scholarly journals Heg.IA: An intelligent system to support diagnosis of Covid-19 based on blood tests

2020 ◽  
Author(s):  
Valter Augusto de Freitas Barbosa ◽  
Juliana Carneiro Gomes ◽  
Maíra Araújo de Santana ◽  
Jeniffer Emídio de Almeida Albuquerque ◽  
Rodrigo Gomes de Souza ◽  
...  
Keyword(s):  
Influenza A ◽  
Intelligent System ◽  
Low Cost ◽  
Hematological Parameters ◽  
Rapid Test ◽  
Albert Einstein ◽  
Classification Performance ◽  
Kappa Index ◽  
Blood Tests ◽  
Intelligent Software

Abstract A new kind of coronavirus, the SARS-Cov2, started the biggest pandemic of the century. It has already killed more than 250,000 people. Due to this fact, it is necessary quick and precise easily available diagnosis tests. The current Covid-19 diagnosis benchmark is RT-PCR with DNA identification, but its results takes too long to be available. Tests based on IgM/IgG antibodies have been used, but their sensitivity and specificity may be very low when viral charge is reduced. Many studies have been demonstrating the Covid-19 impact in hematological parameters. This work proposes an intelligent system to support Covid-19 diagnosis based on blood testing. We employed a dataset provided by Hospital Israelita Albert Einstein, a Brazilian private hospital. The database contains the results of more than one hundred laboratory exams, such as blood count, tests for the presence of viruses such as influenza A, and urine tests, of 5644 patients. Among these patients, 559 of them are infected with SARS-Cov2. We used metaheuristics algorithms to reduce the set of We tested several machine learning methods, and we achieved high classification performance: 95.159% +- 0.693 of overall accuracy, kappa index of 0.903 +- 0.014, sensitivity of 0.968 +- 0.007, precision of 0.938 +- 0.010, and specificity of 0.936 +- 0.011. Experimental results pointed out to Bayes Network as the best configuration. In addition, only 24 blood tests were needed. This points to the possibility of a new low cost rapid test based on common blood exams and intelligent software. The desktop version of the system is fully functional and available for free use.

scholarly journals Heg.IA: An intelligent system to support diagnosis of Covid-19 based on blood tests

2020 ◽  
Author(s):  
Valter Augusto de Freitas Barbosa ◽  
Juliana Carneiro Gomes ◽  
Maira Araujo de Santana ◽  
Jeniffer Emidio de Almeida Albuquerque ◽  
Rodrigo Gomes de Souza ◽  
...  
Keyword(s):  
Intelligent System ◽  
Low Cost ◽  
Hematological Parameters ◽  
Computational Cost ◽  
Rapid Test ◽  
Classification Performance ◽  
Kappa Index ◽  
Blood Tests ◽  
Bayes Network ◽  
Precise Diagnosis

A new kind of coronavirus, the SARS-Cov2, started the biggest pandemic of the century. It has already killed more than 250,000 people. Because of this, it is necessary quick and precise diagnosis test. The current gold standard is the RT-PCR with DNA sequencing and identification, but its results takes too long to be available. Tests base on IgM/IgG antibodies have been used, but their sensitivity and specificity may be very low. Many studies have been demonstrating the Covid-19 impact in hematological parameters. This work proposes an intelligent system to support Covid-19 diagnosis based on blood testing. We tested several machine learning methods, and we achieved high classification performance: 95.159% +- 0.693 of overall accuracy, kappa index of 0.903 +- 0.014, sensitivity of 0.968 +- 0.007, precision of 0.938 +- 0.010 and specificity of 0.936 +- 0.011. These results were achieved using classical and low computational cost classifiers, with Bayes Network being the best of them. In addition, only 24 blood tests were needed. This points to the possibility of a new rapid test with low cost. The desktop version of the system is fully functional and available for free use.

scholarly journals Covid-19 rapid test by combining a random forest based web system and blood tests

2020 ◽  
Author(s):  
Valter Augusto de Freitas Barbosa ◽  
Juliana Carneiro Gomes ◽  
Maíra Araújo de Santana ◽  
Clarisse Lins de Lima ◽  
Raquel Bezerra Calado ◽  
...  
Keyword(s):  
Random Forest ◽  
Decision Trees ◽  
Hematological Parameters ◽  
Rapid Test ◽  
Kappa Index ◽  
Simple Method ◽  
Blood Tests ◽  
Web System ◽  
Public Health Challenges ◽  
Effective Diagnosis

