofeng Wu; Zhen Ye; Hao Guo; Wenkang Chen; Chong Liu; Xinli Zhan
Journal:  Front Surg       Date:  2022-07-25
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.