Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach

Machine learning predictive modeling of the persistence of post-Covid19 disorders: Loss of smell and taste as case studies

The worldwide health crisis triggered by the novel coronavirus (COVID-19) epidemic has resulted in an extensive variety of symptoms in people who have been infected, the most prevalent disorders of which are loss of smell and taste senses. In some patients, these disorders might occasionally last for several months and can strongly affect patients' quality of life. The COVID-19-related loss of taste and smell does not presently have a particular therapy. However, with the help of an early prediction of these disorders, healthcare providers can direct the patients to control these symptoms and prevent complications by following special procedures. The purpose of this research is to develop a machine learning (ML) model that can predict the occurrence and persistence of post-COVID-19-related loss of smell and taste abnormalities. In this study, we used our dataset to describe the symptoms, functioning, and disability of 413 verified COVID-19 patients. In order to prepare accurate classification models, we combined several ML algorithms, including logistic regression, k-nearest neighbors, support vector machine, random forest, extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). The accuracy of the loss of taste model was 91.5 % with an area-under-cure (AUC) of 0.94, and the accuracy of the loss of smell model was 95 % with an AUC of 0.97. Our proposed modelling framework can be utilized by hospitals experts to assess these post-COVID-19 disorders in the early stages, which supports the development of treatment strategies.

A non-invasive AI-based system for precise grading of anosmia in COVID-19 using neuroimaging

COVID-19 (Coronavirus), an acute respiratory disorder, is caused by SARS-CoV-2 (coronavirus severe acute respiratory syndrome). The high prevalence of COVID-19 infection has drawn attention to a frequent illness symptom: olfactory and gustatory dysfunction. The primary purpose of this manuscript is to create a Computer-Assisted Diagnostic (CAD) system to determine whether a COVID-19 patient has normal, mild, or severe anosmia. To achieve this goal, we used fluid-attenuated inversion recovery (FLAIR) Magnetic Resonance Imaging (FLAIR-MRI) and Diffusion Tensor Imaging (DTI) to extract the appearance, morphological, and diffusivity markers from the olfactory nerve. The proposed system begins with the identification of the olfactory nerve, which is performed by a skilled expert or radiologist. It then proceeds to carry out the subsequent primary steps: (i) extract appearance markers (i.e.,1 s t and2 n d order markers), morphology/shape markers (i.e., spherical harmonics), and diffusivity markers (i.e., Fractional Anisotropy (FA) & Mean Diffusivity (MD)), (ii) apply markers fusion based on the integrated markers, and (iii) determine the decision and corresponding performance metrics based on the most-promising classifier. The current study is unusual in that it ensemble bags the learned and fine-tuned ML classifiers and diagnoses olfactory bulb (OB) anosmia using majority voting. In the 5-fold approach, it achieved an accuracy of 94.1%, a balanced accuracy (BAC) of 92.18%, precision of 91.6%, recall of 90.61%, specificity of 93.75%, F1 score of 89.82%, and Intersection over Union (IoU) of 82.62%. In the 10-fold approach, stacking continued to demonstrate impressive results with an accuracy of 94.43%, BAC of 93.0%, precision of 92.03%, recall of 91.39%, specificity of 94.61%, F1 score of 91.23%, and IoU of 84.56%. In the leave-one-subject-out (LOSO) approach, the model continues to exhibit notable outcomes, achieving an accuracy of 91.6%, BAC of 90.27%, precision of 88.55%, recall of 87.96%, specificity of 92.59%, F1 score of 87.94%, and IoU of 78.69%. These results indicate that stacking and majority voting are crucial components of the CAD system, contributing significantly to the overall performance improvements. The proposed technology can help doctors assess which patients need more intensive clinical care.

Symptom-based scoring technique by machine learning to predict COVID-19: a validation study

BACKGROUND

Coronavirus disease 2019 (COVID-19) surges, such as that which occurred when omicron variants emerged, may overwhelm healthcare systems. To function properly, such systems should balance detection and workloads by improving referrals using simple yet precise and sensitive diagnostic predictions. A symptom-based scoring system was developed using machine learning for the general population, but no validation has occurred in healthcare settings. We aimed to validate a COVID-19 scoring system using self-reported symptoms, including loss of smell and taste as major indicators.

METHODS

A cross-sectional study was conducted to evaluate medical records of patients admitted to Dr. Sardjito Hospital, Yogyakarta, Indonesia, from March 2020 to December 2021. Outcomes were defined by a reverse-transcription polymerase chain reaction (RT-PCR). We compared the symptom-based scoring system, as the index test, with antigen tests, antibody tests, and clinical judgements by primary care physicians. To validate use of the index test to improve referral, we evaluated positive predictive value (PPV) and sensitivity.

RESULTS

After clinical judgement with a PPV of 61% (n = 327/530, 95% confidence interval [CI]: 60% to 62%), confirmation with the index test resulted in the highest PPV of 85% (n = 30/35, 95% CI: 83% to 87%) but the lowest sensitivity (n = 30/180, 17%, 95% CI: 15% to 19%). If this confirmation was defined by either positive predictive scoring or antigen tests, the PPV was 92% (n = 55/60, 95% CI: 90% to 94%). Meanwhile, the sensitivity was 88% (n = 55/62, 95% CI: 87% to 89%), which was higher than that when using only antigen tests (n = 29/41, 71%, 95% CI: 69% to 73%).

CONCLUSIONS

The symptom-based COVID-19 predictive score was validated in healthcare settings for its precision and sensitivity. However, an impact study is needed to confirm if this can balance detection and workload for the next COVID-19 surge.

Transient loss and recovery of oral chemesthesis, taste and smell with COVID-19: A small case-control series

Transient loss of smell is a common symptom of influenza and other upper respiratory infections. Loss of taste is possible but rare with these illnesses, and patient reports of 'taste loss' typically arise from a taste / flavor confusion. Thus, initial reports from COVID-19 patients of loss of taste and chemesthesis (i.e., chemical somatosensation like warming or cooling) were met with skepticism until multiple studies confirmed SARS-CoV-2 infections could disrupt these senses. Many studies have been based on self-report or on single time point assessments after acute illness was ended. Here, we describe intensive longitudinal data over 28 days from adults aged 18-45 years recruited in early 2021 (i.e., prior to the Delta and Omicron SARS-CoV-2 waves). These individuals were either COVID-19 positive or close contacts (per U.S. CDC criteria at the time of the study) in the first half of 2021. Upon enrollment, all participants were given nose clips, blinded samples of commercial jellybeans (Sour Cherry and Cinnamon), and scratch-n-sniff odor identification test cards (ScentCheckPro), which they used for daily assessments. In COVID-19 cases who enrolled on or before Day 10 of infection, Gaussian Process Regression showed two distinct measures of function - odor identification and odor intensity - declined relative to controls (exposed individuals who never developed COVID-19). Because enrollment began upon exposure, some participants became ill only after enrollment, which allowed us to capture baseline ratings, onset of loss, and recovery. Data from these four cases and four age- and sex- matched controls were plotted over 28 days to create panel plots. Variables included mean orthonasal intensity of four odors (ScentCheckPro), perceived nasal blockage, oral burn (Cinnamon jellybeans), and sourness and sweetness (Sour Cherry jellybeans). Controls exhibited stable ratings over time. By contrast, COVID-19 cases showed sharp deviations over time. Changes in odor intensity or odor identification were not explained by nasal blockage. No single pattern of taste loss or recovery was apparent, implying different taste qualities might recover at different rates. Oral burn was transiently reduced for some before recovering quickly, suggesting acute loss may be missed in datasets collected only after illness ends. Collectively, intensive daily testing shows orthonasal smell, oral chemesthesis and taste were each altered by acute SARS-CoV-2 infection. This disruption was dyssynchronous for different modalities, with variable loss and recovery rates across both modalities and individuals.

