Discovering symptom patterns of COVID-19 patients using association rule mining

Association of the medication protocols and longitudinal change of COVID-19 symptoms: a hospital-based mixed-statistical methods study

The objective of this study was to identify the relationship between hospitalization treatment strategies leading to change in symptoms during 12-week follow-up among hospitalized patients during the COVID-19 outbreak. In this article, data from a prospective cohort study on COVID-19 patients admitted to Khorshid Hospital, Isfahan, Iran, from February 2020 to February 2021, were analyzed and reported. Patient characteristics, including socio-demographics, comorbidities, signs and symptoms, and treatments during hospitalization, were investigated. Also, to investigate the treatment effects adjusted by other confounding factors that lead to symptom change during follow-up, the binary classification trees, generalized linear mixed model, machine learning, and joint generalized estimating equation methods were applied. This research scrutinized the effects of various medications on COVID-19 patients in a prospective hospital-based cohort study, and found that heparin, methylprednisolone, ceftriaxone, and hydroxychloroquine were the most frequently prescribed medications. The results indicate that of patients under 65 years of age, 76% had a cough at the time of admission, while of patients with Cr levels of 1.1 or more, 80% had not lost weight at the time of admission. The results of fitted models showed that, during the follow-up, women are more likely to have shortness of breath (OR = 1.25; P-value: 0.039), fatigue (OR = 1.31; P-value: 0.013) and cough (OR = 1.29; P-value: 0.019) compared to men. Additionally, patients with symptoms of chest pain, fatigue and decreased appetite during admission are at a higher risk of experiencing fatigue during follow-up. Each day increase in the duration of ceftriaxone multiplies the odds of shortness of breath by 1.15 (P-value: 0.012). With each passing week, the odds of losing weight increase by 1.41 (P-value: 0.038), while the odds of shortness of breath and cough decrease by 0.84 (P-value: 0.005) and 0.56 (P-value: 0.000), respectively. In addition, each day increase in the duration of meropenem or methylprednisolone decreased the odds of weight loss at follow-up by 0.88 (P-value: 0.026) and 0.91 (P-value: 0.023), respectively (among those who took these medications). Identified prognostic factors can help clinicians and policymakers adapt management strategies for patients in any pandemic like COVID-19, which ultimately leads to better hospital decision-making and improved patient quality of life outcomes.

Exploiting the sequential nature of genomic data for improved analysis and identification

Genomic data is growing exponentially, posing new challenges for sequence analysis and classification, particularly for managing and understanding harmful new viruses that may later cause pandemics. Recent genome sequence classification models yield promising performance. However, the majority of them do not consider the sequential arrangement of nucleotides and amino acids, a critical aspect for uncovering their inherent structure and function. To overcome this, we introduce GenoAnaCla, a novel approach for analyzing and classifying genome sequences, based on sequential pattern mining (SPM). The proposed approach first constructs and preprocesses datasets comprising RNA virus genome sequences in three formats: nucleotide, coding region, and protein. Then, to capture sequential features for the analysis and classification of viruses, GenoAnaCla extracts frequent sequential patterns and rules in three forms and in codons. Eight classifiers are utilized, and their effectiveness is assessed by employing a variety of evaluation metrics. A performance comparison demonstrates that the suggested approach surpasses the current state-of-the-art genome sequence classification and detection techniques with a 3.18% performance increase in accuracy on average.

The Treatment with Xinfeng Capsule Can Reduce the Risk of Readmission for Patients with Rheumatoid arthritis:A Cohort Study of Approximately 10000 Individuals

Objective

The present study aimed to investigate the potential association between the treatment with Xinfeng Capsule (XFC) and the risk of readmission among patients with rheumatoid arthritis (RA).

Methods

Through a retrospective approach, data were collected from all hospitalized patients diagnosed with RA at the First Affiliated Hospital of Anhui University of Chinese Medicine between 2013 and 2021. To mitigate selection bias and confounding factors, patients were stratified into an XFC group and a Non-XFC (Non-XFC) group based on their treatment status using propensity score matching with a 1:2 ratio. Variables such as age, gender, and baseline medications were adjusted. Subsequently, the Cox proportional hazards model was employed to calculate the hazard ratio (HR) for readmission among RA patients, while Kaplan-Meier curves were utilized to depict the incidence of readmission.

Results

A total of 9987 RA patients were included in this study. Following rigorous inclusion/exclusion criteria and propensity score matching, the XFC group comprised 2036 patients, while the Non-XFC group contained 4072 patients. The Cox proportional hazards model analysis revealed that XFC acted as a protective factor, significantly reducing the risk of readmission among RA patients. Further examination of Kaplan-Meier curves demonstrated that XFC use not only effectively lowered the frequency of readmissions but also exhibited a more pronounced effect in diminishing the risk of readmission with extended usage durations (beyond 12 months). Additionally, association rule analysis underscored the strong link between XFC and freedom from readmission, as well as the robust correlation between XFC usage and significant improvements in multiple laboratory indicators, including C3, C4, CRP, ESR, and others.

Conclusion

This study underscores a robust and long-term association between XFC usage and lower readmission rates among RA patients. As a protective factor against readmission risk in these patients, the clinical value of XFC merits further promotion and investigation.

Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort.

METHODS

Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.

RESULTS

Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.

CONCLUSION

The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.

Evolutionary Insights from Association Rule Mining of Co-Occurring Mutations in Influenza Hemagglutinin and Neuraminidase

Seasonal influenza viruses continuously evolve via antigenic drift. This leads to recurring epidemics, globally significant mortality rates, and the need for annually updated vaccines. Co-occurring mutations in hemagglutinin (HA) and neuraminidase (NA) are suggested to have synergistic interactions where mutations can increase the chances of immune escape and viral fitness. Association rule mining was used to identify temporal relationships of co-occurring HA-NA mutations of influenza virus A/H3N2 and its role in antigenic evolution. A total of 64 clusters were found. These included well-known mutations responsible for antigenic drift, as well as previously undiscovered groups. A majority (41/64) were associated with known antigenic sites, and 38/64 involved mutations across both HA and NA. The emergence and disappearance of N-glycosylation sites in the pattern of N-X-[S/T] were also identified, which are crucial post-translational processes to maintain protein stability and functional balance (e.g., emergence of NA:339ASP and disappearance of HA:187ASP). Our study offers an alternative approach to the existing mutual-information and phylogenetic methods used to identify co-occurring mutations, enabling faster processing of large amounts of data. Our approach can facilitate the prediction of critical mutations given their occurrence in a previous season, facilitating vaccine development for the next flu season and leading to better preparation for future pandemics.

