Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study
IntroductionThe coronavirus disease 2019 (COVID-19) pandemic threatened public health and placed a significant burden on medical resources. The Immunophenotyping Assessment in a COVID-19 Cohort (IMPACC) study collected clinical, demographic, blood cytometry, serum receptor-binding domain (RBD) antib...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1604388/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850082591137333248 |
|---|---|
| author | Jintong Hou Benjamin Haslund-Gourley Joann Diray-Arce Annmarie Hoch Nadine Rouphael Patrice M. Becker Alison D. Augustine Al Ozonoff Leying Guan Steven H. Kleinstein Bjoern Peters Elaine Reed Matt Altman Charles R. Langelier Holden Maecker Seunghee Kim Ruth R. Montgomery Florian Krammer Michael Wilson Walter Eckalbar Steven E. Bosinger Ofer Levy Hanno Steen Lindsey B. Rosen Lindsey R. Baden Esther Melamed Lauren I. R. Ehrlich Grace A. McComsey Rafick P. Sekaly Joanna Schaenman Albert C. Shaw David A. Hafler David B. Corry Farrah Kheradmand Mark A. Atkinson Scott C. Brakenridge Nelson I. Agudelo Higuita Jordan P. Metcalf Catherine L. Hough William B. Messer Bali Pulendran Kari C. Nadeau Mark M. Davis Ana Fernandez Sesma Viviana Simon Monica Kraft Chris Bime Carolyn S. Calfee David J. Erle IMPACC Network Lucy F. Robinson Charles B. Cairns Elias K. Haddad Mary Ann Comunale |
| author_facet | Jintong Hou Benjamin Haslund-Gourley Joann Diray-Arce Annmarie Hoch Nadine Rouphael Patrice M. Becker Alison D. Augustine Al Ozonoff Leying Guan Steven H. Kleinstein Bjoern Peters Elaine Reed Matt Altman Charles R. Langelier Holden Maecker Seunghee Kim Ruth R. Montgomery Florian Krammer Michael Wilson Walter Eckalbar Steven E. Bosinger Ofer Levy Hanno Steen Lindsey B. Rosen Lindsey R. Baden Esther Melamed Lauren I. R. Ehrlich Grace A. McComsey Rafick P. Sekaly Joanna Schaenman Albert C. Shaw David A. Hafler David B. Corry Farrah Kheradmand Mark A. Atkinson Scott C. Brakenridge Nelson I. Agudelo Higuita Jordan P. Metcalf Catherine L. Hough William B. Messer Bali Pulendran Kari C. Nadeau Mark M. Davis Ana Fernandez Sesma Viviana Simon Monica Kraft Chris Bime Carolyn S. Calfee David J. Erle IMPACC Network Lucy F. Robinson Charles B. Cairns Elias K. Haddad Mary Ann Comunale |
| author_sort | Jintong Hou |
| collection | DOAJ |
| description | IntroductionThe coronavirus disease 2019 (COVID-19) pandemic threatened public health and placed a significant burden on medical resources. The Immunophenotyping Assessment in a COVID-19 Cohort (IMPACC) study collected clinical, demographic, blood cytometry, serum receptor-binding domain (RBD) antibody titers, metabolomics, targeted proteomics, nasal metagenomics, Olink, nasal viral load, autoantibody, SARS-CoV-2 antibody titers, and nasal and peripheral blood mononuclear cell (PBMC) transcriptomics data from patients hospitalized with COVID-19. The aim of this study is to select baseline biomarkers and build predictive models for 28-day in-hospital COVID-19 severity and mortality with most predictive variables while prioritizing routinely collected variables.MethodsWe analyzed 1102 hospitalized COVID-19 participants. We used the lasso and forward selection to select top predictors for severity and mortality, and built predictive models based on balanced training data. We then validated the models on testing data.ResultsSeverity was best predicted by the baseline SpO2/FiO2 ratio obtained from COVID-19 patients (test AUC: 0.874). Adding patient age, BMI, FGF23, IL-6, and LTA to the disease severity prediction model improves the test AUC by an additional 3%. The clinical mortality prediction model using SpO2/FiO2 ratio, age, and BMI resulted in a test AUC of 0.83. Adding laboratory results such as TNFRSF11B and plasma ribitol count increased the prediction model by 3.5%. The severity and mortality prediction models developed outperform the Sequential Organ Failure Assessment (SOFA) score among inpatients and perform similarly to the SOFA score among ICU patients.ConclusionThis study identifies clinical data and laboratory biomarkers of COVID-19 severity and mortality using machine learning models. The study identifies SpO2/FiO2 ratio to be the most important predictor for both severity and mortality. Several biomarkers were identified to modestly improve the predictions. The results also provide a baseline of SARS-CoV-2 infection during the early stages of the coronavirus emergence and can serve as a baseline for future studies that inform how the genetic evolution of the coronavirus affects the host response to new variants. |
| format | Article |
| id | doaj-art-b62aca6b95d54c71a8ceafd20ff024c9 |