The Evolution and Application of Artificial Intelligence in Rhinology: A State of the Art Review

OBJECTIVE

To provide a comprehensive overview on the applications of artificial intelligence (AI) in rhinology, highlight its limitations, and propose strategies for its integration into surgical practice.

DATA SOURCES

Medline, Embase, CENTRAL, Ei Compendex, IEEE, and Web of Science.

REVIEW METHODS

English studies from inception until January 2022 and those focusing on any application of AI in rhinology were included. Study selection was independently performed by 2 authors; discrepancies were resolved by the senior author. Studies were categorized by rhinology theme, and data collection comprised type of AI utilized, sample size, and outcomes, including accuracy and precision among others.

CONCLUSIONS

An overall 5435 articles were identified. Following abstract and title screening, 130 articles underwent full-text review, and 59 articles were selected for analysis. Eleven studies were from the gray literature. Articles were stratified into image processing, segmentation, and diagnostics (n = 27); rhinosinusitis classification (n = 14); treatment and disease outcome prediction (n = 8); optimizing surgical navigation and phase assessment (n = 3); robotic surgery (n = 2); olfactory dysfunction (n = 2); and diagnosis of allergic rhinitis (n = 3). Most AI studies were published from 2016 onward (n = 45).

IMPLICATIONS FOR PRACTICE

This state of the art review aimed to highlight the increasing applications of AI in rhinology. Next steps will entail multidisciplinary collaboration to ensure data integrity, ongoing validation of AI algorithms, and integration into clinical practice. Future research should be tailored at the interplay of AI with robotics and surgical education.

Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model

OBJECTIVE

Idiopathic Sudden Sensorineural Hearing Loss (ISSHL) is an otologic emergency, and an early prediction of prognosis may facilitate proper treatment. Therefore, we investigated the prognostic factors for predicting the recovery in patients with ISSHL treated with combined treatment method using machine learning models.

METHODS

We retrospectively reviewed the medical records of 298 patients with ISSHL at a tertiary medical institution between January 2015 and September 2020. Fifty-two variables were analyzed to predict hearing recovery. Recovery was defined using Siegel's criteria, and the patients were categorized into recovery and non-recovery groups. Recovery was predicted by various machine learning models. In addition, the prognostic factors were analyzed using the difference in the loss function.

RESULTS

There were significant differences in variables including age, hypertension, previous hearing loss, ear fullness, duration of hospital admission, initial hearing level of the affected and unaffected ears, and post-treatment hearing level between recovery and non-recovery groups. The deep neural network model showed the highest predictive performance (accuracy, 88.81%; area under the receiver operating characteristic curve, 0.9448). In addition, initial hearing level of affected and non-affected ear, post-treatment (2-weeks) hearing level of affected ear were significant factors for predicting the prognosis.

CONCLUSION

The deep neural network model showed the highest predictive performance for recovery in patients with ISSHL. Some factors with prognostic value were identified. Further studies using a larger patient population are warranted.

LEVEL OF EVIDENCE

Level 4.

A Comprehensive Analysis of Deep Learning-Based Approaches for Prediction and Prognosis of Infectious Diseases

Artificial intelligence is the most powerful and promising tool for the present analytic technologies. It can provide real-time insights into disease spread and predict new pandemic epicenters by processing massive amount of data. The main aim of the paper is to detect and classify multiple infectious diseases using deep learning models. The work is conducted by using 29,252 images of COVID-19, Middle East Respiratory Syndrome Coronavirus, Pneumonia, normal, Severe Acute Respiratory Syndrome, tuberculosis, viral pneumonia, and lung opacity which has been collected from various disease datasets. These datasets are used to train the deep learning models such as EfficientNetB0, EfficientNetB1, EfficientNetB2, EfficientNetB3, NASNetLarge, DenseNet169, ResNet152V2, and InceptionResNetV2. The images have been initially graphically represented using exploratory data analysis to study the pixel intensity and find anomalies by extracting the color channels in an RGB histogram. Later, the dataset has been pre-processed to remove noisy signals using image augmentation and contrast enhancement techniques. Further, feature extraction techniques such as morphological values of contour features and Otsu thresholding have been applied to extract the feature. The models have been evaluated on the basis of various parameters, and it has been discovered that during the testing phase, the InceptionResNetV2 model generated the highest accuracy of 88%, best loss value of 0.399, and root mean square error of 0.63.

Transient loss and recovery of oral chemesthesis, taste and smell with COVID-19: a small case-control series

Anosmia is common with respiratory virus infections, but loss of taste or chemesthesis is rare. Reports of true taste loss with COVID-19 were viewed skeptically until confirmed by multiple studies. Nasal menthol thresholds are elevated in some with prior COVID-19 infections, but data on oral chemesthesis are lacking. Many patients recover quickly, but precise timing and synchrony of recovery are unclear. Here, we collected broad sensory measures over 28 days, recruiting adults (18-45 years) who were COVID-19 positive or recently exposed (close contacts per U.S. CDC criteria at the time of the study) in the first half of 2021. Participants received nose clips, red commercial jellybeans (Sour Cherry and Cinnamon), and scratch-n-sniff cards (ScentCheckPro). Among COVID-19 cases who entered the study on or before Day 10 of infection, Gaussian Process Regression showed odor identification and odor intensity (two distinct measures of function) each declined relative to controls (close contacts who never developed COVID-19), but effects were larger for intensity than identification. To assess changes during early onset, we identified four COVID-19 cases who enrolled on or prior to Day 1 of their illness â€" this allowed for visualization of baseline ratings, loss, and recovery of function over time. Four controls were matched for age, gender, and race. Variables included sourness and sweetness (Sour Cherry jellybeans), oral burn (Cinnamon jellybeans), mean orthonasal intensity of four odors (ScentCheckPro), and perceived nasal blockage. Data were plotted over 28 days, creating panel plots for the eight cases and controls. Controls exhibited stable ratings over time. By contrast, COVID-19 cases showed sharp deviations over time. No single pattern of taste loss or recovery was apparent, implying different taste qualities might recover at different rates. Oral burn was transiently reduced for some before recovering quickly, suggesting acute loss may be missed in data collected after acute illness ends. Changes in odor intensity or odor identification were not explained by nasal blockage. Collectively, intensive daily testing shows orthonasal smell, oral chemesthesis and taste were each altered by acute COVID-19 infection, and this disruption was dyssynchronous for different modalities, with variable loss and recovery rates across modalities and individuals.

