4.7 Article

Prognosing the risk of COVID-19 death through a machine learning-based routine blood panel: A retrospective study in Brazil

Related references

Note: Only part of the references are listed.
Review Medical Laboratory Technology

How is test laboratory data used and characterised by machine learning models? A systematic review of diagnostic and prognostic models developed for COVID-19 patients using only laboratory data

Anna Carobene et al.

Summary: The current gold standard for COVID-19 diagnosis, rRT-PCR test, has limitations. Machine learning methods applied to digital imagery have attracted attention. This review focuses on machine learning-based diagnostic and prognostic studies using hematochemical parameters. The reviewed studies show heterogeneity and reporting issues. Closer collaboration between data scientists and medical laboratory professionals is needed.

CLINICAL CHEMISTRY AND LABORATORY MEDICINE (2022)

Article Medicine, Research & Experimental

Prediction of SARS-CoV-2-positivity from million-scale complete blood counts using machine learning

Gianlucca Zuin et al.

Summary: Using a large dataset, Zuin et al. developed machine learning models for COVID-19 diagnosis based on CBCs, achieving high performance in validation. The study highlights the importance of incorporating information about other respiratory diseases to ensure robust results.

COMMUNICATIONS MEDICINE (2022)

Article Computer Science, Information Systems

The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression

Ruben van den Goorbergh et al.

Summary: This study examined the effect of correcting class imbalance on the performance of logistic regression models and found that methods such as random undersampling, random oversampling, and SMOTE did not improve model performance and resulted in poorly calibrated models. Imbalance correction did not enhance the ability of the models to distinguish between patients with and without the outcome event.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2022)

Letter Hematology

Coombs-negative hemolytic anemia and elevated plasma hemoglobin levels in COVID-19

Guido Lancman et al.

ANNALS OF HEMATOLOGY (2021)

Review Virology

The cytokine storm and COVID-19

Biying Hu et al.

Summary: COVID-19, caused by SARS-CoV-2, has become a global pandemic since its emergence in Wuhan, China, in December 2019, posing a serious threat to public health. Close contact and respiratory droplets are the main modes of transmission. The cytokine storm is closely associated with disease severity and mortality, emphasizing the importance of studying and treating the cytokine storm in COVID-19.

JOURNAL OF MEDICAL VIROLOGY (2021)

Article Pathology

Development of a prognostic model for mortality in COVID-19 infection using machine learning

Adam L. Booth et al.

Summary: This study aimed to identify prognostic serum biomarkers in COVID-19 patients at high risk of mortality using a machine learning model, achieving high prediction accuracy. This is crucial for timely and effective management during the pandemic.

MODERN PATHOLOGY (2021)

Review Medical Laboratory Technology

Molecular diagnostic assays for COVID-19: an overview

Parham Habibzadeh et al.

Summary: The COVID-19 pandemic has emphasized the crucial role of rapid and accurate diagnostic assays, with molecular diagnostic assays being a major group of tests used to diagnose the disease. RT-PCR for detecting SARS-CoV-2 RNA is currently the most widely used method, while alternative molecular methods such as CRISPR technology, isothermal amplification, and others show promising potential as well.

CRITICAL REVIEWS IN CLINICAL LABORATORY SCIENCES (2021)

Article Multidisciplinary Sciences

A multipurpose machine learning approach to predict COVID-19 negative prognosis in SAo Paulo, Brazil

Fernando Timoteo Fernandes et al.

Summary: This study successfully predicted the risk of developing critical conditions in COVID-19 patients using multipurpose algorithms trained on laboratory, clinical, and demographic data, showing high predictive performance. The top three most important variables in the multipurpose algorithms were the ratio of lymphocyte per C-reactive protein, C-reactive protein, and Braden Scale, highlighting the potential of machine learning algorithms to predict unspecific negative COVID-19 outcomes from routinely-collected data.

SCIENTIFIC REPORTS (2021)

Article Biotechnology & Applied Microbiology

Simple Parameters from Complete Blood Count Predict In-Hospital Mortality in COVID-19

Mattia Bellan et al.

Summary: A retrospective study in Northern Italy involving 664 COVID-19 hospitalized patients found that simple laboratory parameters like red cell distribution width, neutrophil-to-lymphocyte ratio, and platelet count accurately predicted in-hospital mortality, providing guidance for clinical decisions.

DISEASE MARKERS (2021)

Article Multidisciplinary Sciences

Spatiotemporal pattern of COVID-19 spread in Brazil

Marcia C. Castro et al.

