tetano
Editor, Senior Moderator
Nat Commun
. 2024 May 20;15(1):4259.
doi: 10.1038/s41467-024-47557-1. Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality
Yvan Devaux[SUP] 1 [/SUP], Lu Zhang[SUP] 2 [/SUP], Andrew I Lumley[SUP] 3 [/SUP], Kanita Karaduzovic-Hadziabdic[SUP] 4 [/SUP], Vincent Mooser[SUP] 5 [/SUP], Simon Rousseau[SUP] 6 [/SUP], Muhammad Shoaib[SUP] 7 [/SUP], Venkata Satagopam[SUP] 7 [/SUP], Muhamed Adilovic[SUP] 4 [/SUP], Prashant Kumar Srivastava[SUP] 8 [/SUP], Costanza Emanueli[SUP] 8 [/SUP], Fabio Martelli[SUP] 9 [/SUP], Simona Greco[SUP] 9 [/SUP], Lina Badimon[SUP] 10 [/SUP], Teresa Padro[SUP] 10 [/SUP], Mitja Lustrek[SUP] 11 [/SUP], Markus Scholz[SUP] 12 [/SUP], Maciej Rosolowski[SUP] 12 [/SUP], Marko Jordan[SUP] 11 [/SUP], Timo Brandenburger[SUP] 13 [/SUP], Bettina Benczik[SUP] 14 [/SUP], Bence Agg[SUP] 14 [/SUP], Peter Ferdinandy[SUP] 14 [/SUP], Jörg Janne Vehreschild[SUP] 15 16 17 18 [/SUP], Bettina Lorenz-Depiereux[SUP] 19 [/SUP], Marcus Dörr[SUP] 20 [/SUP], Oliver Witzke[SUP] 21 [/SUP], Gabriel Sanchez[SUP] 22 [/SUP], Seval Kul[SUP] 22 [/SUP], Andy H Baker[SUP] 23 24 [/SUP], Guy Fagherazzi[SUP] 25 [/SUP], Markus Ollert[SUP] 26 27 [/SUP], Ryan Wereski[SUP] 28 [/SUP], Nicholas L Mills[SUP] 28 29 [/SUP], Hüseyin Firat[SUP] 22 [/SUP]
Affiliations
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.
. 2024 May 20;15(1):4259.
doi: 10.1038/s41467-024-47557-1. Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality
Yvan Devaux[SUP] 1 [/SUP], Lu Zhang[SUP] 2 [/SUP], Andrew I Lumley[SUP] 3 [/SUP], Kanita Karaduzovic-Hadziabdic[SUP] 4 [/SUP], Vincent Mooser[SUP] 5 [/SUP], Simon Rousseau[SUP] 6 [/SUP], Muhammad Shoaib[SUP] 7 [/SUP], Venkata Satagopam[SUP] 7 [/SUP], Muhamed Adilovic[SUP] 4 [/SUP], Prashant Kumar Srivastava[SUP] 8 [/SUP], Costanza Emanueli[SUP] 8 [/SUP], Fabio Martelli[SUP] 9 [/SUP], Simona Greco[SUP] 9 [/SUP], Lina Badimon[SUP] 10 [/SUP], Teresa Padro[SUP] 10 [/SUP], Mitja Lustrek[SUP] 11 [/SUP], Markus Scholz[SUP] 12 [/SUP], Maciej Rosolowski[SUP] 12 [/SUP], Marko Jordan[SUP] 11 [/SUP], Timo Brandenburger[SUP] 13 [/SUP], Bettina Benczik[SUP] 14 [/SUP], Bence Agg[SUP] 14 [/SUP], Peter Ferdinandy[SUP] 14 [/SUP], Jörg Janne Vehreschild[SUP] 15 16 17 18 [/SUP], Bettina Lorenz-Depiereux[SUP] 19 [/SUP], Marcus Dörr[SUP] 20 [/SUP], Oliver Witzke[SUP] 21 [/SUP], Gabriel Sanchez[SUP] 22 [/SUP], Seval Kul[SUP] 22 [/SUP], Andy H Baker[SUP] 23 24 [/SUP], Guy Fagherazzi[SUP] 25 [/SUP], Markus Ollert[SUP] 26 27 [/SUP], Ryan Wereski[SUP] 28 [/SUP], Nicholas L Mills[SUP] 28 29 [/SUP], Hüseyin Firat[SUP] 22 [/SUP]
Affiliations
- PMID: 38769334
- DOI: 10.1038/s41467-024-47557-1
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.