Combating Covid-19 using machine learning and deep learning: Applications, challenges, and future perspectives

COVID-19, a worldwide pandemic that has affected many people and thousands of individuals have died due to COVID-19, during the last two years. Due to the benefits of Artificial Intelligence (AI) in X-ray image interpretation, sound analysis, diagnosis, patient monitoring, and CT image identification, it has been further researched in the area of medical science during the period of COVID-19. This study has assessed the performance and investigated different machine learning (ML), deep learning (DL), and combinations of various ML, DL, and AI approaches that have been employed in recent studies with diverse data formats to combat the problems that have arisen due to the COVID-19 pandemic. Finally, this study shows the comparison among the stand-alone ML and DL-based research works regarding the COVID-19 issues with the combinations of ML, DL, and AI-based research works. After in-depth analysis and comparison, this study responds to the proposed research questions and presents the future research directions in this context. This review work will guide different research groups to develop viable applications based on ML, DL, and AI models, and will also guide healthcare institutes, researchers, and governments by showing them how these techniques can ease the process of tackling the COVID-19.

Associations of Country-Specific and Sociodemographic Factors With Self-Reported COVID-19-Related Symptoms: Multivariable Analysis of Data From the CoronaCheck Mobile Health Platform

BACKGROUND

The COVID-19 symptom-monitoring apps provide direct feedback to users about the suspected risk of infection with SARS-CoV-2 and advice on how to proceed to prevent the spread of the virus. We have developed the CoronaCheck mobile health (mHealth) platform, the first free app that provides easy access to valid information about the risk of infection with SARS-CoV-2 in English and German. Previous studies have suggested that the clinical characteristics of individuals infected with SARS-CoV-2 vary by age, gender, and viral variant; however, potential differences between countries have not been adequately studied.

OBJECTIVE

The aim of this study is to describe the characteristics of the users of the CoronaCheck mHealth platform and to determine country-specific and sociodemographic associations of COVID-19-related symptoms and previous contacts with individuals infected with COVID-19.

METHODS

Between April 8, 2020, and February 3, 2022, data on sociodemographic characteristics, symptoms, and reports of previous close contacts with individuals infected with COVID-19 were collected from CoronaCheck users in different countries. Multivariable logistic regression analyses were performed to examine whether self-reports of COVID-19-related symptoms and recent contact with a person infected with COVID-19 differed between countries (Germany, India, South Africa), gender identities, age groups, education, and calendar year.

RESULTS

Most app users (N=23,179) were from Germany (n=8116, 35.0%), India (n=6622, 28.6%), and South Africa (n=3705, 16.0%). Most data were collected in 2020 (n=19,723, 85.1%). In addition, 64% (n=14,842) of the users were male, 52.1% (n=12,077) were ≥30 years old, and 38.6% (n=8953) had an education level of more than 11 years of schooling. Headache, muscle pain, fever, loss of smell, loss of taste, and previous contacts with individuals infected with COVID-19 were reported more frequently by users in India (adjusted odds ratios [aORs] 1.3-8.3, 95% CI 1.2-9.2) and South Africa (aORs 1.1-2.6, 95% CI 1.0-3.0) than those in Germany. Cough, general weakness, sore throat, and shortness of breath were more frequently reported in India (aORs 1.3-2.6, 95% CI 1.2-2.9) compared to Germany. Gender-diverse users reported symptoms and contacts with confirmed COVID-19 cases more often compared to male users.

CONCLUSIONS

Patterns of self-reported COVID-19-related symptoms and awareness of a previous contact with individuals infected with COVID-19 seemed to differ between India, South Africa, and Germany, as well as by gender identity in these countries. Viral symptom-collecting apps, such as the CoronaCheck mHealth platform, may be promising tools for pandemics to support appropriate assessments. Future mHealth research on country-specific differences during a pandemic should aim to recruit representative samples.

A novel scoring system for early assessment of the risk of the COVID-19-associated mortality in hospitalized patients: COVID-19 BURDEN

BACKGROUND

Corona Virus Disease 2019 (COVID-19) presentations range from those similar to the common flu to severe pneumonia resulting in hospitalization with significant morbidity and/or mortality. In this study, we made an attempt to develop a predictive scoring model to improve the early detection of high risk COVID-19 patients by analyzing the clinical features and laboratory data available on admission.

METHODS

We retrospectively included 480 consecutive adult patients, aged 21-95, who were admitted to Faghihi Teaching Hospital. Clinical and laboratory features were collected from the medical records and analyzed using multiple logistic regression analysis. The final data analysis was utilized to develop a simple scoring model for the early prediction of mortality in COVID-19 patients. The score given to each associated factor was based on the coefficients of the regression analyses.

RESULTS

A novel mortality risk score (COVID-19 BURDEN) was derived, incorporating risk factors identified in this cohort. CRP (> 73.1 mg/L), O2 saturation variation (greater than 90%, 84-90%, and less than 84%), increased PT (> 16.2 s), diastolic blood pressure (≤ 75 mmHg), BUN (> 23 mg/dL), and raised LDH (> 731 U/L) were the features constituting the scoring system. The patients are triaged to the groups of low- (score < 4) and high-risk (score ≥ 4) groups. The area under the curve, sensitivity, and specificity for predicting mortality in patients with a score of ≥ 4 were 0.831, 78.12%, and 70.95%, respectively.

CONCLUSIONS

Using this scoring system in COVID-19 patients, the patients with a higher risk of mortality can be identified which will help to reduce hospital care costs and improve its quality and outcome.

Taste loss as a distinct symptom of COVID-19: a systematic review and meta-analysis

Chemosensory scientists have been skeptical that reports of COVID-19 taste loss are genuine, in part because before COVID-19 taste loss was rare and often confused with smell loss. Therefore, to establish the predicted prevalence rate of taste loss in COVID-19 patients, we conducted a systematic review and meta-analysis of 376 papers published in 2020-2021, with 235 meeting all inclusion criteria. Drawing on previous studies and guided by early meta-analyses, we explored how methodological differences (direct vs. self-report measures) may affect these estimates. We hypothesized that direct measures of taste are at least as sensitive as those obtained by self-report and that the preponderance of evidence confirms taste loss is a symptom of COVID-19. The meta-analysis showed that, among 138,015 COVID-19-positive patients, 36.62% reported taste dysfunction (95% confidence interval: 33.02%-40.39%), and the prevalence estimates were slightly but not significantly higher from studies using direct (n = 15) versus self-report (n = 220) methodologies (Q = 1.73, df = 1, P = 0.1889). Generally, males reported lower rates of taste loss than did females, and taste loss was highest among middle-aged adults. Thus, taste loss is likely a bona fide symptom of COVID-19, meriting further research into the most appropriate direct methods to measure it and its underlying mechanisms.

