TY - JOUR
T1 - Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality
AU - Devaux, Yvan
AU - Zhang, Lu
AU - Lumley, Andrew I.
AU - Karaduzovic-Hadziabdic, Kanita
AU - Mooser, Vincent
AU - Rousseau, Simon
AU - Shoaib, Muhammad
AU - Satagopam, Venkata
AU - Adilovic, Muhamed
AU - Srivastava, Prashant Kumar
AU - Emanueli, Costanza
AU - Martelli, Fabio
AU - Greco, Simona
AU - Badimon, Lina
AU - Padro, Teresa
AU - Lustrek, Mitja
AU - Scholz, Markus
AU - Rosolowski, Maciej
AU - Jordan, Marko
AU - Brandenburger, Timo
AU - Benczik, Bettina
AU - Agg, Bence
AU - Ferdinandy, Peter
AU - Vehreschild, Jörg Janne
AU - Lorenz-Depiereux, Bettina
AU - Dörr, Marcus
AU - Witzke, Oliver
AU - Sanchez, Gabriel
AU - Kul, Seval
AU - Baker, Andy H.
AU - Fagherazzi, Guy
AU - Ollert, Markus
AU - Wereski, Ryan
AU - Mills, Nicholas L.
AU - Firat, Hüseyin
N1 - This work was supported by the EU Horizon 2020 project COVIRNA (grant agreement # 101016072) The Predi-COVID study was supported by the Luxembourg National Research Fund (FNR) (Predi-COVID, grant number 14716273), the André Losch Foundation and by European Regional Development Fund (FEDER, convention 2018-04-026-21)
Publisher Copyright:
© The Author(s) 2024.
PY - 2024/5/20
Y1 - 2024/5/20
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85193708350
UR - https://pubmed.ncbi.nlm.nih.gov/38769334
U2 - 10.1038/s41467-024-47557-1
DO - 10.1038/s41467-024-47557-1
M3 - Article
C2 - 38769334
AN - SCOPUS:85193708350
SN - 2041-1723
VL - 15
SP - 4259
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 4259
ER -