Using Association Rules to Obtain Sets of Prevalent Symptoms throughout the COVID-19 Pandemic: An Analysis of Similarities between Cases of COVID-19 and Unspecified SARS in São Paulo-Brazil

The efficient recognition of symptoms in viral infections holds promise for swift and precise diagnosis, thus mitigating health implications and the potential recurrence of infections. COVID-19 presents unique challenges due to various factors influencing diagnosis, especially regarding disease symptoms that closely resemble those of other viral diseases, including other strains of SARS, thus impacting the identification of useful and meaningful symptom patterns as they emerge in infections. Therefore, this study proposes an association rule mining approach, utilising the Apriori algorithm to analyse the similarities between individuals with confirmed SARS-CoV-2 diagnosis and those with unspecified SARS diagnosis. The objective is to investigate, through symptom rules, the presence of COVID-19 patterns among individuals initially not diagnosed with the disease. Experiments were conducted using cases from Brazilian SARS datasets for São Paulo State. Initially, reporting percentage similarities of symptoms in both groups were analysed. Subsequently, the top ten rules from each group were compared. Finally, a search for the top five most frequently occurring positive rules among the unspecified ones, and vice versa, was conducted to identify identical rules, with a particular focus on the presence of positive rules among the rules of individuals initially diagnosed with unspecified SARS.

Identifying diseases symptoms and general rules using supervised and unsupervised machine learning

The symptoms of diseases can vary among individuals and may remain undetected in the early stages. Detecting these symptoms is crucial in the initial stage to effectively manage and treat cases of varying severity. Machine learning has made major advances in recent years, proving its effectiveness in various healthcare applications. This study aims to identify patterns of symptoms and general rules regarding symptoms among patients using supervised and unsupervised machine learning. The integration of a rule-based machine learning technique and classification methods is utilized to extend a prediction model. This study analyzes patient data that was available online through the Kaggle repository. After preprocessing the data and exploring descriptive statistics, the Apriori algorithm was applied to identify frequent symptoms and patterns in the discovered rules. Additionally, the study applied several machine learning models for predicting diseases, including stepwise regression, support vector machine, bootstrap forest, boosted trees, and neural-boosted methods. Several predictive machine learning models were applied to the dataset to predict diseases. It was discovered that the stepwise method for fitting outperformed all competitors in this study, as determined through cross-validation conducted for each model based on established criteria. Moreover, numerous significant decision rules were extracted in the study, which can streamline clinical applications without the need for additional expertise. These rules enable the prediction of relationships between symptoms and diseases, as well as between different diseases. Therefore, the results obtained in this study have the potential to improve the performance of prediction models. We can discover diseases symptoms and general rules using supervised and unsupervised machine learning for the dataset. Overall, the proposed algorithm can support not only healthcare professionals but also patients who face cost and time constraints in diagnosing and treating these diseases.

The Discovery of Oral Cancer Prognostic Factor Ranking Using Association Rule Mining

OBJECTIVE

 A 5-year survival rate is a predictor for the assessment of oral cancer prognosis. The purpose of this study is to analyze oral cancer data to discover and rank the prognostic factors associated with oral cancer 5-year survival using the association rule mining (ARM) technique.

MATERIALS AND METHODS

 This study is a retrospective analysis of 897 oral cancer patients from a regional cancer center between 2011 and 2017. The 5-year survival rate was assessed. The multivariable Cox proportional hazards analysis was performed to determine prognostic factors. ARM was applied to clinicopathologic and treatment modalities data to identify and rank the prognostic factors associated with oral cancer 5-year survival.

RESULTS

 The 5-year overall survival rate was 35.1%. Multivariable Cox proportional hazards analysis showed that tumor (T) stage, lymph node metastasis, surgical margin, extranodal extension, recurrence, and distant metastasis of tumor were significantly associated with overall survival rate (p < 0.05). The top associated death within 5 years rule was positive extranodal extension, followed by positive perineural and lymphovascular invasion, with confidence levels of 0.808, 0.808, and 0.804, respectively.

CONCLUSION

 This study has shown that extranodal extension, and perineural and lymphovascular invasion were the top ranking and major deadly prognostic factors affecting the 5-year survival of oral cancer.

Temporal Association Rule Mining: Race-Based Patterns of Treatment-Adverse Events in Breast Cancer Patients Using SEER-Medicare Dataset

PURPOSE

Disparities in the screening, treatment, and survival of African American (AA) patients with breast cancer extend to adverse events experienced with systemic therapy. However, data are limited and difficult to obtain. We addressed this challenge by applying temporal association rule (TAR) mining using the SEER-Medicare dataset for differences in the association of specific adverse events (AEs) and treatments (TRs) for breast cancer between AA and White women. We considered two categories of cancer care providers and settings: practitioners providing care in the outpatient units of hospitals and institutions and private practitioners providing care in their offices.

PATIENTS AN METHODS

We considered women enrolled in the Medicare fee-for-service option at age 65 who qualified by age and not disability, who were diagnosed with breast cancer with attributed patient factors of age and race, marital status, comorbidities, prior malignancies, prior therapy, disease factors of stage, grade, and ER/PR and Her2 status and laterality. We included 141 HCPCS drug J codes for chemotherapy, biotherapy, and hormone therapy drugs, which we consolidated into 46 mechanistic categories and generated AE data. We consolidated AEs from ICD9 codes into 18 categories associated with breast cancer therapy. We applied TAR mining to determine associations between the 46 TR and 18 AE categories in the context of the patient categories outlined. We applied the spark.mllib implementation of the FPGrowth algorithm, a parallel version called PFP. We considered differences of at least one unit of lift as significant between groups. The model's results demonstrated a high overlap between the model's identified TR-AEs associated set and the actual set.

RESULTS

Our results demonstrate that specific TR/AE associations are highly dependent on race, stage, and venue of care administration.

CONCLUSIONS

Our data demonstrate the usefulness of this approach in identifying differences in the associations between TRs and AEs in different populations and serve as a reference for predicting the likelihood of AEs in different patient populations treated for breast cancer. Our novel approach using unsupervised learning enables the discovery of association rules while paying special attention to temporal information, resulting in greater predictive and descriptive power as a patient's health and life status change over time.