Compression-Complexity Measures for Analysis and Classification of Coronaviruses

Finding a vaccine or specific antiviral treatment for a global pandemic of virus diseases (such as the ongoing COVID-19) requires rapid analysis, annotation and evaluation of metagenomic libraries to enable a quick and efficient screening of nucleotide sequences. Traditional sequence alignment methods are not suitable and there is a need for fast alignment-free techniques for sequence analysis. Information theory and data compression algorithms provide a rich set of mathematical and computational tools to capture essential patterns in biological sequences. In this study, we investigate the use of compression-complexity (Effort-to-Compress or ETC and Lempel-Ziv or LZ complexity) based distance measures for analyzing genomic sequences. The proposed distance measure is used to successfully reproduce the phylogenetic trees for a mammalian dataset consisting of eight species clusters, a set of coronaviruses belonging to group I, group II, group III, and SARS-CoV-1 coronaviruses, and a set of coronaviruses causing COVID-19 (SARS-CoV-2), and those not causing COVID-19. Having demonstrated the usefulness of these compression complexity measures, we employ them for the automatic classification of COVID-19-causing genome sequences using machine learning techniques. Two flavors of SVM (linear and quadratic) along with linear discriminant and fine K Nearest Neighbors classifer are used for classification. Using a data set comprising 1001 coronavirus sequences (causing COVID-19 and those not causing COVID-19), a classification accuracy of 98% is achieved with a sensitivity of 95% and a specificity of 99.8%. This work could be extended further to enable medical practitioners to automatically identify and characterize coronavirus strains and their rapidly growing mutants in a fast and efficient fashion.

Post-COVID conditions and healthcare utilization among adults with and without disabilities-2021 Porter Novelli FallStyles survey

BACKGROUND

Adults with disabilities are at increased risk for SARS-CoV-2 infection and severe disease; whether adults with disabilities are at an increased risk for ongoing symptoms after acute SARS-CoV-2 infection is unknown.

OBJECTIVES

To estimate the frequency and duration of long-term symptoms (>4 weeks) and health care utilization among adults with and without disabilities who self-report positive or negative SARS-CoV-2 test results.

METHODS

Data from a nationwide survey of 4510 U.S. adults administered from September 24, 2021-October 7, 2021, were analyzed for 3251 (79%) participants who self-reported disability status, symptom(s), and SARS-CoV-2 test results (a positive test or only negative tests). Multivariable models were used to estimate the odds of having ≥1 COVID-19-like symptom(s) lasting >4 weeks by test result and disability status, weighted and adjusted for socio-demographics.

RESULTS

Respondents who tested positive for SARS-CoV-2 had higher odds of reporting ≥1 long-term symptom (with disability: aOR = 4.50 [95% CI: 2.37, 8.54] and without disability: aOR = 9.88 [95% CI: 7.13, 13.71]) compared to respondents testing negative. Among respondents who tested positive, those with disabilities were not significantly more likely to experience long-term symptoms compared to respondents without disabilities (aOR = 1.65 [95% CI: 0.78, 3.50]). Health care utilization for reported symptoms was higher among respondents with disabilities who tested positive (40%) than among respondents without disabilities who tested positive (18%).

CONCLUSIONS

Ongoing symptoms among adults with and without disabilities who also test positive for SARS-CoV-2 are common; however, the frequency of health care utilization for ongoing symptoms is two-fold among adults with disabilities.

Construction and validation of a COVID-19 pandemic trend forecast model based on Google Trends data for smell and taste loss

Aim

To explore the role of smell and taste changes in preventing and controlling the COVID-19 pandemic, we aimed to build a forecast model for trends in COVID-19 prediction based on Google Trends data for smell and taste loss.

Methods

Data on confirmed COVID-19 cases from 6 January 2020 to 26 December 2021 were collected from the World Health Organization (WHO) website. The keywords "loss of smell" and "loss of taste" were used to search the Google Trends platform. We constructed a transfer function model for multivariate time-series analysis and to forecast confirmed cases.

Results

From 6 January 2020 to 28 November 2021, a total of 99 weeks of data were analyzed. When the delay period was set from 1 to 3 weeks, the input sequence (Google Trends of loss of smell and taste data) and response sequence (number of new confirmed COVID-19 cases per week) were significantly correlated (P < 0.01). The transfer function model showed that worldwide and in India, the absolute error of the model in predicting the number of newly diagnosed COVID-19 cases in the following 3 weeks ranged from 0.08 to 3.10 (maximum value 100; the same below). In the United States, the absolute error of forecasts for the following 3 weeks ranged from 9.19 to 16.99, and the forecast effect was relatively accurate. For global data, the results showed that when the last point of the response sequence was at the midpoint of the uptrend or downtrend (25 July 2021; 21 November 2021; 23 May 2021; and 12 September 2021), the absolute error of the model forecast value for the following 4 weeks ranged from 0.15 to 5.77. When the last point of the response sequence was at the extreme point (2 May 2021; 29 August 2021; 20 June 2021; and 17 October 2021), the model could accurately forecast the trend in the number of confirmed cases after the extreme points. Our developed model could successfully predict the development trends of COVID-19.

Conclusion

Google Trends for loss of smell and taste could be used to accurately forecast the development trend of COVID-19 cases 1-3 weeks in advance.

Predictive models for COVID-19 detection using routine blood tests and machine learning

The problem of accurate, fast, and inexpensive COVID-19 tests has been urgent till now. Standard COVID-19 tests need high-cost reagents and specialized laboratories with high safety requirements, are time-consuming. Data of routine blood tests as a base of SARS-CoV-2 invasion detection allows using the most practical medicine facilities. But blood tests give general information about a patient's state, which is not directly associated with COVID-19. COVID-19-specific features should be selected from the list of standard blood characteristics, and decision-making software based on appropriate clinical data should be created. This review describes the abilities to develop predictive models for COVID-19 detection using routine blood tests and machine learning.

Analysis of Prevalence and Predictive Factors of Long-Lasting Olfactory and Gustatory Dysfunction in COVID-19 Patients

Background: Although smell and taste disorders are highly prevalent symptoms of COVID-19 infection, the predictive factors leading to long-lasting chemosensory dysfunction are still poorly understood. Methods: 102 out of 421 (24.2%) mildly symptomatic COVID-19 patients completed a second questionnaire about the evolution of their symptoms one year after the infection using visual analog scales (VAS). A subgroup of 69 patients also underwent psychophysical evaluation of olfactory function through UPSIT. Results: The prevalence of chemosensory dysfunction decreased from 82.4% to 45.1% after 12 months, with 46.1% of patients reporting a complete recovery. Patients older than 40 years (OR = 0.20; 95% CI: [0.07, 0.56]) and with a duration of loss of smell longer than four weeks saw a lower odds ratio for recovery (OR = 0.27; 95% CI: [0.10, 0.76]). In addition, 28 patients (35.9%) reported suffering from parosmia, which was associated with moderate to severe taste dysfunction at the baseline (OR = 7.80; 95% CI: [1.70, 35.8]). Among the 69 subjects who underwent the UPSIT, 57 (82.6%) presented some degree of smell dysfunction, showing a moderate correlation with self-reported VAS (r = −0.36, p = 0.0027). Conclusion: A clinically relevant number of subjects reported persistent chemosensory dysfunction and parosmia one year after COVID-19 infection, with a moderate correlation with psychophysical olfactory tests.

