scholarly journals The Role of Machine Learning Techniques to Tackle COVID-19 Crisis: A Systematic Review. (Preprint)

2020 ◽  
Author(s):  
Hafsa Bareen Syeda ◽  
Mahanazuddin Syed ◽  
Kevin Wayne Sexton ◽  
Shorabuddin Syed ◽  
Salma Begum ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Disease Progression ◽  
Meta Analysis ◽  
Machine Learning Techniques ◽  
Data Types ◽  
Detection And Diagnosis ◽  
Novel Coronavirus ◽  
The Impact

BACKGROUND The novel coronavirus responsible for COVID-19 has caused havoc with patients presenting a spectrum of complications forcing the healthcare experts around the globe to explore new technological solutions, and treatment plans. Machine learning (ML) based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize them in response to the challenges posed by the COVID-19 pandemic. OBJECTIVE The objective of this study is to conduct a systematic literature review on the role of ML as a comprehensive and decisive technology to fight the COVID-19 crisis in the arena of epidemiology, diagnosis, and disease progression. METHODS A systematic search in PubMed, Web of Science, and CINAHL databases was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines to identify all potentially relevant studies published and made available between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and ML. A total of 128 qualified articles were reviewed and analyzed based on the study objectives. RESULTS The 128 publications selected were classified into three themes based on ML applications employed to combat the COVID-19 crisis: Computational Epidemiology (CE), Early Detection and Diagnosis (EDD), and Disease Progression (DP). Of the 128 studies, 70 focused on predicting the outbreak, the impact of containment policies, and potential drug discoveries, which were grouped into the CE theme. For the EDD, we grouped forty studies that applied ML techniques to detect the presence of COVID-19 using the patient's radiological images or lab results. Eighteen publications that focused on predicting the disease progression, outcomes (recovery and mortality), Length of Stay (LOS), and number of Intensive Care Unit (ICU) days for COVID-19 positive patients were classified under the DP theme. CONCLUSIONS In this systematic review, we assembled the current COVID-19 literature that utilized ML methods to provide insights into the COVID-19 themes, highlighting the important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research.

scholarly journals The Role of Machine Learning Techniques to Tackle COVID-19 Crisis: A Systematic Review.

2020 ◽  
Author(s):  
Hafsa Bareen Syeda ◽  
Mahanazuddin Syed ◽  
Kevin Wayne Sexton ◽  
Shorabuddin Syed ◽  
Salma Begum ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Disease Progression ◽  
Meta Analysis ◽  
Machine Learning Techniques ◽  
Data Types ◽  
Detection And Diagnosis ◽  
Novel Coronavirus ◽  
The Impact

Background: The novel coronavirus responsible for COVID-19 has caused havoc with patients presenting a spectrum of complications forcing the healthcare experts around the globe to explore new technological solutions, and treatment plans. Machine learning (ML) based technologies have played a substantial role in solving complex problems, and several organizations have been swift to adopt and customize them in response to the challenges posed by the COVID-19 pandemic. Objective: The objective of this study is to conduct a systematic literature review on the role of ML as a comprehensive and decisive technology to fight the COVID-19 crisis in the arena of epidemiology, diagnosis, and disease progression. Methods: A systematic search in PubMed, Web of Science, and CINAHL databases was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines to identify all potentially relevant studies published and made available between December 1, 2019, and June 27, 2020. The search syntax was built using keywords specific to COVID-19 and ML. A total of 128 qualified articles were reviewed and analyzed based on the study objectives. Results: The 128 publications selected were classified into three themes based on ML applications employed to combat the COVID-19 crisis: Computational Epidemiology (CE), Early Detection and Diagnosis (EDD), and Disease Progression (DP). Of the 128 studies, 70 focused on predicting the outbreak, the impact of containment policies, and potential drug discoveries, which were grouped into the CE theme. For the EDD, we grouped forty studies that applied ML techniques to detect the presence of COVID-19 using the patient's radiological images or lab results. Eighteen publications that focused on predicting the disease progression, outcomes (recovery and mortality), Length of Stay (LOS), and number of Intensive Care Unit (ICU) days for COVID-19 positive patients were classified under the DP theme. Conclusions: In this systematic review, we assembled the current COVID-19 literature that utilized ML methods to provide insights into the COVID-19 themes, highlighting the important variables, data types, and available COVID-19 resources that can assist in facilitating clinical and translational research.

scholarly journals The Effect of Anakinra in Hospitalized Patients with COVID-19: An Updated Systematic Review and Meta-Analysis