AbstractBackgroundThe disease caused by the new type of coronavirus, the Covid-19, has posed major public health challenges for many countries. With its rapid spread, since the beginning of the outbreak in December 2019, the disease transmitted by SARS-Cov2 has already caused over 400 thousand deaths to date. The diagnosis of the disease has an important role in combating Covid-19.ObjectiveIn this work, we propose a web system, Heg.IA, which seeks to optimize the diagnosis of Covid-19 through the use of artificial intelligence.MethodThe main ideia is that healthcare professionals can insert 41 hematological parameters from common blood tests and arterial gasometry into the system. Then, Heg.IA will provide a diagnostic report. It will indicate if the patient is infected with SARS-Cov2 virus, and also predict the type of hospitalization (regular ward, semi-ICU, or ICU).ResultsWe developed a web system called Heg.IA to support decision-making regarding to diagnosis of Covid-19 and to the indication of hospitalization on regular ward, semi-ICU or ICU. This application is based on decision trees in a Random Forest architecture with 90 trees. The system showed to be highly efficient, with great results for both Covid-19 diagnosis and to recommend hospitalization. For the first scenario we found average results of accuracy of 92.891% ± 0.851, kappa index of 0.858 ± 0.017, sensitivity of 0.936 ± 0.011, precision of 0.923 ± 0.011, specificity of 0.921 ± 0.012 and area under ROC of 0.984 ± 0.003. As for the indication of hospitalization, we achieved excellent performance of accuracies above 99% and more than 0.99 for the other metrics in all situations.ConclusionBy using a computationally simple method, based on the classical decision trees, we were able to achieve high diagnosis performance. Heg.IA system may be a way to overcome the testing unavailability in the context of Covid-19. We also expect the system will provide wide access to Covid-19 effective diagnosis and thereby reach and help saving lives.

scholarly journals Identification of Ramularia Leaf Blight Cotton Disease Infection Levels by Multispectral, Multiscale UAV Imagery

Drones ◽  
2019 ◽  
Vol 3 (2) ◽  
pp. 33 ◽  
Author(s):  
Thomaz W. F. Xavier ◽  
Roberto N. V. Souto ◽  
Thiago Statella ◽  
Rafael Galbieri ◽  
Emerson S. Santos ◽  
...  
Keyword(s):  
Production Cost ◽  
Low Cost ◽  
Classification Performance ◽  
Leaf Blight ◽  
Multispectral Imagery ◽  
Kappa Index ◽  
Pesticide Application ◽  
Flight Height ◽  
Farm Scale ◽  
Airborne Vehicle

The reduction of the production cost and negative environmental impacts by pesticide application to control cotton diseases depends on the infection patterns spatialized in the farm scale. Here, we evaluate the potential of three-band multispectral imagery from a multi-rotor unmanned airborne vehicle (UAV) platform for the detection of ramularia leaf blight from different flight heights in an experimental field. Increasing infection levels indicate the progressive degradation of the spectral vegetation signal, however, they were not sufficient to differentiate disease severity levels. At resolutions of ~5 cm (100 m) and ~15 cm (300 m) up to a ground spatial resolution of ~25 cm (500 m flight height), two-scaled infection levels can be detected for the best performing algorithm of four classifiers tested, with an overall accuracy of ~79% and a kappa index of ~0.51. Despite limited classification performance, the results show the potential interest of low-cost multispectral systems to monitor ramularia blight in cotton.

Triticum aestivum Assay - A Useful Tool for Environmental Monitoring and Toxicity Assessment

2019 ◽  
Vol 47 (4) ◽  
pp. 1005-1018
Author(s):  
Alexandra JITĂREANU ◽  
Ioana-Cezara CABA ◽  
Adriana TRIFAN ◽  
Silvica PĂDUREANU ◽  
Luminița AGOROAEI
Keyword(s):  
Triticum Aestivum ◽  
Higher Plants ◽  
Low Cost ◽  
Environmental Pollutants ◽  
Rapid Test ◽  
Toxicity Assessment ◽  
Pollution Monitoring ◽  
Present Review ◽  
Digital Object Identifier ◽  
Biological Assays