| institution | DOAJ |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-b62aca6b95d54c71a8ceafd20ff024c92025-08-20T02:44:29ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-07-011210.3389/fmed.2025.16043881604388Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC studyJintong Hou0Benjamin Haslund-Gourley1Joann Diray-Arce2Annmarie Hoch3Nadine Rouphael4Patrice M. Becker5Alison D. Augustine6Al Ozonoff7Leying Guan8Steven H. Kleinstein9Bjoern Peters10Elaine Reed11Matt Altman12Charles R. Langelier13Holden Maecker14Seunghee Kim15Ruth R. Montgomery16Florian Krammer17Michael Wilson18Walter Eckalbar19Steven E. Bosinger20Ofer Levy21Hanno Steen22Lindsey B. Rosen23Lindsey R. Baden24Esther Melamed25Lauren I. R. Ehrlich26Grace A. McComsey27Rafick P. Sekaly28Joanna Schaenman29Albert C. Shaw30David A. Hafler31David B. Corry32Farrah Kheradmand33Mark A. Atkinson34Scott C. Brakenridge35Nelson I. Agudelo Higuita36Jordan P. Metcalf37Catherine L. Hough38William B. Messer39Bali Pulendran40Kari C. Nadeau41Mark M. Davis42Ana Fernandez Sesma43Viviana Simon44Monica Kraft45Chris Bime46Carolyn S. Calfee47David J. Erle48 IMPACC NetworkLucy F. Robinson49Charles B. Cairns50Elias K. Haddad51Mary Ann Comunale52Department of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesDepartment of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesClinical and Data Coordinating Center (CDCC) Precision Vaccines Program, Boston Children's Hospital, Boston, MA, United StatesClinical and Data Coordinating Center (CDCC) Precision Vaccines Program, Boston Children's Hospital, Boston, MA, United StatesEmory School of Medicine, Atlanta, GA, United StatesNational Institute of Allergy and Infectious Diseases, National Institute of Health, Bethesda, MD, United StatesNational Institute of Allergy and Infectious Diseases, National Institute of Health, Bethesda, MD, United StatesClinical and Data Coordinating Center (CDCC) Precision Vaccines Program, Boston Children's Hospital, Boston, MA, United StatesYale School of Public Health, and Yale School of Medicine, New Haven, CT, United StatesYale School of Public Health, and Yale School of Medicine, New Haven, CT, United StatesLa Jolla Institute for Immunology, La Jolla, CA, United StatesDavid Geffen School of Medicine at the University of California Los Angeles, Los Angeles, CA, United StatesDepartment of Medicine, Benaroya Research Institute, University of Washington, Seattle, WA, United StatesSchool of Medicine, University of California San Francisco, San Francisco, CA, United States0Stanford University School of Medicine, Palo Alto, CA, United States1Icahn School of Medicine at Mount Sinai, New York, NY, United StatesYale School of Public Health, and Yale School of Medicine, New Haven, CT, United States0Stanford University School of Medicine, Palo Alto, CA, United StatesSchool of Medicine, University of California San Francisco, San Francisco, CA, United StatesSchool of Medicine, University of California San Francisco, San Francisco, CA, United StatesEmory School of Medicine, Atlanta, GA, United States2Precision Vaccines Program, Boston Children's Hospital, Harvard Medical School, Boston, MA, United States2Precision Vaccines Program, Boston Children's Hospital, Harvard Medical School, Boston, MA, United StatesNational Institute of Allergy and Infectious Diseases, National Institute of Health, Bethesda, MD, United States3Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States4Department of Neurology/Department of Molecular Biosciences, University of Texas, Austin, TX, United States4Department of Neurology/Department of Molecular Biosciences, University of Texas, Austin, TX, United States5Case Western Reserve University and University Hospitals of Cleveland, Cleveland, OH, United States5Case Western Reserve University and University Hospitals of Cleveland, Cleveland, OH, United StatesDavid Geffen School of Medicine at the University of California Los Angeles, Los Angeles, CA, United StatesYale School of Public Health, and Yale School of Medicine, New Haven, CT, United StatesYale School of Public Health, and Yale School of Medicine, New Haven, CT, United States6Baylor College of Medicine and the Center for Translational Research on Inflammatory Diseases, Houston, TX, United States6Baylor College of Medicine and the Center for Translational Research on Inflammatory Diseases, Houston, TX, United States7Department of Pathology, Immunology and Laboratory Medicine/Department of Surgery, University of Florida, Gainesville, FL, United States7Department of Pathology, Immunology and Laboratory Medicine/Department of Surgery, University of Florida, Gainesville, FL, United States8Oklahoma University Health Sciences Center, Oklahoma