An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model
© 2023. BioMed Central Ltd., part of Springer Nature..
Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:17 |
---|---|
Enthalten in: |
Human genomics - 17(2023), 1 vom: 29. Aug., Seite 80 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Charkoftaki, Georgia [VerfasserIn] |
---|
Links: |
---|
Themen: |
344S277G0Z |
---|
Anmerkungen: |
Date Completed 31.08.2023 Date Revised 07.03.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1186/s40246-023-00521-4 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM361391250 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM361391250 | ||
003 | DE-627 | ||
005 | 20240307231955.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s40246-023-00521-4 |2 doi | |
028 | 5 | 2 | |a pubmed24n1319.xml |
035 | |a (DE-627)NLM361391250 | ||
035 | |a (NLM)37641126 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Charkoftaki, Georgia |e verfasserin |4 aut | |
245 | 1 | 3 | |a An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 31.08.2023 | ||
500 | |a Date Revised 07.03.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023. BioMed Central Ltd., part of Springer Nature. | ||
520 | |a Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
650 | 4 | |a Research Support, N.I.H., Extramural | |
650 | 7 | |a Allantoin |2 NLM | |
650 | 7 | |a 344S277G0Z |2 NLM | |
700 | 1 | |a Aalizadeh, Reza |e verfasserin |4 aut | |
700 | 1 | |a Santos-Neto, Alvaro |e verfasserin |4 aut | |
700 | 1 | |a Tan, Wan Ying |e verfasserin |4 aut | |
700 | 1 | |a Davidson, Emily A |e verfasserin |4 aut | |
700 | 1 | |a Nikolopoulou, Varvara |e verfasserin |4 aut | |
700 | 1 | |a Wang, Yewei |e verfasserin |4 aut | |
700 | 1 | |a Thompson, Brian |e verfasserin |4 aut | |
700 | 1 | |a Furnary, Tristan |e verfasserin |4 aut | |
700 | 1 | |a Chen, Ying |e verfasserin |4 aut | |
700 | 1 | |a Wunder, Elsio A |e verfasserin |4 aut | |
700 | 1 | |a Coppi, Andreas |e verfasserin |4 aut | |
700 | 1 | |a Schulz, Wade |e verfasserin |4 aut | |
700 | 1 | |a Iwasaki, Akiko |e verfasserin |4 aut | |
700 | 1 | |a Pierce, Richard W |e verfasserin |4 aut | |
700 | 1 | |a Cruz, Charles S Dela |e verfasserin |4 aut | |
700 | 1 | |a Desir, Gary V |e verfasserin |4 aut | |
700 | 1 | |a Kaminski, Naftali |e verfasserin |4 aut | |
700 | 1 | |a Farhadian, Shelli |e verfasserin |4 aut | |
700 | 1 | |a Veselkov, Kirill |e verfasserin |4 aut | |
700 | 1 | |a Datta, Rupak |e verfasserin |4 aut | |
700 | 1 | |a Campbell, Melissa |e verfasserin |4 aut | |
700 | 1 | |a Thomaidis, Nikolaos S |e verfasserin |4 aut | |
700 | 1 | |a Ko, Albert I |e verfasserin |4 aut | |
700 | 0 | |a Yale IMPACT Study Team |e verfasserin |4 aut | |
700 | 1 | |a Thompson, David C |e verfasserin |4 aut | |
700 | 1 | |a Vasiliou, Vasilis |e verfasserin |4 aut | |
700 | 1 | |a Grubaugh, Nathan |e investigator |4 oth | |
700 | 1 | |a Nelson, Allison |e investigator |4 oth | |
700 | 1 | |a Wyllie, Anne L |e investigator |4 oth | |
700 | 1 | |a Casanovas-Massana, Arnau |e investigator |4 oth | |
700 | 1 | |a White, Elizabeth B |e investigator |4 oth | |
700 | 1 | |a Chiorazzi, Michael |e investigator |4 oth | |
700 | 1 | |a Rainone, Michael |e investigator |4 oth | |
700 | 1 | |a Earnest, Rebecca |e investigator |4 oth | |
