Efficient analysis of COVID-19 clinical data using machine learning models

Alteration of circulating ACE2-network related microRNAs in patients with COVID-19

Angiotensin converting enzyme 2 (ACE2) serves as the primary receptor for the SARS-CoV-2 virus and has implications for the functioning of the cardiovascular system. Based on our previously published bioinformatic analysis, in this study we aimed to analyze the diagnostic and predictive utility of miRNAs (miR-10b-5p, miR-124-3p, miR-200b-3p, miR-26b-5p, miR-302c-5p) identified as top regulators of ACE2 network with potential to affect cardiomyocytes and cardiovascular system in patients with COVID-19. The expression of miRNAs was determined through qRT-PCR in a cohort of 79 hospitalized COVID-19 patients as well as 32 healthy volunteers. Blood samples and clinical data of COVID-19 patients were collected at admission, 7-days and 21-days after admission. We also performed SHAP analysis of clinical data and miRNAs target predictions and advanced enrichment analyses. Low expression of miR-200b-3p at the seventh day of admission is indicative of predictive value in determining the length of hospital stay and/or the likelihood of mortality, as shown in ROC curve analysis with an AUC of 0.730 and a p-value of 0.002. MiR-26b-5p expression levels in COVID-19 patients were lower at the baseline, 7 and 21-days of admission compared to the healthy controls (P < 0.0001). Similarly, miR-10b-5p expression levels were lower at the baseline and 21-days post admission (P = 0.001). The opposite situation was observed in miR-124-3p and miR-302c-5p. Enrichment analysis showed influence of analyzed miRNAs on IL-2 signaling pathway and multiple cardiovascular diseases through COVID-19-related targets. Moreover, the COVID-19-related genes regulated by miR-200b-3p were linked to T cell protein tyrosine phosphatase and the HIF-1 transcriptional activity in hypoxia. Analysis focused on COVID-19 associated genes showed that all analyzed miRNAs are strongly affecting disease pathways related to CVDs which could be explained by their strong interaction with the ACE2 network.

Artificial intelligence-driven prediction of COVID-19-related hospitalization and death: a systematic review

Aim

To perform a systematic review on the use of Artificial Intelligence (AI) techniques for predicting COVID-19 hospitalization and mortality using primary and secondary data sources.

Study eligibility criteria

Cohort, clinical trials, meta-analyses, and observational studies investigating COVID-19 hospitalization or mortality using artificial intelligence techniques were eligible. Articles without a full text available in the English language were excluded.

Data sources

Articles recorded in Ovid MEDLINE from 01/01/2019 to 22/08/2022 were screened.

Data extraction

We extracted information on data sources, AI models, and epidemiological aspects of retrieved studies.

Bias assessment

A bias assessment of AI models was done using PROBAST.

Participants

Patients tested positive for COVID-19.

Results

We included 39 studies related to AI-based prediction of hospitalization and death related to COVID-19. The articles were published in the period 2019-2022, and mostly used Random Forest as the model with the best performance. AI models were trained using cohorts of individuals sampled from populations of European and non-European countries, mostly with cohort sample size <5,000. Data collection generally included information on demographics, clinical records, laboratory results, and pharmacological treatments (i.e., high-dimensional datasets). In most studies, the models were internally validated with cross-validation, but the majority of studies lacked external validation and calibration. Covariates were not prioritized using ensemble approaches in most of the studies, however, models still showed moderately good performances with Area under the Receiver operating characteristic Curve (AUC) values >0.7. According to the assessment with PROBAST, all models had a high risk of bias and/or concern regarding applicability.

Conclusions

A broad range of AI techniques have been used to predict COVID-19 hospitalization and mortality. The studies reported good prediction performance of AI models, however, high risk of bias and/or concern regarding applicability were detected.

Future forecasting prediction of Covid-19 using hybrid deep learning algorithm

Due the quick spread of coronavirus disease 2019 (COVID-19), identification of that disease, prediction of mortality rate and recovery rate are considered as one of the critical challenges in the whole world. The occurrence of COVID-19 dissemination beyond the world is analyzed in this research and an artificial-intelligence (AI) based deep learning algorithm is suggested to detect positive cases of COVID19 patients, mortality rate and recovery rate using real-world datasets. Initially, the unwanted data like prepositions, links, hashtags etc., are removed using some pre-processing techniques. After that, term frequency inverse-term frequency (TF-IDF) andBag of Words (BoW) techniques are utilized to extract the features from pre-processed dataset. Then, Mayfly Optimization (MO) algorithm is performed to pick the relevant features from the set of features. Finally, two deep learning procedures, ResNet model and GoogleNet model, are hybridized to achieve the prediction process. Our system examines two different kinds of publicly available text datasets to identify COVID-19 disease as well as to predict mortality rate and recovery rate using those datasets. There are four different datasets are taken to analyse the performance, in which the proposed method achieves 97.56% accuracy which is 1.40% greater than Linear Regression (LR) and Multinomial Naive Bayesian (MNB), 3.39% higher than Random Forest (RF) and Stochastic gradient boosting (SGB) as well as 5.32% higher than Decision tree (DT) and Bagging techniques if first dataset. When compared to existing machine learning models, the simulation result indicates that a proposed hybrid deep learning method is valuable in corona virus identification and future mortality forecast study.

Feature Selection Using Artificial Gorilla Troop Optimization for Biomedical Data: A Case Analysis with COVID-19 Data

Feature selection (FS) is commonly thought of as a pre-processing strategy for determining the best subset of characteristics from a given collection of features. Here, a novel discrete artificial gorilla troop optimization (DAGTO) technique is introduced for the first time to handle FS tasks in the healthcare sector. Depending on the number and type of objective functions, four variants of the proposed method are implemented in this article, namely: (1) single-objective (SO-DAGTO), (2) bi-objective (wrapper) (MO-DAGTO1), (3) bi-objective (filter wrapper hybrid) (MO-DAGTO2), and (4) tri-objective (filter wrapper hybrid) (MO-DAGTO3) for identifying relevant features in diagnosing a particular disease. We provide an outstanding gorilla initialization strategy based on the label mutual information (MI) with the aim of increasing population variety and accelerate convergence. To verify the performance of the presented methods, ten medical datasets are taken into consideration, which are of variable dimensions. A comparison is also implemented between the best of the four suggested approaches (MO-DAGTO2) and four established multi-objective FS strategies, and it is statistically proven to be the superior one. Finally, a case study with COVID-19 samples is performed to extract the critical factors related to it and to demonstrate how this method is fruitful in real-world applications.