Rapid health data repository allocation using predictive machine learning
- Authors: Uddin, Ashraf , Stranieri, Andrew , Gondal, Iqbal , Balasubramanian, Venki
- Date: 2020
- Type: Text , Journal article
- Relation: Health Informatics Journal Vol. 26, no. 4 (2020), p. 3009-3036
- Full Text:
- Reviewed:
- Description: Health-related data is stored in a number of repositories that are managed and controlled by different entities. For instance, Electronic Health Records are usually administered by governments. Electronic Medical Records are typically controlled by health care providers, whereas Personal Health Records are managed directly by patients. Recently, Blockchain-based health record systems largely regulated by technology have emerged as another type of repository. Repositories for storing health data differ from one another based on cost, level of security and quality of performance. Not only has the type of repositories increased in recent years, but the quantum of health data to be stored has increased. For instance, the advent of wearable sensors that capture physiological signs has resulted in an exponential growth in digital health data. The increase in the types of repository and amount of data has driven a need for intelligent processes to select appropriate repositories as data is collected. However, the storage allocation decision is complex and nuanced. The challenges are exacerbated when health data are continuously streamed, as is the case with wearable sensors. Although patients are not always solely responsible for determining which repository should be used, they typically have some input into this decision. Patients can be expected to have idiosyncratic preferences regarding storage decisions depending on their unique contexts. In this paper, we propose a predictive model for the storage of health data that can meet patient needs and make storage decisions rapidly, in real-time, even with data streaming from wearable sensors. The model is built with a machine learning classifier that learns the mapping between characteristics of health data and features of storage repositories from a training set generated synthetically from correlations evident from small samples of experts. Results from the evaluation demonstrate the viability of the machine learning technique used. © The Author(s) 2020.
Dynamically recommending repositories for health data : a machine learning model
- Authors: Uddin, Md Ashraf , Stranieri, Andrew , Gondal, Iqbal , Balasubramanian, Venki
- Date: 2020
- Type: Text , Conference proceedings
- Relation: 2020 Australasian Computer Science Week Multiconference, ACSW 2020
- Full Text: false
- Reviewed:
- Description: Recently, a wide range of digital health record repositories has emerged. These include Electronic Health record managed by the government, Electronic Medical Record (EMR) managed by healthcare providers, Personal Health Record (PHR) managed directly by the patient and new Blockchain-based systems mainly managed by technologies. Health record repositories differ from one another on the level of security, privacy, and quality of services (QoS) they provide. Health data stored in these repositories also varies from patient to patient in sensitivity, and significance depending on medical, personal preference, and other factors. Decisions regarding which digital record repository is most appropriate for the storage of each data item at every point in time are complex and nuanced. The challenges are exacerbated with health data continuously streamed from wearable sensors. In this paper, we propose a recommendation model for health data storage that can accommodate patient preferences and make storage decisions rapidly, in real-time, even with streamed data. The model maps health data to be stored in the repositories. The mapping between health data features and characteristics of each repository is learned using a machine learning-based classifier mediated through clinical rules. Evaluation results demonstrate the model's feasibility. © 2020 ACM.
- Description: E1