Conceptually Funded Usability Evaluation of an Application for Leveraging Descriptive Data Analysis Models for Cardiovascular Research

The focus of this study, and the subject of this article, resides in the conceptually funded usability evaluation of an application of descriptive models to a specific dataset obtained from the East Slovak Institute of Heart and Vascular Diseases targeting cardiovascular patients. Delving into the current state-of-the-art practices, we examine the extent of cardiovascular diseases, descriptive data analysis models, and their practical applications. Most importantly, our inquiry focuses on exploration of usability, encompassing its application and evaluation methodologies, including Van Welie's layered model of usability and its inherent advantages and limitations. The primary objective of our research was to conceptualize, develop, and validate the usability of an application tailored to supporting cardiologists' research through descriptive modeling. Using the R programming language, we engineered a Shiny dashboard application named DESSFOCA (Decision Support System For Cardiologists) that is structured around three core functionalities: discovering association rules, applying clustering methods, and identifying association rules within predefined clusters. To assess the usability of DESSFOCA, we employed the System Usability Scale (SUS) and conducted a comprehensive evaluation. Additionally, we proposed an extension to Van Welie's layered model of usability, incorporating several crucial aspects deemed essential. Subsequently, we rigorously evaluated the proposed extension within the DESSFOCA application with respect to the extended usability model, drawing insightful conclusions from our findings.

Individualized Prediction of SARS-CoV-2 Infection in Mexico City Municipality during the First Six Waves of the Pandemic

After COVID-19 emerged, alternative methods to laboratory tests for the individualized prediction of SARS-CoV-2 were developed in several world regions. The objective of this investigation was to develop models for the individualized prediction of SARS-CoV-2 infection in a large municipality of Mexico. The study included data from 36,949 patients with suspected SARS-CoV-2 infection who received a diagnostic tested at health centers of the Alvaro Obregon Jurisdiction in Mexico City registered in the Epidemiological Surveillance System for Viral Respiratory Diseases (SISVER-SINAVE). The variables that were different between a positive test and a negative test were used to generate multivariate binary logistic regression models. There was a large variation in the prediction variables for the models of different pandemic waves. The models obtained an overall accuracy of 73% (63-82%), sensitivity of 52% (18-71%), and specificity of 84% (71-92%). In conclusion, the individualized prediction models of a positive COVID-19 test based on SISVER-SINAVE data had good performance. The large variation in the prediction variables for the models of different pandemic waves highlights the continuous change in the factors that influence the spread of COVID-19. These prediction models could be applied in early case identification strategies, especially in vulnerable populations.

Lichen - air quality association rule mining for urban environments in the tropics

There are significant gaps in air quality monitoring across many low- and middle-income countries, which can be filled by bioindicators like lichen. This study examined the links between lichen and air quality across urban environments in Nigeria. Lichen surveys and air quality monitoring were carried out across four major cities focusing on NO2, SO2, PM2.5, and PM10. Association rule mining was used to identify robust rules defining the association between lichen and air quality categories. For the maximal frequent set with Lichen in the antecedent, 9 and 5 rules were identified by A priori and Eclat, respectively. These indicated that three genera: Diorygma, Pyxine, and Physcia are the most commonly associated lichen with poor air quality particularly NO2 and SO2. This showed that these lichens are viable indicators of long-term air quality due to their consistent occurrence across the rules from different algorithms.

Association between traditional Chinese Medicine and osteoarthritis outcome: A 5-year matched cohort study

Objective

The aim of this study was to investigate the relationship between Traditional Chinese medicine (TCM) and pain reduction, hospital readmission, and joint replacement in patients with osteoarthritis (OA). Chinese herbal medicine (CHM) prescription patterns were further analyzed to confirm the association with prognosis and quality of life in OA patients.

Methods

We retrospectively followed 3,850 hospitalized patients with osteoarthritis between January 2018 and December 2022 using the hospital's HIS system. Propensity score matching (PSM) was used for data matching. Cox's proportional risk model was used to assess the impact of various factors on the outcomes of patients with OA, including pain worsening, readmission, and joint replacement. The Kaplan-Meier survival curve was applied to determine the impact of TCM intervention time on patient outcomes. Data mining methods including association rules, cluster analysis, and random walks have been used to assess the efficacy of TCM.

Results

The utilization rate of TCM in OA patients was 67.01% (2,511/3,747). After PSM matching, 1,228 TCM non-user patients and 1,228 TCM user patients were eventually included. The outcomes of pain worsening, re-admission rate, and joint replacement rate of the TCM non-user group were observably higher than those of the TCM user group with OA (p < 0.05). Based on the Cox proportional risk model, TCM is an independent protective factor. Compared with non-TCM users, TCM users had 58.4% lower rates of pain, 51.1% lower rates of re-admission, and 42% lower rates of joint replacement. In addition, patients in the high-exposure subgroup (TCM＞24 months) had a markedly lower risk of outcome events than those in the low-exposure subgroup (TCM ≤24 months). Data mining methods have shown that TCM therapy can significantly improve immune-inflammatory indices, VAS scores, and SF-36 scale scores in OA patients.

Conclusion

s TCM acts as a protective factor to improve the prognosis of patients with OA, and the benefits of long-term use of herbal medicines are even greater.

Synergistic horizontal transfer of antibiotic resistance genes and transposons in the infant gut microbial genome

Transposons, plasmids, bacteriophages, and other mobile genetic elements facilitate horizontal gene transfer in the gut microbiota, allowing some pathogenic bacteria to acquire antibiotic resistance genes (ARGs). Currently, the relationship between specific ARGs and specific transposons in the comprehensive infant gut microbiome has not been elucidated. In this study, ARGs and transposons were annotated from the Unified Human Gastrointestinal Genome (UHGG) and the Early-Life Gut Genomes (ELGG). Association rules mining was used to explore the association between specific ARGs and specific transposons in UHGG, and the robustness of the association rules was validated using the external database in ELGG. Our results suggested that ARGs and transposons were more likely to be relevant in infant gut microbiota compared to adult gut microbiota, and nine robust association rules were identified, among which Klebsiella pneumoniae, Enterobacter hormaechei_A, and Escherichia coli_D played important roles in this association phenomenon. The emphasis of this study is to investigate the synergistic transfer of specific ARGs and specific transposons in the infant gut microbiota, which can contribute to the study of microbial pathogenesis and the ARG dissemination dynamics.IMPORTANCEThe transfer of transposons carrying antibiotic resistance genes (ARGs) among microorganisms accelerates antibiotic resistance dissemination among infant gut microbiota. Nonetheless, it is unclear what the relationship between specific ARGs and specific transposons within the infant gut microbiota. K. pneumoniae, E. hormaechei_A, and E. coli_D were identified as key players in the nine robust association rules we discovered. Meanwhile, we found that infant gut microorganisms were more susceptible to horizontal gene transfer events about specific ARGs and specific transposons than adult gut microorganisms. These discoveries could enhance the understanding of microbial pathogenesis and the ARG dissemination dynamics within the infant gut microbiota.

