scholarly journals Machine Learning-Based HIV Risk Estimation Using Incidence Rate Ratios

2021 ◽  
Vol 3 ◽  
Author(s):  
Oliver Haas ◽  
Andreas Maier ◽  
Eva Rothgang
Keyword(s):  
Machine Learning ◽  
Incidence Rate ◽  
Clinical Data ◽  
Hiv Risk ◽  
Point Of Care ◽  
Risk Estimation ◽  
Expert Opinions ◽  
Point Of Care Diagnostics ◽  
Wide Range ◽  
Hiv Aids

HIV/AIDS is an ongoing global pandemic, with an estimated 39 million infected worldwide. Early detection is anticipated to help improve outcomes and prevent further infections. Point-of-care diagnostics make HIV/AIDS diagnoses available both earlier and to a broader population. Wide-spread and automated HIV risk estimation can offer objective guidance. This supports providers in making an informed decision when considering patients with high HIV risk for HIV testing or pre-exposure prophylaxis (PrEP). We propose a novel machine learning method that allows providers to use the data from a patient's previous stays at the clinic to estimate their HIV risk. All features available in the clinical data are considered, making the set of features objective and independent of expert opinions. The proposed method builds on association rules that are derived from the data. The incidence rate ratio (IRR) is determined for each rule. Given a new patient, the mean IRR of all applicable rules is used to estimate their HIV risk. The method was tested and validated on the publicly available clinical database MIMIC-IV, which consists of around 525,000 hospital stays that included a stay at the intensive care unit or emergency department. We evaluated the method using the area under the receiver operating characteristic curve (AUC). The best performance with an AUC of 0.88 was achieved with a model consisting of 53 rules. A threshold value of 0.66 leads to a sensitivity of 98% and a specificity of 53%. The rules were grouped into drug abuse, psychological illnesses (e.g., PTSD), previously known associations (e.g., pulmonary diseases), and new associations (e.g., certain diagnostic procedures). In conclusion, we propose a novel HIV risk estimation method that builds on existing clinical data. It incorporates a wide range of features, leading to a model that is independent of expert opinions. It supports providers in making informed decisions in the point-of-care diagnostics process by estimating a patient's HIV risk.

scholarly journals 'All In One' SARS-CoV-2 variant recognition platform: Machine learning-enabled point of care diagnostics

2022 ◽  
pp. 100105
Author(s):  
Duygu Beduk ◽  
José Ilton de Oliveira Filho ◽  
Tutku Beduk ◽  
Duygu Harmanci ◽  
Figen Zihnioglu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Point Of Care ◽  
Point Of Care Diagnostics

Fabrication Techniques for Production of Thermoplastic-Based Microfluidics Devices

2016 ◽  
Vol 04 (03) ◽  
pp. 1640016 ◽  
Author(s):  
Zhenfeng Wang
Keyword(s):  
Point Of Care ◽  
Emerging Market ◽  
Science Research ◽  
Polymer Materials ◽  
Microfluidic Chips ◽  
Face Lift ◽  
Point Of Care Diagnostics ◽  
Wide Range ◽  
The Face ◽  
Micro Tooling

Microfluidics is a multidisciplinary technology which enables the face-lift crossing a wide range of applications such as life science research, point-of-care diagnostics and personal medicine. Polymer materials, especially thermoplastics, are dominating this emerging market due to the low material cost and the ease of mass production. This paper reviews the major fabrication technologies for making polymer, especially thermoplastic microfluidic chips, such as micro tooling, injection molding, bonding and surface treatment. The paper also summarizes the key challenges in fulfilling the needs of next generation microfluidic products.

scholarly journals Self-Powered Portable Electronic Reader for Point-of-Care Amperometric Measurements