700 | 1 | |a Lapidus, Sarah |e investigator |4 oth | |
700 | 1 | |a Lim, Joseph |e investigator |4 oth | |
700 | 1 | |a Nakahata, Maura |e investigator |4 oth | |
700 | 1 | |a Nunez, Angela |e investigator |4 oth | |
700 | 1 | |a Shepard, Denise |e investigator |4 oth | |
700 | 1 | |a Matos, Irene |e investigator |4 oth | |
700 | 1 | |a Strong, Yvette |e investigator |4 oth | |
700 | 1 | |a Anastasio, Kelly |e investigator |4 oth | |
700 | 1 | |a Brower, Kristina |e investigator |4 oth | |
700 | 1 | |a Kuang, Maxine |e investigator |4 oth | |
700 | 1 | |a Muenker, M Catherine |e investigator |4 oth | |
700 | 1 | |a Moore, Adam J |e investigator |4 oth | |
700 | 1 | |a Rahming, Harold |e investigator |4 oth | |
700 | 1 | |a Glick, Laura |e investigator |4 oth | |
700 | 1 | |a Silva, Erin |e investigator |4 oth | |
700 | 1 | |a Bermejo, Santos |e investigator |4 oth | |
700 | 1 | |a Vijayakumar, Pavithra |e investigator |4 oth | |
700 | 1 | |a Geng, Bertie |e investigator |4 oth | |
700 | 1 | |a Fournier, John |e investigator |4 oth | |
700 | 1 | |a Minasyan, Maksym |e investigator |4 oth | |
700 | 1 | |a Bickerton, Sean |e investigator |4 oth | |
700 | 1 | |a Linehan, Melissa |e investigator |4 oth | |
700 | 1 | |a Wong, Patrick |e investigator |4 oth | |
700 | 1 | |a Goldman-Israelow, Benjamin |e investigator |4 oth | |
700 | 1 | |a Martin, Anjelica |e investigator |4 oth | |
700 | 1 | |a Rice, Tyler |e investigator |4 oth | |
700 | 1 | |a Khoury-Hanold, William |e investigator |4 oth | |
700 | 1 | |a Nouws, Jessica |e investigator |4 oth | |
700 | 1 | |a McDonald, David |e investigator |4 oth | |
700 | 1 | |a Rose, Kadi-Ann |e investigator |4 oth | |
700 | 1 | |a Cao, Yiyun |e investigator |4 oth | |
700 | 1 | |a Sharma, Lokesh |e investigator |4 oth | |
700 | 1 | |a Smolgovsky, Mikhail |e investigator |4 oth | |
700 | 1 | |a Obaid, Abeer |e investigator |4 oth | |
700 | 1 | |a DeIuliis, Giuseppe |e investigator |4 oth | |
700 | 1 | |a Park, Hong-Jai |e investigator |4 oth | |
700 | 1 | |a Sonnert, Nicole |e investigator |4 oth | |
700 | 1 | |a Velazquez, Sofia |e investigator |4 oth | |
700 | 1 | |a Peng, Xiaohua |e investigator |4 oth | |
700 | 1 | |a Askenase, Michael H |e investigator |4 oth | |
700 | 1 | |a Todeasa, Codruta |e investigator |4 oth | |
700 | 1 | |a Bucklin, Molly L |e investigator |4 oth | |
700 | 1 | |a Batsu, Maria |e investigator |4 oth | |
700 | 1 | |a Robertson, Alexander |e investigator |4 oth | |
700 | 1 | |a Balkcom, Natasha |e investigator |4 oth | |
700 | 1 | |a Liu, Yicong |e investigator |4 oth | |
700 | 1 | |a Lin, Zitong |e investigator |4 oth | |
700 | 1 | |a Dorgay, Coriann |e investigator |4 oth | |
700 | 1 | |a Borg, Ryan |e investigator |4 oth | |
700 | 1 | |a Di Giuseppe, Erendira Carmen |e investigator |4 oth | |
700 | 1 | |a Young, H Patrick |e investigator |4 oth | |
700 | 1 | |a Herbst, Roy S |e investigator |4 oth | |
773 | 0 | 8 | |i Enthalten in |t Human genomics |d 2003 |g 17(2023), 1 vom: 29. Aug., Seite 80 |w (DE-627)NLM15254156X |x 1479-7364 |7 nnns |
773 | 1 | 8 | |g volume:17 |g year:2023 |g number:1 |g day:29 |g month:08 |g pages:80 |
856 | 4 | 0 | |u http://dx.doi.org/10.1186/s40246-023-00521-4 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 17 |j 2023 |e 1 |b 29 |c 08 |h 80 |