The Ransomware Menace
Open Access DepositedA Statistical Approach in Protecting US Healthcare Organizations from Cyber Threats
Ransomware attacks are rising at an alarming rate across hospitals in the US, though the factors underlying the differences between the contained incidents and those progressing to treatment disruptions remain inadequately explained. This paper aims to provide insights regarding the impact of clinical integration and architecture of the involved vendors, the type of breach itself, and patient performance metrics of hospitals on the impact of cyber-attacks. A pool of data from the U.S. Department of Health and Human Services (HHS) Office for Civil Rights (OCR) database was combined with Centers for Medicare & Medicaid Services (CMS) Hospital General Information (HGI) and Timely and Effective Care (TEC) data files.The study considers three research questions. First, the interaction model examines if clinical coordination can affect the relationship between system complexity and the level of a breach. Second, the classification model examines the type of breach that has the maximum correlation with the failure of containing the breach. Third, the predictive model examines if the addition of quality CMS factors reduces the latency of disruption disruptions. The results show that the effect of architecture complexity on the level of breach severity can be moderated by the level of coordination. The rate of containing the breach is over two times higher when there are multiple vendors and multiple systems compared to when there is only one system. The addition of information from the context of the hospital and CMS quality metrics helps in improving the accuracy of the results by over ten percent. The improved model has a variance in Area Under Precision-Recall Curve (AUPRC) of forty percent and a latency of less than six percent. AUPRC is a metric used to evaluate binary classification models especially those with imbalanced data. This research confirms the socio-technical framework of cyber risks in the healthcare sector. Cyber risks are the result of an interplay of the threat environment and the internal characteristics of the organization itself in terms of clinical coordination architecture and performance measurement. This research has been able to provide insights about the ability of models using internal characteristics to predict hospitals at risk and improve their level of readiness in this regard. This will allow improved cyber security planning and management.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.