Novel Visualization of Large Health Related Data Sets

2015 ◽  
Author(s):  
William E. Hammond ◽  
Vivian L. West ◽  
David Borland ◽  
Igor Akushevich ◽  
Eugenia M. Heinz
2015 ◽  
Author(s):  
William E. Hammond ◽  
Vivian West ◽  
David Borland ◽  
Igor Akushevich ◽  
Eugenia M. Heinz

2021 ◽  
pp. 002214652110281
Author(s):  
Bruce G. Link ◽  
San Juanita García

We identify a gap in health inequalities research that sociologists are particularly well situated to fill—an underrepresentation of research on the role advantaged groups play in creating inequalities. We name the process that creates the imbalance health-inequality diversions. We gathered evidence from awarded grants (349), major health-related data sets (7), research articles (324), and Healthy People policy recommendations. We assess whether the inequality-generating actions of advantaged groups are considered either directly by capturing their behaviors or indirectly by asking disadvantaged people about discrimination or exploitation from advantaged groups. We further assess whether there is a tendency to locate the problem in the person or group experiencing health inequalities. We find that diversions are prevalent across all steps of the research process. The diversion concept suggests new lines of sociological research to understand why diversions occur and how gaps in evidence concerning the role of the advantaged might be filled.


2022 ◽  
pp. 979-992
Author(s):  
Pavani Konagala

A large volume of data is stored electronically. It is very difficult to measure the total volume of that data. This large amount of data is coming from various sources such as stock exchange, which may generate terabytes of data every day, Facebook, which may take about one petabyte of storage, and internet archives, which may store up to two petabytes of data, etc. So, it is very difficult to manage that data using relational database management systems. With the massive data, reading and writing from and into the drive takes more time. So, the storage and analysis of this massive data has become a big problem. Big data gives the solution for these problems. It specifies the methods to store and analyze the large data sets. This chapter specifies a brief study of big data techniques to analyze these types of data. It includes a wide study of Hadoop characteristics, Hadoop architecture, advantages of big data and big data eco system. Further, this chapter includes a comprehensive study of Apache Hive for executing health-related data and deaths data of U.S. government.


Author(s):  
Pavani Konagala

A large volume of data is stored electronically. It is very difficult to measure the total volume of that data. This large amount of data is coming from various sources such as stock exchange, which may generate terabytes of data every day, Facebook, which may take about one petabyte of storage, and internet archives, which may store up to two petabytes of data, etc. So, it is very difficult to manage that data using relational database management systems. With the massive data, reading and writing from and into the drive takes more time. So, the storage and analysis of this massive data has become a big problem. Big data gives the solution for these problems. It specifies the methods to store and analyze the large data sets. This chapter specifies a brief study of big data techniques to analyze these types of data. It includes a wide study of Hadoop characteristics, Hadoop architecture, advantages of big data and big data eco system. Further, this chapter includes a comprehensive study of Apache Hive for executing health-related data and deaths data of U.S. government.


2014 ◽  
Author(s):  
William E. Hammond ◽  
Vivian West ◽  
David Borland ◽  
Igor Akushevich ◽  
Eugenia M. Heinz

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yahya Albalawi ◽  
Jim Buckley ◽  
Nikola S. Nikolov

AbstractThis paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.


2021 ◽  
Vol 13 (6) ◽  
pp. 3572
Author(s):  
Lavinia-Maria Pop ◽  
Magdalena Iorga ◽  
Iulia-Diana Muraru ◽  
Florin-Dumitru Petrariu

A busy schedule and demanding tasks challenge medical students to adjust their lifestyle and dietary habits. The aim of this study was to identify dietary habits and health-related behaviours among students. A number of 403 students (80.40% female, aged M = 21.21 ± 4.56) enrolled in a medical university provided answers to a questionnaire constructed especially for this research, which was divided into three parts: the first part collected socio-demographic, anthropometric, and medical data; the second part inquired about dietary habits, lifestyle, sleep, physical activity, water intake, and use of alcohol and cigarettes; and the third part collected information about nutrition-related data and the consumption of fruit, vegetables, meat, eggs, fish, and sweets. Data were analysed using SPSS v24. Students usually slept M = 6.71 ± 1.52 h/day, and one-third had self-imposed diet restrictions to control their weight. For both genders, the most important meal was lunch, and one-third of students had breakfast each morning. On average, the students consumed 1.64 ± 0.88 l of water per day and had 220 min of physical activity per week. Data about the consumption of fruit, vegetables, meat, eggs, fish, sweets, fast food, coffee, tea, alcohol, or carbohydrate drinks were presented. The results of our study proved that medical students have knowledge about how to maintain a healthy life and they practice it, which is important for their subsequent professional life.


2021 ◽  
Author(s):  
Ben Philip ◽  
Mohamed Abdelrazek ◽  
Alessio Bonti ◽  
Scott Barnett ◽  
John Grundy

UNSTRUCTURED Our objective is to better understand health-related data collection across different mHealth app categories. This would help in developing a health domain model for mHealth apps to facilitate app development and data sharing between these apps to improve user experience and reduce redundancy in data collection. We identified app categories listed in a curated library which was then used to explore the Google Play Store for health/medical apps that were then filtered using our inclusion criteria. We downloaded and analysed these apps using a script we developed around the popular AndroGuard tool. We analysed the use of Bluetooth peripherals and built-in sensors to understand how a given app collects/generates health data. We retrieved 3,251 applications meeting our criteria, and our analysis showed that only 10.7% of these apps requested permission for Bluetooth access. We found 50.9% of the Bluetooth Service UUIDs to be known in these apps, with the remainder being vendor specific. The most common health-related services using the known UUIDs were Heart Rate, Glucose and Body Composition. App permissions show the most used device module/sensor to be the camera (20.57%), closely followed by GPS (18.39%). Our findings are consistent with previous studies in that not many health apps were found to use built-in sensors or peripherals for collecting health data. The use of more peripherals and automated data collection along with integration with other apps could increase usability and convenience which would eventually also improve user experience and data reliability.


Author(s):  
Sotiris Diamantopoulos ◽  
Dimitris Karamitros ◽  
Luigi Romano ◽  
Luigi Coppolino ◽  
Vassilis Koutkias ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document