Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
20 May 2024
20 May 2024
Historique:
received:
11
12
2023
accepted:
03
04
2024
medline:
21
5
2024
pubmed:
21
5
2024
entrez:
20
5
2024
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 38769334
doi: 10.1038/s41467-024-47557-1
pii: 10.1038/s41467-024-47557-1
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
4259Subventions
Organisme : European Commission (EC)
ID : 101016072
Organisme : Fonds National de la Recherche Luxembourg (National Research Fund)
ID : C17/BM/11613033
Organisme : Fonds National de la Recherche Luxembourg (National Research Fund)
ID : C14/BM/8225223
Organisme : Fonds National de la Recherche Luxembourg (National Research Fund)
ID : COVID-19/2020-1/14719577/miRCOVID
Informations de copyright
© 2024. The Author(s).
Références
2023, N. P. O. A. The Nobel Prize in Physiology or Medicine 2023, https://www.nobelprize.org/prizes/medicine/2023/summary/ (2023).
Winkle, M., El-Daly, S. M., Fabbri, M. & Calin, G. A. Noncoding RNA therapeutics—challenges and potential solutions. Nat. Rev. Drug Discov. 20, 629–651 (2021).
doi: 10.1038/s41573-021-00219-z
pubmed: 34145432
pmcid: 8212082
Badimon, L. & Devaux, Y. Transcriptomics research to improve cardiovascular healthcare. Eur. Heart J. 41, 3296–3298 (2020).
doi: 10.1093/eurheartj/ehaa237
pubmed: 33033839
Gomes, C. P. C. et al. Catalyzing transcriptomics research in cardiovascular disease: the CardioRNA COST action CA17129. Noncoding RNA 5, 31 (2019).
pubmed: 30934986
pmcid: 6630366
Badimon, L. et al. Cardiovascular RNA markers and artificial intelligence may improve COVID-19 outcome: a position paper from the EU-CardioRNA COST Action CA17129. Cardiovasc. Res. 117, 1823–1840 (2021).
doi: 10.1093/cvr/cvab094
pubmed: 33839767
pmcid: 8083253
Robinson, E. L., Emanueli, C., Martelli, F. & Devaux, Y. Leveraging non-coding RNAs to fight cardiovascular disease: the EU-CardioRNA network. Eur. Heart J. 42, 4881–4883 (2021).
doi: 10.1093/eurheartj/ehab326
pubmed: 34109376
Firat, H. et al. FIMICS: a panel of long noncoding RNAs for cardiovascular conditions. Heliyon 9, e13087 (2023).
doi: 10.1016/j.heliyon.2023.e13087
pubmed: 36747920
pmcid: 9898641
Chauviere, L. et al. Firalink: a bioinformatics pipeline for long non-coding RNA data analysis. Noncoding RNA Res. 8, 602–604 (2023).
doi: 10.1016/j.ncrna.2023.09.002
pubmed: 37771472
pmcid: 10523182
Mohamed, H. A. et al. MicroRNAs and cytokines as potential predictive biomarkers for COVID-19 disease progression. Sci. Rep. 13, 3531 (2023).
doi: 10.1038/s41598-023-30474-6
pubmed: 36864077
pmcid: 9979137
Gelzo, M. et al. Matrix metalloproteinases (MMP) 3 and 9 as biomarkers of severity in COVID-19 patients. Sci. Rep. 12, 1212 (2022).
doi: 10.1038/s41598-021-04677-8
pubmed: 35075175
pmcid: 8786927
Fu, Z. et al. A virus-derived microRNA-like small RNA serves as a serum biomarker to prioritize the COVID-19 patients at high risk of developing severe disease. Cell Discov. 7, 48 (2021).
doi: 10.1038/s41421-021-00289-8
pubmed: 34226530
pmcid: 8257610
Greco, S. et al. HCG18, LEF1AS1 and lncCEACAM21 as biomarkers of disease severity in the peripheral blood mononuclear cells of COVID-19 patients. J. Transl. Med. 21, 758 (2023).
doi: 10.1186/s12967-023-04497-6
pubmed: 37884975
pmcid: 10605335
Wynants, L. et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ 369, m1328 (2020).
doi: 10.1136/bmj.m1328
pubmed: 32265220
pmcid: 7222643
Hausburg, M. A., Banton, K. L., Roshon, M. & Bar-Or, D. Clinically distinct COVID-19 cases share notably similar immune response progression: a follow-up analysis. Heliyon 7, e05877 (2021).
doi: 10.1016/j.heliyon.2020.e05877
pubmed: 33437888
Yang, M. et al. Lef1 is transcriptionally activated by Klf4 and suppresses hyperoxia-induced alveolar epithelial cell injury. Exp. Lung Res. 48, 213–223 (2022).