City, OK, United States8Oklahoma University Health Sciences Center, Oklahoma City, OK, United States9Department of Medicine, Oregon Health Sciences University, Portland, OR, United States9Department of Medicine, Oregon Health Sciences University, Portland, OR, United States0Stanford University School of Medicine, Palo Alto, CA, United States0Stanford University School of Medicine, Palo Alto, CA, United States0Stanford University School of Medicine, Palo Alto, CA, United States1Icahn School of Medicine at Mount Sinai, New York, NY, United States1Icahn School of Medicine at Mount Sinai, New York, NY, United States0Department of Medicine, University of Arizona, Tucson, AZ, United States9Department of Medicine, Oregon Health Sciences University, Portland, OR, United StatesSchool of Medicine, University of California San Francisco, San Francisco, CA, United StatesSchool of Medicine, University of California San Francisco, San Francisco, CA, United StatesDepartment of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesDepartment of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesDepartment of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesDepartment of Microbiology and Immunology/Department of Medicine/Department of Epidemiology & Biostatistics, Drexel University, Philadelphia, PA, United StatesIntroductionThe coronavirus disease 2019 (COVID-19) pandemic threatened public health and placed a significant burden on medical resources. The Immunophenotyping Assessment in a COVID-19 Cohort (IMPACC) study collected clinical, demographic, blood cytometry, serum receptor-binding domain (RBD) antibody titers, metabolomics, targeted proteomics, nasal metagenomics, Olink, nasal viral load, autoantibody, SARS-CoV-2 antibody titers, and nasal and peripheral blood mononuclear cell (PBMC) transcriptomics data from patients hospitalized with COVID-19. The aim of this study is to select baseline biomarkers and build predictive models for 28-day in-hospital COVID-19 severity and mortality with most predictive variables while prioritizing routinely collected variables.MethodsWe analyzed 1102 hospitalized COVID-19 participants. We used the lasso and forward selection to select top predictors for severity and mortality, and built predictive models based on balanced training data. We then validated the models on testing data.ResultsSeverity was best predicted by the baseline SpO2/FiO2 ratio obtained from COVID-19 patients (test AUC: 0.874). Adding patient age, BMI, FGF23, IL-6, and LTA to the disease severity prediction model improves the test AUC by an additional 3%. The clinical mortality prediction model using SpO2/FiO2 ratio, age, and BMI resulted in a test AUC of 0.83. Adding laboratory results such as TNFRSF11B and plasma ribitol count increased the prediction model by 3.5%. The severity and mortality prediction models developed outperform the Sequential Organ Failure Assessment (SOFA) score among inpatients and perform similarly to the SOFA score among ICU patients.ConclusionThis study identifies clinical data and laboratory biomarkers of COVID-19 severity and mortality using machine learning models. The study identifies SpO2/FiO2 ratio to be the most important predictor for both severity and mortality. Several biomarkers were identified to modestly improve the predictions. The results also provide a baseline of SARS-CoV-2 infection during the early stages of the coronavirus emergence and can serve as a baseline for future studies that inform how the genetic evolution of the coronavirus affects the host response to new variants.https://www.frontiersin.org/articles/10.3389/fmed.2025.1604388/fullCOVID-19severitymortalitymachine learningSpO2/FiO2TNFRSF11B |
| spellingShingle | Jintong Hou Benjamin Haslund-Gourley Joann Diray-Arce Annmarie Hoch Nadine Rouphael Patrice M. Becker Alison D. Augustine Al Ozonoff Leying Guan Steven H. Kleinstein Bjoern Peters Elaine Reed Matt Altman Charles R. Langelier Holden Maecker Seunghee Kim Ruth R. Montgomery Florian Krammer Michael Wilson Walter Eckalbar Steven E. Bosinger Ofer Levy Hanno Steen Lindsey B. Rosen Lindsey R. Baden Esther Melamed Lauren I. R. Ehrlich Grace A. McComsey Rafick P. Sekaly Joanna Schaenman Albert C. Shaw David A. Hafler David B. Corry Farrah Kheradmand Mark A. Atkinson Scott C. Brakenridge Nelson I. Agudelo Higuita Jordan P. Metcalf Catherine L. Hough William B. Messer Bali Pulendran Kari C. Nadeau Mark M. Davis Ana Fernandez Sesma Viviana Simon Monica Kraft Chris Bime Carolyn S. Calfee David J. Erle IMPACC Network Lucy F. Robinson Charles B. Cairns Elias K. Haddad Mary Ann Comunale Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study Frontiers in Medicine COVID-19 severity mortality machine learning SpO2/FiO2 TNFRSF11B |