Roses Have Thorns: Understanding the Downside of Oncological Care Delivery Through Visual Analytics and Sequential Rule Mining

Personalized head and neck cancer therapeutics have greatly improved survival rates for patients, but are often leading to understudied long-lasting symptoms which affect quality of life. Sequential rule mining (SRM) is a promising unsupervised machine learning method for predicting longitudinal patterns in temporal data which, however, can output many repetitive patterns that are difficult to interpret without the assistance of visual analytics. We present a data-driven, human-machine analysis visual system developed in collaboration with SRM model builders in cancer symptom research, which facilitates mechanistic knowledge discovery in large scale, multivariate cohort symptom data. Our system supports multivariate predictive modeling of post-treatment symptoms based on during-treatment symptoms. It supports this goal through an SRM, clustering, and aggregation back end, and a custom front end to help develop and tune the predictive models. The system also explains the resulting predictions in the context of therapeutic decisions typical in personalized care delivery. We evaluate the resulting models and system with an interdisciplinary group of modelers and head and neck oncology researchers. The results demonstrate that our system effectively supports clinical and symptom research.

Drug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study

BACKGROUND

Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, "drug repurposing" (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies.

OBJECTIVE

The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer.

METHODS

We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer.

RESULTS

We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024.

CONCLUSIONS

This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/48925.

Machine learning algorithms' application to predict childhood vaccination among children aged 12-23 months in Ethiopia: Evidence 2016 Ethiopian Demographic and Health Survey dataset

INTRODUCTION

Childhood vaccination is a cost-effective public health intervention to reduce child mortality and morbidity. But, vaccination coverage remains low, and previous similar studies have not focused on machine learning algorithms to predict childhood vaccination. Therefore, knowledge extraction, association rule formulation, and discovering insights from hidden patterns in vaccination data are limited. Therefore, this study aimed to predict childhood vaccination among children aged 12-23 months using the best machine learning algorithm.

METHODS

A cross-sectional study design with a two-stage sampling technique was used. A total of 1617 samples of living children aged 12-23 months were used from the 2016 Ethiopian Demographic and Health Survey dataset. The data was pre-processed, and 70% and 30% of the observations were used for training, and evaluating the model, respectively. Eight machine learning algorithms were included for consideration of model building and comparison. All the included algorithms were evaluated using confusion matrix elements. The synthetic minority oversampling technique was used for imbalanced data management. Informational gain value was used to select important attributes to predict childhood vaccination. The If/ then logical association was used to generate rules based on relationships among attributes, and Weka version 3.8.6 software was used to perform all the prediction analyses.

RESULTS

PART was the first best machine learning algorithm to predict childhood vaccination with 95.53% accuracy. J48, multilayer perceptron, and random forest models were the consecutively best machine learning algorithms to predict childhood vaccination with 89.24%, 87.20%, and 82.37% accuracy, respectively. ANC visits, institutional delivery, health facility visits, higher education, and being rich were the top five attributes to predict childhood vaccination. A total of seven rules were generated that could jointly determine the magnitude of childhood vaccination. Of these, if wealth status = 3 (Rich), adequate ANC visits = 1 (yes), and residency = 2 (Urban), then the probability of childhood vaccination would be 86.73%.

CONCLUSIONS

The PART, J48, multilayer perceptron, and random forest algorithms were important algorithms for predicting childhood vaccination. The findings would provide insight into childhood vaccination and serve as a framework for further studies. Strengthening mothers' ANC visits, institutional delivery, improving maternal education, and creating income opportunities for mothers could be important interventions to enhance childhood vaccination.

Oral manifestations in patients with coronavirus disease 2019 (COVID-19) identified using text mining: an observational study

Text mining enables search, extraction, categorisation and information visualisation. This study aimed to identify oral manifestations in patients with COVID-19 using text mining to facilitate extracting relevant clinical information from a large set of publications. A list of publications from the open-access COVID-19 Open Research Dataset was downloaded using keywords related to oral health and dentistry. A total of 694,366 documents were retrieved. Filtering the articles using text mining yielded 1,554 oral health/dentistry papers. The list of articles was classified into five topics after applying a Latent Dirichlet Allocation (LDA) model. This classification was compared to the author's classification which yielded 17 categories. After a full-text review of articles in the category "Oral manifestations in patients with COVID-19", eight papers were selected to extract data. The most frequent oral manifestations were xerostomia (n = 405, 17.8%) and mouth pain or swelling (n = 289, 12.7%). These oral manifestations in patients with COVID-19 must be considered with other symptoms to diminish the risk of dentist-patient infection.

Discovering associations between radiological features and COVID-19 patients' deterioration

Background and Aims

Data mining methods are effective and well-known tools for developing predictive models and extracting useful information from various data of patients. The present study aimed to predict the severity of patients with COVID-19 by applying the rule mining method using characteristics of medical images.

Methods

This retrospective study has analyzed the radiological data from 104 COVID-19 hospitalized patients diagnosed with COVID-19 in a hospital in Iran. A data set containing 75 binary features was generated. Apriori method is utilized for association rule mining on this data set. Only rules with confidence equal to one were generated. The performance of rules is calculated by support, coverage, and lift indexes.

Results

Ten rules were extracted with only X-ray-related features on cases referred to ICU. The Support and Coverage index of all of these rules was 0.087, and the Lift index of them was 1.58. Thirteen rules were extracted from only CT scan-related features on cases referred to ICU. The CXR_Pleural effusion feature has appeared in all the rules. The CXR_Left upper zone feature appears in 9 rules out of 10. The Support and Coverage index of all rules was 0.15, and the Lift index of all rules was 1.63. the CT_Adjacent pleura thickening feature has appeared in all rules, and the CT_Right middle lobe appeared in 9 rules out of 13.

Conclusion

This study could reveal the application and efficacy of CXR and CT scan imaging modalities in predicting ICU admission to a major COVID-19 infection via data mining methods. The findings of this study could help data scientists, radiologists, and clinicians in the future development and implementation of these methods in similar conditions and timely and appropriately save patients from adverse disease outcomes.

