Machine Learning Based Prediction Models for the Prognosis of COVID-19 Patients with DKA

Overview

Journal Sci Rep

Date 2025 Jan 21

PMID 39837852

Authors

Zhongyuan Xiang

Jingyi Hu

Shengfang Bu

Jin Ding

Xi Chen

Ziyang Li

Affiliations

Soon will be listed here.

Abstract

Patients with Diabetic ketoacidosis (DKA) have increased critical illness and mortality during coronavirus diseases 2019 (COVID-19). The aim of our study was to develop a predictive model for the occurrence of critical illness and mortality in COVID-19 patients with DKA utilizing machine learning. Blood samples and clinical data from 242 COVID-19 patients with DKA collected from December 2022 to January 2023 at Second Xiangya Hospital. Patients were categorized into non-death (n = 202) and death (n = 38) groups, and non-severe (n = 146) and severe (n = 96) groups. We developed five machine learning-based prediction models-Extreme Gradient Boosting (XGB), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP)-to evaluate the prognosis of COVID-19 patients with DKA. We employed 5-fold cross-validation for model evaluation and used the Shapley Additive Explanations (SHAP) algorithm for result interpretation to ensure reliability. The LR model demonstrated the highest accuracy (AUC = 0.933) in predicting mortality. Additionally, the LR model excelled (AUC = 0.898) in predicting progression to severe disease. This study developed a machine learning-based predictive model for the progression to severe disease or death in COVID-19 patients with DKA, which can serve as a valuable tool to guide clinical treatment decisions.

References

Khadem H, Nemat H, Eissa M, Elliott J, Benaissa M . COVID-19 mortality risk assessments for individuals with and without diabetes mellitus: Machine learning models integrated with interpretation framework. Comput Biol Med. 2022; 144:105361. PMC: 8887960. DOI: 10.1016/j.compbiomed.2022.105361. View

Weng J, Zhou Z, Guo L, Zhu D, Ji L, Luo X . Incidence of type 1 diabetes in China, 2010-13: population based study. BMJ. 2018; 360:j5295. PMC: 5750780. DOI: 10.1136/bmj.j5295. View

Iparraguirre-Villanueva O, Espinola-Linares K, Flores Castaneda R, Cabanillas-Carbonell M . Application of Machine Learning Models for Early Detection and Accurate Classification of Type 2 Diabetes. Diagnostics (Basel). 2023; 13(14). PMC: 10378239. DOI: 10.3390/diagnostics13142383. View

Li H, Tian S, Chen T, Cui Z, Shi N, Zhong X . Newly diagnosed diabetes is associated with a higher risk of mortality than known diabetes in hospitalized patients with COVID-19. Diabetes Obes Metab. 2020; 22(10):1897-1906. PMC: 7283710. DOI: 10.1111/dom.14099. View

Nyenwe E, Kitabchi A . The evolution of diabetic ketoacidosis: An update of its etiology, pathogenesis and management. Metabolism. 2016; 65(4):507-21. DOI: 10.1016/j.metabol.2015.12.007. View

Verity R, Okell L, Dorigatti I, Winskill P, Whittaker C, Imai N . Estimates of the severity of coronavirus disease 2019: a model-based analysis. Lancet Infect Dis. 2020; 20(6):669-677. PMC: 7158570. DOI: 10.1016/S1473-3099(20)30243-7. View

Birkebaek N, Kamrath C, Grimsmann J, Aakesson K, Cherubini V, Dovc K . Impact of the COVID-19 pandemic on long-term trends in the prevalence of diabetic ketoacidosis at diagnosis of paediatric type 1 diabetes: an international multicentre study based on data from 13 national diabetes registries. Lancet Diabetes Endocrinol. 2022; 10(11):786-794. PMC: 9597608. DOI: 10.1016/S2213-8587(22)00246-7. View

Lindner D, Fitzek A, Brauninger H, Aleshcheva G, Edler C, Meissner K . Association of Cardiac Infection With SARS-CoV-2 in Confirmed COVID-19 Autopsy Cases. JAMA Cardiol. 2020; 5(11):1281-1285. PMC: 7385672. DOI: 10.1001/jamacardio.2020.3551. View

Rahmati M, Keshvari M, Mirnasuri S, Yon D, Lee S, Shin J . The global impact of COVID-19 pandemic on the incidence of pediatric new-onset type 1 diabetes and ketoacidosis: A systematic review and meta-analysis. J Med Virol. 2022; 94(11):5112-5127. PMC: 9350204. DOI: 10.1002/jmv.27996. View

10.