2021 ◽  
Vol 10 (19) ◽  
pp. 4462
Author(s):  
Konstantinos G. Kyriakoulis ◽  
Anastasios Kollias ◽  
Garyphallia Poulakou ◽  
Ioannis G. Kyriakoulis ◽  
Ioannis P. Trontzas ◽  
...  
Keyword(s):  
Systematic Review ◽  
Meta Analysis ◽  
Interleukin 1 ◽  
Severe Pneumonia ◽  
Hospitalized Patients ◽  
Current Evidence ◽  
Adjusted Risk ◽  
Risk Of Death ◽  
The Impact

The role of immunomodulatory agents in the treatment of hospitalized patients with COVID-19 has been of increasing interest. Anakinra, an interleukin-1 inhibitor, has been shown to offer significant clinical benefits in patients with COVID-19 and hyperinflammation. An updated systematic review and meta-analysis regarding the impact of anakinra on the outcomes of hospitalized patients with COVID-19 was conducted. Studies, randomized or non-randomized with adjustment for confounders, reporting on the adjusted risk of death in patients treated with anakinra versus those not treated with anakinra were deemed eligible. A search was performed in PubMed/EMBASE databases, as well as in relevant websites, until 1 August 2021. The meta-analysis of six studies that fulfilled the inclusion criteria (n = 1553 patients with moderate to severe pneumonia, weighted age 64 years, men 66%, treated with anakinra 50%, intubated 3%) showed a pooled hazard ratio for death in patients treated with anakinra at 0.47 (95% confidence intervals 0.34, 0.65). A meta-regression analysis did not reveal any significant associations between the mean age, percentage of males, mean baseline C-reactive protein levels, mean time of administration since symptoms onset among the included studies and the hazard ratios for death. All studies were considered as low risk of bias. The current evidence, although derived mainly from observational studies, supports a beneficial role of anakinra in the treatment of selected patients with COVID-19.

scholarly journals Monitoring the Impact of Air Quality on the COVID-19 Fatalities in Delhi, India: Using Machine Learning Techniques

2020 ◽  
pp. 1-8
Author(s):  
Jasleen Kaur Sethi ◽  
Mamta Mittal
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Air Pollutants ◽  
Machine Learning Techniques ◽  
Environmental Restoration ◽  
The Novel ◽  
Ozone Pollution ◽  
Learning Techniques ◽  
Novel Coronavirus ◽  
The Impact

ABSTRACT Objective: The focus of this study is to monitor the effect of lockdown on the various air pollutants due to the coronavirus disease (COVID-19) pandemic and identify the ones that affect COVID-19 fatalities so that measures to control the pollution could be enforced. Methods: Various machine learning techniques: Decision Trees, Linear Regression, and Random Forest have been applied to correlate air pollutants and COVID-19 fatalities in Delhi. Furthermore, a comparison between the concentration of various air pollutants and the air quality index during the lockdown period and last two years, 2018 and 2019, has been presented. Results: From the experimental work, it has been observed that the pollutants ozone and toluene have increased during the lockdown period. It has also been deduced that the pollutants that may impact the mortalities due to COVID-19 are ozone, NH3, NO2, and PM10. Conclusions: The novel coronavirus has led to environmental restoration due to lockdown. However, there is a need to impose measures to control ozone pollution, as there has been a significant increase in its concentration and it also impacts the COVID-19 mortality rate.

scholarly journals The impact of 2019 novel coronavirus on heart injury: A Systematic review and Meta-analysis

2020 ◽  
Vol 63 (4) ◽  
pp. 518-524 ◽  
Author(s):  
Jing-Wei Li ◽  
Tian-Wen Han ◽  
Mark Woodward ◽  
Craig S. Anderson ◽  
Hao Zhou ◽  
...  
Keyword(s):  
Systematic Review ◽  
Meta Analysis ◽  
Heart Injury ◽  
Novel Coronavirus ◽  
The Impact

scholarly journals Obesity is associated with increased severity of disease in COVID-19 pneumonia: a systematic review and meta-analysis

2020 ◽  
Vol 25 (1) ◽  
Author(s):  
Yanan Chu ◽  
Jinxiu Yang ◽  
Jiaran Shi ◽  
Pingping Zhang ◽  
Xingxiang Wang
Keyword(s):  
Systematic Review ◽  
Hospital Mortality ◽  
Disease Progression ◽  
Fixed Effects ◽  
Data Extraction ◽  
Meta Analysis ◽  
Critical Role ◽  
Invasive Mechanical Ventilation ◽  
Poor Outcomes ◽  
The Impact