A novel FCTF evaluation and prediction model for food efficacy based on association rule mining

Introduction

Food-components-target-function (FCTF) is an evaluation and prediction model based on association rule mining (ARM) and network interaction analysis, which is an innovative exploration of interdisciplinary integration in the food field.

Methods

Using the components as the basis, the targets and functions are comprehensively explored in various databases and platforms under the guidance of the ARM concept. The focused active components, key targets and preferred efficacy are then analyzed by different interaction calculations. The FCTF model is particularly suitable for preliminary studies of medicinal plants in remote and poor areas.

Results

The FCTF model of the local medicinal food Laoxianghuang focuses on the efficacy of digestive system cancers and neurological diseases, with key targets ACE, PTGS2, CYP2C19 and corresponding active components citronellal, trans-nerolidol, linalool, geraniol, α-terpineol, cadinene and α-pinene.

Discussion

Centuries of traditional experience point to the efficacy of Laoxianghuang in alleviating digestive disorders, and our established FCTF model of Laoxianghuang not only demonstrates this but also extends to its possible adjunctive efficacy in neurological diseases, which deserves later exploration. The FCTF model is based on the main line of components to target and efficacy and optimizes the research level from different dimensions and aspects of interaction analysis, hoping to make some contribution to the future development of the food discipline.

Vaccine effectiveness in symptom and viral load mitigation in COVID-19 breakthrough infections in South Korea

OBJECTIVES

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccine effectiveness in coronavirus disease (COVID-19) patients with breakthrough infections has not been established in South Korea. To address this, we assessed the impact of vaccination on symptom occurrence and viral load.

METHODS

We performed a retrospective cohort study of 9,030 COVID-19 patients enrolled between February and November 2021. The impact of vaccination on the incidence of symptoms and viral load as indicated by cycle threshold (Ct) values of RdRp and E genes was evaluated using relative risks (RRs) and 95% confidence intervals (95% CIs).

RESULTS

Compared with unvaccinated patients, fully vaccinated patients were associated with a reduced symptom onset of cough, sputum, and myalgia in COVID-19 patients (RR (95% CI) = 0.86 (0.75-0.99) for cough; RR (95% CI) = 0.74 (0.56-0.98) for sputum; RR (95% CI) = 0.65 (0.53-0.79) for myalgia, respectively). Additionally, lower risk of high viral load, Ct value of RdRp gene <15 or Ct value of E gene <15, was observed especially in fully vaccinated patients younger than 40 years ((RR (95% CI) = 0.69 (0.49-0.96) for RdRp gene; (RR (95% CI) = 0.71 (0.53-0.95) for E gene).

CONCLUSION

SARS-CoV-2 vaccination was associated with a reduced risk of COVID-19 symptoms as well as decreased viral load, especially in patients younger than 40 years.

Ontology is what makes data interesting: Interestingness framework for COVID-19 corpora

The COVID-19 pandemic has already shown to be a worldwide threat, demonstrating how susceptible humans may be. It has also inspired experts from a range of aspects and countries to find the potential solution to control the widespread. In line with this, our research proposes a novel framework for finding interesting facts from COVID-19 corpora using domain ontology. Since data mining with domain knowledge provides semantically rich facts, we use ontology in our proposed approaches. Most of the state-of-the-art methods rely on instance level or user intervention. These methods do not entirely exploit the richness of ontology. In this work, we demonstrate how to extract exciting rules from data at ontology’s schema and instance levels. Our experiments were carried out on two COVID-19 corpora that depict COVID-19 patients’ symptoms and drug information. The proposed framework outperformed the traditional methods by reducing the number of rules by 70% and generating semantic-rich rules that are more user-readable and quickly adopted by decision-makers. Furthermore, to support our claims, we compared the outcomes of the proposed framework with the most recent approach in the field. Also, statistically significant tests and domain expert evaluations are conducted to validate our framework.

Analysis of COVID-19 vaccine adverse event using language model and unsupervised machine learning

BACKGROUND

After the COVID-19 pandemic, the world has made efforts to recover from the chaotic situation. Vaccination is a way to help control infectious diseases, and many people have been vaccinated against COVID-19 by this point. However, an extremely small number of those who received the vaccine have experienced diverse side effects.

METHODS AND FINDINGS

In this study, we examined people who experienced adverse events with the COVID-19 vaccine by gender, age, vaccine manufacturer, and dose of vaccinations by using the Vaccine Adverse Event Reporting System datasets. Then we used a language model to vectorize symptom words and reduced their dimensionality. We also clustered symptoms by using unsupervised machine learning and analyzed the characteristics of each symptom cluster. Lastly, to discover any association rules among adverse events, we used a data mining approach. The frequency of adverse events was higher for women than men, for Moderna than for Pfizer or Janssen, and for the first dose than for the second dose. However, we found that characteristics of vaccine adverse events, including gender, vaccine manufacturer, age, and underlying diseases were different for each symptom cluster, and that fatal cases were significantly related to a particular cluster (associated with hypoxia). Also, as a result of the association analysis, the {chills ↔ pyrexia} and {vaccination site pruritus ↔ vaccination site erythema} rules had the highest support value of 0.087 and 0.046, respectively.

CONCLUSIONS

We aim to contribute accurate information on the adverse events of the COVID-19 vaccine to relieve public anxiety due to unconfirmed statements about vaccines.

Mining association rules between lichens and air quality to support urban air quality monitoring in Nigeria

Urban environments represent the most intense human-environment interaction. This interaction can result in negative outcomes like air pollution and its health implications. There is a significant data deficit in air quality monitoring across many developing nations, which prevents effective policies and measures from being taken to promote the accomplishment of sustainable development. Around the world, lichens have been used to track environmental changes due to their sensitivity to changes and concentration of atmospheric pollutants. This study investigated the relationships between lichen and air quality across some Nigerian cities. Lichen surveys were conducted in four cities. At various periods during the day, NO₂, SO₂, PM_2.5, and PM₁₀ levels were measured. Association rule mining was carried out to investigate the relationship between lichen found and air quality categories. Results showed that the most prevalent lichen Genera are Pyxine in Abuja and Kano, Diorygma in Lagos, and Dirinaria in Port Harcourt. Out of the 40 rules found from the rule mining, 17 are important (lift values ≥ 1.1), capturing six of the fourteen lichen genera identified in the field. The findings indicated that there are important relationships between lichens and air quality indices, suggesting that some lichen species in Nigeria may serve as indicators of long-term air quality. To develop a network of urban environmental quality bioindicators across Nigerian cities, surveying and transplanting are advised. The use of lichen for air quality monitoring can provide information for sustainable management of air quality and environmental quality in Nigeria.