| title | Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study |
| title_full | Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study |
| title_fullStr | Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study |
| title_full_unstemmed | Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study |
| title_short | Baseline predictors for 28-day COVID-19 severity and mortality among hospitalized patients: results from the IMPACC study |
| title_sort | baseline predictors for 28 day covid 19 severity and mortality among hospitalized patients results from the impacc study |
| topic | COVID-19 severity mortality machine learning SpO2/FiO2 TNFRSF11B |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1604388/full |
| work_keys_str_mv | AT jintonghou baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT benjaminhaslundgourley baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT joanndirayarce baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT annmariehoch baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT nadinerouphael baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT patricembecker baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT alisondaugustine baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT alozonoff baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT leyingguan baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT stevenhkleinstein baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT bjoernpeters baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT elainereed baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT mattaltman baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT charlesrlangelier baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT holdenmaecker baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT seungheekim baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT ruthrmontgomery baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT floriankrammer baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT michaelwilson baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT waltereckalbar baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT stevenebosinger baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT oferlevy baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT hannosteen baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT lindseybrosen baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT lindseyrbaden baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT esthermelamed baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT laurenirehrlich baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT graceamccomsey baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT rafickpsekaly baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT joannaschaenman baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT albertcshaw baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT davidahafler baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT davidbcorry baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT farrahkheradmand baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT markaatkinson baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT scottcbrakenridge baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT nelsoniagudelohiguita baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT jordanpmetcalf baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT catherinelhough baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT williambmesser baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT balipulendran baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT karicnadeau baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT markmdavis baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT anafernandezsesma baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT vivianasimon baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT monicakraft baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT chrisbime baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT carolynscalfee baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT davidjerle baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT impaccnetwork baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT lucyfrobinson baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT charlesbcairns baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT eliaskhaddad baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy AT maryanncomunale baselinepredictorsfor28daycovid19severityandmortalityamonghospitalizedpatientsresultsfromtheimpaccstudy |