Rapid health data repository allocation using predictive machine learning

Abstract

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.

Artificial Intelligence and Blockchain Integration in Business: Trends from a Bibliometric-Content Analysis

“… Fusco et al ( 2020 ) A predictive model for intelligent storage allocation decision for health data using a machine learning classifier and a blockchain-based repository. Uddin et al ( 2020 ) Cluster 3. Secure transactions De-anonymizing the bitcoin blockchain through a supervised machine learning approach to identify bitcoin users involved in cybercriminal activities.…”

“…Finally, with the exponential growth in digital health data and the increase in the variety of data repositories, Uddin et al ( 2020 ) present a predictive model for intelligent storage allocation decision for health data, wherein a machine learning classifier maps the type of health data with the features of storage repositories before allocating that data to the blockchain-based repository. Similarly, Badré et al ( 2020 ) introduce the concept of shared decision making in integrated health services and propose a decentralized patient assignment system that uses machine learning, blockchain technology, and integer programming to improve the coordination among healthcare providers and patients.…”

“… • Blockchain • Integer programming • Machine learning Badré et al ( 2020 ) Health data repository A predictive model based on a machine learning classifier to help patients make data storage decisions in different types of blockchain-based data repository. • Blockchain • Machine learning Uddin et al ( 2020 ) 4 Intellectual property right (IPR) IPR management AI and blockchain can be used to manage the IPR lifecycle, wherein blockchain-based solutions can be used for notarization of IPR assets, whereas machine learning-based data processing pipeline can be used to compare the IPR assets among competitors. • Blockchain • Machine learning Ragot et al ( 2020 ) IPR management system New IPR can be registered on a blockchain platform that can empower eligible stakeholders to use IPR data from the blockchain network, wherein text mining can help to identify the type of IPR for retrieval.…”

A supervised learning model to identify the star potential of a basketball player

“…The prediction will only define the winning team regardless of the score. The prediction rate will be higher than the rate of naïve majority vote classifier that looked at previous games in the season and picked one with fewer losses as the winner (Uddin et al, 2020). It also aims to classify the position of one player based on his features.…”

Ensemble learning based functional independence ability estimator for pediatric brain tumor survivors

“…For example, the government manages electronic health records, health-care providers control electronic medical records, and patients directly manage their personal health records. 16 Numerous studies have analyzed health records. [15][16][17] Some have applied medical imaging data to brain tumor classification [18][19][20][21][22][23][24] and grading.…”