Cargando…
A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity
Worldwide, testing capacity for SARS-CoV-2 is limited and bottlenecks in the scale up of polymerase chain reaction (PCR-based testing exist. Our aim was to develop and evaluate a machine learning algorithm to diagnose COVID-19 in the inpatient setting. The algorithm was based on basic demographic an...
Autores principales: | , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7508387/ https://www.ncbi.nlm.nih.gov/pubmed/32960917 http://dx.doi.org/10.1371/journal.pone.0239474 |
_version_ | 1783585410414280704 |
---|---|
author | Goodman-Meza, David Rudas, Akos Chiang, Jeffrey N. Adamson, Paul C. Ebinger, Joseph Sun, Nancy Botting, Patrick Fulcher, Jennifer A. Saab, Faysal G. Brook, Rachel Eskin, Eleazar An, Ulzee Kordi, Misagh Jew, Brandon Balliu, Brunilda Chen, Zeyuan Hill, Brian L. Rahmani, Elior Halperin, Eran Manuel, Vladimir |
author_facet | Goodman-Meza, David Rudas, Akos Chiang, Jeffrey N. Adamson, Paul C. Ebinger, Joseph Sun, Nancy Botting, Patrick Fulcher, Jennifer A. Saab, Faysal G. Brook, Rachel Eskin, Eleazar An, Ulzee Kordi, Misagh Jew, Brandon Balliu, Brunilda Chen, Zeyuan Hill, Brian L. Rahmani, Elior Halperin, Eran Manuel, Vladimir |
author_sort | Goodman-Meza, David |
collection | PubMed |
description | Worldwide, testing capacity for SARS-CoV-2 is limited and bottlenecks in the scale up of polymerase chain reaction (PCR-based testing exist. Our aim was to develop and evaluate a machine learning algorithm to diagnose COVID-19 in the inpatient setting. The algorithm was based on basic demographic and laboratory features to serve as a screening tool at hospitals where testing is scarce or unavailable. We used retrospectively collected data from the UCLA Health System in Los Angeles, California. We included all emergency room or inpatient cases receiving SARS-CoV-2 PCR testing who also had a set of ancillary laboratory features (n = 1,455) between 1 March 2020 and 24 May 2020. We tested seven machine learning models and used a combination of those models for the final diagnostic classification. In the test set (n = 392), our combined model had an area under the receiver operator curve of 0.91 (95% confidence interval 0.87–0.96). The model achieved a sensitivity of 0.93 (95% CI 0.85–0.98), specificity of 0.64 (95% CI 0.58–0.69). We found that our machine learning algorithm had excellent diagnostic metrics compared to SARS-CoV-2 PCR. This ensemble machine learning algorithm to diagnose COVID-19 has the potential to be used as a screening tool in hospital settings where PCR testing is scarce or unavailable. |
format | Online Article Text |
id | pubmed-7508387 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-75083872020-10-01 A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity Goodman-Meza, David Rudas, Akos Chiang, Jeffrey N. Adamson, Paul C. Ebinger, Joseph Sun, Nancy Botting, Patrick Fulcher, Jennifer A. Saab, Faysal G. Brook, Rachel Eskin, Eleazar An, Ulzee Kordi, Misagh Jew, Brandon Balliu, Brunilda Chen, Zeyuan Hill, Brian L. Rahmani, Elior Halperin, Eran Manuel, Vladimir PLoS One Research Article Worldwide, testing capacity for SARS-CoV-2 is limited and bottlenecks in the scale up of polymerase chain reaction (PCR-based testing exist. Our aim was to develop and evaluate a machine learning algorithm to diagnose COVID-19 in the inpatient setting. The algorithm was based on basic demographic and laboratory features to serve as a screening tool at hospitals where testing is scarce or unavailable. We used retrospectively collected data from the UCLA Health System in Los Angeles, California. We included all emergency room or inpatient cases receiving SARS-CoV-2 PCR testing who also had a set of ancillary laboratory features (n = 1,455) between 1 March 2020 and 24 May 2020. We tested seven machine learning models and used a combination of those models for the final diagnostic classification. In the test set (n = 392), our combined model had an area under the receiver operator curve of 0.91 (95% confidence interval 0.87–0.96). The model achieved a sensitivity of 0.93 (95% CI 0.85–0.98), specificity of 0.64 (95% CI 0.58–0.69). We found that our machine learning algorithm had excellent diagnostic metrics compared to SARS-CoV-2 PCR. This ensemble machine learning algorithm to diagnose COVID-19 has the potential to be used as a screening tool in hospital settings where PCR testing is scarce or unavailable. Public Library of Science 2020-09-22 /pmc/articles/PMC7508387/ /pubmed/32960917 http://dx.doi.org/10.1371/journal.pone.0239474 Text en © 2020 Goodman-Meza et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Goodman-Meza, David Rudas, Akos Chiang, Jeffrey N. Adamson, Paul C. Ebinger, Joseph Sun, Nancy Botting, Patrick Fulcher, Jennifer A. Saab, Faysal G. Brook, Rachel Eskin, Eleazar An, Ulzee Kordi, Misagh Jew, Brandon Balliu, Brunilda Chen, Zeyuan Hill, Brian L. Rahmani, Elior Halperin, Eran Manuel, Vladimir A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title | A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title_full | A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title_fullStr | A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title_full_unstemmed | A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title_short | A machine learning algorithm to increase COVID-19 inpatient diagnostic capacity |
title_sort | machine learning algorithm to increase covid-19 inpatient diagnostic capacity |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7508387/ https://www.ncbi.nlm.nih.gov/pubmed/32960917 http://dx.doi.org/10.1371/journal.pone.0239474 |
work_keys_str_mv | AT goodmanmezadavid amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT rudasakos amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT chiangjeffreyn amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT adamsonpaulc amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT ebingerjoseph amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT sunnancy amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT bottingpatrick amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT fulcherjennifera amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT saabfaysalg amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT brookrachel amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT eskineleazar amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT anulzee amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT kordimisagh amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT jewbrandon amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT balliubrunilda amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT chenzeyuan amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT hillbrianl amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT rahmanielior amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT halperineran amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT manuelvladimir amachinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT goodmanmezadavid machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT rudasakos machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT chiangjeffreyn machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT adamsonpaulc machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT ebingerjoseph machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT sunnancy machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT bottingpatrick machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT fulcherjennifera machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT saabfaysalg machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT brookrachel machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT eskineleazar machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT anulzee machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT kordimisagh machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT jewbrandon machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT balliubrunilda machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT chenzeyuan machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT hillbrianl machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT rahmanielior machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT halperineran machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity AT manuelvladimir machinelearningalgorithmtoincreasecovid19inpatientdiagnosticcapacity |