Diagnosing internal illnesses using pervasive healthcare computing and neural networks

Bayraktar, Canan; Karan, Oğuz; Gümüşkaya, Halûk

doi:10.1016/j.procs.2010.12.097

Cited by 9 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another mobile health related system is proposed by Bayraktar et al (2011) that diagnoses internal illnesses. The authors acknowledge the fact that a lot of patients with internal diseases need to undergo many tests at hospitals, which it can be a time consuming and error prone process for patients and doctors respectively.…”

Section: Introductionmentioning

confidence: 99%

M-health: supporting automated diagnosis and electonic health records

Alepis

Lambrinidis

2013

SpringerPlus

View full text Add to dashboard Cite

BackgroundMobile technology has become a part of our everyday life. Mobile services are used in a wide variety of scientific areas including healthcare. As an intersection of computer supported technology and medicine, m-health is expected to bring higher quality in healthcare. A remedy to deter people from neglecting their health issues is providing further and targeted information, while this information is available on the main devices most people use on a regular basis, namely any station or a mobile phone connected to Internet, enabling access to their health status anytime and at any place.ResultsThe authors present a framework that is built based on mobile health and which, in addition, incorporates a module that is responsible for making diagnoses. To achieve this, we have applied the Analytical Hierarchical Process algorithm (AHP) on the test results, making the system able to infer the presence or not of an illness in the subject. Data to be processed emerge from the corresponding subjects’ electronic health records. Through the resulting system, doctors and health companies, which are involved in medical sciences, are offered a sophisticated, powerful tool that provides supplementary diagnoses about their clients by employing their laboratory medical tests.ConclusionsIn this paper a novel computer supported framework is presented, which is targeted basically in the scientific area of mobile health. The incorporated medical diagnosis module and the online presentation of medical tests results may not only facilitate doctors’ and medical agencies work and support healthcare in general, but also and most importantly can benefit users by having an analytical picture of their health status at any place and time. Perhaps one of the most challenging targets for this system to reach is to draw individuals’ attention and give them motives to be more concerned about their health.

show abstract

Section: Introductionmentioning

confidence: 99%

M-health: supporting automated diagnosis and electonic health records

Alepis

Lambrinidis

2013

SpringerPlus

View full text Add to dashboard Cite

show abstract

“…In "Diagnosing internal illnesses using pervasive healthcare computing and neural networks" (Bayraktar et al, 2011) (Talukder et al, 2020). With seven features and one output node, the model was implemented with success and enabled interesting conclusions once the author started to change the input values.…”

Section: Figure 2 A2 Neuron Ann From Input To Output Keras and Tensor...mentioning

confidence: 99%

Machine Learning Applied to Health Information Exchange

Miranda

Sousa

Duarte

et al. 2022

International Journal of Reliable and Quality E-Healthcare

View full text Add to dashboard Cite

The interest in Artificial Intelligence (AI) has grown in the last few years. The healthcare community is no exception. The present work is focused on the exchange of medical information, using the Health Level Seven (HL7) international standards. The main objective of the present work is to develop an AI model capable of inferring if for a given hour exists a peak in the number of exchanged messages. To accomplish that two different deep learning models were created, an Artificial Neural Networks (ANN) and Long-short Term Memory (LSTM). The intention is to observe which is capable to perceive the situation better considering the environment and features of a healthcare facility. Using laboratory-generated data was possible to simulate variations and differences in “traffic”. Comparing the LSTM vs ANN model, the first is capable of outputting peaks better but for considered mean values that do not happen. For the given context, predicting the peak is essential, so the LSTM is the right choice and uses fewer features that are good regarding performance.

show abstract

“…This work can also be extended to priority and inter body communication. In the paper [8], authors present a novel distributed pervasive healthcare computing and artificial neural networks for diagnosing internal illnesses and reporting healthcare results to the patients. Patients with internal diseases will have more test results and such reports are time consuming and error prone process for a doctor to diagnose.…”

Section: Fig 2 Corresponding Tree Topologymentioning

confidence: 99%

Energy Efficient Fuzzy Cost-Effective Routing for Transmission of Critical Physiological Parameters in Wireless Body Area Network under Emergency Scenarios

2019

IJITEE

View full text Add to dashboard Cite

Wireless body area networks with routing and collaborative fuzzy mechanisms for network analysis have become more efficient in today’s healthcare technology. In this article, a novelthreshold-based probability theory and fuzzy logic cost-effective routing technique is proposed that depends on location and residual energy attributes to reduce the overall energy consumption among the sensing nodes and increasing network lifetime. Attributes such as energy and distance are considered for generating if-then rules and membership functions. A fuzzy conditional reasoning is performed using interference mechanism and a defuzzification methodology is applied on the computed cost value to make an efficient choice. Mamdani-Fuzzy logic toolbox in matrix laboratory is used to evaluate the simulation performance of the proposed method with that of other existing conventional methods. From the results obtained, it is observed that for the different metrics, the proposed technique provides improvements in terms of energy efficiency, stability period and network lifetime.

show abstract

Diagnosing internal illnesses using pervasive healthcare computing and neural networks

Cited by 9 publications

References 10 publications

M-health: supporting automated diagnosis and electonic health records

M-health: supporting automated diagnosis and electonic health records

Machine Learning Applied to Health Information Exchange

Energy Efficient Fuzzy Cost-Effective Routing for Transmission of Critical Physiological Parameters in Wireless Body Area Network under Emergency Scenarios

Contact Info

Product

Resources

About