Applied Difference Techniques of Machine Learning Algorithm and Web-Based Management System for Sickle Cell Disease

2015 ◽  
Author(s):  
Mohammed Khalaf ◽  
Abir Jaafar Hussain ◽  
Dhiya Al-Jumeily ◽  
Russell Keenan ◽  
Robert Keight ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sickle Cell Disease ◽  
Sickle Cell ◽  
Management System ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Cell Disease ◽  
Web Based

Twitter Users' Classification Based on Interest

2020 ◽  
Vol 10 (1) ◽  
pp. 1-12
Author(s):  
Noura A. AlSomaikhi ◽  
Zakarya A. Alzamil
Keyword(s):  
Machine Learning ◽  
Experimental Study ◽  
Knowledge Sharing ◽  
Naive Bayes ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Software System ◽  
Web Based ◽  
Twitter Users

Microblogging platforms, such as Twitter, have become a popular interaction media that are used widely for different daily purposes, such as communication and knowledge sharing. Understanding the behaviors and interests of these platforms' users become a challenge that can help in different areas such as recommendation and filtering. In this article, an approach is proposed for classifying Twitter users with respect to their interests based on their Arabic tweets. A Multinomial Naïve Bayes machine learning algorithm is used for such classification. The proposed approach has been developed as a web-based software system that is integrated with Twitter using Twitter API. An experimental study on Arabic tweets has been investigated on the proposed system as a case study.

scholarly journals A WEB-BASED FAST AND RELIABLE TEXT CLASSIFICATION TOOL

2019 ◽  
Vol 1 ◽  
pp. 24
Author(s):  
Jānis Kapenieks
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Data Storage ◽  
Text Classification ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Web Based ◽  
Opinion Analysis ◽  
Classification Tool ◽  
User Friendly

INTRODUCTION Opinion analysis in the big data analysis context has been a hot topic in science and the business world recently. Social media has become a key data source for opinions generating a large amount of data every day providing content for further analysis. In the Big data age, unstructured data classification is one of the key tools for fast and reliable content analysis. I expect significant growth in the demand for content classification services in the nearest future. There are many online text classification tools available providing limited functionality -such as automated text classification in predefined categories and sentiment analysis based on a pre-trained machine learning algorithm. The limited functionality does not provide tools such as data mining support and/or a machine learning algorithm training interface. There are a limited number of tools available providing the whole sets of tools required for text classification, i.e. this includes all the steps starting from data mining till building a machine learning algorithm and applying it to a data stream from a social network source. My goal is to create a tool able to generate a classified text stream directly from social media with a user friendly set-up interface. METHODS AND MATERIALS The text classification tool will have a core based modular structure (each module providing certain functionality) so the system can be scaled in terms of technology and functionality. The tool will be built on open source libraries and programming languages running on a Linux OS based server. The tool will be based on three key components: frontend, backend and data storage as described below: backend: Python and Nodejs programming language with machine learning and text filtering libraries: TensorFlow, and Keras, for data storage Mysql 5.7/8 will be used, frontend will be based on web technologies built using PHP and Javascript. EXPECTED RESULTS The expected result of my work is a web-based text classification tool for opinion analysis using data streams from social media. The tool will provide a user friendly interface for data collection, algorithm selection, machine learning algorithm setup and training. Multiple text classification algorithms will be available as listed below: Linear SVM Random Forest Multinomial Naive Bayes Bernoulli Naive Bayes Ridge Regressio Perceptron Passive Aggressive Classifier Deep machine learning algorithm. System users will be able to identify the most effective algorithm for their text classification task and compare them based on their accuracy. The architecture of the text classification tool will be based on a frontend interface and backend services. The frontend interface will provide all the tools the system user will be interacting with the system. This includes setting up data collection streams from multiple social networks and allocating them to pre-specified channels based on keywords. Data from each channel can be classified and assigned to a pre-defined cluster. The tool will provide a training interface for machine learning algorithms. This text classification tool is currently in active development for a client with planned testing and implementation in April 2019.

scholarly journals Point-of-Care Screening for Sickle Cell Disease By a Mobile Micro-Electrophoresis Platform

Blood ◽  
2015 ◽  
Vol 126 (23) ◽  
pp. 3379-3379 ◽  
Author(s):  
Ryan Ung ◽  
Yunus Alapan ◽  
Muhammad Noman Hasan ◽  
Megan Romelfanger ◽  
Ping He ◽  
...  
Keyword(s):  
Image Processing ◽  
Sickle Cell Disease ◽  
Sickle Cell ◽  
Operating Characteristic ◽  
Point Of Care ◽  
Cell Disease ◽  
Web Based ◽  
Processing Application ◽  
Image Processing Application ◽  
Objective Quantification