Summary: The study found that COVID-19 in Brazil is spreading rapidly across municipalities with distinct spatial and temporal patterns of clustering, trajectories, and speed. Analysis shows that inadequate policy measures have led to high transmission and mortality burdens. The current surge in cases and deaths, along with the circulation of concerning variants, highlights the need for government to strengthen prevention and control measures.

SCIENCE (2021)

Article Medical Informatics

Machine Learning Approach to Predicting COVID-19 Disease Severity Based on Clinical Blood Test Data: Statistical Analysis and Model Development

Sakifa Aktar et al.

Summary: The study found that clinical parameters obtained from peripheral blood samples of COVID-19 patients can accurately predict disease severity, with developed analytical methods showing high accuracy and precision. This predictive approach can help identify high-risk patients and optimize hospital facilities for COVID-19 treatment.

JMIR MEDICAL INFORMATICS (2021)

Article Computer Science, Interdisciplinary Applications

Machine learning models for predicting diagnosis or prognosis of COVID-19: A systematic review

Rufaidah Dabbagh et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Article Computer Science, Interdisciplinary Applications

The importance of being external. methodological insights for the external validation of machine learning models in medicine

Federico Cabitza et al.

Summary: This study introduces a meta-validation method to assess the robustness of medical machine learning models through external validation procedures, considering dataset cardinality and data similarity. The results showed that the validation datasets had adequate cardinality and similarity, leading to good performance of the validated model, indicating the reliability of the results.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Article Computer Science, Information Systems

The need to separate the wheat from the chaff in medical informatics Introducing a comprehensive checklist for the (self)-assessment of medical AI studies

Federico Cabitza et al.

Summary: The editorial proposes a practical checklist to help authors self-assess the quality of their contributions and aid reviewers in distinguishing high-quality medical ML studies from the mere application of ML techniques to medical data.

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS (2021)

Article Multidisciplinary Sciences

Mapping the human genetic architecture of COVID-19

Mari E. K. Niemi et al.

Summary: The genetic make-up of an individual plays a role in susceptibility and response to viral infections. A global network of researchers identified 13 significant genetic loci associated with SARS-CoV-2 infection and severe COVID-19 cases. Mendelian randomization analyses suggest a causal role for smoking and body-mass index in severe COVID-19. Collaboration among human genetics researchers has allowed for the discovery of novel host genetic factors linked to COVID-19.

NATURE (2021)

Article Multidisciplinary Sciences

The selection of indicators from initial blood routine test results to improve the accuracy of early prediction of COVID-19 severity

Jiaqing Luo et al.

Summary: The global pandemic of COVID-19 has brought unprecedented pressure to the medical system, and blood routine test has become the only possible check for COVID-19 patients at fever clinics. Through the study, it is found that age is a key indicator for predicting the severity of COVID-19, with an accuracy of 0.77 and an AUC of 0.92. By proposing a Multi Criteria Decision Making algorithm, effective indicators from patients' initial blood test results were further selected, and optimized prediction model with an accuracy of 0.82 and an AUC of 0.93 was achieved, indicating Age, WBC, LYMC, and NEUT were critical factors for COVID-19 severity prediction.

PLOS ONE (2021)

Proceedings Paper Engineering, Electrical & Electronic

A Novel Machine Learning Based Screening Method For High-Risk Covid-19 Patients Based On Simple Blood Exams

Narayana Darapaneni et al.

Summary: This paper introduces a predictive model based on circulatory blood markers to identify high-risk COVID-19 patients and provide effective care programs. The machine learning-based SV-LAR model shows high precision and recall in classifying high-risk patients needing hospitalization.

2021 IEEE INTERNATIONAL IOT, ELECTRONICS AND MECHATRONICS CONFERENCE (IEMTRONICS) (2021)

Article Hematology

Heparin-induced thrombocytopenia and COVID-19

Michelangelo Sartori et al.

Summary: HIT can develop in COVID-19 patients treated with heparin, indicating a need to consider it as a possible cause of thrombocytopenia in such patients.

HEMATOLOGY REPORTS (2021)

Review Medicine, General & Internal

Biomarkers and outcomes of COVID-19 hospitalisations: systematic review and meta-analysis

Preeti Malik et al.

Summary: This study found a significant association between lymphopenia, thrombocytopenia, and elevated levels of CRP, PCT, LDH, D-dimer, and COVID-19 severity. These results have the potential to be used as early biomarkers to improve the management of COVID-19 patients by identifying high-risk patients and allocating healthcare resources appropriately in the pandemic.

BMJ EVIDENCE-BASED MEDICINE (2021)

Letter Medical Laboratory Technology

Laboratory abnormalities in patients with COVID-2019 infection

Giuseppe Lippi et al.