Sharma A, Garcia Jr G, Wang Y, Plummer J, Morizono K, Arumugaswami V . Human iPSC-Derived Cardiomyocytes Are Susceptible to SARS-CoV-2 Infection. Cell Rep Med. 2020; 1(4):100052. PMC: 7323681. DOI: 10.1016/j.xcrm.2020.100052. View

11.

Sun H, Saeedi P, Karuranga S, Pinkepank M, Ogurtsova K, Duncan B . IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045. Diabetes Res Clin Pract. 2021; 183:109119. PMC: 11057359. DOI: 10.1016/j.diabres.2021.109119. View

12.

Zou Y, Shi Y, Sun F, Liu J, Guo Y, Zhang H . Extreme gradient boosting model to assess risk of central cervical lymph node metastasis in patients with papillary thyroid carcinoma: Individual prediction using SHapley Additive exPlanations. Comput Methods Programs Biomed. 2022; 225:107038. DOI: 10.1016/j.cmpb.2022.107038. View

13.

Goel H, Melot J, Krinock M, Kumar A, Nadar S, Lip G . Heart-type fatty acid-binding protein: an overlooked cardiac biomarker. Ann Med. 2020; 52(8):444-461. PMC: 7877932. DOI: 10.1080/07853890.2020.1800075. View

14.

Otero Sanchez L, Zhan C, Gomes Da Silveira Cauduro C, Crenier L, Njimi H, Englebert G . A machine learning-based classification of adult-onset diabetes identifies patients at risk of liver-related complications. JHEP Rep. 2023; 5(8):100791. PMC: 10339249. DOI: 10.1016/j.jhepr.2023.100791. View

15.

Alberti K, Zimmet P . Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus provisional report of a WHO consultation. Diabet Med. 1998; 15(7):539-53. DOI: 10.1002/(SICI)1096-9136(199807)15:7<539::AID-DIA668>3.0.CO;2-S. View

16.

Stevens J, Bogun M, McMahon D, Zucker J, Kurlansky P, Mohan S . Diabetic ketoacidosis and mortality in COVID-19 infection. Diabetes Metab. 2021; 47(6):101267. PMC: 8317499. DOI: 10.1016/j.diabet.2021.101267. View

17.

Carney M, Pelaia T, Chew T, Teoh S, Phu A, Kim K . Host transcriptomics and machine learning for secondary bacterial infections in patients with COVID-19: a prospective, observational cohort study. Lancet Microbe. 2024; 5(3):e272-e281. DOI: 10.1016/S2666-5247(23)00363-4. View

18.

Shrestha D, Budhathoki P, Raut S, Adhikari S, Ghimire P, Thapaliya S . New-onset diabetes in COVID-19 and clinical outcomes: A systematic review and meta-analysis. World J Virol. 2021; 10(5):275-287. PMC: 8474977. DOI: 10.5501/wjv.v10.i5.275. View

19.

Chadaga K, Prabhu S, Sampathila N, Chadaga R, Umakanth S, Bhat D . Explainable artificial intelligence approaches for COVID-19 prognosis prediction using clinical markers. Sci Rep. 2024; 14(1):1783. PMC: 10799946. DOI: 10.1038/s41598-024-52428-2. View

20.

Petroulia V, Kurmann C, Haenggi M, Wagner F, Hakim A . Reversible global hypoperfusion in an adult patient with a mixed diabetic ketoacidosis/hyperglycemic hyperosmolar coma: A case report. Clin Case Rep. 2022; 10(4):e05576. PMC: 8979142. DOI: 10.1002/ccr3.5576. View