Potential pitfalls in analysing a SARS-CoV-2 RT-PCR assay and how to standardise data interpretation

The emergence of SARS-CoV-2 in December 2019 lead to the rapid implementation of assays for virus detection, with real-time RT-PCR arguably considered the gold-standard. In our laboratory Altona RealStar SARS-Cov-2 RT-PCR kits are used with Applied Biosystems QuantStudio 7 Flex thermocyclers. Real-time PCR data interpretation is potentially complex and time-consuming, particularly for SARS-CoV-2, where the laboratory handles up to 2000 samples each day. To simplify this, an automated system that rapidly interprets the curves, developed by diagnostics.ai was introduced. QuantStudio software provides two methods for interpretation, relative threshold and baseline threshold. Many of our assays are analysed using relative threshold and directly exported into pcr.ai software, however, in some rare cases the QuantStudio software assigns positive results to ‘ambiguous’ curves, flagged by pcr.ai, requiring manual intervention. Due to the sample numbers processed and the proportionate increase in curves flagged by pcr.ai, the two methods were investigated. An audit was carried out to determine the frequency of these curves, involving 138 samples tested during November 2020, including 97 serial samples from 38 patients and it was determined that the relative threshold method produced unreliable results in many of these cases. In addition, we present a solution to simplify the interpretation and automate the process.

A Hybrid Feature Selection Approach to Screen a Novel Set of Blood Biomarkers for Early COVID-19 Mortality Prediction

The increase in coronavirus disease 2019 (COVID-19) infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has placed pressure on healthcare services worldwide. Therefore, it is crucial to identify critical factors for the assessment of the severity of COVID-19 infection and the optimization of an individual treatment strategy. In this regard, the present study leverages a dataset of blood samples from 485 COVID-19 individuals in the region of Wuhan, China to identify essential blood biomarkers that predict the mortality of COVID-19 individuals. For this purpose, a hybrid of filter, statistical, and heuristic-based feature selection approach was used to select the best subset of informative features. As a result, minimum redundancy maximum relevance (mRMR), a two-tailed unpaired t-test, and whale optimization algorithm (WOA) were eventually selected as the three most informative blood biomarkers: International normalized ratio (INR), platelet large cell ratio (P-LCR), and D-dimer. In addition, various machine learning (ML) algorithms (random forest (RF), support vector machine (SVM), extreme gradient boosting (EGB), naïve Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN)) were trained. The performance of the trained models was compared to determine the model that assist in predicting the mortality of COVID-19 individuals with higher accuracy, F1 score, and area under the curve (AUC) values. In this paper, the best performing RF-based model built using the three most informative blood parameters predicts the mortality of COVID-19 individuals with an accuracy of 0.96 ± 0.062, F1 score of 0.96 ± 0.099, and AUC value of 0.98 ± 0.024, respectively on the independent test data. Furthermore, the performance of our proposed RF-based model in terms of accuracy, F1 score, and AUC was significantly better than the known blood biomarkers-based ML models built using the Pre_Surv_COVID_19 data. Therefore, the present study provides a novel hybrid approach to screen the most informative blood biomarkers to develop an RF-based model, which accurately and reliably predicts in-hospital mortality of confirmed COVID-19 individuals, during surge periods. An application based on our proposed model was implemented and deployed at Heroku.

Prediction of SARS-CoV-2 infection with a Symptoms-Based model to aid public health decision making in Latin America and other low and middle income settings

•

Early non-pharmacological interventions are necessary limit the spread of COVID-19.

•

In low to middle-income countries, there are limited resources to face the pandemic.

•

Symptoms (i.e. anosmia) can be used to apply early strategies in suspicious cases.

•

Logistic regression provides interpretability in prediction analysis.

•

Machine learning analysis aids prediction because of its capacity of data synthesis.

Symptoms-based models for predicting SARS-CoV-2 infection may improve clinical decision-making and be an alternative to resource allocation in under-resourced settings. In this study we aimed to test a model based on symptoms to predict a positive test result for SARS-CoV-2 infection during the COVID-19 pandemic using logistic regression and a machine-learning approach, in Bogotá, Colombia. Participants from the CoVIDA project were included. A logistic regression using the model was chosen based on biological plausibility and the Akaike Information criterion. Also, we performed an analysis using machine learning with random forest, support vector machine, and extreme gradient boosting. The study included 58,577 participants with a positivity rate of 5.7%. The logistic regression showed that anosmia (aOR = 7.76, 95% CI [6.19, 9.73]), fever (aOR = 4.29, 95% CI [3.07, 6.02]), headache (aOR = 3.29, 95% CI [1.78, 6.07]), dry cough (aOR = 2.96, 95% CI [2.44, 3.58]), and fatigue (aOR = 1.93, 95% CI [1.57, 2.93]) were independently associated with SARS-CoV-2 infection. Our final model had an area under the curve of 0.73. The symptoms-based model correctly identified over 85% of participants. This model can be used to prioritize resource allocation related to COVID-19 diagnosis, to decide on early isolation, and contact-tracing strategies in individuals with a high probability of infection before receiving a confirmatory test result. This strategy has public health and clinical decision-making significance in low- and middle-income settings like Latin America.

COVID-19 Induced Taste Dysfunction and Recovery: Association with Smell Dysfunction and Oral Health Behaviour

Background and Objectives: Disruption to taste and smell are common symptoms of COVID-19 infection. The current literature overlooks taste symptoms and tends to focus on the sense of smell. Persisting cases (>28 days) of taste dysfunction are increasingly recognised as a major future healthcare challenge. This study focuses on the severity and recovery of COVID-19 induced taste loss and association with olfactory symptoms, lifestyle and oral health factors. Materials and Methods: This study was a cross-sectional survey comparing 182 rapid taste recovery participants (≤28 days) with 47 participants with prolonged taste recovery >28 days. Analyses of taste loss in association with smell loss, age, sex, illness severity, diet, BMI, vitamin-D supplementation, antidepressants, alcohol use, smoking, brushing frequency, flossing, missing teeth, appliances and number of dental restorations were conducted. Differences in the severity of the loss of sour, sweet, salt, bitter and umami tastes were explored. Results: Both the severity and the duration of taste and smell loss were closely correlated (p < 0.001). Salt taste was significantly less affected than all other taste qualities (p < 0.001). Persisting taste loss was associated with older age (mean ± 95% CI = 31.73 ± 1.23 years vs. 36.66 ± 3.59 years, p < 0.001) and reduced likelihood of using floss (odds ratio ± 95% CI = 2.22 (1.15−4.25), p = 0.047). Conclusions: Smell and taste loss in COVID-19 are closely related, although a minority of individuals can experience taste or smell dysfunction in the absence of the other. The taste of salt may be less severely affected than other taste qualities and future work exploring this finding objectively is indicated. The association of flossing with rapid taste recovery adds to the growing evidence of a link between good periodontal health and favourable COVID-19 outcomes.