Prediction of contraceptive discontinuation among reproductive-age women in Ethiopia using Ethiopian Demographic and Health Survey 2016 Dataset: A Machine Learning Approach

BACKGROUND

Globally, 38% of contraceptive users discontinue the use of a method within the first twelve months. In Ethiopia, about 35% of contraceptive users also discontinue within twelve months. Discontinuation reduces contraceptive coverage, family planning program effectiveness and contributes to undesired fertility. Hence understanding potential predictors of contraceptive discontinuation is crucial to reducing its undesired outcomes. Predicting the risk of discontinuing contraceptives is also used as an early-warning system to notify family planning programs. Thus, this study could enable to predict and determine the predictors for contraceptive discontinuation in Ethiopia.

METHODOLOGY

Secondary data analysis was done on the 2016 Ethiopian Demographic and Health Survey. Eight machine learning algorithms were employed on a total sample of 5885 women and evaluated using performance metrics to predict and identify important predictors of discontinuation through python software. Feature importance method was used to select top predictors of contraceptive discontinuation. Finally, association rule mining was applied to discover the relationship between contraceptive discontinuation and its top predictors by using R statistical software.

RESULT

Random forest was the best predictive model with 68% accuracy which identified the top predictors of contraceptive discontinuation. Association rule mining identified women's age, women's education level, family size, husband's desire for children, husband's education level, and women's fertility preference as predictors most frequently associated with contraceptive discontinuation.

CONCLUSION

Results have shown that machine learning algorithms can accurately predict the discontinuation status of contraceptives, making them potentially valuable as decision-support tools for the relevant stakeholders. Through association rule mining analysis of a large dataset, our findings also revealed previously unknown patterns and relationships between contraceptive discontinuation and numerous predictors.

A survey on the use of association rules mining techniques in textual social media

The incursion of social media in our lives has been much accentuated in the last decade. This has led to a multiplication of data mining tools aimed at obtaining knowledge from these data sources. One of the greatest challenges in this area is to be able to obtain this knowledge without the need for training processes, which requires structured information and pre-labelled datasets. This is where unsupervised data mining techniques come in. These techniques can obtain value from these unstructured and unlabelled data, providing very interesting solutions to enhance the decision-making process. In this paper, we first address the problem of social media mining, as well as the need for unsupervised techniques, in particular association rules, for its treatment. We follow with a broad overview of the applications of association rules in the domain of social media mining, specifically, their application to the problems of mining textual entities, such as tweets. We also focus on the strengths and weaknesses of using association rules for solving different tasks in textual social media. Finally, the paper provides a perspective overview of the challenges that association rules must face in the next decade within the field of social media mining.

Forecasting COVID-19 cases using time series modeling and association rule mining

BACKGROUND

The aim of this study was to evaluate the most effective combination of autoregressive integrated moving average (ARIMA), a time series model, and association rule mining (ARM) techniques to identify meaningful prognostic factors and predict the number of cases for efficient COVID-19 crisis management.

METHODS

The 3685 COVID-19 patients admitted at Thailand's first university field hospital following the four waves of infections from March 2020 to August 2021 were analyzed using the autoregressive integrated moving average (ARIMA), its derivative to exogenous variables (ARIMAX), and association rule mining (ARM).

RESULTS

The ARIMA (2, 2, 2) model with an optimized parameter set predicted the number of the COVID-19 cases admitted at the hospital with acceptable error scores (R² = 0.5695, RMSE = 29.7605, MAE = 27.5102). Key features from ARM (symptoms, age, and underlying diseases) were selected to build an ARIMAX (1, 1, 1) model, which yielded better performance in predicting the number of admitted cases (R² = 0.5695, RMSE = 27.7508, MAE = 23.4642). The association analysis revealed that hospital stays of more than 14 days were related to the healthcare worker patients and the patients presented with underlying diseases. The worsening cases that required referral to the hospital ward were associated with the patients admitted with symptoms, pregnancy, metabolic syndrome, and age greater than 65 years old.

CONCLUSIONS

This study demonstrated that the ARIMAX model has the potential to predict the number of COVID-19 cases by incorporating the most associated prognostic factors identified by ARM technique to the ARIMA model, which could be used for preparation and optimal management of hospital resources during pandemics.

Target association rule mining to explore novel paediatric illness patterns in emergency settings

BACKGROUND AND AIMS

To assess the hospitalized sick children admitted to the pediatric emergency department (ED) and to find new patterns of clinical and laboratory attributes using association rule mining (ARM).

METHODS

In this observational study, 158 children with median (IQR) age 11 months and a PRISM III score of 5 (2-9) were enrolled. Hotspot data mining method was applied to assess clinical attributes, lab investigations and pre-defined outcome parameters of children and their association in sick hospitalized children aged 1 month to 12 years.

RESULTS

We obtained 30 rules with value for outcome as discharge is given attributes as follows: duration of hospitalization > 4 days, lactate > 1.2 mmol/L, platelet = 3.67/μL, dur_ventil = 0 h, serum K = 5.2 mmol/L, SBP = 120 mmHg, pCO2 = 41.9 mmHg, PaO2 = 163 mmHg, age = 92 months, heart rate > 114-159 per minute, temperature > 98 °F, GCS (Glasgow Coma Scale) > 7-14, gas K = 4.14 mmol/L, gas Na = 138.1 mmol/L, BUN (Blood Urea Nitrogen) = 18.69 mg/dL, Diagnosis > 1-718, Creatinine = 1.2 mg/dL, serum Na = 148 mmol/L, shock = 2, Glucose = 144 mg/dL, Mg(i) > 0.23 meq/L, BUN > 6.54 mg/dL.

CONCLUSION

ARM is an effective data analysis technique to find meaningful patterns using clinical features with actual numbers in pediatric critical illness. It can prove to be important while analysing the association of clinical attributes with disease pattern, its features, and therapeutic or intervention success patterns.

