Across healthcare systems, the focus with AI has generally been on using new technology to improve the quality and delivery of patient care.  But behind the scenes, tech managers are tapping AI to help them battle a ubiquitous scourge: cybercrime.

According to a recent “Spotlight Report on Healthcare” from cyber security experts, Vectra, machine learning and AI can help detect hidden threat behaviors within an organization before a cybercriminal takes advantage of the weakness.

"Machine learning and AI can assist healthcare organizations in better securing networks, workloads and devices, and provide data security by analyzing behaviors across systems," said Jon Oltsik, senior principal analyst at Enterprise Strategy Group, in a statement accompanying the report. According to ESG research, "12 percent of enterprise organizations have already deployed AI-based security analytics extensively, and 27 percent have deployed AI-based security analytics on a limited basis. We expect these implementation trends will continue to gain.”

In addition, with new and old systems in place, gaps and policies and procedures may cause an influx in human errors. Experts also note that while the increase in medical Internet of Things (IoT) is beneficial for patients, it makes securing healthcare systems a challenge due to limited security controls around these devices.  By leveraging AI, hospitals can reduce the opportunities for human error.  

"Healthcare organizations struggle with managing legacy systems and medical devices that traditionally have weak security controls, yet both provide critical access to patient health information," said Chris Morales, head of security analytics at Vectra. "Improving visibility into network behavior enables healthcare organizations to manage risk of legacy systems and new technology they embrace.”

The Vectra healthcare report explored the behaviors and trends from 354 opt-in enterprise organizations in healthcare and eight other industries. From July to December 2018, Vectra monitored network traffic and collected metadata from more than 3 million workloads and devices.

Among other things, the report found that while many healthcare organizations have experienced ransomware attacks in recent years, ransomware threats were not as prevalent in the second half of 2018. It is still important, however, to catch ransomware attacks early, before files are encrypted and clinical operations are disrupted.