tetano
Editor, Senior Moderator
J Cell Mol Med
. 2022 Jan 22.
doi: 10.1111/jcmm.17098. Online ahead of print.
Genetic prediction of ICU hospitalization and mortality in COVID-19 patients using artificial neural networks
Panagiotis G Asteris[SUP] 1 [/SUP], Eleni Gavriilaki[SUP] 2 [/SUP], Tasoula Touloumenidou[SUP] 2 [/SUP], Evaggelia-Evdoxia Koravou[SUP] 2 [/SUP], Maria Koutra[SUP] 2 [/SUP], Penelope Georgia Papayanni[SUP] 2 [/SUP], Alexandros Pouleres[SUP] 3 [/SUP], Vassiliki Karali[SUP] 4 [/SUP], Minas E Lemonis[SUP] 1 [/SUP], Anna Mamou[SUP] 1 [/SUP], Athanasia D Skentou[SUP] 1 [/SUP], Apostolia Papalexandri[SUP] 2 [/SUP], Christos Varelas[SUP] 2 [/SUP], Fani Chatzopoulou[SUP] 5 [/SUP], Maria Chatzidimitriou[SUP] 6 [/SUP], Dimitrios Chatzidimitriou[SUP] 5 [/SUP], Anastasia Veleni[SUP] 7 [/SUP], Evdoxia Rapti[SUP] 8 [/SUP], Ioannis Kioumis[SUP] 9 [/SUP], Evaggelos Kaimakamis[SUP] 10 [/SUP], Milly Bitzani[SUP] 10 [/SUP], Dimitrios Boumpas[SUP] 4 [/SUP], Argyris Tsantes[SUP] 8 [/SUP], Damianos Sotiropoulos[SUP] 2 [/SUP], Anastasia Papadopoulou[SUP] 2 [/SUP], Ioannis G Kalantzis[SUP] 11 [/SUP], Lydia A Vallianatou[SUP] 12 [/SUP], Danial J Armaghani[SUP] 13 [/SUP], Liborio Cavaleri[SUP] 14 [/SUP], Amir H Gandomi[SUP] 15 [/SUP], Mohsen Hajihassani[SUP] 16 [/SUP], Mahdi Hasanipanah[SUP] 17 [/SUP], Mohammadreza Koopialipoor[SUP] 18 [/SUP], Paulo B Lourenço[SUP] 19 [/SUP], Pijush Samui[SUP] 20 [/SUP], Jian Zhou[SUP] 21 [/SUP], Ioanna Sakellari[SUP] 2 [/SUP], Serena Valsami[SUP] 22 [/SUP], Marianna Politou[SUP] 22 [/SUP], Styliani Kokoris[SUP] 8 [/SUP], Achilles Anagnostopoulos[SUP] 2 [/SUP]
Affiliations
Abstract
There is an unmet need of models for early prediction of morbidity and mortality of Coronavirus disease-19 (COVID-19). We aimed to a) identify complement-related genetic variants associated with the clinical outcomes of ICU hospitalization and death, b) develop an artificial neural network (ANN) predicting these outcomes and c) validate whether complement-related variants are associated with an impaired complement phenotype. We prospectively recruited consecutive adult patients of Caucasian origin, hospitalized due to COVID-19. Through targeted next-generation sequencing, we identified variants in complement factor H/CFH, CFB, CFH-related, CFD, CD55, C3, C5, CFI, CD46, thrombomodulin/THBD, and A Disintegrin and Metalloproteinase with Thrombospondin motifs (ADAMTS13). Among 381 variants in 133 patients, we identified 5 critical variants associated with severe COVID-19: rs2547438 (C3), rs2250656 (C3), rs1042580 (THBD), rs800292 (CFH) and rs414628 (CFHR1). Using age, gender and presence or absence of each variant, we developed an ANN predicting morbidity and mortality in 89.47% of the examined population. Furthermore, THBD and C3a levels were significantly increased in severe COVID-19 patients and those harbouring relevant variants. Thus, we reveal for the first time an ANN accurately predicting ICU hospitalization and death in COVID-19 patients, based on genetic variants in complement genes, age and gender. Importantly, we confirm that genetic dysregulation is associated with impaired complement phenotype.
Keywords: COVID-19; SARS-CoV2; artificial intelligence; complement; complement inhibition; genetic susceptibility.