Discovering Patterns of Cardiovascular Disease and Diabetes in Myocardial Infarction Patients Using Association Rule Mining

Highlights: Association Rule Mining tools predict the association of early-onset Myocardial Infarction with Hypertension and Diabetes Mellitus. Association Rule Mining tools using clinical and biochemical attributes can predict the development of Hypertension and Diabetes Mellitus in Myocardial Infarction patients. Abstract: Cardiovascular diseases (CVDs) are a major cause of mortality in diabetic patients. Hypertensive patients are more likely to develop diabetes and hypertension contributes to the high prevalence of CVDs, in addition to dyslipidemia and smoking. This study was to find the different patterns and overall rules among CVD patients, including rules broken down by age, sex, cholesterol and triglyceride levels, smoking habits, myocardial infarction (MI) type on ECG, diabetes, and hypertension. The cross-sectional study was performed on 240 subjects (135 patients of ST-elevation MI below 45 years and 105 age matched controls). Association rule mining was used to detect new patterns for early-onset myocardial infarction. A hotspot algorithm was used to extract frequent patterns and various promising rules within real medical data. The experiment was carried out using "Weka'', a tool for extracting rules to find out the association between different stored real parameters. In this study, we found out various rules of hypertension like “Rule 6” says that if levels of BP Systolic > 131 mmHg, LpA2 > 43.2 ng/ml, hsCRP > 3.71 mg/L, initial creatinine > 0.5 mg/dl, and initial Hb ≤15 g/dl (antecedent), then the patient will have 88% chance of developing hypertension (consequent). Similarly for diabetes mellitus with finding their lift and confidence for different support like “Rule 6”, if MI type on ECG = ’Inferior Wall MI’ with STATIN=No, and levels of Triglycerides ≤325 (antecedent), then the patient had a 67% chance of developing diabetes mellitus. We concluded that early-onset myocardial infarction is significantly associated with hypertension and diabetes mellitus.Using association rule mining, we can predict the development of hypertension and diabetes mellitus in MI patients.

ElGamal Homomorphic Encryption-Based Privacy Preserving Association Rule Mining on Horizontally Partitioned Healthcare Data

In today’s world, life-threatening diseases have become a pre-eminent issue in healthcare due to the higher mortality rate. It is possible to lower this mortality rate by utilizing healthcare intelligence to detect diseases early. Patient’s medical data is stored in the EHR system, which is kept up to date by the healthcare provider. Data mining techniques like Association Rule Mining can detect a patient’s disease from their symptoms using digital healthcare data stored in the EHR system. Association rule mining’s efficacy can be improved by using global data from various EHR systems. It mandates that all EHR systems exchange healthcare records to a central server. When personal health information is made available on an untrusted server, several privacy laws may be violated. As a result, the challenge of privacy preserving distributed healthcare data mining has become a well-known study field in the healthcare industry. This research uses an efficient ElGamal homomorphic encryption technique to protect privacy in a distributed association rule mining. The proposed approach to discover the risk factor of most life-threatening diseases like breast cancer and heart disease with its symptoms and discuss the scope for combating COVID-19. Theoretical analysis of the proposed approach shows that it is efficient and maintains privacy in an insecure communication environment. An experimental study with a real dataset shows the proposed approach’s benefit compared to the local single EHR system results.

Gender Difference in Psychological, Cognitive, and Behavioral Patterns Among University Students During COVID-19: A Machine Learning Approach

The COVID-19 pandemic affects all population segments and is especially detrimental to university students because social interaction is critical for a rewarding campus life and valuable learning experiences. In particular, with the suspension of in-person activities and the adoption of virtual teaching modalities, university students face drastic changes in their physical activities, academic careers, and mental health. Our study applies a machine learning approach to explore the gender differences among U.S. university students in response to the global pandemic. Leveraging a proprietary survey dataset collected from 322 U.S. university students, we employ association rule mining (ARM) techniques to identify and compare psychological, cognitive, and behavioral patterns among male and female participants. To formulate our task under the conventional ARM framework, we model each unique question-answer pair of the survey questionnaire as a market basket item. Consequently, each participant's survey report is analogous to a customer's transaction on a collection of items. Our findings suggest that significant differences exist between the two gender groups in psychological distress and coping strategies. In addition, the two groups exhibit minor differences in cognitive patterns and consistent preventive behaviors. The identified gender differences could help professional institutions to facilitate customized advising or counseling for males and females in periods of unprecedented challenges.

Different Coping Patterns among US Graduate and Undergraduate Students during COVID-19 Pandemic: A Machine Learning Approach

COVID-19 caused unprecedented disruptions to regular university operations worldwide. Dealing with 100% virtual classrooms and suspension of essential in-person activities resulted in significant stress and anxiety for students coping with isolation, fear, and uncertainties in their academic careers. In this study, we applied a machine learning approach to identify distinct coping patterns between graduate and undergraduate students when facing these challenges. We based our study on a large proprietary dataset collected from 517 students in US professional institutions during an early peak of the pandemic. In particular, we cast our problem under the association rule mining (ARM) framework by introducing a new method to transform survey data into market basket items and customer transactions in which students' behavioral patterns were analogous to customer purchase patterns. Our experimental results suggested that graduate and undergraduate students adopted different ways of coping that could be attributed to their different maturity levels and lifestyles. Our findings can further serve as a focus of attention (FOA) tool to facilitate customized advising or counseling to address the unique challenges associated with each group that may warrant differentiated interventions.

A Graph-Based Differentially Private Algorithm for Mining Frequent Sequential Patterns

Currently, individuals leave a digital trace of their activities when they use their smartphones, social media, mobile apps, credit card payments, Internet surfing profile, etc. These digital activities hide intrinsic usage patterns, which can be extracted using sequential pattern algorithms. Sequential pattern mining is a promising approach for discovering temporal regularities in huge and heterogeneous databases. These sequences represent individuals’ common behavior and could contain sensitive information. Thus, sequential patterns should be sanitized to preserve individuals’ privacy. Hence, many algorithms have been proposed to accomplish this task. However, these techniques add noise to the candidate support before they are validated as, frequently, and thus, they cannot be applied without having access to all the users’ sequences data. In this paper, we propose a differential privacy graph-based technique for publishing frequent sequential patterns. It is applied at the post-processing stage; hence it may be used to protect frequent sequential patterns after they have been extracted, without the need to access all the users’ sequences. To validate our proposal, we performed a detailed assessment of its utility as a pattern mining algorithm and calculated the impact of the sanitization mechanism on a recommender system. We further evaluated its information loss disclosure risk and performed a comparison with the DP-FSM algorithm.