The present review summarizes the literature data regarding the application of Triticum aestivum assay as an alternative method for toxicity assessment of environmental pollutants or potential therapeutic agents. Plant bioassays present several advantages among other biological assays (simplicity, low cost, rapid test activation, a wide array of assessment endpoints). They present a good correlation with animal and human cells models, and are a reliable tool for genotoxicity assessment. Furthermore, in the context of toxicology guidelines that promote the substitution of assays using animal models with other bioassays, genotoxicity assays using higher plants models have gained in popularity. The present review focuses on three major aspects regarding Triticum aestivum assay - its utility in environmental pollution monitoring, its application in genotoxicity assessment studies, and its application in phytotoxicity evaluation of nanomaterials.   ********* In press - Online First. Article has been peer reviewed, accepted for publication and published online without pagination. It will receive pagination when the issue will be ready for publishing as a complete number (Volume 47, Issue 4, 2019). The article is searchable and citable by Digital Object Identifier (DOI). DOI link will become active after the article will be included in the complete issue. *********

scholarly journals Performance of BioFire array or QuickVue influenza A + B test versus a validation qPCR assay for detection of influenza A during a volunteer A/California/2009/H1N1 challenge study

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
David R. McIlwain ◽  
Han Chen ◽  
Maria Apkarian ◽  
Melton Affrime ◽  
Bonnie Bock ◽  
...  
Keyword(s):  
Influenza A ◽  
Rapid Test ◽  
Influenza Viruses ◽  
Qpcr Assay ◽  
Superior Performance ◽  
Qrt Pcr ◽  
Challenge Study ◽  
Test Kit ◽  
2009 H1n1 ◽  
B Test

Abstract Background Influenza places a significant burden on global health and economics. Individual case management and public health efforts to mitigate the spread of influenza are both strongly impacted by our ability to accurately and efficiently detect influenza viruses in clinical samples. Therefore, it is important to understand the performance characteristics of available assays to detect influenza in a variety of settings. We provide the first report of relative performance between two products marketed to streamline detection of influenza virus in the context of a highly controlled volunteer influenza challenge study. Methods Nasopharyngeal swab samples were collected during a controlled A/California/2009/H1N1 influenza challenge study and analyzed for detection of virus shedding using a validated qRT-PCR (qPCR) assay, a sample-to-answer qRT-PCR device (BioMerieux BioFire FilmArray RP), and an immunoassay based rapid test kit (Quidel QuickVue Influenza A + B Test). Results Relative to qPCR, the sensitivity and specificity of the BioFire assay was 72.1% [63.7–79.5%, 95% confidence interval (CI)] and 93.5% (89.3–96.4%, 95% CI) respectively. For the QuickVue rapid test the sensitivity was 8.5% (4.8–13.7%, 95% CI) and specificity was 99.2% (95.6–100%, 95% CI). Conclusion Relative to qPCR, the BioFire assay had superior performance compared to rapid test in the context of a controlled influenza challenge study.

scholarly journals Influenza colloidal gold method and blood routine tests combination for rapid diagnosis of influenza: a decision tree-based analysis

2021 ◽  
Vol 31 (1) ◽  
Author(s):  
Xiaoguang Li ◽  
Jing Chen ◽  
Fei Lin ◽  
Wei Wang ◽  
Jie Xu ◽  
...  
Keyword(s):  
Decision Tree ◽  
Predictive Value ◽  
Colloidal Gold ◽  
Influenza A ◽  
Clinical Manifestations ◽  
Rapid Test ◽  
Test Results ◽  
Tree Model ◽  
Routine Blood ◽  
Test Result

AbstractRapid influenza diagnosis can facilitate targeted treatment and reduce antibiotic misuse. However, diagnosis efficacy remains unclear. This study examined the efficacy of a colloidal gold rapid test for rapid influenza diagnosis. Clinical characteristics of 520 patients with influenza-like illness presenting at a fever outpatient clinic during two influenza seasons (2017–2018; 2018–2019) were evaluated. The clinical manifestations and results of routine blood, colloidal gold, and nucleic acid tests were used to construct a decision tree with three layers, nine nodes, and five terminal nodes. The combined positive predictive value of a positive colloidal gold test result and monocyte level within 10.95–12.55% was 88.2%. The combined negative predictive value of a negative colloidal gold test result and white blood cell count > 9.075 × 109/L was 84.9%. The decision-tree model showed the satisfactory accuracy of an early influenza diagnosis based on colloidal gold and routine blood test results.

