1. Artificial intelligence in clinical care amidst COVID-19 pandemic: A systematic review
- Author
-
Konstantina S. Nikita, Eleni S. Adamidi, and Konstantinos Mitsis
- Subjects
LR, Logistic Regression ,APTT, Activated Partial Thromboplastin Time ,DNN, Deep Neural Networks ,GNB, Gaussian Naïve Bayes ,RSV, Respiratory Syncytial Virus ,SVM, Support Vector Machine ,Review ,Disease ,Biochemistry ,WBC, White Blood Cell count ,0302 clinical medicine ,Multimodal data ,DLC, Density Lipoprotein Cholesterol ,Medicine ,CPP, COVID-19 Positive Patients ,Nadam optimizer, Nesterov Accelerated Adaptive Moment optimizer ,0303 health sciences ,CRT, Classification and Regression Decision Tree ,Prognosis ,LDLC, Low Density Lipoprotein Cholesterol ,CRP, C-Reactive Protein ,GFS, Gradient boosted feature selection ,LDA, Linear Discriminant Analysis ,Systematic review ,ADA, Adenosine Deaminase ,ML, Machine Learning ,CNN, Convolutional Neural Networks ,030220 oncology & carcinogenesis ,GGT, Glutamyl Transpeptidase ,RBP, Retinol Binding Protein ,RF, Random Forest ,NLP, Natural Language Processing ,INR, International Normalized Ratio ,LASSO, Least Absolute Shrinkage and Selection Operator ,FCV, Fold Cross Validation ,SEN, Sensitivity ,Biophysics ,ABG, Arterial Blood Gas ,SRLSR, Sparse Rescaled Linear Square Regression ,RBF, Radial Basis Function ,AI, Artificial Intelligence ,03 medical and health sciences ,PWD, Platelet Distribution Width ,RFE, Recursive Feature Elimination ,Genetics ,OB, Occult Blood test ,Paco2, Arterial Carbondioxide Tension ,MLP, MultiLayer Perceptron ,DL, Deep Learning ,ED, Emergency Department ,Guideline ,CI, Confidence Interval ,ANN, Artificial Neural Networks ,GFR, Glomerular Filtration Rate ,MPV, Mean Platelet Volume ,TBA, Total Bile Acid ,Adaboost, Adaptive Boosting ,TP248.13-248.65 ,MCV, Mean corpuscular volume ,ET, Extra Trees ,Artificial intelligence ,L1LR, L1 Regularized Logistic Regression ,MCHC, Mean Corpuscular Hemoglobin Concentration ,ARMED, Attribute Reduction with Multi-objective Decomposition Ensemble optimizer ,CK-MB, Creatine Kinase isoenzyme ,LSTM, Long-Short Term Memory ,FL, Federated Learning ,PCT, Thrombocytocrit ,Structural Biology ,Pandemic ,Diagnosis ,TTS, Training Test Split ,HDLC, High Density Lipoprotein Cholesterol ,PPV, Positive Predictive Values ,k-NN, K-Nearest Neighbor ,Computer Science Applications ,BUN, Blood Urea Nitrogen ,FiO2, Fraction of Inspiration O2 ,RBC, Red Blood Cell ,SG, Specific Gravity ,GDCNN, Genetic Deep Learning Convolutional Neural Network ,Screening ,XGB, eXtreme Gradient Boost ,Apol B, Apolipoprotein B ,GBDT, Gradient Boost Decision Tree ,PaO2, Arterial Oxygen Tension ,Biotechnology ,NB, Naïve Bayes ,Coronavirus disease 2019 (COVID-19) ,Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) ,SMOTE, Synthetic Minority Oversampling Technique ,Apol AI, Apolipoprotein AI ,CoxPH, Cox Proportional Hazards ,Acc, Accuracy ,AUC, Area Under the Curve ,ComputingMethodologies_COMPUTERGRAPHICS ,030304 developmental biology ,ESR, Erythrocyte Sedimentation Rate ,LDH, Lactate Dehydrogenase ,BNB, Bernoulli Naïve Bayes ,business.industry ,RDW, Red blood cell Distribution Width ,NPV, Negative Predictive Values ,GBM light, Gradient Boosting Machine light ,DCNN, Deep Convolutional Neural Networks ,SPE, Specificity ,COVID-19 ,Inception Resnet, Inception Residual Neural Network ,DT, Decision Tree ,MRMR, Maximum Relevance Minimum Redundancy ,SaO2, Arterial Oxygen saturation ,business ,Predictive modelling - Abstract
Graphical abstract, The worldwide health crisis caused by the SARS-Cov-2 virus has resulted in>3 million deaths so far. Improving early screening, diagnosis and prognosis of the disease are critical steps in assisting healthcare professionals to save lives during this pandemic. Since WHO declared the COVID-19 outbreak as a pandemic, several studies have been conducted using Artificial Intelligence techniques to optimize these steps on clinical settings in terms of quality, accuracy and most importantly time. The objective of this study is to conduct a systematic literature review on published and preprint reports of Artificial Intelligence models developed and validated for screening, diagnosis and prognosis of the coronavirus disease 2019. We included 101 studies, published from January 1st, 2020 to December 30th, 2020, that developed AI prediction models which can be applied in the clinical setting. We identified in total 14 models for screening, 38 diagnostic models for detecting COVID-19 and 50 prognostic models for predicting ICU need, ventilator need, mortality risk, severity assessment or hospital length stay. Moreover, 43 studies were based on medical imaging and 58 studies on the use of clinical parameters, laboratory results or demographic features. Several heterogeneous predictors derived from multimodal data were identified. Analysis of these multimodal data, captured from various sources, in terms of prominence for each category of the included studies, was performed. Finally, Risk of Bias (RoB) analysis was also conducted to examine the applicability of the included studies in the clinical setting and assist healthcare providers, guideline developers, and policymakers.
- Published
- 2021