Review on the Evaluation and Development of Artificial Intelligence for COVID-19 Containment

Sensors, Год журнала: 2023, Номер 23(1), С. 527 - 527

Опубликована: Янв. 3, 2023

Artificial intelligence has significantly enhanced the research paradigm and spectrum with a substantiated promise of continuous applicability in real world domain. intelligence, driving force current technological revolution, been used many frontiers, including education, security, gaming, finance, robotics, autonomous systems, entertainment, most importantly healthcare sector. With rise COVID-19 pandemic, several prediction detection methods using artificial have employed to understand, forecast, handle, curtail ensuing threats. In this study, recent related publications, methodologies medical reports were investigated purpose studying intelligence's role pandemic. This study presents comprehensive review specific attention machine learning, deep image processing, object detection, segmentation, few-shot learning studies that utilized tasks COVID-19. particular, genetic analysis, clinical data sound biomedical classification, socio-demographic anomaly health monitoring, personal protective equipment (PPE) observation, social control, patients' mortality risk approaches forecast threatening factors demonstrates artificial-intelligence-based algorithms integrated into Internet Things wearable devices quite effective efficient forecasting insights which actionable through wide usage. The results produced by prove is promising arena can be applied for disease prognosis, forecasting, drug discovery, development sector on global scale. We indeed played important helping fight against COVID-19, insightful knowledge provided here could extremely beneficial practitioners experts domain implement systems curbing next pandemic or disaster.

Язык: Английский

---

Diagnosing COVID-19 using artificial intelligence: a comprehensive review

Network Modeling Analysis in Health Informatics and Bioinformatics, Год журнала: 2022, Номер 11(1)

Опубликована: Июль 12, 2022

Abstract In early March 2020, the World Health Organization (WHO) proclaimed novel COVID-19 as a global pandemic. The coronavirus went on to be life-threatening infection and is still wreaking havoc all around globe. Though vaccines have been rolled out, section of population (the elderly people with comorbidities) succumb this deadly illness. Hence, it imperative diagnose prevent potential severe prognosis. This contagious disease usually diagnosed using conventional technique called Reverse Transcription Polymerase Chain Reaction (RT-PCR). However, procedure leads number wrong false-negative results. Moreover, might also not newer variants mutating virus. Artificial Intelligence has one most widely discussed topics in recent years. It used tackle various issues across multiple domains modern world. extensive review, applications detection modalities such CT-Scans, X-rays, Cough sounds, MRIs, ultrasound clinical markers are explored depth. review provides data enthusiasts broader health community complete assessment current state-of-the-art approaches diagnosing COVID-19. key future directions provided for upcoming researchers.

Язык: Английский

---

Machine Learning, Deep Learning, and Mathematical Models to Analyze Forecasting and Epidemiology of COVID-19: A Systematic Literature Review

International Journal of Environmental Research and Public Health, Год журнала: 2022, Номер 19(9), С. 5099 - 5099

Опубликована: Апрель 22, 2022

COVID-19 is a disease caused by SARS-CoV-2 and has been declared worldwide pandemic the World Health Organization due to its rapid spread. Since first case was identified in Wuhan, China, battle against this deadly started disrupted almost every field of life. Medical staff laboratories are leading from front, but researchers various fields governmental agencies have also proposed healthy ideas protect each other. In article, Systematic Literature Review (SLR) presented highlight latest developments analyzing data using machine learning deep algorithms. The number studies related Machine Learning (ML), Deep (DL), mathematical models discussed research shown significant impact on forecasting spread COVID-19. results discussion study based PRISMA (Preferred Reporting Items for Reviews Meta-Analyses) guidelines. Out 218 articles selected at stage, 57 met criteria were included review process. findings therefore associated with those studies, which recorded that CNN (DL) SVM (ML) most used algorithms forecasting, classification, automatic detection. importance compartmental useful measuring epidemiological features Current suggest it will take around 1.7 140 days epidemic double size studies. 12 estimates basic reproduction range 0 7.1. main purpose illustrate use ML, DL, can be helpful generate valuable solutions higher authorities healthcare industry reduce epidemic.