. 2022 Jan 22.
doi: 10.1111/jcmm.17098. Online ahead of print.
Genetic prediction of ICU hospitalization and mortality in COVID-19 patients using artificial neural networks
Panagiotis G Asteris[SUP] 1 [/SUP], Eleni Gavriilaki[SUP] 2 [/SUP], Tasoula Touloumenidou[SUP] 2 [/SUP], Evaggelia-Evdoxia Koravou[SUP] 2 [/SUP], Maria Koutra[SUP] 2 [/SUP], Penelope Georgia Papayanni[SUP] 2 [/SUP], Alexandros Pouleres[SUP] 3 [/SUP], Vassiliki Karali[SUP] 4 [/SUP], Minas E Lemonis[SUP] 1 [/SUP], Anna Mamou[SUP] 1 [/SUP], Athanasia D Skentou[SUP] 1 [/SUP], Apostolia Papalexandri[SUP] 2 [/SUP], Christos Varelas[SUP] 2 [/SUP], Fani Chatzopoulou[SUP] 5 [/SUP], Maria Chatzidimitriou[SUP] 6 [/SUP], Dimitrios Chatzidimitriou[SUP] 5 [/SUP], Anastasia Veleni[SUP] 7 [/SUP], Evdoxia Rapti[SUP] 8 [/SUP], Ioannis Kioumis[SUP] 9 [/SUP], Evaggelos Kaimakamis[SUP] 10 [/SUP], Milly Bitzani[SUP] 10 [/SUP], Dimitrios Boumpas[SUP] 4 [/SUP], Argyris Tsantes[SUP] 8 [/SUP], Damianos Sotiropoulos[SUP] 2 [/SUP], Anastasia Papadopoulou[SUP] 2 [/SUP], Ioannis G Kalantzis[SUP] 11 [/SUP], Lydia A Vallianatou[SUP] 12 [/SUP], Danial J Armaghani[SUP] 13 [/SUP], Liborio Cavaleri[SUP] 14 [/SUP], Amir H Gandomi[SUP] 15 [/SUP], Mohsen Hajihassani[SUP] 16 [/SUP], Mahdi Hasanipanah[SUP] 17 [/SUP], Mohammadreza Koopialipoor[SUP] 18 [/SUP], Paulo B Lourenço[SUP] 19 [/SUP], Pijush Samui[SUP] 20 [/SUP], Jian Zhou[SUP] 21 [/SUP], Ioanna Sakellari[SUP] 2 [/SUP], Serena Valsami[SUP] 22 [/SUP], Marianna Politou[SUP] 22 [/SUP], Styliani Kokoris[SUP] 8 [/SUP], Achilles Anagnostopoulos[SUP] 2 [/SUP]
Affiliations
- PMID: 35064759
- DOI: 10.1111/jcmm.17098
Abstract
There is an unmet need of models for early prediction of morbidity and mortality of Coronavirus disease-19 (COVID-19). We aimed to a) identify complement-related genetic variants associated with the clinical outcomes of ICU hospitalization and death, b) develop an artificial neural network (ANN) predicting these outcomes and c) validate whether complement-related variants are associated with an impaired complement phenotype. We prospectively recruited consecutive adult patients of Caucasian origin, hospitalized due to COVID-19. Through targeted next-generation sequencing, we identified variants in complement factor H/CFH, CFB, CFH-related, CFD, CD55, C3, C5, CFI, CD46, thrombomodulin/THBD, and A Disintegrin and Metalloproteinase with Thrombospondin motifs (ADAMTS13). Among 381 variants in 133 patients, we identified 5 critical variants associated with severe COVID-19: rs2547438 (C3), rs2250656 (C3), rs1042580 (THBD), rs800292 (CFH) and rs414628 (CFHR1). Using age, gender and presence or absence of each variant, we developed an ANN predicting morbidity and mortality in 89.47% of the examined population. Furthermore, THBD and C3a levels were significantly increased in severe COVID-19 patients and those harbouring relevant variants. Thus, we reveal for the first time an ANN accurately predicting ICU hospitalization and death in COVID-19 patients, based on genetic variants in complement genes, age and gender. Importantly, we confirm that genetic dysregulation is associated with impaired complement phenotype.
Keywords: COVID-19; SARS-CoV2; artificial intelligence; complement; complement inhibition; genetic susceptibility.