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3715 ◽  
Author(s):  
Yaiza Montes-Cebrián ◽  
Albert Álvarez-Carulla ◽  
Jordi Colomer-Farrarons ◽  
Manel Puig-Vidal ◽  
Pere Ll. Miribel-Català
Keyword(s):  
Low Power ◽  
Point Of Care ◽  
Power Source ◽  
Laboratory Equipment ◽  
Fuel Concentration ◽  
Point Of Care Diagnostics ◽  
External Power Source ◽  
Wide Range ◽  
External Power ◽  
Self Powered

In this work, we present a self-powered electronic reader (e-reader) for point-of-care diagnostics based on the use of a fuel cell (FC) which works as a power source and as a sensor. The self-powered e-reader extracts the energy from the FC to supply the electronic components concomitantly, while performing the detection of the fuel concentration. The designed electronics rely on straightforward standards for low power consumption, resulting in a robust and low power device without needing an external power source. Besides, the custom electronic instrumentation platform can process and display fuel concentration without requiring any type of laboratory equipment. In this study, we present the electronics system in detail and describe all modules that make up the system. Furthermore, we validate the device’s operation with different emulated FCs and sensors presented in the literature. The e-reader can be adjusted to numerous current ranges up to 3 mA, with a 13 nA resolution and an uncertainty of 1.8%. Besides, it only consumes 900 µW in the low power mode of operation, and it can operate with a minimum voltage of 330 mV. This concept can be extended to a wide range of fields, from biomedical to environmental applications.

scholarly journals Nanozymes in Point-of-Care Diagnosis: An Emerging Futuristic Approach for Biosensing

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Bhaskar Das ◽  
Javier Lou Franco ◽  
Natasha Logan ◽  
Paramasivan Balasubramanian ◽  
Moon Il Kim ◽  
...  
Keyword(s):  
Surface Chemistry ◽  
Point Of Care ◽  
Low Cost ◽  
Metal Organic Framework ◽  
World Health ◽  
Point Of Care Diagnostics ◽  
Enzyme Mimicking ◽  
Wide Range ◽  
Metal Metal

AbstractNanomaterial-based artificial enzymes (or nanozymes) have attracted great attention in the past few years owing to their capability not only to mimic functionality but also to overcome the inherent drawbacks of the natural enzymes. Numerous advantages of nanozymes such as diverse enzyme-mimicking activities, low cost, high stability, robustness, unique surface chemistry, and ease of surface tunability and biocompatibility have allowed their integration in a wide range of biosensing applications. Several metal, metal oxide, metal–organic framework-based nanozymes have been exploited for the development of biosensing systems, which present the potential for point-of-care analysis. To highlight recent progress in the field, in this review, more than 260 research articles are discussed systematically with suitable recent examples, elucidating the role of nanozymes to reinforce, miniaturize, and improve the performance of point-of-care diagnostics addressing the ASSURED (affordable, sensitive, specific, user-friendly, rapid and robust, equipment-free and deliverable to the end user) criteria formulated by World Health Organization. The review reveals that many biosensing strategies such as electrochemical, colorimetric, fluorescent, and immunological sensors required to achieve the ASSURED standards can be implemented by using enzyme-mimicking activities of nanomaterials as signal producing components. However, basic system functionality is still lacking. Since the enzyme-mimicking properties of the nanomaterials are dictated by their size, shape, composition, surface charge, surface chemistry as well as external parameters such as pH or temperature, these factors play a crucial role in the design and function of nanozyme-based point-of-care diagnostics. Therefore, it requires a deliberate exertion to integrate various parameters for truly ASSURED solutions to be realized. This review also discusses possible limitations and research gaps to provide readers a brief scenario of the emerging role of nanozymes in state-of-the-art POC diagnosis system development for futuristic biosensing applications.

scholarly journals Thin Flexible Lab-on-a-Film for Impedimetric Sensing in Biomedical Applications