Язык: Английский

---

Multi-region machine learning-based novel ensemble approaches for predicting COVID-19 pandemic in Africa

Environmental Science and Pollution Research, Год журнала: 2022, Номер 30(2), С. 3621 - 3643

Опубликована: Авг. 11, 2022

Язык: Английский

---

Extracting relevant predictive variables for COVID-19 severity prognosis: An exhaustive comparison of feature selection techniques

PLoS ONE, Год журнала: 2023, Номер 18(4), С. e0284150 - e0284150

Опубликована: Апрель 13, 2023

With the COVID-19 pandemic having caused unprecedented numbers of infections and deaths, large research efforts have been undertaken to increase our understanding disease factors which determine diverse clinical evolutions. Here we focused on a fully data-driven exploration regarding (clinical or otherwise) were most informative for SARS-CoV-2 pneumonia severity prediction via machine learning (ML). In particular, feature selection techniques (FS), designed reduce dimensionality data, allowed us characterize variables useful ML prognosis. We conducted multi-centre study, enrolling n = 1548 patients hospitalized due pneumonia: where 792, 238, 598 experienced low, medium high-severity evolutions, respectively. Up 106 patient-specific collected at admission, although 14 them had be discarded containing ⩾60% missing values. Alongside 7 socioeconomic attributes 32 exposures air pollution (chronic acute), these became d 148 features after variable encoding. addressed this ordinal classification problem both as regression task. Two imputation data explored, along with total 166 unique FS algorithm configurations: 46 filters, 100 wrappers 20 embeddeds. Of these, 21 setups achieved satisfactory bootstrap stability (⩾0.70) reasonable computation times: 16 2 wrappers, 3 The subsets selected by each technique showed modest Jaccard similarities across them. However, they consistently pointed out importance certain explanatory variables. Namely: patient’s C-reactive protein (CRP), index (PSI), respiratory rate (RR) oxygen levels –saturation Sp O2, quotients O2/RR arterial Sat O2/Fi O2–, neutrophil-to-lymphocyte ratio (NLR) –to extent, also neutrophil lymphocyte counts separately–, lactate dehydrogenase (LDH), procalcitonin (PCT) in blood. A remarkable agreement has found posteriori between strategy independent works investigating risk severity. Hence, findings stress suitability type approaches knowledge extraction, complementary perspectives.

Язык: Английский

---

Binary or Integer Chromosome: Which Is the Best Structure for Supervised Machine Learning Using Genetic Algorithms?

Applied Sciences, Год журнала: 2025, Номер 15(5), С. 2608 - 2608

Опубликована: Фев. 28, 2025

Supervised machine learning is widely researched nowadays. Several works have already been developed using genetic algorithms (GAs) for classification tasks evolving IF-THEN rules. Oftentimes, these methods are built integers and real values from one’s chromosome structure. In this paper, new important improvements proposed to Non-linear Computation Evolutionary Environment (NLCEE), a GA-based rule-set generator by Amaral Hruschka. The GA, called BIN-NLCEE, uses binary representation in its structure simplify mutation also produce higher search space. main goal that produces simple interpretable rules with good accuracy better converge rates. BIN-NLCEE performance was compared other GAs-based four traditional classifiers five medical domain datasets. results showed convergence rate fitness when the CEE NLCEE. 20 comparisons, achieved 9 (45%), and, according confidence interval, equivalent were obtained 11 (55%). way, or equal NLCEE 100% of comparisons. Also, outperformed all classifiers’ results, i.e.,

Язык: Английский

---

Preictal phase detection on EEG signals using hybridized machine learning classifiers with a novel feature selection procedure based GAs and ICOMP

Expert Systems with Applications, Год журнала: 2022, Номер 212, С. 118825 - 118825