CLINICAL CHEMISTRY AND LABORATORY MEDICINE (2020)

Editorial Material Medicine, General & Internal

COVID-19: the gendered impacts of the outbreak

Clare Wenham et al.

LANCET (2020)

Review Hematology

Mechanism of thrombocytopenia in COVID-19 patients

Panyang Xu et al.

ANNALS OF HEMATOLOGY (2020)

Article Medical Laboratory Technology

The critical role of laboratory medicine during coronavirus disease 2019 (COVID-19) and other viral outbreaks

Giuseppe Lippi et al.

CLINICAL CHEMISTRY AND LABORATORY MEDICINE (2020)

Review Critical Care Medicine

Coagulopathy of Coronavirus Disease 2019

Toshiaki Iba et al.

CRITICAL CARE MEDICINE (2020)

Article Endocrinology & Metabolism

Diabetes is a risk factor for the progression and prognosis of COVID-19

Weina Guo et al.

DIABETES-METABOLISM RESEARCH AND REVIEWS (2020)

Review Hematology

COVID-19 and the clinical hematology laboratory

John L. Frater et al.

INTERNATIONAL JOURNAL OF LABORATORY HEMATOLOGY (2020)

Article Medicine, Research & Experimental

Clinical and immunological features of severe and moderate coronavirus disease 2019

Guang Chen et al.

JOURNAL OF CLINICAL INVESTIGATION (2020)

Article Immunology

Characteristics of Peripheral Lymphocyte Subset Alteration in COVID-19 Pneumonia

Fan Wang et al.

JOURNAL OF INFECTIOUS DISEASES (2020)

Review Infectious Diseases

Lymphopenia is associated with severe coronavirus disease 2019 (COVID-19) infections: A systemic review and meta-analysis

Qianwen Zhao et al.

INTERNATIONAL JOURNAL OF INFECTIOUS DISEASES (2020)

Article Medical Informatics

As if sand were stone. New concepts and metrics to probe the ground on which to build trustable AI

Federico Cabitza et al.

BMC MEDICAL INFORMATICS AND DECISION MAKING (2020)

Article Health Care Sciences & Services

An Easy-to-Use Machine Learning Model to Predict the Prognosis of Patients With COVID-19: Retrospective Cohort Study

Hyung-Jun Kim et al.

JOURNAL OF MEDICAL INTERNET RESEARCH (2020)

Article Immunology

Prognostic Value of Leukocytosis and Lymphopenia for Coronavirus Disease Severity

Glen Huang et al.

EMERGING INFECTIOUS DISEASES (2020)

Article Multidisciplinary Sciences

The art of using t-SNE for single-cell transcriptomics

Dmitry Kobak et al.

NATURE COMMUNICATIONS (2019)

Article Medicine, General & Internal

Azithromycin-Induced Thrombocytopenia: A Rare Etiology of Drug-Induced Immune Thrombocytopenia

Muhammad Umer Butt et al.

CASE REPORTS IN MEDICINE (2019)

Article Cardiac & Cardiovascular Systems

Red Cell Distribution Width and Mortality in Patients With Acute Coronary Syndrome: A Meta-Analysis on Prognosis

Lauro L. Abrahan et al.

CARDIOLOGY RESEARCH (2018)

Article Computer Science, Artificial Intelligence

Missing data imputation by K nearest neighbours based on grey relational structure and mutual information

Ruilin Pan et al.

APPLIED INTELLIGENCE (2015)

Review Medical Laboratory Technology

Red blood cell distribution width: A simple parameter with multiple clinical applications

Gian Luca Salvagno et al.

CRITICAL REVIEWS IN CLINICAL LABORATORY SCIENCES (2015)

Review Immunology

Iron homeostasis in host defence and inflammation

Tomas Ganz et al.

NATURE REVIEWS IMMUNOLOGY (2015)

Article Surgery

A case of thrombocytopenia associated with the use of hydroxychloroquine following open heart surgery

Deniz Demir et al.

INTERNATIONAL JOURNAL OF SURGERY CASE REPORTS (2014)

Article Meteorology & Atmospheric Sciences

Sampling Uncertainty and Confidence Intervals for the Brier Score and Brier Skill Score

A. Allen Bradley et al.

WEATHER AND FORECASTING (2008)

Article Biochemistry & Molecular Biology

Adaptive immune cells temper initial innate responses

Kwang Dong Kim et al.

NATURE MEDICINE (2007)

Article Computer Science, Artificial Intelligence

An introduction to ROC analysis

Tom Fawcett

PATTERN RECOGNITION LETTERS (2006)

Article Medicine, Research & Experimental

C-reactive protein: a critical update

MB Pepys et al.

JOURNAL OF CLINICAL INVESTIGATION (2003)