Clinical prediction models for diagnosis of COVID-19 among adult patients: a validation and agreement study

BACKGROUND

Since the beginning of the pandemic, hospitals have been constantly overcrowded, with several observed waves of infected cases and hospitalisations. To avoid as much as possible this situation, efficient tools to facilitate the diagnosis of COVID-19 are needed.

OBJECTIVE

To evaluate and compare prediction models to diagnose COVID-19 identified in a systematic review published recently using performance indicators such as discrimination and calibration measures.

METHODS

A total of 1618 adult patients present at two Emergency Department triage centers and for whom qRT-PCR tests had been performed were included in this study. Six previously published models were reconstructed and assessed using diagnostic tests as sensitivity (Se) and negative predictive value (NPV), discrimination (Area Under the Roc Curve (AUROC)) and calibration measures. Agreement was also measured between them using Kappa's coefficient and IntraClass Correlation Coefficient (ICC). A sensitivity analysis has been conducted by waves of patients.

RESULTS

Among the 6 selected models, those based only on symptoms and/or risk exposure were found to be less efficient than those based on biological parameters and/or radiological examination with smallest AUROC values (< 0.80). However, all models showed good calibration and values above > 0.75 for Se and NPV but poor agreement (Kappa and ICC < 0.5) between them. The results of the first wave were similar to those of the second wave.

CONCLUSION

Although quite acceptable and similar results were found between all models, the importance of radiological examination was also emphasized, making it difficult to find an appropriate triage system to classify patients at risk for COVID-19.

Is There Less Alteration of Smell Sensation in Patients With Omicron SARS-CoV-2 Variant Infection?

The ongoing pandemic Coronavirus Disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a matter of global concern in terms of public health Within the symptoms secondary to SARS-CoV-2 infection, hyposmia and anosmia have emerged as characteristic symptoms during the onset of the pandemic. Although many researchers have investigated the etiopathogenesis of this phenomenon, the main cause is not clear. The appearance of the new variant of concern Omicron has meant a breakthrough in the chronology of this pandemic, presenting greater transmissibility and less severity, according to the first reports. We have been impressed by the decrease in anosmia reported with this new variant and in patients reinfected or who had received vaccination before becoming infected. Based on the literature published to date, this review proposes different hypotheses to explain this possible lesser affectation of smell. On the one hand, modifications in the SARS-CoV-2 spike protein could produce changes in cell tropism and interaction with proteins that promote virus uptake (ACE-2, TMPRSS2, and TMEM16F). These proteins can be found in the sustentacular cells and glandular cells of the olfactory epithelium. Second, due to the characteristics of the virus or previous immunity (infection or vaccination), there could be less systemic or local inflammation that would generate less cell damage in the olfactory epithelium and/or in the central nervous system.

The Accuracy of Machine Learning Approaches Using Non-image Data for the Prediction of COVID-19: A Meta-Analysis

Objective

COVID-19 is a novel, severely contagious disease with enormous negative impact on humanity as well as the world economy. An expeditious, feasible tool for detecting COVID-19 remains yet elusive. Recently, there has been a surge of interest in applying machine learning techniques to predict COVID-19 using non-image data. We have therefore undertaken a meta-analysis to quantify the diagnostic performance of machine learning models facilitating the prediction of COVID-19.

Materials and methods

A comprehensive electronic database search for the period between January 1st, 2021 and December 3rd, 2021 was undertaken in order to identify eligible studies relevant to this meta-analysis. Summary sensitivity, specificity, and the area under receiver operating characteristic curves were used to assess potential diagnostic accuracy. Risk of bias was assessed by means of a revised Quality Assessment of Diagnostic Studies.

Results

A total of 30 studies, including 34 models, met all of the inclusion criteria. Summary sensitivity, specificity, and area under receiver operating characteristic curves were 0.86, 0.86, and 0.91, respectively. The purpose of machine learning models, class imbalance, and feature selection are significant covariates useful in explaining the between-study heterogeneity, in terms of both sensitivity and specificity.

Conclusions

Our study findings show that non-image data can be used to predict COVID-19 with an acceptable performance. Further, class imbalance and feature selection are suggested to be incorporated whenever building models for the prediction of COVID-19, thus improving further diagnostic performance.

Taste loss as a distinct symptom of COVID-19: a systematic review and meta-analysis

Chemosensory scientists have been skeptical that reports of COVID-19 taste loss are genuine, in part because before COVID-19 taste loss was rare and often confused with smell loss. Therefore, to establish the predicted prevalence rate of taste loss in COVID-19 patients, we conducted a systematic review and meta-analysis of 376 papers published in 2020-2021, with 241 meeting all inclusion criteria. Drawing on previous studies and guided by early meta-analyses, we explored how methodological differences (direct vs. self-report measures) may affect these estimates. We hypothesized that direct measures of taste are at least as sensitive as those obtained by self-report and that the preponderance of evidence confirms taste loss is a symptom of COVID-19. The meta-analysis showed that, among 138,897 COVID-19-positive patients, 39.2% reported taste dysfunction (95% confidence interval: 35.34%-43.12%), and the prevalence estimates were slightly but not significantly higher from studies using direct (n = 18) versus self-report (n = 223) methodologies (Q = 0.57, df = 1, P = 0.45). Generally, males reported lower rates of taste loss than did females, and taste loss was highest among middle-aged adults. Thus, taste loss is likely a bona fide symptom of COVID-19, meriting further research into the most appropriate direct methods to measure it and its underlying mechanisms.

Prediction of diagnosis and prognosis of COVID-19 disease by blood gas parameters using decision trees machine learning model: a retrospective observational study

The coronavirus disease 2019 (COVID-19) epidemic went down in history as a pandemic caused by corona-viruses that emerged in 2019 and spread rapidly around the world. The different symptoms of COVID-19 made it difficult to understand which variables were more influential on the diagnosis, course and mortality of the disease. Machine learning models can accurately assess hidden patterns among risk factors by analyzing large-datasets to quickly predict diagnosis, prognosis and mortality of diseases. Because of this advantage, the use of machine learning models as decision support systems in health services is increasing. The aim of this study is to determine the diagnosis and prognosis of COVID-19 disease with blood-gas data using the Chi-squared Automatic Interaction Detector (CHAID) decision-tree-model, one of the machine learning methods, which is a subfield of artificial intelligence. This study was carried out on a total of 686 patients with COVID-19 (n = 343) and non-COVID-19 (n = 343) treated at Erzincan-Mengücek-Gazi-Training and Research-Hospital between April 1, 2020 and March 1, 2021. Arterial blood gas values of all patients were obtained from the hospital registry system. While the total-accuracyratio of the decision-tree-model was 65.0% in predicting the prognosis of the disease, it was 68.2% in the diagnosis of the disease. According to the results obtained, the low ionized-calcium value (< 1.10 mM) significantly predicted the need for intensive care of COVID-19 patients. At admission, low-carboxyhemoglobin (< 1.00%), high-pH (> 7.43), low-sodium (< 135.0 mM), hematocrit (< 40.0%), and methemoglobin (< 1.30%) values are important biomarkers in the diagnosis of COVID-19 and the results were promising. The findings in the study may aid in the early-diagnosis of the disease and the intensive-care treatment of patients who are severe. The study was approved by the Ministry of Health and Erzincan University Faculty of Medicine Clinical Research Ethics Committee.

