Artificial-Intelligence-Driven Algorithms for Predicting
Response to Corticosteroid Treatment in Patients with
Post-Acute COVID-19

J 2023

Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19

MYSKA, Vojtech; Samuel GENZOR; Anzhelika MEZINA; Radim BURGET; Jan MIZERA et al.

Základní údaje

Originální název

Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19

Autoři

MYSKA, Vojtech; Samuel GENZOR; Anzhelika MEZINA; Radim BURGET; Jan MIZERA; Michal STYBNAR; Martin KOLARIK; Milan SOVA a Malay Kishore DUTTA

Vydání

Diagnostics, Basel, MDPI, 2023, 2075-4418

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30203 Respiratory systems

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 3.000

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14110/23:00133302

Organizační jednotka

Lékařská fakulta

Klíčová slova anglicky

personalised medication recommendation algorithms; artificial intelligence; post-COVID syndrome; prediction model; respiratory system; corticosteroids; eHealth

Štítky

14110215, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 5. 4. 2024 09:21, Mgr. Tereza Miškechová

Anotace

V originále

Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

Citovat

MYSKA, Vojtech; Samuel GENZOR; Anzhelika MEZINA; Radim BURGET; Jan MIZERA; Michal STYBNAR; Martin KOLARIK; Milan SOVA a Malay Kishore DUTTA. Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19. Diagnostics. Basel: MDPI, 2023, roč. 13, č. 10, s. 1-17. ISSN 2075-4418. Dostupné z: https://doi.org/10.3390/diagnostics13101755.

@article{2367201,
   author = {Myska, Vojtech and Genzor, Samuel and Mezina, Anzhelika and Burget, Radim and Mizera, Jan and Stybnar, Michal and Kolarik, Martin and Sova, Milan and Dutta, Malay Kishore},
   article_location = {Basel},
   article_number = {10},
   doi = {https://doi.org/10.3390/diagnostics13101755},
   keywords = {personalised medication recommendation algorithms; artificial intelligence; post-COVID syndrome; prediction model; respiratory system; corticosteroids; eHealth},
   language = {eng},
   issn = {2075-4418},
   journal = {Diagnostics},
   title = {Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19},
   url = {https://www.mdpi.com/2075-4418/13/10/1755},
   volume = {13},
   year = {2023}
}

TY  - JOUR
ID  - 2367201
AU  - Myska, Vojtech - Genzor, Samuel - Mezina, Anzhelika - Burget, Radim - Mizera, Jan - Stybnar, Michal - Kolarik, Martin - Sova, Milan - Dutta, Malay Kishore
PY  - 2023
TI  - Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19
JF  - Diagnostics
VL  - 13
IS  - 10
SP  - 1-17
EP  - 1-17
PB  - MDPI
SN  - 20754418
KW  - personalised medication recommendation algorithms
KW  - artificial intelligence
KW  - post-COVID syndrome
KW  - prediction model
KW  - respiratory system
KW  - corticosteroids
KW  - eHealth
UR  - https://www.mdpi.com/2075-4418/13/10/1755
N2  - Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.
ER  -

MYSKA, Vojtech; Samuel GENZOR; Anzhelika MEZINA; Radim BURGET; Jan MIZERA; Michal STYBNAR; Martin KOLARIK; Milan SOVA a Malay Kishore DUTTA. Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19. \textit{Diagnostics}. Basel: MDPI, 2023, roč.~13, č.~10, s.~1-17. ISSN~2075-4418. Dostupné z: https://doi.org/10.3390/diagnostics13101755.

Přehled o publikaci