Hypertension and Obesity: Risk Factors for Thyroid Disease

Thyroid disease instances have rapidly increased in the past few decades; however, the cause of the disease remains unclear. Understanding the pathogenesis of thyroid disease will potentially reduce morbidity and mortality rates. Currently, the identified risk factors from existing studies are controversial as they were determined through qualitative analysis and were not further confirmed by quantitative implementations. Association rule mining, as a subset of data mining techniques, is dedicated to revealing underlying correlations among multiple attributes from a complex heterogeneous dataset, making it suitable for thyroid disease pathogenesis identification. This study adopts two association rule mining algorithms (i.e., Apriori and FP-Growth Tree) to identify risk factors correlated with thyroid disease. Extensive experiments were conducted to reach impartial findings with respect to knowledge discovery through two independent digital health datasets. The findings confirmed that gender, hypertension, and obesity are positively related to thyroid disease development. The history of I₁₃₁ treatment and Triiodothyronine level can be potential factors for evaluating subsequent thyroid disease.

Kynurenine and Hemoglobin as Sex-Specific Variables in COVID-19 Patients: A Machine Learning and Genetic Algorithms Approach

Differences in clinical manifestations, immune response, metabolic alterations, and outcomes (including disease severity and mortality) between men and women with COVID-19 have been reported since the pandemic outbreak, making it necessary to implement sex-specific biomarkers for disease diagnosis and treatment. This study aimed to identify sex-associated differences in COVID-19 patients by means of a genetic algorithm (GALGO) and machine learning, employing support vector machine (SVM) and logistic regression (LR) for the data analysis. Both algorithms identified kynurenine and hemoglobin as the most important variables to distinguish between men and women with COVID-19. LR and SVM identified C10:1, cough, and lysoPC a 14:0 to discriminate between men with COVID-19 from men without, with LR being the best model. In the case of women with COVID-19 vs. women without, SVM had a higher performance, and both models identified a higher number of variables, including 10:2, lysoPC a C26:0, lysoPC a C28:0, alpha-ketoglutaric acid, lactic acid, cough, fever, anosmia, and dysgeusia. Our results demonstrate that differences in sexes have implications in the diagnosis and outcome of the disease. Further, genetic and machine learning algorithms are useful tools to predict sex-associated differences in COVID-19.

A Novel COVID-19 Diagnosis Support System Using the Stacking Approach and Transfer Learning Technique on Chest X-Ray Images

COVID-19 is an infectious disease-causing flu-like respiratory problem with various symptoms such as cough or fever, which in severe cases can cause pneumonia. The aim of this paper is to develop a rapid and accurate medical diagnosis support system to detect COVID-19 in chest X-ray images using a stacking approach combining transfer learning techniques and KNN algorithm for selection of the best model. In deep learning, we have multiple approaches for building a classification system for analyzing radiographic images. In this work, we used the transfer learning technique. This approach makes it possible to store and use the knowledge acquired from a pretrained convolutional neural network to solve a new problem. To ensure the robustness of the proposed system for diagnosing patients with COVID-19 using X-ray images, we used a machine learning method called the stacking approach to combine the performances of the many transfer learning-based models. The generated model was trained on a dataset containing four classes, namely, COVID-19, tuberculosis, viral pneumonia, and normal cases. The dataset used was collected from a six-source dataset of X-ray images. To evaluate the performance of the proposed system, we used different common evaluation measures. Our proposed system achieves an extremely good accuracy of 99.23% exceeding many previous related studies.

Computational simulations to dissect the cell immune response dynamics for severe and critical cases of SARS-CoV-2 infection

BACKGROUND

COVID-19 is a global pandemic leading to high death tolls worldwide day by day. Clinical evidence suggests that COVID-19 patients can be classified as non-severe, severe, and critical cases. In particular, studies have highlighted the relationship between lymphopenia and the severity of the illness, where CD8+ T cells have the lowest levels in critical cases. However, a quantitative understanding of the immune responses in COVID-19 patients is still missing.

OBJECTIVES

In this work, we aim to elucidate the key parameters that define the course of the disease deviating from severe to critical cases. The dynamics of different immune cells are taken into account in mechanistic models to elucidate those that contribute to the worsening of the disease.

METHODS

Several mathematical models based on ordinary differential equations are proposed to represent data sets of different immune response cells dynamics such as CD8+ T cells, NK cells, and also CD4+ T cells in patients with SARS-CoV-2 infection. Parameter fitting is performed using the differential evolution algorithm. Non-parametric bootstrap approach is introduced to abstract the stochastic environment of the infection.

RESULTS

The mathematical model that represents the data more appropriately is considering CD8+ T cell dynamics. This model had a good fit to reported experimental data, and in accordance with values found in the literature. The NK cells and CD4+ T cells did not contribute enough to explain the dynamics of the immune responses.

CONCLUSIONS

Our computational results highlight that a low viral clearance rate by CD8+ T cells could lead to the severity of the disease. This deregulated clearance suggests that it is necessary immunomodulatory strategies during the course of the infection to avoid critical states in COVID-19 patients.

Biomarkers of severe COVID-19 pneumonia on admission using data-mining powered by common laboratory blood tests-datasets

In the epidemiological COVID-19 research, artificial intelligence is a unique approach to make predictions about disease severity to manage COVID-19 patients. A limitation of artificial intelligence is, however, the high risk of bias. We investigated the skill of data mining and machine learning, two advanced forms of artificial intelligence, to predict severe COVID-19 pneumonia based on routine laboratory tests. A sample of 4009 COVID-19 patients was divided into Severe (PaO₂< 60 mmHg, 489 cases) and Non-Severe (PaO₂ ≥ 60 mmHg, 3520 cases) groups according to blood hypoxemia on admission and their laboratory datasets analyzed by the R software and WEKA workbench. After curation, data were processed for the selection of the most influential features including hemogram, pCO₂, blood acid-base balance, prothrombin time, inflammation biomarkers, and glucose. The best fit of variables was successfully confirmed by either the Multilayer Perceptron, a feedforward neural network algorithm that performed machine recognition of severe COVID-19 with 96.5% precision, or by the C4.5 software, a supervised learning algorithm based on an objective-predefined variable (severity) that generated a decision tree with 89.4% precision. Finally, a complex bivariate Pearson's correlation matrix combined with advanced hierarchical clustering (dendrograms) were conducted for knowledge discovery. The hidden structure of the datasets revealed shift patterns related to the development of COVID-19-induced pneumonia that involved the lymphocyte-to-C-reactive protein and leukocyte-to-C-protein ratios, neutrophil %, pH and pCO₂. The data mining approaches to the hematological fluctuations associated with severe COVID-19 pneumonia could not only anticipate adverse clinical outcomes, but also reveal putative therapeutic targets.