Опубликована: Сен. 17, 2022

Язык: Английский

---

Exploring Machine Learning Strategies in COVID-19 Prognostic Modelling: A Systematic Analysis of Diagnosis, Classification and Outcome Prediction

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Март 18, 2024

Abstract Background The COVID-19 pandemic, which has impacted over 222 countries resulting in incalcu-lable losses, necessitated innovative solutions via machine learning (ML) to tackle the problem of overburdened healthcare systems. This study consolidates research employing ML models for prognosis, evaluates prevalent and performance, provides an overview suitable features while offering recommendations experimental protocols, reproducibility integration algorithms clinical settings. Methods We conducted a review following PRISMA framework, examining utilisation prediction. Five databases were searched relevant studies up 24 January 2023, 1,824 unique articles. Rigorous selection criteria led 204 included studies. Top-performing extracted, with area under receiver operating characteristic curve (AUC) evaluation metric used performance assessment. Results systematic investigated on prognosis across automated diagnosis (18.1%), severity classification (31.9%), outcome prediction (50%). identified thirty-four five categories twenty-one distinct six categories. most chest CT, radiographs, advanced age, frequently employed CNN, XGB, RF. neural networks (ANN, MLP, DNN), distance-based methods (kNN), ensemble (XGB), regression (PLS-DA), all exhibiting high AUC values. Conclusion Machine have shown considerable promise improving diagnostic accuracy, risk stratification, Advancements techniques their complementary technologies will be essential expediting decision-making informing decisions, long-lasting implications systems globally.

Язык: Английский

---

Telemedicine Framework in COVID-19 Pandemic

2021 International Conference on Engineering and Emerging Technologies (ICEET), Год журнала: 2022, Номер unknown, С. 1 - 8

Опубликована: Окт. 27, 2022

The COVID-19 pandemic coincided with the growth and ripeness of several digital methods, such as Artificial Intelligence (AI) (including Machine Learning (ML) Deep (DL)), internet things (IoT), big-data analytics, Software Defined Network (SDN), robotic technology, blockchain, etc. resulting in an experience chance for telemedicine advancement. In nations, a platform based on technology has been built integrated into clinical workflow variety modes, including many-to-one, one-to-many, consultation mode, practical-operation modes. These platforms are practical, efficient, successful exchanging epidemiological data, facilitating face-to-face interactions between patients or healthcare professionals over long distances, lowering risk disease transmission, enhancing patient outcomes. This article provides Systematic Literature Review (SLR) to call attention most recent advancements evaluating data utilizing various methodologies ML, DL, SDN, IoT. number studies ML DL provided reviewed this proven considerable effect prediction spreading COVID-19. main goal study is show how IoT, SDN may be used by researchers provide significant solutions authorities statements lessen influence pestilence. report also includes many novel strategies raising prevalent use.

Язык: Английский

---

Application of boosted trees to the prognosis prediction of COVID‐19

Health Science Reports, Год журнала: 2024, Номер 7(5)

Опубликована: Май 1, 2024

Abstract Background and Aims The precise prediction of COVID‐19 prognosis remains a clinical challenge. In this regard, early identification severe cases facilitates the triage management cases. present paper aims to explore patients based on routine laboratory tests taken when are admitted. Methods A data set including 1455 (727 male, 728 female) their conducted upon hospital admission, age, Intensive Care Unit (ICU) outcome were gathered. was randomly split into train (75% data) test (25% data). explainable boosting machine (EBM) extreme gradient (XGBoost) used for predicting mortality ICU admission Also, feature importance extracted using EBM XGBoost. Results XGBoost achieved 86.38% 88.56% accuracy in set, respectively. addition, predicted with an 89.37%, 79.29% patients, obtained models indicated that aspartate transaminase (AST), lymphocyte, blood urea nitrogen (BUN), age most significant predictors mortality. Furthermore, lymphocyte count, AST, BUN level patients. Conclusions current study both could predict hematological chemistry evaluation at time admission. results, levels be as prognosis.

Язык: Английский

---