doi: 10.1080/01902148.2022.2108945
pubmed: 35950640
Forrest, I. S. et al. Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts. Lancet 401, 215–225 (2023).
doi: 10.1016/S0140-6736(22)02079-7
pubmed: 36563696
Ng, S., Masarone, S., Watson, D. & Barnes, M. R. The benefits and pitfalls of machine learning for biomarker discovery. Cell Tissue Res. 394, 17–31 (2023).
doi: 10.1007/s00441-023-03816-z
pubmed: 37498390
pmcid: 10558383
Sammut, S. J. et al. Multi-omic machine learning predictor of breast cancer therapy response. Nature 601, 623–629 (2022).
doi: 10.1038/s41586-021-04278-5
pubmed: 34875674
Wang, C., Lue, W., Kaalia, R., Kumar, P. & Rajapakse, J. C. Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma. Sci. Rep. 12, 15425 (2022).
doi: 10.1038/s41598-022-19019-5
pubmed: 36104347
pmcid: 9475034
Mi, X., Zou, B., Zou, F. & Hu, J. Permutation-based identification of important biomarkers for complex diseases via machine learning models. Nat. Commun. 12, 3008 (2021).
doi: 10.1038/s41467-021-22756-2
pubmed: 34021151
pmcid: 8140109
Dolgin, E. Why rings of RNA could be the next blockbuster drug. Nature 622, 22–24 (2023).
doi: 10.1038/d41586-023-03058-7
pubmed: 37794271
Reme, B. A., Gjesvik, J. & Magnusson, K. Predictors of the post-COVID condition following mild SARS-CoV-2 infection. Nat. Commun. 14, 5839 (2023).
doi: 10.1038/s41467-023-41541-x
pubmed: 37730740
pmcid: 10511472
Thaweethai, T. et al. Development of a definition of postacute sequelae of SARS-CoV-2 infection. JAMA 329, 1934–1946 (2023).
doi: 10.1001/jama.2023.8823
pubmed: 37278994
pmcid: 10214179
Global Burden of Disease Long, C. C. et al. Estimated global proportions of individuals with persistent fatigue, cognitive, and respiratory symptom clusters following symptomatic COVID-19 in 2020 and 2021. JAMA 328, 1604–1615. https://doi.org/10.1001/jama.2022.18931 (2022).
Wilmes, P. et al. SARS-CoV-2 transmission risk from asymptomatic carriers: Results from a mass screening programme in Luxembourg. Lancet Reg. Health Eur. 4, 100056 (2021).
doi: 10.1016/j.lanepe.2021.100056
pubmed: 33997830
pmcid: 7912359
Fagherazzi, G. et al. Protocol for a prospective, longitudinal cohort of people with COVID-19 and their household members to study factors associated with disease severity: the Predi-COVID study. BMJ Open 10, e041834 (2020).
doi: 10.1136/bmjopen-2020-041834
pubmed: 33234656
pmcid: 7684799
Schons, M. et al. The German National Pandemic Cohort Network (NAPKON): rationale, study design and baseline characteristics. Eur. J. Epidemiol. 37, 849–870 (2022).
doi: 10.1007/s10654-022-00896-z
pubmed: 35904671
pmcid: 9336157
Tremblay, K. et al. The Biobanque quebecoise de la COVID-19 (BQC19)-A cohort to prospectively study the clinical and biological determinants of COVID-19 clinical trajectories. PLoS One 16, e0245031 (2021).
doi: 10.1371/journal.pone.0245031
pubmed: 34010280
pmcid: 8133500
Stekhoven, D. J. & Bühlmann, P. MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics 28, 112–118 (2011).
doi: 10.1093/bioinformatics/btr597
pubmed: 22039212
Law, C. W., Chen, Y., Shi, W. & Smyth, G. K. voom: precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biol. 15, R29 (2014).
doi: 10.1186/gb-2014-15-2-r29
pubmed: 24485249
pmcid: 4053721
Love, M. I., Huber, W. & Anders, S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15, 550 (2014).
doi: 10.1186/s13059-014-0550-8
pubmed: 25516281
pmcid: 4302049
Kursa, M. B. & Rudnicki, W. R. Feature selection with the Boruta package. J. Stat. Softw. 36, 1–13 (2010).
doi: 10.18637/jss.v036.i11
Code accompanying the paper “Development of a long noncoding RNA-based machine learning model to predict COVID-19 in-hospital mortality”. https://doi.org/10.24433/CO.6166592.v1