scholarly journals A20 DIAGNOSTIC ACCURACY OF A LOW COST, WIDELY AVAILABLE TEST STRIP FOR PREDICTING A POSITIVE FECAL CALPROTECTIN TEST

2021 ◽  
Vol 4 (Supplement_1) ◽  
pp. 210-212
Author(s):  
R Trasolini ◽  
S Wong ◽  
B Salh
Keyword(s):  
Sample Size ◽  
Likelihood Ratio ◽  
Gold Standard ◽  
Low Cost ◽  
Positive Likelihood Ratio ◽  
Negative Likelihood Ratio ◽  
Rapid Test ◽  
Test Strip ◽  
Fecal Calprotectin ◽  
Type I

Abstract Background Fecal calprotectin is a non-invasive test of colonic inflammation used for monitoring inflammatory bowel disease activity and for risk stratifying non-specific colonic symptoms. Calprotectin is a leukocyte specific enzyme. A similar test, leukocyte esterase is used to detect leukocytes in urine and is widely available as a low-cost point-of-care test strip. We hypothesize that an unmodified version of the urine test strip would be highly accurate in predicting a positive fecal calprotectin test in a real world sample of patients. Aims To explore a low cost, rapid alternative to the fecal calprotectin test Methods All inpatient and outpatient stool samples tested for calprotectin by the Vancouver General Hospital laboratory from February 2020 to November 2020 were included prospectively. Samples were simultaneously tested for fecal leukocyte esterase using an unmodified Roche Cobas Chemstrip urinalysis test strip by central lab personnel. An identical aliquot was sent to LifeLabs for calprotectin as per standard protocol. All samples were suspended in buffer using established laboratory protocols prior to testing. Fecal leukocyte esterase results were reported as 0–4+ based on visual interpretation, calprotectin results were reported as mcg/g of stool. REB review and approval was obtained prior to data collection. Sensitivity, Specificity and AUROC were calculated using Microsoft Excel and JROCFIT. Results 26 samples were collected. Using a fecal calprotectin greater than 120 mcg/g as a gold standard an AUROC of 0.89 (SE= .06) was calculated. A leukocyte esterase reading of 2+ or greater had the best test characteristics based on ROC curve analysis. Using this cutoff, 21/26 samples were concordant, giving an accuracy of 80.8%, sensitivity of 90.9% and specificity of 73.3%. Positive likelihood ratio was 8.07 and negative likelihood ratio was 0.29. Assuming an AUROC of 0.8, the sample size N=26 is 90% powered (β=0.9) to predict the true AUROC within 0.1 with a type I error rate of .05 (α<.05). Conclusions This study suggests application of a prepared stool sample to a urinalysis test strip gives a result highly predictive of a positive fecal calprotectin test. Further results are being collected prospectively to improve the robustness of these preliminary data. Secondary outcomes including comparison to endoscopy and biopsy results where available are planned if an adequate sample size can be accrued. Future studies justifying independent clinical use of leukocyte esterase would require a common gold standard comparator such as endoscopy. Fecal calprotectin testing is not universally insured and is not available as a rapid test strip. Use of fecal leukocyte esterase may reduce costs and shorten time to results if proven to be independently reliable. Funding Agencies None

scholarly journals A Machine Learning Model Incorporating Laboratory Blood Tests Discriminates Between SARS-CoV-2 and Influenza Infections at Emergency Department Visit

2021 ◽  
Author(s):  
Junyi Liu ◽  
Lars F Westblade ◽  
Amy Chadburn ◽  
Richard Fideli ◽  
Arryn Craney ◽  
...  
Keyword(s):  
Emergency Department ◽  
Laboratory Test ◽  
Calcium Level ◽  
Influenza A ◽  
Respiratory Pathogens ◽  
Rt Pcr ◽  
Blood Tests ◽  
Laboratory Test Results ◽  
Presentation Methods ◽  
The Impact