Taste loss as a distinct symptom of COVID-19: A systematic review and meta-analysis

Chemosensory scientists have been skeptical that reports of COVID-19 taste loss are genuine, in part because before COVID-19, taste loss was rare and often confused with smell loss. Therefore, to establish the predicted prevalence rate of taste loss in COVID-19 patients, we conducted a systematic review and meta-analysis of 376 papers published in 2020-2021, with 241 meeting all inclusion criteria. Additionally, we explored how methodological differences (direct vs. self-report measures) may affect these estimates. We hypothesized that direct prevalence measures of taste loss would be the most valid because they avoid the taste/smell confusion of self-report. The meta-analysis showed that, among 138,897 COVID-19-positive patients, 39.2% reported taste dysfunction (95% CI: 35.34-43.12%), and the prevalence estimates were slightly but not significantly higher from studies using direct (n = 18) versus self-report (n = 223) methodologies (Q = 0.57, df = 1, p = 0.45). Generally, males reported lower rates of taste loss than did females and taste loss was highest in middle-aged groups. Thus, taste loss is a bona fide symptom COVID-19, meriting further research into the most appropriate direct methods to measure it and its underlying mechanisms.

An update comprehensive review on the status of COVID-19: vaccines, drugs, variants and neurological symptoms

Various recently reported mutant variants, candidate and urgently approved current vaccines against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), many current situations with severe neurological damage and symptoms as well as respiratory tract disorders have begun to be reported. In particular, drug, vaccine, and neutralizing monoclonal antibodies (mAbs) have been developed and are currently being evaluated in clinical trials. Here, we review lessons learned from the use of novel mutant variants of the COVID-19 virus, immunization, new drug solutions, and antibody therapies for infections. Next, we focus on the B 1.1.7, B 1.351, P.1, and B.1.617 lineages or variants of concern that have been reported worldwide, the new manifestations of neurological manifestations, the current therapeutic drug targets for its treatment, vaccine candidates and their efficacy, implantation of convalescent plasma, and neutralization of mAbs. We review specific clinical questions, including many emerging neurological effects and respiratory tract injuries, as well as new potential biomarkers, new studies in addition to known therapeutics, and chronic diseases of vaccines that have received immediate approval. To answer these questions, further understanding of the burden kinetics of COVID-19 and its correlation with neurological clinical outcomes, endogenous antibody responses to vaccines, pharmacokinetics of neutralizing mAbs, and action against emerging viral mutant variants is needed.

A systematic review of prediction models to diagnose COVID-19 in adults admitted to healthcare centers

BACKGROUND

The COVID-19 pandemic is putting significant pressure on the hospital system. To help clinicians in the rapid triage of patients at high risk of COVID-19 while waiting for RT-PCR results, different diagnostic prediction models have been developed. Our objective is to identify, compare, and evaluate performances of prediction models for the diagnosis of COVID-19 in adult patients in a health care setting.

METHODS

A search for relevant references has been conducted on the MEDLINE and Scopus databases. Rigorous eligibility criteria have been established (e.g., adult participants, suspicion of COVID-19, medical setting) and applied by two independent investigators to identify suitable studies at 2 different stages: (1) titles and abstracts screening and (2) full-texts screening. Risk of bias (RoB) has been assessed using the Prediction model study Risk of Bias Assessment Tool (PROBAST). Data synthesis has been presented according to a narrative report of findings.

RESULTS

Out of the 2334 references identified by the literature search, 13 articles have been included in our systematic review. The studies, carried out all over the world, were performed in 2020. The included articles proposed a model developed using different methods, namely, logistic regression, score, machine learning, XGBoost. All the included models performed well to discriminate adults at high risks of presenting COVID-19 (all area under the ROC curve (AUROC) > 0.500). The best AUROC was observed for the model of Kurstjens et al (AUROC = 0.940 (0.910-0.960), which was also the model that achieved the highest sensitivity (98%). RoB was evaluated as low in general.

CONCLUSION

Thirteen models have been developed since the start of the pandemic in order to diagnose COVID-19 in suspected patients from health care centers. All these models are effective, to varying degrees, in identifying whether patients were at high risk of having COVID-19.

Cross sectional study of the clinical characteristics of French primary care patients with COVID-19

The early identification of patients suffering from SARS-CoV-2 infection in primary care is of outmost importance in the current pandemic. The objective of this study was to describe the clinical characteristics of primary care patients who tested positive for SARS-CoV-2. We conducted a cross-sectional study between March 24 and May 7, 2020, involving consecutive patients undergoing RT-PCR testing in two community-based laboratories in Lyon (France) for a suspicion of COVID-19. We examined the association between symptoms and a positive test using univariable and multivariable logistic regression, adjusted for clustering within laboratories, and calculated the diagnostic performance of these symptoms. Of the 1561 patients tested, 1543 patients (99%) agreed to participate. Among them, 253 were positive for SARS-CoV-2 (16%). The three most frequently reported 'ear-nose-throat' and non-'ear-nose-throat' symptoms in patients who tested positive were dry throat (42%), loss of smell (36%) and loss of taste (31%), respectively fever (58%), cough (52%) and headache (45%). In multivariable analyses, loss of taste (OR 3.8 [95% CI 3.3-4.4], p-value < 0.001), loss of smell (OR 3.0 [95% CI 1.9-4.8], p < 0.001), muscle pain (OR 1.6 [95% CI 1.2-2.0], p = 0.001) and dry nose (OR 1.3 [95% CI 1.1-1.6], p = 0.01) were significantly associated with a positive result. In contrast, sore throat (OR 0.6 [95% CI 0.4-0.8], p = 0.003), stuffy nose (OR 0.6 [95% CI 0.6-0.7], p < 0.001), diarrhea (OR 0.6 [95% CI 0.5-0.6], p < 0.001) and dyspnea (OR 0.5 [95% CI 0.3-0.7], p < 0.001) were inversely associated with a positive test. The combination of loss of taste or smell had the highest diagnostic performance (OR 6.7 [95% CI 5.9-7.5], sensitivity 44.7% [95% CI 38.4-51.0], specificity 90.8% [95% CI 89.1-92.3]). No other combination of symptoms had a higher performance. Our data could contribute to the triage and early identification of new clusters of cases.