Abstract In developing countries, diagnostic tests for homozygous (HbSS) or compound heterozygous (HbSC or HbS-Beta thalassemia) sickle cell disease (SCD) are not readily available at the point-of-care (POC). Very few infants are screened in Africa for SCD because of the high cost and level of skill needed to run traditional tests. Current methods are too costly and take too much time to enable equitable and timely diagnosis to save lives. The World Health Organization recognizes a crucial need for early detection of SCD in newborns, since it is estimated that 70% SCD-related deaths in Africa are preventable with early cost-effective interventions. The diagnostic barrier can be broken with affordable, POC tools that facilitate early detection immediately after birth. We have developed a mobile micro-electrophoretic device (HemeChip) through which to quickly, accurately, and affordably screen for SCD (Fig. 1A). The HemeChip uses a microfabricated platform housing cellulose acetate electrophoresis to rapidly separate hemoglobin (Hb) types. Less than 5 microliters of blood, which can be obtained through a finger stick or heel stick, is processed on a piece of cellulose paper in alkaline buffer. The HemeChip reliably identifies and discriminates amongst Hb C/A2, S, F and A0. The micro-electrophoresis results were validated against standard clinical hemoglobin screening methods, including high performance liquid chromatography (HPLC), with Pearson Correlation Coefficient (PCC) of ≥0.96 relative to HPLC for all Hb types tested. The receiver Operating-Characteristic (ROC) curves showed more than 0.89 sensitivity and 0.86 specificity for identification of hemoglobin types using the HemeChip, based on the travelling distance from the sample application point (Fig. 1B). We developed a web-based image processing application for automated and objective quantification of HemeChip results at the POC using cloud computing resources (Fig. 1C). This intensity-based mobile phone image quantitation method showed high correlation with HPLC results for tested patient blood samples (PCC=0.95). HemeChip can distinguish between different patient phenotypes, including HbSS (HbS only), transfused HbSS (HbS and HbA), and Hemoglobin SC disease (HbS and HbC). In conclusion, the HemeChip identification and quantification of hemoglobin phenotypes, as a POC technique, were comparable to standard clinical methods. This platform has clinical potential in under-served populations worldwide, in which SCD is endemic. Figure 1. Mobile micro-electrophoretic device (HemeChip) for point-of-care screening for sickle cell disease. ( A) HemeChip prototype is shown with a miniscule blood sample that has been separated into characteristic hemoglobin bands. (B) The receiver Operating-Characteristic (ROC) curves show sensitivity and specificity of HemeChip for differentiating between adjacent hemoglobin bands based on the travelling distance from the sample application point. band traveling distance thresholds are shown: circle=7.5 mm, triangle=10.0 mm, and square=12.5 mm. (C) Web-based image processing application for automated and objective quantification of HemeChip results at the POC using cloud computing resources. Figure 1. Mobile micro-electrophoretic device (HemeChip) for point-of-care screening for sickle cell disease. ( A) HemeChip prototype is shown with a miniscule blood sample that has been separated into characteristic hemoglobin bands. (B) The receiver Operating-Characteristic (ROC) curves show sensitivity and specificity of HemeChip for differentiating between adjacent hemoglobin bands based on the travelling distance from the sample application point. band traveling distance thresholds are shown: circle=7.5 mm, triangle=10.0 mm, and square=12.5 mm. (C) Web-based image processing application for automated and objective quantification of HemeChip results at the POC using cloud computing resources. Disclosures No relevant conflicts of interest to declare.

scholarly journals Web-Based Technology to Improve Disease Knowledge Among Adolescents With Sickle Cell Disease: Pilot Study (Preprint)

2019 ◽  
Author(s):  
Anjelica C Saulsberry ◽  
Jason R Hodges ◽  
Audrey Cole ◽  
Jerlym S Porter ◽  
Jane Hankins
Keyword(s):  
Sickle Cell Disease ◽  
Sickle Cell ◽  
Participation Rate ◽  
Self Management ◽  
Cell Disease ◽  
Adult Care ◽  
Web Based ◽  
Disease Knowledge ◽  
Transition Readiness ◽  
One Step

