Operational Efficiencies and Simulated Performance of Big Data Analytics Platform over Billions of Patient Records of a Hospital System

Chrimes, Dillon; Moa, Belaid; Kuo, Mu-Hsing; Kushniruk, André

doi:10.25046/aj020104

Cited by 7 publications

(14 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a hospital system, the capacity to record patient data efficiently in the ADT is crucial to timely patient care and quality patient-care deliverables. Thus, the ADT system is often referred to as the source of truth for reporting operations of inpatient to outpatient and discharged (Chrimes et al, 2017b). A suitable analysis of ADT and DAD integrated data in this study shows many benefits of using big data technologies to produce high volumes while interactively applying new ways to query the data to find unknown correlations and trends.…”

Section: Data Emulation and Modelingmentioning

confidence: 96%

“…4. Data analysis: Data analysis or analytics is highly important for a successful BDA (Chrimes et al, 2017b). BDA complexity involves analytic algorithms to be programmed in that the computing time increases dramatically even with small increases in data volume.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Based on the design philosophy of simulation with multiple interactive components for end users to query data at extreme volumes within seconds, we constructed a dynamic platform with interfaced backend applications, such as Apache Phoenix, Spark, and Drill, linked to backend HBase over Hadoop Distributed File System (HDFS). With the Hadoop/MapReduce framework, the platform allowed users to easily analyze and visualize health Big Data (Chrimes et al, 2017b). The overall platform included four main components (shown in Figure 2): Figure 2.…”

Section: Platform Architecturementioning

confidence: 99%

“…Several of the open-source software were installed and configured to form the analytics platform (Chrimes et al, 2017b). The software stack formed is shown in Figure 3.…”

Section: Developing Toolsmentioning

confidence: 99%

“…It offers a low latency query engine and utilizes Zoo Keeper. As opposed to the master/slave architecture of Spark in which a driver is handling the execution of the Directed Acyclic Graph (DAG) on a given set of executors, the drillbits are loosely coupled and each can accept a query from the client (Chrimes et al, 2017b). To run Drill over a distributed mode, the user will need a ZooKeeper cluster continuously running.…”

Section: Developing Toolsmentioning

confidence: 99%

See 4 more Smart Citations

Simulations of Hadoop/MapReduce-Based Platform to Support its Usability of Big Data Analytics in Healthcare

Chrimes¹,

Zamani²,

Moa³

et al. 2018

AJTE

Self Cite

View full text Add to dashboard Cite

In many hospital systems, new technologies that influence patient data require extensive technical testing before implementation into production. Therefore, to implement, an existing High Performance Computing (HPC) Linux node clusters via WestGrid were used to represent a simulation of patient data benchmarked and cross-referenced with current metadata profiles in operational hospital systems at the Vancouver Island Health Authority (VIHA), Victoria, Canada. Over the tested cross-platform, the data were generated, indexed and stored over a Hadoop Distributed File System (HDFS) to noSQL database (HBase) that represented three billion patient records. The study objective to establish an interactive Big Data Platform (BDA) was successful implemented in that Hadoop/MapReduce technologies formed the framework of the platform distributed with HBase (key-value NoSQL database storage) and generated desired hospital-specific metadata at very extremely large volumes. In fact, the framework over generated HBase data files took a week or a month for one billion (10TB) and three billion (30TB), respectively. Further performance tests retrieved results from simulated patient records with Apache tools in Hadoop's ecosystem. At optimized iteration, HDFS ingestion with HBase exhibited sustained database integrity over hundreds of iterations; however, to complete the bulk loading via MapReduce to HBase required a month. Inconsistencies of MapReduce limited the capacity to generate/replicate data to HBase efficiently. Hospital system based on patient encounter database was very difficult and data profiles were fully representative of complex patient-to-hospital relationships. Our platform is important to lead discovery of useful big data technologies across multiple hospital systems.

show abstract

Section: Data Emulation and Modelingmentioning

confidence: 96%

Section: Literature Reviewmentioning

confidence: 99%

Section: Platform Architecturementioning

confidence: 99%

“…Several of the open-source software were installed and configured to form the analytics platform (Chrimes et al, 2017b). The software stack formed is shown in Figure 3.…”

Section: Developing Toolsmentioning

confidence: 99%

Section: Developing Toolsmentioning

confidence: 99%

See 3 more Smart Citations

Simulations of Hadoop/MapReduce-Based Platform to Support its Usability of Big Data Analytics in Healthcare

Chrimes¹,

Zamani²,

Moa³

et al. 2018

AJTE

Self Cite

View full text Add to dashboard Cite

show abstract

Role, Characteristics and Critical Success Factors of Big Data (BD): Implications for Marketing in Africa

Mohammed

Sulemana

Arko-Cole

2022

Digital Business in Africa

View full text Add to dashboard Cite

Big health data for elderly employees job performance of SOEs: visionary and enticing challenges

Qian

2023

Multimed Tools Appl

View full text Add to dashboard Cite

The method is providing and overview of the organization in the management perspective, within the health big data analysis, especially for the elderly employees, the organizations could sign the elderly employees within the right tasks, it reducing the costs by increasing the employees' job performance and organization performance. By addressing the importance role of big health data analytics (BDHA) in the healthcare system .moreover BDHA enables a patient's medical records to be searched in a dynamic, interactive manner. One billion records were made in two hours. Current clinical reporting compares large health data profiles and meta-big health data, giving health apps basic interfaces. A combination of Hadoop/MapReduce and HBase was used to generate the necessary hospital-specific large heath data. One billion (10TB) and three billion (30TB) HBase large health data files might be created in a week or a month using the concept. Apache Hadoop technologies tested simulated medical records. Inconsistencies reduced big health data. An encounter-centered big health database was difficult to set up due to the complicated medical system connections between big health data profiles. Associated with job performance such as the gender, current/past job positions and the health conditions are important. For genders the 66.36% of respondents in the experiments are females, 33.64 are males, majority of are healthy which are 66.97%, 30.58% are common geriatric disease, rest 2.45% are suffering from occupational disease; In terms of the current/past job positions, 20% of the respondents are working as accountant, followed by sales and management level. The Diagnostic and Statistical Manual, lists 157 distinct illnesses. Individuals may be diagnosed with one or more illnesses as a consequence of medical health professionals watching and analyzing their symptoms. It has been discovered that mental health issues have a negative impact on employees' job performance. For example, research on individuals with anxiety and depression has a direct impact on concentrations, decision-making process, and risk-taking behavior, which can be determined for job performance. Machine learning focuses on approaches that can be used to create accurate predictions about future characteristics based on previous training and post training. Principles such as job task and computational learning are crucial for machine learning algorithms that use a large amount of big health data.

show abstract

Operational Efficiencies and Simulated Performance of Big Data Analytics Platform over Billions of Patient Records of a Hospital System

Cited by 7 publications

References 49 publications

Simulations of Hadoop/MapReduce-Based Platform to Support its Usability of Big Data Analytics in Healthcare

Simulations of Hadoop/MapReduce-Based Platform to Support its Usability of Big Data Analytics in Healthcare

Role, Characteristics and Critical Success Factors of Big Data (BD): Implications for Marketing in Africa

Big health data for elderly employees job performance of SOEs: visionary and enticing challenges

Contact Info

Product

Resources

About