Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality.

Journal: Nature communications
PMID: 38769334

Abstract

Tools for predicting COVID-19 outcomes enable personalized healthcare, potentially easing the disease burden. This collaborative study by 15 institutions across Europe aimed to develop a machine learning model for predicting the risk of in-hospital mortality post-SARS-CoV-2 infection. Blood samples and clinical data from 1286 COVID-19 patients collected from 2020 to 2023 across four cohorts in Europe and Canada were analyzed, with 2906 long non-coding RNAs profiled using targeted sequencing. From a discovery cohort combining three European cohorts and 804 patients, age and the long non-coding RNA LEF1-AS1 were identified as predictive features, yielding an AUC of 0.83 (95% CI 0.82-0.84) and a balanced accuracy of 0.78 (95% CI 0.77-0.79) with a feedforward neural network classifier. Validation in an independent Canadian cohort of 482 patients showed consistent performance. Cox regression analysis indicated that higher levels of LEF1-AS1 correlated with reduced mortality risk (age-adjusted hazard ratio 0.54, 95% CI 0.40-0.74). Quantitative PCR validated LEF1-AS1's adaptability to be measured in hospital settings. Here, we demonstrate a promising predictive model for enhancing COVID-19 patient management.

Authors

  • Yvan Devaux
    Cardiovascular Research Unit, Department of Population Health, Luxembourg Institute of Health, 1A-B rue Edison, L-1445 Strassen, Luxembourg.
  • Lu Zhang
    Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, United States.
  • Andrew I Lumley
    Cardiovascular Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg.
  • Kanita Karaduzovic-Hadziabdic
    Faculty of Engineering and Natural Sciences, International University of Sarajevo, Sarajevo, Bosnia and Herzegovina.
  • Vincent Mooser
    Department of Human Genetics, McGill University, Montréal, QC, Canada.
  • Simon Rousseau
    The Meakins-Christie Laboratories at the Research Institute of the McGill University Heath Centre Research Institute, & Department of Medicine, Faculty of Medicine, McGill University, Montréal, QC, Canada.
  • Muhammad Shoaib
    College of Computer and Information Science, King Saud University, Riyadh, Saudi Arabia.
  • Venkata Satagopam
    Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Esch-sur-Alzette, Luxembourg.
  • Muhamed Adilovic
    Faculty of Engineering and Natural Sciences, International University of Sarajevo, Sarajevo, Bosnia and Herzegovina.
  • Prashant Kumar Srivastava
    National Heart and Lung Institute, Imperial College London, London, England, UK.
  • Costanza Emanueli
    National Heart & Lung Institute, Faculty of Medicine, Imperial College London, London, UK.
  • Fabio Martelli
    Molecular Cardiology Laboratory, IRCCS Policlinico San Donato, San Donato Milanese, Milan 20097, Italy.
  • Simona Greco
    Molecular Cardiology Laboratory, IRCCS Policlinico San Donato, Milan, Italy.
  • Lina Badimon
    Cardiovascular Science Program-ICCC, IR-Hospital de la Santa Creu i Santa Pau, Ciber CV, Autonomous University of Barcelona, Barcelona, Spain.
  • Teresa Padro
    Cardiovascular Program-ICCC, Institut d'Investigació Biomèdica Sant Pau (IIB SANT PAU); CIBERCV, Autonomous University of Barcelona, Barcelona, Spain.
  • Mitja Lustrek
  • Markus Scholz
    Institute for Medical Informatics, Statistics and Epidemiology, Medical Faculty, University of Leipzig, Leipzig, Germany; LIFE Research Center of Civilization Diseases, Leipzig, Germany.
  • Maciej Rosolowski
    Image Biopsy Lab GmbH, Vienna, Austria.
  • Marko Jordan
    Department of Intelligent Systems, Jozef Stefan Institute, Ljubljana, Slovenia.
  • Timo Brandenburger
    Department of Anaesthesiology, University Hospital Düsseldorf, Düsseldorf, Germany.
  • Bettina Benczik
    Cardiometabolic and MTA-SE System Pharmacology Research Group, Department of Pharmacology and Pharmacotherapy, Semmelweis University, Nagyvárad tér 4, Budapest, 1089, Hungary.
  • Bence Ágg
    Cardiometabolic and MTA-SE System Pharmacology Research Group, Department of Pharmacology and Pharmacotherapy, Semmelweis University, Nagyvárad tér 4, Budapest, 1089, Hungary. agg.bence@med.semmelweis-univ.hu.
  • Péter Ferdinandy
    Cardiometabolic Research Group and MTA-SE System Pharmacology Research Group, Department of Pharmacology and Pharmacotherapy, Semmelweis University, Budapest,Hungary.
  • Jörg Janne Vehreschild
    Medical Department 2 (Hematology/Oncology and Infectious Diseases), Center for Internal Medicine, Goethe University Frankfurt, University Hospital, Frankfurt, Germany.
  • Bettina Lorenz-Depiereux
    Institute of Epidemiology, Helmholtz Center Munich, Munich, Germany.
  • Marcus Dörr
    Department of Internal Medicine B, Cardiology, Angiology & Pneumology, University Medicine of Greifswald, Greifswald, Germany; German Centre for Cardiovascular Research (DZHK), partner site Greifswald, Greifswald, Germany.
  • Oliver Witzke
    Department of Infectious Diseases, University Hospital Essen, University of Duisburg-Essen, Duisburg, Germany.
  • Gabriel Sanchez
    Instituto Politécnico Nacional ESIME Culhuacan, Av. Santana 1000, Coyoacan, 04260, Ciudad de México, Mexico.
  • Seval Kul
    Firalis SA, Huningue, France.
  • Andy H Baker
    Centre for Cardiovascular Science, The Queen's Medical Research Institute, University of Edinburgh, Edinburgh, Scotland.
  • Guy Fagherazzi
    Deep Digital Phenotyping Research Unit, Department of Population Health, Luxembourg Institute of Health, 1A-B, rue Thomas Edison, 1445, Strassen, Luxembourg. guy.fagherazzi@lih.lu.
  • Markus Ollert
    Department of Infection and Immunity, Luxembourg Institute of Health, Esch-Sur-Alzette, Luxembourg.
  • Ryan Wereski
    Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK.
  • Nicholas L Mills
    Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK.
  • Hüseyin Firat
    Firalis, Huningue, France. Electronic address: hueseyin.firat@firalis.com.

Keywords

External Resources

Popular Topics
Recent Journals