BACKGROUND Advancements in treatment have contributed to increased survivorship among children with sickle cell disease (SCD). Increased transition readiness, encompassing disease knowledge and self-management skills before transfer to adult care, is necessary to ensure optimal health outcomes. The Sickle Cell Transition E-Learning Program (STEP) is a public, Web-based, 6-module tool designed to increase transition readiness for youth with SCD. OBJECTIVE The objective of our study was to investigate the participation rate of youth with SCD in STEP and its association with transition readiness. METHODS This was a single-center, Institution Review Board–approved, retrospective cohort review. A total of 183 youths with SCD, aged between 12 and 15 years, were offered STEP as an adjunct to in-clinic disease education sessions. Participation rate (number of patients who used at least one STEP module divided by those approached) was calculated. The association among the number of STEP modules completed, disease knowledge, and self-management was explored. RESULTS Overall, 53 of the 183 approached adolescents completed at least one STEP module, yielding a participation rate in STEP of 29.0%. Of the 53 participants, 37 and 39 adolescents had disease knowledge and self-management confidence rating available, respectively. A positive correlation (<italic>r</italic>=0.47) was found between the number of STEP modules completed and disease knowledge scores (<italic>P</italic>=.003). No association was found between the number of modules completed and self-management confidence ratings. Disease knowledge scores were significantly higher among participants who completed ≥3 STEP modules compared with those who completed &lt;3 STEP modules (<italic>U</italic>=149.00; <italic>P</italic>=.007). CONCLUSIONS Improvement in disease knowledge in adolescence is critical to ensure the youth’s ability to self-care during the period of transition to adult care. Despite low participation, the cumulative exposure to the STEP program suggested greater promotion of disease knowledge among adolescents with SCD before transfer to adult care.

scholarly journals Machine learning predicts early-onset acute organ failure in critically ill patients with sickle cell disease

2019 ◽  
Author(s):  
Akram Mohammed ◽  
Pradeep S. B. Podila ◽  
Robert L. Davis ◽  
Kenneth I. Ataga ◽  
Jane S. Hankins ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care ◽  
Sickle Cell Disease ◽  
Kidney Disease ◽  
Organ Failure ◽  
Organ Dysfunction ◽  
Sickle Cell ◽  
Machine Learning Techniques ◽  
Cell Disease ◽  
Learning Techniques

AbstractBackgroundSickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable earlier identification and treatment, and potentially reduce mortality. We tested the hypothesis that machine learning physiomarkers could predict the development of organ dysfunction in an adult sample of patients with SCD admitted to intensive care units.Methods and FindingsWe studied 63 sequential SCD patients with 163 patient encounters, mean age 33.0±11.0 years, admitted to intensive care units, some of whom (6.7%) had pre-existing cardiovascular or kidney disease. A subset of these patient encounters (37; 23%) met sequential organ failure assessment (SOFA) criteria. The site of organ failure included: central nervous system (32), cardiovascular (11), renal (10), liver (7), respiratory (5) and coagulation (2) systems. Most (81.5%) of the patient encounters who experienced organ failure had single organ failure. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast fourier transform, energy, continuous wavelet transform, etc.) derived from heart rate, blood pressure, and respiratory rate were identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure, from SCD patients who did not meet the criteria. A random forest model accurately predicted organ failure up to six hours prior to onset, with a five-fold cross-validation accuracy of 94.57% (average sensitivity and specificity of 90.24% and 98.9% respectively).ConclusionsThis study demonstrates the viability of using machine learning to predict acute physiological deterioration heralded organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.

Machine‐learning algorithms for predicting hospital re‐admissions in sickle cell disease

2020 ◽  
Vol 192 (1) ◽  
pp. 158-170
Author(s):  
Arisha Patel ◽  
Kyra Gan ◽  
Andrew A. Li ◽  
Jeremy Weiss ◽  
Mehdi Nouraie ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sickle Cell Disease ◽  
Sickle Cell ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Cell Disease

scholarly journals Feasibility of Web-based Technology to Assess Adherence to Clinic Appointments in Youth With Sickle Cell Disease

2012 ◽  
Vol 34 (3) ◽  
pp. e93-e96 ◽  
Author(s):  
Avani C. Modi ◽  
Lori E. Crosby ◽  
Janelle Hines ◽  
Dennis Drotar ◽  
Monica J. Mitchell
Keyword(s):  
Sickle Cell Disease ◽  
Sickle Cell ◽  
Cell Disease ◽  
Web Based
Sign in / Sign up

Export Citation Format

Share Document