Predicting Increased Blood Pressure Using Machine Learning

Golino, Hudson; Amaral, Liliany Souza de Brito; Duarte, Stênio Fernando Pimentel; Gomes, Cristiano Mauro Assis; Soares, Telma de Jesus; Reis, Luciana Araújo dos; Santos, Joselito

doi:10.1155/2014/637635

Cited by 87 publications

(60 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…arterial hypertension [12,13], coronary artery disease [14,15] or pulmonary hypertension [16] -metabolic diseases, e.g. diabetes [17] -neoplasms [5] -AIDS [18] These models allow for automatic extraction of selected aspects or features that are supportive to physicians in making decisions regarding the applied therapy.…”

Section: Computational Methods For Models Developmentmentioning

confidence: 99%

“…Among the computational methods used for developing models of disease progression and therapy effects, the following principal groups of methods can be distinguished: -regression methods [10,17,24,25] -supervised learning methods [10,12,15,17] -unsupervised learning methods [11,13] -Markov Decision Process (MDP)-based methods [16,23] -Monte-Carlo methods [18] The first group of methods, i.e. regression-based prediction, roughly speaking relies on fitting a multidimensional function h(x), called a hypothesis, onto a given dataset, so that its values are as close as possible to the values in the dataset within a specific function form.…”

Section: Computational Methods For Models Developmentmentioning

confidence: 99%

See 1 more Smart Citation

13. From telemedicine to modeling and proactive medicine

Czekierda¹,

Gackowski²,

Konieczny³

et al. 2015

Simulations in Medicine

View full text Add to dashboard Cite

Contemporary healthcare delivers vast amounts of data. Telemedical systems contribute considerably to this, broadening the spectrum of available information greatly to include: -general medical and social profiles -history of previous therapies -laboratory and imaging examination results -records of everyday activities of patients and prescribed rehabilitation -records of food calories and times of meals -basic body parameters such as blood pressure, heart rate, body weight, temperature, blood glucose level, etc. -records of drug intakeThe sensing and monitoring of our life activity is going to be pervasive [1]. It will be a source of very valuable information which may considerably improve healthcare operation leading to personalized and proactive medicine, currently perceived as a very promising research area. At the same time demand for healthcare will become more and more widespread due to commonly observed trends: -better living conditions (including medical care) and civilization progress mean that people live longer than before. An ageing population is, however, at greater risk of cognitive impairment and frailty -chronic diseases like obesity and diabetes affect a considerable percentage of the population in highly developed countries -intensive and successful promotion of a healthy lifestyle and awareness of the importance of self-management of health and diseases Efficient utilization of this information requires employing advanced ICT technologies such as big data processing, machine learning, cognitive computing, predictive analytics etc. One of the interesting areas of medical data processing is modeling of selected aspects of human body behavior, supporting medical diagnoses and proactive treatment. This chapter presents how existing telemedical systems may contribute to this vision of future medicine. In Section 13.2 the traditional model of healthcare supported

show abstract

Section: Computational Methods For Models Developmentmentioning

confidence: 99%

Section: Computational Methods For Models Developmentmentioning

confidence: 99%

13. From telemedicine to modeling and proactive medicine

Czekierda¹,

Gackowski²,

Konieczny³

et al. 2015

Simulations in Medicine

View full text Add to dashboard Cite

show abstract

“…In this paper we use the time window model on the two features sleep time and blood pressure. It increases the accuracy of the classification [5]. The prediction steps are as follows: 1) Establish a set of formatted data files and read data from files.…”

Section: Logistic Based On Time Windowmentioning

confidence: 99%

Medical health data analysis based on Spark Mllib

Xiao¹,

Shi²

2016

Proceedings of the 2016 International Conference on Artificial Intelligence and Engineering Applications

View full text Add to dashboard Cite

Abstract. In recent years, health and disease prediction has become an important part of medical wisdom, and has attracted more and more attention. At this stage, the prediction of health care mainly relies on the medical health records data. For predicting results, it is only in view of the disease or not. At present, for the lack of adaptability and limitations of the data feature selection, in this paper we use the existing health records data and available life habit data, combined with the current popular Spark machine learning computing platform, and establish a multi-classification model, which can provide a reasonable prediction and evaluation. This design has a certain degree of accuracy and efficiency and it has a certain use value.

show abstract

“…Fat people, with BMI exceeding 30 kg/mm 2 , have higher probability in gaining high blood pressure (hypertension) because their hearts need to provide more nutrients and oxygen to body tissues. Golino et al [11] carried out a study to predict the blood pressure by machine learning method and gave a conclusion that body mass index, waist circumference, and waist-hip ratio have the correlated relationship with the heart diseases, such as hypertension and cardiovascular diseases.…”

Section: Bmimentioning

confidence: 99%

Predicting Systolic Blood Pressure Using Machine Learning

Pang

Kwong³

2014

7th International Conference on Information and Automation for Sustainability

View full text Add to dashboard Cite

In this paper, a new study based on machine learning technique, specifically artificial neural network, is investigated to predict the systolic blood pressure by correlated variables (BMI, age, exercise, alcohol, smoke level etc.). The raw data are split into two parts, 80% for training the machine and the remaining 20% for testing the performance. Two neural network algorithms, back-propagation neural network and radial basis function network, are used to construct and validate the prediction system. Based on a database with 498 people, the probabilities of the absolute difference between the measured and predicted value of systolic blood pressure under 10mm Hg are 51.9% for men and 52.5% for women using the backpropagation neural network. With the same input variables and network status, the corresponding results based on the radial basis function network are 51.8% and 49.9% for men and women respectively. This novel method of predicting systolic blood pressure contributes to giving early warnings to young and middle-aged people who may not take regular blood pressure measurements. Also, as it is known an isolated blood pressure measurement is sometimes not very accurate due to the daily fluctuation, our predictor can provide another reference value to the medical staff. Our experimental result shows that artificial neural networks are suitable for modeling and predicting systolic blood pressure.

show abstract

Predicting Increased Blood Pressure Using Machine Learning

Cited by 87 publications

References 30 publications

13. From telemedicine to modeling and proactive medicine

13. From telemedicine to modeling and proactive medicine

Medical health data analysis based on Spark Mllib

Predicting Systolic Blood Pressure Using Machine Learning

Contact Info

Product

Resources

About