2021 ◽  
Author(s):  
Amina Farooq ◽  
Fezan Hayat ◽  
Sobia Zafar ◽  
Nauman Zafar Butt
Keyword(s):  
Bond Strength ◽  
Signal To Noise Ratio ◽  
Point Of Care ◽  
Flexible Substrate ◽  
Pulse Amplitude ◽  
Medical Diagnostics ◽  
Design Guidelines ◽  
Covalent Crosslinking ◽  
Point Of Care Diagnostics ◽  
Wide Range

Abstract Microfluidic cytometers based on coulter principle have recently shown a great potential for point of care biosensors for medical diagnostics. Here, we explore the design of an impedimetric microfluidic cytometer on flexible substrate. Two coplanar microfluidic geometries are compared to highlight the sensitivity of the device to the microelectrode positions relative to the detection volume. We show that the microelectrodes surface area and the geometry of the sensing volume for the cells strongly influence the output response of the sensor. Reducing the sensing volume decreases the pulse width but increases the overall pulse amplitude with an enhanced signal-to-noise ratio (~max. SNR=38.78dB). For the proposed design, the SNR was adequate to enable good detection and differentiation of 10 µm diameter polystyrene beads and leukemia cells (~6-21 µm). Also, a systematic approach for irreversible & strong bond strength between the thin flexible surfaces that make up the biochip is explored in this work. We observed the changes in surface wettability due to various methods of surface treatment can be a valuable metric for determining bond strength. We observed permanent bonding between microelectrode defined polypropylene surface and microchannel carved PDMS due to polar/silanol groups formed by plasma treatment and consequent covalent crosslinking by amine groups. These experimental insights provide valuable design guidelines for enhancing the sensitivity of coulter based flexible lab-on-a-chip devices which have a wide range of applications in point of care diagnostics.

scholarly journals The Burden of HIV/AIDS in Ethiopia from 1990 to 2016: Evidence from the Global Burden of Diseases 2016 Study

1970 ◽  
Vol 29 (1) ◽  
Author(s):  
Amare Deribew ◽  
Sibhatu Biadgilign ◽  
Kebede Deribe ◽  
Tariku Dejene ◽  
Gizachew Assefa Tessema ◽  
...  
Keyword(s):  
Mortality Rate ◽  
United Nations ◽  
Incidence Rate ◽  
Global Burden ◽  
Life Years ◽  
Incidence And Mortality ◽  
Wide Range ◽  
Global Burden Of Diseases ◽  
Burden Of Diseases ◽  
Hiv Aids

BACKGROUND: The burden of HIV/AIDS in Ethiopia has not been comprehensively assessed over the last two decades. In this study, we used the 2016 Global Burden of Diseases, Injuries and Risk factors (GBD) data to analyze the incidence, prevalence, mortality and Disability-adjusted Life Years Lost (DALY) rates of Human Immunodeficiency Virus / Acquired Immune Deficiency Syndrome (HIV/AIDS) in Ethiopia over the last 26 years.METHODS: The GBD 2016 used a wide range of data source for Ethiopia such as verbal autopsy (VA), surveys, reports of the Federal Ministry of Health and the United Nations (UN) and published scientific articles. The modified United Nations Programme on HIV/AIDS (UNAIDS) Spectrum model was used to estimate the incidence and mortality rates for HIV/AIDS.RESULTS: In 2016, an estimated 36,990 new HIV infections (95% uncertainty interval [UI]: 8775-80262), 670,906 prevalent HIV cases (95% UI: 568,268-798,970) and 19,999 HIV deaths (95% UI:16426-24412) occurred in Ethiopia. The HIV/AIDS incidence rate peaked in 1995 and declined by 6.3% annually for both sexes with a total reduction of 77% between 1990 and 2016. The annualized HIV/AIDS mortality rate reduction during 1990 to 2016 for both sexes was 0.4%.CONCLUSIONS: Ethiopia has achieved the 50% reduction of the incidence rate of HIV/AIDS based on the Millennium Development Goals (MDGs) target. However, the decline in HIV/AIDS mortality rate has been comparatively slow. The country should strengthen the HIV/AIDS detection and treatment programs at community level to achieve its targets during the Sustainable Development Program (SDGs)-era. 

Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using DFT and Machine Learning

2018 ◽  
Author(s):  
Sherif Tawfik ◽  
Olexandr Isayev ◽  
Catherine Stampfl ◽  
Joseph Shapter ◽  
David Winkler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Band Gap ◽  
Density Functional ◽  
2D Materials ◽  
Van Der Waals ◽  
Building Blocks ◽  
Machine Learning Techniques ◽  
Interlayer Distance ◽  
Computational Screening ◽  
Wide Range

Materials constructed from different van der Waals two-dimensional (2D) heterostructures offer a wide range of benefits, but these systems have been little studied because of their experimental and computational complextiy, and because of the very large number of possible combinations of 2D building blocks. The simulation of the interface between two different 2D materials is computationally challenging due to the lattice mismatch problem, which sometimes necessitates the creation of very large simulation cells for performing density-functional theory (DFT) calculations. Here we use a combination of DFT, linear regression and machine learning techniques in order to rapidly determine the interlayer distance between two different 2D heterostructures that are stacked in a bilayer heterostructure, as well as the band gap of the bilayer. Our work provides an excellent proof of concept by quickly and accurately predicting a structural property (the interlayer distance) and an electronic property (the band gap) for a large number of hybrid 2D materials. This work paves the way for rapid computational screening of the vast parameter space of van der Waals heterostructures to identify new hybrid materials with useful and interesting properties.

COVID-19 Outbreak Prediction with Machine Learning

2020 ◽  
Author(s):  
Sina Faizollahzadeh Ardabili ◽  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Filip Ferdinand ◽  
Annamaria R. Varkonyi-Koczy ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Fuzzy Inference ◽  
Control Measures ◽  
Future Research ◽  
Complex Nature ◽  
Inference System ◽  
Wide Range ◽  
Standard Models ◽  
High Level

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to SIR and SEIR models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. Paper further suggests that real novelty in outbreak prediction can be realized through integrating machine learning and SEIR models.

Intelligent Techniques Analysis for Glycosylation Site Prediction

2021 ◽  
Vol 15 ◽  
Author(s):  
Alhassan Alkuhlani ◽  
Walaa Gad ◽  
Mohamed Roushdy ◽  
Abdel-Badeeh M. Salem
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Cell Interaction ◽  
Glycosylation Site ◽  
Machine Learning Classification ◽  
Site Prediction ◽  
Glycosylation Sites ◽  
Wide Range ◽  
Feature Extraction And Selection ◽  
Computational Intelligent

Background: Glycosylation is one of the most common post-translation modifications (PTMs) in organism cells. It plays important roles in several biological processes including cell-cell interaction, protein folding, antigen’s recognition, and immune response. In addition, glycosylation is associated with many human diseases such as cancer, diabetes and coronaviruses. The experimental techniques for identifying glycosylation sites are time-consuming, extensive laboratory work, and expensive. Therefore, computational intelligence techniques are becoming very important for glycosylation site prediction. Objective: This paper is a theoretical discussion of the technical aspects of the biotechnological (e.g., using artificial intelligence and machine learning) to digital bioinformatics research and intelligent biocomputing. The computational intelligent techniques have shown efficient results for predicting N-linked, O-linked and C-linked glycosylation sites. In the last two decades, many studies have been conducted for glycosylation site prediction using these techniques. In this paper, we analyze and compare a wide range of intelligent techniques of these studies from multiple aspects. The current challenges and difficulties facing the software developers and knowledge engineers for predicting glycosylation sites are also included. Method: The comparison between these different studies is introduced including many criteria such as databases, feature extraction and selection, machine learning classification methods, evaluation measures and the performance results. Results and conclusions: Many challenges and problems are presented. Consequently, more efforts are needed to get more accurate prediction models for the three basic types of glycosylation sites.

Sign in / Sign up

Export Citation Format

Share Document