Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1144188

Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression


Blagojević, Anđela; Šušteršič, Tijana; Lorencin, Ivan; Baressi Šegota, Sandi; Anđelić, Nikola; Milovanović, Dragan; Baskić, Danijela; Baskić, Dejan; Petrović Zdravković, Nataša; Sazdanović, Predrag et al.
Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression // Computers in biology and medicine, 138 (2021), 104869, 11 doi:10.1016/j.compbiomed.2021.104869 (međunarodna recenzija, članak, ostalo)


CROSBI ID: 1144188 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression

Autori
Blagojević, Anđela ; Šušteršič, Tijana ; Lorencin, Ivan ; Baressi Šegota, Sandi ; Anđelić, Nikola ; Milovanović, Dragan ; Baskić, Danijela ; Baskić, Dejan ; Petrović Zdravković, Nataša ; Sazdanović, Predrag ; Car, Zlatan ; Filipović, Nenad

Izvornik
Computers in biology and medicine (0010-4825) 138 (2021); 104869, 11

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, ostalo

Ključne riječi
COVID-19 ; clinical condition assessment ; predictive blood biomarkers ; rule-based machine learning ; personalized model

Sažetak
Background and objectives: Although ML has been studied for different epidemiological and clinical issues as well as for survival prediction of COVID-19, there is a noticeable shortage of literature dealing with ML usage in prediction of disease severity changes through the course of the disease. In that way, predicting disease progression from mild towards moderate, severe and critical condition, would help not only to respond in a timely manner to prevent lethal results, but also to minimize the number of patients in hospitals where this is not necessary. Methods: We present a methodology for the classification of patients into 4 distinct categories of the clinical condition of COVID-19 disease. Classification of patients is based on the values of blood biomarkers that were assessed by Gradient boosting regressor and which were selected as biomarkers that have the greatest influence in the classification of patients with COVID- 19. Results: The results show that among several tested algorithms, XGBoost classifier achieved best results with an average accuracy of 94% and an average F1-score of 94.3%. We have also extracted 10 best features from blood analysis that are strongly associated with patient condition and based on those features we can predict the severity of the clinical condition. Conclusions: The main advantage of our system is that it is a decision tree-based algorithm which is easier to interpret, instead of the use of black box models, which are not appealing in medical practice.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti, Temeljne medicinske znanosti, Javno zdravstvo i zdravstvena zaštita



POVEZANOST RADA


Projekti:
Ostalo-CEI - 305.6019-20 - Use of regressive artificial intelligence (AI) and machine learning (ML) methods in modelling of COVID-19 spread (COVIDAi) (Car, Zlatan, Ostalo - CEI Extraordinary Call for Proposals 2020) ( POIROT)

Ustanove:
Tehnički fakultet, Rijeka

Citiraj ovu publikaciju:

Blagojević, Anđela; Šušteršič, Tijana; Lorencin, Ivan; Baressi Šegota, Sandi; Anđelić, Nikola; Milovanović, Dragan; Baskić, Danijela; Baskić, Dejan; Petrović Zdravković, Nataša; Sazdanović, Predrag et al.
Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression // Computers in biology and medicine, 138 (2021), 104869, 11 doi:10.1016/j.compbiomed.2021.104869 (međunarodna recenzija, članak, ostalo)
Blagojević, A., Šušteršič, T., Lorencin, I., Baressi Šegota, S., Anđelić, N., Milovanović, D., Baskić, D., Baskić, D., Petrović Zdravković, N. & Sazdanović, P. (2021) Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression. Computers in biology and medicine, 138, 104869, 11 doi:10.1016/j.compbiomed.2021.104869.
@article{article, author = {Blagojevi\'{c}, An\djela and \v{S}u\v{s}ter\v{s}i\v{c}, Tijana and Lorencin, Ivan and Baressi \v{S}egota, Sandi and An\djeli\'{c}, Nikola and Milovanovi\'{c}, Dragan and Baski\'{c}, Danijela and Baski\'{c}, Dejan and Petrovi\'{c} Zdravkovi\'{c}, Nata\v{s}a and Sazdanovi\'{c}, Predrag and Car, Zlatan and Filipovi\'{c}, Nenad}, year = {2021}, pages = {11}, DOI = {10.1016/j.compbiomed.2021.104869}, chapter = {104869}, keywords = {COVID-19, clinical condition assessment, predictive blood biomarkers, rule-based machine learning, personalized model}, journal = {Computers in biology and medicine}, doi = {10.1016/j.compbiomed.2021.104869}, volume = {138}, issn = {0010-4825}, title = {Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression}, keyword = {COVID-19, clinical condition assessment, predictive blood biomarkers, rule-based machine learning, personalized model}, chapternumber = {104869} }
@article{article, author = {Blagojevi\'{c}, An\djela and \v{S}u\v{s}ter\v{s}i\v{c}, Tijana and Lorencin, Ivan and Baressi \v{S}egota, Sandi and An\djeli\'{c}, Nikola and Milovanovi\'{c}, Dragan and Baski\'{c}, Danijela and Baski\'{c}, Dejan and Petrovi\'{c} Zdravkovi\'{c}, Nata\v{s}a and Sazdanovi\'{c}, Predrag and Car, Zlatan and Filipovi\'{c}, Nenad}, year = {2021}, pages = {11}, DOI = {10.1016/j.compbiomed.2021.104869}, chapter = {104869}, keywords = {COVID-19, clinical condition assessment, predictive blood biomarkers, rule-based machine learning, personalized model}, journal = {Computers in biology and medicine}, doi = {10.1016/j.compbiomed.2021.104869}, volume = {138}, issn = {0010-4825}, title = {Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression}, keyword = {COVID-19, clinical condition assessment, predictive blood biomarkers, rule-based machine learning, personalized model}, chapternumber = {104869} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus
  • MEDLINE


Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font