Predictive models for COVID-19 detection using routine blood tests and machine learning

Kistenev, Yury V.; Vrazhnov, Denis A.; Шнайдер, Е.Е.; Zuhayri, Hala

doi:10.1016/j.heliyon.2022.e11185

Cited by 21 publications

(12 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Platelets are blood cells that are crucial in clotting and wound healing. The significance of these variables in predicting COVID-19 is not surprising, as leukocytes are essential in the body’s immune response, and platelets are necessary for clotting and wound healing, both of which play a crucial role in combating viral infections [ 1 ]. The next identified most important features are ‘Urea’, ‘Monocytes’, and ‘Eosinophils’, respectively.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Semi-Supervised KPCA-Based Monitoring Techniques for Detecting COVID-19 Infection through Blood Tests

et al. 2023

View full text Add to dashboard Cite

This study introduces a new method for identifying COVID-19 infections using blood test data as part of an anomaly detection problem by combining the kernel principal component analysis (KPCA) and one-class support vector machine (OCSVM). This approach aims to differentiate healthy individuals from those infected with COVID-19 using blood test samples. The KPCA model is used to identify nonlinear patterns in the data, and the OCSVM is used to detect abnormal features. This approach is semi-supervised as it uses unlabeled data during training and only requires data from healthy cases. The method’s performance was tested using two sets of blood test samples from hospitals in Brazil and Italy. Compared to other semi-supervised models, such as KPCA-based isolation forest (iForest), local outlier factor (LOF), elliptical envelope (EE) schemes, independent component analysis (ICA), and PCA-based OCSVM, the proposed KPCA-OSVM approach achieved enhanced discrimination performance for detecting potential COVID-19 infections. For the two COVID-19 blood test datasets that were considered, the proposed approach attained an AUC (area under the receiver operating characteristic curve) of 0.99, indicating a high accuracy level in distinguishing between positive and negative samples based on the test results. The study suggests that this approach is a promising solution for detecting COVID-19 infections without labeled data.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Detection of contaminated cases with COVID-19 is crucial for controlling the spread of the virus [ 1 ]. When contaminated cases are identified, they can be isolated and treated, preventing them from spreading the virus to others.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised KPCA-Based Monitoring Techniques for Detecting COVID-19 Infection through Blood Tests

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Additionally, Subramanian et al [ 31 ] offers a thorough overview of techniques for coronavirus infection using deep learning identification from CT scans or CXR pictures. The use of standard blood testing and ML strategies to create prediction models for COVID-19 recognition is also included in this study [ 14 ]. In 2020, a Convolutional Neural Network (CNN) for COVID-19 detection utilizing CT pictures developed by [ 29 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Learning Based COVID-19 Detection via Hard Voting Ensemble Method

Shareef

Kurnaz

2023

Wireless Pers Commun

View full text Add to dashboard Cite

Healthcare systems throughout the world are under a great deal of strain because to the continuing COVID-19 epidemic, making early and precise diagnosis critical for limiting the virus’s propagation and efficiently treating victims. The utilization of medical imaging methods like X-rays can help to speed up the diagnosis procedure. Which can offer valuable insights into the virus’s existence in the lungs. We present a unique ensemble approach to identify COVID-19 using X-ray pictures (X-ray-PIC) in this paper. The suggested approach, based on hard voting, combines the confidence scores of three classic deep learning models: CNN, VGG16, and DenseNet. We also apply transfer learning to enhance performance on small medical image datasets. Experiments indicate that the suggested strategy outperforms current techniques with a 97% accuracy, a 96% precision, a 100% recall, and a 98% F1-score.These results demonstrate the effectiveness of using ensemble approaches and COVID-19 transfer-learning diagnosis using X-ray-PIC, which could greatly aid in early detection and reducing the burden on global health systems.

show abstract

“…Consequently, identifying risk factors and characteristics at the individual patient level becomes imperative to accurately identify those at high risk of developing PCC and to establish diagnostic criteria [8]. Therefore, prioritizing the development and validation of laboratory biomarkers for the accurate diagnosis and prediction of PCC is critical [9]. The role of vaccination in mitigating the prolonged symptoms of COVID-19 is signi cant.…”

Section: Introductionmentioning

confidence: 99%

Early Biomarkers in Hospitalized Patients as Predictors of Long-Term Post- COVID-19 Conditions: A One-Year Cohort Study

Nair,

Malavika,

Gutjahr

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Post-COVID-19 conditions represent a significant challenge in patient care, with symptoms persisting beyond three month’s post-recovery. This study aimed to evaluate the incidence of post-COVID-19 conditions at one year post-COVID-19 and identify predictive biomarkers and comorbidities for effective risk stratification.Methods A cohort of 120 adult patients, including 50 intensive care and 70 non-intensive care patients, was followed up at two weeks, six weeks, and one-year post-discharge using structured questionnaires. The study integrated comorbidities and laboratory biomarkers to forecast the risk for PCC.Results The median age of participants was 56 years, with 40% having moderate to severe comorbidities. A year post-recovery, 32.8% exhibited post COVID-19 conditions. The most common symptoms were constitutional (16%), respiratory (8.4%), and neuropsychiatric (2.5%). Bayesian network analysis indicated significant correlations between constitutional symptoms, rehospitalisation, and biomarkers including C-reactive protein, lactate-dehydrogenase, ferritin, and albumin.Conclusion This study highlights the prolonged impact of post-COVID-19 conditions, one-year post infection. It highlights the role of specific biomarkers such as C-reactive protein, lactate-dehydrogenase, ferritin, and albumin in tailoring individual patient care by advancing understanding in post-COVID-19 symptoms prediction. Our findings support the need for further research to refine these insights, which are pivotal for the ongoing care of patients in the aftermath of COVID-19.

show abstract

Predictive models for COVID-19 detection using routine blood tests and machine learning

Cited by 21 publications

References 87 publications

Semi-Supervised KPCA-Based Monitoring Techniques for Detecting COVID-19 Infection through Blood Tests

Semi-Supervised KPCA-Based Monitoring Techniques for Detecting COVID-19 Infection through Blood Tests

Deep Learning Based COVID-19 Detection via Hard Voting Ensemble Method

Early Biomarkers in Hospitalized Patients as Predictors of Long-Term Post- COVID-19 Conditions: A One-Year Cohort Study

Contact Info

Product

Resources

About