Performance characteristics of five SARS-CoV-2 serological assays: Clinical utility in health-care workers

STUDY OBJECTIVE

SARS-CoV-2, which causes coronavirus disease (COVID-19), continues to cause significant morbidity and mortality. The diagnosis of acute infection relies on reverse transcription-polymerase chain reaction (RT-PCR)-based viral detection. The objective of this study was to evaluate the optimal serological testing strategy for anti-SARS-CoV-2 antibodies which provides an important indicator of prior infection and potential short-term immunity.

METHODS

The sensitivity and specificity of four different ELISA assays (Euroimmun IgG, Euroimmun NCP-IgG, Fortress and DIAsource) and one CLIA assay (Roche ELECSYS) were evaluated in 423 samples; 137 patients with confirmed RT-PCR COVID-19 infection (true positives), and 100 pre-pandemic samples collected prior to October 2019 (true negatives). A further 186 samples were collected from health-care staff and analysed by all five assays.

RESULTS

The Fortress ELISA assay demonstrated the highest sensitivity and specificity followed by the Roche ECLIA assay. The highest overall sensitivity came from the assays that measured total antibody (IgM-IgG combined) and the three assays that performed the best (Fortress, Roche, Euroimmun IgG) all have different antigens as their target proteins which suggests that antigen target does not affect assay performance. In mildly symptomatic participants with either a negative RT-PCR or no RT-PCR performed, 16.76% had detectable antibodies suggesting previous infection.

CONCLUSIONS

We recommend a combined testing strategy utilizing assays with different antigenic targets using the fully automated Roche ECLIA assay and confirming discordant samples with the Fortress Total Antibody ELISA assay. This study provides an important indicator of prior infection in symptomatic and asymptomatic individuals.

Clinical features and prognostic factors of intensive and non-intensive 1014 COVID-19 patients: an experience cohort from Alahsa, Saudi Arabia

BACKGROUND

COVID-19 is a worldwide pandemic and has placed significant demand for acute and critical care services on hospitals in many countries.

OBJECTIVES

To determine the predictors of severe COVID-19 disease requiring admission to an ICU by comparing patients who were ICU admitted to non-ICU groups.

METHODS

A cohort study was conducted for the laboratory-confirmed COVID-19 patients who were admitted to six Saudi Ministry of Health's hospitals in Alahsa, between March 1, 2020, and July 30, 2020, by reviewing patient's medical records retrospectively.

RESULTS

This cohort included 1014 patients with an overall mean age of 47.2 ± 19.3 years and 582 (57%) were males. A total of 205 (20%) of the hospitalized patients were admitted to the ICU. Hypertension, diabetes and obesity were the most common comorbidities in all study patients (27.2, 19.9, and 9%, respectively). The most prevalent symptoms were cough (47.7%), shortness of breath (35.7%) and fever (34.3%). Compared with non-ICU group, ICU patients had older age (p ≤ 0.0005) and comprised a higher proportion of the current smokers and had higher respiratory rates (p ≤ 0.0005), and more percentage of body temperatures in the range of 37.3-38.0 °C (p ≥ 0.0005); and had more comorbidities including diabetes (p ≤ 0.0005), hypertension (p ≥ 0.0005), obesity (p = 0.048), and sickle cell disease (p = 0.039). There were significant differences between the non-ICU and ICU groups for fever, shortness of breath, cough, fatigue, vomiting, dizziness; elevated white blood cells, neutrophils, alanine aminotransferase and alkaline aminotransferase, lactate dehydrogenase, and ferritin, and decreased hemoglobin; and proportion of abnormal bilateral chest CT images (p < 0.05). Significant differences were also found for multiple treatments (p < 0.05). ICU patients group had a much higher mortality rate than those with non-ICU admission (p ≤ 0.0005).

CONCLUSION

Identifying key clinical characteristics of COVID-19 that predict ICU admission and high mortality can be useful for frontline healthcare providers in making the right clinical decision under time-sensitive and resource-constricted environment.

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

The coronavirus disease 2019 (COVID-19), caused by the virus SARS-CoV-2, is an acute respiratory disease that has been classified as a pandemic by the World Health Organization (WHO). The sudden spike in the number of infections and high mortality rates have put immense pressure on the public healthcare systems. Hence, it is crucial to identify the key factors for mortality prediction to optimize patient treatment strategy. Different routine blood test results are widely available compared to other forms of data like X-rays, CT-scans, and ultrasounds for mortality prediction. This study proposes machine learning (ML) methods based on blood tests data to predict COVID-19 mortality risk. A powerful combination of five features: neutrophils, lymphocytes, lactate dehydrogenase (LDH), high-sensitivity C-reactive protein (hs-CRP), and age helps to predict mortality with 96% accuracy. Various ML models (neural networks, logistic regression, XGBoost, random forests, SVM, and decision trees) have been trained and performance compared to determine the model that achieves consistently high accuracy across the days that span the disease. The best performing method using XGBoost feature importance and neural network classification, predicts with an accuracy of 90% as early as 16 days before the outcome. Robust testing with three cases based on days to outcome confirms the strong predictive performance and practicality of the proposed model. A detailed analysis and identification of trends was performed using these key biomarkers to provide useful insights for intuitive application. This study provide solutions that would help accelerate the decision-making process in healthcare systems for focused medical treatments in an accurate, early, and reliable manner.

Epidemiological and Clinical Characteristics of COVID-19: A Retrospective Multi-Center Study in Pakistan

The emergence of a pathogen responsible for a mysterious respiratory disease was identified in China and later called a novel coronavirus. This disease was named COVID-19. The present study seeks to determine the epidemiological and clinical characteristics of COVID-19 in Pakistan. This report will exhibit a linkage between epidemiology and clinical aspects which in turn can be helpful to prevent the transmission of the virus in Pakistan. A retrospective, multiple center study was performed by collecting the data from patients' with their demographics, epidemiological status, history of co-morbid conditions, and clinical manifestations of the disease. The data was collected from 31 public-sector and 2 private hospitals across Pakistan by on-field healthcare workers. A Chi-square test was applied to assess the relationship between categorical data entries. A total of 194 medical records were examined. The median age of these patients was found to be 34 years. A total of 53.6% active cases were present including 41.2% males and 12.4% females till the end of the study. Adults accounted for most of the cases (94.3%) of COVID-19. Fever (86.60%), cough (85.05%), fatigue (36.60%), dyspnea (24.74%), and gastrointestinal discomfort (10.31%) were among the most frequently reported signs and symptoms by the patients. However, 4.12% of the total patient population remained asymptomatic. The median duration of hospital stay was found to be 14 (0-19) days. The earliest source of the spread of the virus may be linked to the foreigners traveling to Pakistan. Spread among men was more as compared to women. A few cases were found to be positive, due to the direct contact with pets or livestock. Hypertension (7.73%), diabetes (4.64%), cardiovascular conditions (2.58%) were the most common co-morbidities. The percentage mortality was 2.50% with the highest mortality among elders.