Abstract Background Obesity has been widely reported to be associated with the disease progression of coronavirus disease 2019 (COVID-19); however, some studies have reported different findings. We conducted a systematic review and meta-analysis to investigate the association between obesity and poor outcomes in patients with COVID-19 pneumonia. Methods A systematic review and meta-analysis of studies from the PubMed, Embase, and Web of Science databases from 1 November 2019 to 24 May 2020 was performed. Study quality was assessed, and data extraction was conducted. The meta-analysis was carried out using fixed-effects and random-effects models to calculate odds ratios (ORs) of several poor outcomes in obese and non-obese COVID-19 patients. Results Twenty-two studies (n = 12,591 patients) were included. Pooled analysis demonstrated that body mass index (BMI) was higher in severe/critical COVID-19 patients than in mild COVID-19 patients (MD 2.48 kg/m2, 95% CI [2.00 to 2.96 kg/m2]). Additionally, obesity in COVID-19 patients was associated with poor outcomes (OR = 1.683, 95% CI [1.408–2.011]), which comprised severe COVID-19, ICU care, invasive mechanical ventilation use, and disease progression (OR = 4.17, 95% CI [2.32–7.48]; OR = 1.57, 95% CI [1.18–2.09]; OR = 2.13, 95% CI [1.10–4.14]; OR = 1.41, 95% CI [1.26–1.58], respectively). Obesity as a risk factor was greater in younger patients (OR 3.30 vs. 1.72). However, obesity did not increase the risk of hospital mortality (OR = 0.89, 95% CI [0.32–2.51]). Conclusions As a result of a potentially critical role of obesity in determining the severity of COVID-19, it is important to collect anthropometric information for COVID-19 patients, especially the younger group. However, obesity may not be associated with hospital mortality, and efforts to understand the impact of obesity on the mortality of COVID-19 patients should be a research priority in the future.

scholarly journals Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

2020 ◽  
Author(s):  
KOFFKA KHAN ◽  
Emilie Ramsahai
Keyword(s):  
Machine Learning ◽  
Reporting Rate ◽  
Machine Learning Techniques ◽  
Patient Treatment ◽  
Third Wave ◽  
The United Kingdom ◽  
Learning Techniques ◽  
And Gender ◽  
Novel Coronavirus ◽  
The Impact

Abstract Background: An ongoing outbreak of a novel coronavirus (2019-nCoV) pneumonia continues to aect the whole world including major countries such as China, USA, Italy, France and the United Kingdom. We present outcome ('recovered', 'isolated' or 'death') risk estimates of 2019-nCoV over 'early' datasets. A major consideration is the likelihood of death for patients with 2019-nCoV.Method: Accounting for the impact of the variations in the reporting rate of 2019-nCoV, we used machine learning techniques (AdaBoost, bagging, extra-trees, decision trees and k-nearest neighbour classiers) on two 2019-nCoVdatasets obtained from Kaggle on March 30, 2020. We used 'country', 'age' and 'gender' as features to predict outcome for both datasets. We included the patient's 'disease' history (only present in the second dataset) to predict the outcome for the second dataset.Results: The use of a patient's 'disease' history improves the prediction of 'death' by more than 7-fold. The models ignoring a patent's 'disease' history performed poorly in test predictions.Conclusion: Our ndings indicate the potential of using a patient's 'disease' history as part of the feature set in machine learning techniques to improve 2019-nCoV predictions. This development can have a positive eect on predictive patient treatment and can result in easing currently overburdened healthcare systems worldwide, especially with the increasing prevalence of second and third wave re-infections in some countries.

scholarly journals O-195 The impact of the COVID-19 outbreak on psychological distress due to the cancellation of ART. A systematic review and meta-analysis

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
Z Donarelli ◽  
G Lo Coco ◽  
S Gullo ◽  
V Oieni ◽  
A Volpes ◽  
...  
Keyword(s):  
Systematic Review ◽  
Psychological Distress ◽  
Meta Analysis ◽  
Risk Of Bias ◽  
Inclusion Criteria ◽  
Cross Sectional ◽  
Infertile Couples ◽  
The Impact ◽  
Infertile Patients