Introduction: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and influenza virus are contagious respiratory pathogens with similar symptoms but require different treatment and management strategies. This study investigated whether laboratory blood tests can discriminate between SARS-CoV-2 and influenza infections at emergency department (ED) presentation. Methods: 723 influenza A/B positive (2018/1/1 to 2020/3/15) and 1,281 SARS-CoV-2 positive (2020/3/11 to 2020/6/30) ED patients were retrospectively analyzed. Laboratory test results completed within 48 hours prior to reporting of virus RT-PCR results, as well as patient demographics were included to train and validate a random forest (RF) model. The dataset was randomly divided into training (2/3) and testing (1/3) sets with the same SARS-CoV-2/influenza ratio. The Shapley Additive Explanations technique was employed to visualize the impact of each laboratory test on the differentiation. Results: The RF model incorporating results from 15 laboratory tests and demographic characteristics discriminated SARS-CoV-2 and influenza infections, with an area under the ROC curve value 0.90 in the independent testing set. The overall agreement with the RT-PCR results was 83% (95% CI: 80-86%). The test with the greatest impact on the differentiation was serum total calcium level. Further, the model achieved an AUC of 0.82 in a new dataset including 519 SARS-CoV-2 ED patients (2020/12/1 to 2021/2/28) and the previous 723 influenza positive patients. Serum calcium level remained the most impactful feature on the differentiation. Conclusion: We identified characteristic laboratory test profiles differentiating SARS-CoV-2 and influenza infections, which may be useful for the preparedness of overlapping COVID-19 resurgence and future seasonal influenza.

scholarly journals Become A Star: Teaching the Process of Design and Implementation of an Intelligent System

10.28945/2894 ◽  
2005 ◽  
Author(s):  
Anne Venables ◽  
Grace Tan
Keyword(s):  
Intelligent Systems ◽  
Knowledge Engineering ◽  
Intelligent System ◽  
Development Project ◽  
Project Manager ◽  
Domain Experts ◽  
Software Development Project ◽  
Intelligent Software ◽  
Practical Experiences ◽  
Complete Process

Teaching future knowledge engineers, the necessary skills for designing and implementing intelligent software solutions required by business, industry and research today, is a very tall order. These skills are not easily taught in traditional undergraduate computer science lectures; nor are the practical experiences easily reinforced in laboratory sessions. In an attempt to address this issue, a software development project, designed to take students through a complete process of knowledge engineering, was introduced in an undergraduate Intelligent Systems subject. In this project, students were required to act as domain experts, knowledge engineers, programmers, end users and project manager in the production of a game-playing expert system. The paper describes the project, its objectives and development, as well as some of the benefits.

scholarly journals IDIOPATHIC THROMBOCYTOPENIA IN DOGS - CASE REPORT

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Goran PARAŠ ◽  
Smiljana PARAŠ ◽  
Bojan LUKAČ ◽  
Igor ČEGAR ◽  
Ognjen VITKOVIĆ
Keyword(s):  
Differential Diagnosis ◽  
Case Report ◽  
Autoimmune Diseases ◽  
Blood Platelets ◽  
Hematological Parameters ◽  
Small Animal ◽  
Behavioral Changes ◽  
Blood Tests ◽  
Pathological Conditions ◽  
Frequent Monitoring

Thrombocytopenia represents a significant reduction in number of blood platelets in thecirculation of mammals. The causes of thrombocytopenia in dogs and cats are: various infectiousfactors, viruses, bacterias, parasites, various pathological conditions of the liver, spleen, bonemarrow or autoimmune diseases. Sometimes, thrombocytopenia causes many different factors orthe real cause can not be detected, and its origin is called idiopathic. In our practice, in the course ofhaematological analysis of blood, we encounter a reduced number of platelets in the blood of dogsand cats. Then we are facing the great challenge of diagnosing and treating possible idiopathicthrombocytopenia in animals.In our case, we have a Miniature poodle whose problems began at the age of 2.5. The dog had thefollowing symptoms: inapetency, somnolence, temperature of 38.80C, pale oral mucosa withpetechiae and behavioral changes. After the first hematological blood tests were performed, theresults of the parameters indicated thrombocytopenia in this dog. Diagnosis of the disease issupported by symptoms and differential diagnosis, so we started with frequent monitoring ofhaematological parameters.We included adequate therapy with the first symptoms of the disease in our case of idiopathicthrombocytopenia in a young dog. The therapy was successful, hematological parameters and thequality of life improved, and the dog is now eight years old. The treatment of idiopathicthrombocytopenia is a challenge for every small animal veterinarian and for this reason in this paperwe share our experiences with colleagues.

Sign in / Sign up

Export Citation Format

Share Document