ML-based cyber incident detection for Electronic Medical Record (EMR) systems

Abstract

An upward trend in cyber incidents across both U.K. and U.S. hospitals has been observed since 2015. Attacks range from identity theft to insurance fraud and extortion/blackmail. The Electronic Medical Record (EMR) systems used in hospitals are targeted due to the sensitivity of data within a healthcare setting. This work is motivated by the necessity to protect patient information and to

An Analysis of Integrating Machine Learning in Healthcare for Ensuring Confidentiality of the Electronic Records

“…Boddy et al discuss healthcare data confidentiality and specify that both the insider as well as outsider threats violate healthcare data confidentiality and results in patients' loss of trust in the healthcare service providers [45,57]. Statistics regarding healthcare data confidentiality [46] specify that there is a 63% increment in cyber-attacks from 2015 to 2016 against hospitals of the USA. Moreover, health data records have ten to twenty times higher selling value than credit card data in the online market.…”

“…Identification of relevant data with the characteristic of completeness and accuracy provides a strong base for a high quality ML model [69]. But because of data privacy policies, it is not always possible to find real data for research experiments [46]. Therefore the researchers use different tools such as Synthea [46] and CA technologies Datamaker [70] to generate synthetic data sets to train and validate ML models [71].…”

“…But because of data privacy policies, it is not always possible to find real data for research experiments [46]. Therefore the researchers use different tools such as Synthea [46] and CA technologies Datamaker [70] to generate synthetic data sets to train and validate ML models [71]. Similarly, for the present SLR, the researchers have selected either the data sets generated from the real healthcare environment as real data sets or produced synthetic data sets to conduct the experiments.…”

A Conceptual Redesign of a Modelling Language for Cyber Resiliency of Healthcare Systems

“…Healthcare overall appeared to have five different meanings. In 3 papers coincides with the term hospital [44][16] [17], in 6 papers with a form of a system, including medical cyber-physical systems, electronic medical records systems and healthcare information systems [14][45] [11][43][7] [30], in 3 papers as a healthcare critical infrastructure or a particular type (e.g. NHS) [45][7][18], in 2 papers addressed healthcare organizations in general [21][23] and 1 was focusing on healthcare information [12].…”

“…But validation and evaluation approaches for the assessment of resiliency plans and their resilience capability is limited [44][14][16][18] [12]. Restrictions in the form of time, security capabilities, actors' skills, responder's motivation, financial resources and heterogeneity among systems are also addressed [14][45][11][21][18] [30] showing the need for a holistic approach. The technological heterogeneity that introduces complexity associated with the healthcare context yields a technical conflict [7][23].…”