Abstract Study question Is there evidence that infertile patients have been more likely to experience distress during the COVID-19 outbreak with the consequent interruption of treatment plans? Summary answer High levels of psychological distress among infertile patients have been found during the COVID-19 pandemic, greater than that reported in the general population. What is known already Preliminary research on the negative consequences of the COVID-19 outbreak on mental health evidenced heightened levels of anxiety, depression and post-traumatic stress in some clinical populations as well as in community samples. However, little is known about the impact of COVID-19 on psychological distress of infertile patients who have been forced to suspend infertility treatment and postpone parenthood goals during the pandemic. The aim of this meta-analytic review is to summarize extant literature on the prevalence of psychological distress symptoms in infertile patients during the COVID-19 pandemic. Study design, size, duration A systematic review and meta-analysis were conducted following the PRISMA guidelines on PsycInfo, PubMed, Embase, Web of Science, MedRxiv from March 2020 to mid-December 2020. Study inclusion criteria were specified according to the PICOS guideline. All naturalistic or RCT studies published in 2020 that examined infertility as the primary diagnosis and had a quantitative measurement of distress, were eligible. The primary outcomes were symptoms of psychological distress and secondary outcomes were indicators of psychological health. Participants/materials, setting, methods The database search identified 144 papers. Two reviewers independently screened potential studies by title and abstracts based on the inclusion criteria. The full texts were then screened for eligibility. The Newcastle-Ottawa Scale was used to judge the methodological quality of the studies. In order to estimate the pooled prevalence of distress, Odds Ratios with 95% Confidence Interval were calculated as the effect size by using a random-effects model. Heterogeneity was tested using I2 statistics. Main results and the role of chance Fourteen studies met the inclusion criteria and were summarized for the systematic review (N = 6473). Only six studies did not include males although, in the surveys, females made up 92% of the total sample. Ten studies adopted a cross-sectional study design. 100% gathered data through an online survey. Nine studies showed a high risk of bias, and five had a moderate risk. Review results showed that 56,4% of patients wished to resume treatment; participants were mostly worried about the delay in treatment because of their age (>35 years) or diminished ovarian reserve, or money constraints and low education level. Only five studies examined the role of protective factors such as social support, coping, optimism trait and intolerance of uncertainty. Nine studies were included for meta-analysis. The prevalence of psychological distress was 0.58 (95% CI 0.32÷0.84). The pooled point estimates of prevalence for anxiety (N = 6) were 0.56 (95% CI 0.24÷0.88), whereas the prevalence for depression (N = 5) was 0.46 (95% CI 0.15÷0.77). There was significant heterogeneity among studies to estimate the prevalence (I² ranging from 99% to 100%). Limitations, reasons for caution Results are preliminary, given the small number of studies and their cross-sectional data. The risk of bias was high or moderate across studies. Wider implications of the findings Infertile couples reported high levels of distress due to cancellation of their diagnostic procedures or treatment; they would benefit from information, appropriate support and advice from healthcare professionals, with an important role in maintaining the wishes of infertile couples to continue their parenthood goals. Trial registration number not applicable

Impact of the menstrual cycle on peripheral vascular function in premenopausal women: systematic review and meta-analysis

2020 ◽  
Vol 319 (6) ◽  
pp. H1327-H1337
Author(s):  
Jennifer S. Williams ◽  
Emily C. Dunford ◽  
Maureen J. MacDonald
Keyword(s):  
Systematic Review ◽  
Menstrual Cycle ◽  
Endothelial Function ◽  
Vascular Function ◽  
Meta Analysis ◽  
Premenopausal Women ◽  
Cycle Phase ◽  
Peripheral Vascular ◽  
The Impact

Fluctuations in endogenous hormones estrogen and progesterone during the menstrual cycle may offer vasoprotection for endothelial and smooth muscle (VSM) function. While numerous studies have been published, the results are conflicting, leaving our understanding of the impact of the menstrual cycle on vascular function unclear. The purpose of this systematic review and meta-analysis was to consolidate available research exploring the role of the menstrual cycle on peripheral vascular function. A systematic search of MEDLINE, Web of Science, and EMBASE was performed for articles evaluating peripheral endothelial and VSM function across the natural menstrual cycle: early follicular (EF) phase versus late follicular (LF), early luteal, mid luteal, or late luteal. A meta-analysis examined the effect of the menstrual cycle on the standardized mean difference (SMD) of the outcome measures. Analysis from 30 studies ( n = 1,363 women) observed a “very low” certainty of evidence that endothelial function increased in the LF phase (SMD: 0.45, P = 0.0001), with differences observed in the macrovasculature but not in the microvasculature (SMD: 0.57, P = 0.0003, I2 = 84%; SMD: 0.21, P = 0.17, I2 = 34%, respectively). However, these results are partially explained by differences in flow-mediated dilation [e.g., discrete (SMD: 0.86, P = 0.001) vs. continuous peak diameter assessment (SMD: 0.25, P = 0.30)] and/or menstrual cycle phase methodologies. There was a “very low” certainty that endothelial function was largely unchanged in the luteal phases, and VSM was unchanged across the cycle. The menstrual cycle appears to have a small effect on macrovascular endothelial function but not on microvascular or VSM function; however, these results can be partially attributed to methodological differences.

Sign in / Sign up

Export Citation Format

Share Document