The Future of Machine Learning and AI in Healthcare Security

According to a 2017 report from ABI Research, the comprehensive healthcare damages from cybercrime will amount to greater than $1 trillion in 2018. Since healthcare firms want to avoid the huge costs of a breach (and all the ramifications related to HIPAA compliance and reputation), there is a huge incentive to adopt more intuitive and adaptive security protections.

Enter artificial intelligence – and, more specifically, machine learning.

These two concepts are very similar, so to clarify the definitions:

• Artificial intelligence – This branch of computer science is committed to create machines that are “smart”; i.e., that have the same characteristics as human intelligence. Another way to look at it comes from Stanford, which defines it as “the science of getting computers to act without being explicitly programmed.”
• Machine learning – This application of artificial intelligence, which is experiencing faster growth than any other part of AI, allows computers to pick up new information (“learn”) and refine their capabilities in response, without any code directing them to do so (per Expert System).

The future of the AI & machine learning market

To say that artificial intelligence (AI) and machine learning are growing rapidly within healthcare does not adequately capture the magnitude of the growth. A 2017 report from analyst Market Study Report forecasts that machine learning will grow to $10 billion by 2024.

One of its biggest areas will be diagnosis and medical imaging, which is expected to hit $2.5 billion (USD) by that same point. In 2016, the market size was $320 million, so to get to that total figure of $10B by 2024, the market will be skyrocketing at greater than a 38% compound annual growth rate (CAGR); during that same period, the diagnosis and imaging segment is projected to increase more than 40%.

The promise of vast machine learning expansion is even more impressive. MarketsandMarkets predicts that spending on machine learning will hit $8.81 billion in 2022, exploding from a 2017 scope of $1.41 billion, at a CAGR of 44.1%.

Beyond medical imaging and diagnostics, other primary areas of healthcare AI that will be expanding rapidly in the years to come are genomics, pharmaceutical discovery, and personal assistants.

The ABI research report noted that machine learning will not just cause ripples but large wakes; by 2021, it will have propelled the analytics, intelligence, and big data market to $96 billion.

How AI will grow

As noted by Intel senior principal engineer Ted Wilke, healthcare AI started as a method to make it easier to perform day-to-day tasks and manage big data. Now, the AI market will expand dramatically because big data is becoming ever larger, so storing and management of data must be optimally effective and efficient. Applications have become much more diverse and complex: improving treatment plans, performing genomic sequencing, and uncovering sophisticated patterns within medical images.

Furthermore, many healthcare entities are wading (or diving) into predictive clinical analytics. This branch of AI helps its users determine the percentage chance that a patient might experience a return of their illness, via analysis of patient records through increasingly strong algorithms.

Broadly speaking, applications for healthcare AI can be categorized as fulfilling needs for automated reasoning; but the demand for the less tantalizing search and classification applications is more prominent.

What is extraordinary about artificial intelligence is that it can utilize methods such as natural language processing and text analytics to make fast sense out of big data. Both medical researchers and clinicians can use these systems to find similitude between data as well as patterns. Reasoning capacity allows these platforms to advise security personnel of steps they may want to take.

How machine learning will grow

Machine learning will grow for some of the same reasons related to new innovations. The huge scope of data generation and technological progression will be key reasons businesses start to turn increasingly to machine learning, as indicated by MarketsandMarkets. Additionally, the market has strong expansion potential because more modern systems are implemented within healthcare and because the effort to make services and operations intelligent is becoming a more central point of focus.

The ABI team noted that machine learning will replace traditional AV, heuristics, and  signature-based systems. As that happens, security information and event management (SIEM) systems and protocols will become more sophisticated, fostering automatic threat discovery by incorporating analytics techniques such as machine learning.

The ABI researchers expect for deep learning algorithms (a type of machine learning and further evolution of task-specific algorithms) and user and entity behavior analytics, or UEBA (automatic threat discovery, incorporating analytics techniques such as machine learning, an evolution of rule-based systems), to blossom. Given this climate, providers of security solutions are starting to transition their offerings to incorporate deep learning, UEBA, and other machine learning methods.

Today, SIEM is considered a best-practice way to approach the threat landscape in a manner that can give the infrastructure of healthcare outfits the protection they need. SIEM programs pull in data from an organization’s infrastructural components across a complete spectrum (including network security elements such as antivirus and firewalls, as well as general software and hosting platforms). After collecting this data, this software aggregates log data, giving security teams access to a full monitoring log, along with critical insights. Security analytics dynamically allow the company to identify and mitigate any threats immediately, using real-time processing.

With the advent of the machine learning era, insider error will become a less common cause of compromise because the method is unsupervised. The log-centered approach of SIEM will be joined with additional UEBA programs – both isolating them from one another but also integrating their approaches and findings.

How healthcare can prepare for the AI & machine learning world

It is not necessary to adopt Silicon Valley systems to embrace these technologies. Instead, machine learning techniques can be leveraged by organizations to build custom AI big data analytics environments.

Many healthcare companies are approaching the AI field through incorporation of semantic data lakes, explained Albert Einstein College of Medicine professor Parsa Mirhaji, MD, PhD. The semantic approach is an upgrade from relational databases, which have very exact structural requirements. The relational method makes it necessary to have a pre-established, organized schematic strategy. Isolated data silos result.

Data lakes are collections of data in a wide variety of formats. Insights are derived by bringing together data without any known relationship by applying unique standardized identifiers to each. This capability is permitted by the incorporation of natural language processing within data lakes. All of these applications will require a HIPAA compliant database.

HIPAA-compliant AI infrastructure

Is your organization planning to implement more robust AI and machine learning systems? As always, healthcare systems must go beyond stopping data breaches to meet the standards and regulations of federal law. At Atlantic.Net, we are not only HIPAA and HITECH audited, but also SSAE 18 SOC 1 and SOC 2 certified. See our HIPAA Compliant Server Hosting.