HITInfrastructure

Networking News

Using Healthcare AI, Machine Learning for HIT Infrastructure

As the amount of data increases, organizations are looking to include healthcare AI and machine learning in their HIT infrastructure to process it.

healthcare AI

Source: Thinkstock

By Bill Kleyman

- The engine that is healthcare is getting some pretty cool upgrades. We know that there are technical innovations happening within the healthcare world, especially with HIT infrastructure, and we also know that there is a lot more data being created around patients and the systems they use.

However, unstructured data isn’t always useful and not always easy to quantify. This is why there are new solutions impacting backend process and vastly improving healthcare services. In following the market, I’ve been thoroughly impressed with the type of investments happening around healthcare innovation. Three areas have actually stuck out – artificial intelligence (AI), machine learning (ML), and natural language processing (NLP).

Artificial Intelligence

AI isn’t here to just help create new healthcare services. This technology is also here to improve healthcare efficiency. Accenture points out that key clinical health AI applications can potentially create $150 billion in annual savings for the United States healthcare economy by 2026. As their research indicates, acquisitions of AI startups are rapidly increasing while the health AI market is set to register an explosive CAGR of 40 percent through 2021. There are some really cool applications to these AI systems.

Just to give you an idea, these applications include:

  • Robot-assisted surgery
  • Virtual Nursing Assistants
  • Administrator Workflow Assistants
  • Fraud Detection
  • Dosage Error Reduction
  • Connected Machines
  • Preliminary Diagnosis

READ MORE: How Artificial Intelligence Can Shape Health IT Infrastructure

So, why invest in these kinds of solutions? Not only can they potentially provide powerful use-cases for healthcare, they can also fill critical gaps within healthcare. According to Accenture analysis, the physician shortage alone is expected to double in the next nine years. AI can potentially alleviate administrative and clinician burdens and help bring even more value from the healthcare process.

Machine Learning

Imagine a platform that helps empower clinicians around radiological images while leveraging AI and machine learning capabilities. Well, this is exactly what Microsoft and its ‘InnerEye’ research project is doing. Leveraging machine learning technology to build innovative tools for the automatic, quantitative analysis of three-dimensional radiological images. Project InnerEye turns radiological images into measuring devices.

“…We are pursuing AI so that we can empower every person and every institution that people build with tools of AI so that they can go on to solve the most pressing problems of our society and our economy,” stated Satya Nadella, at his keynote address at Microsoft IGNITE 2016. “That’s the pursuit.”

According to Microsoft, Project InnerEye develops machine learning techniques for the automatic delineation of tumors as well as healthy anatomy in 3D radiological images. This enables: 1. extraction of targeted radiomics measurements for quantitative radiology, 2. fast radiotherapy planning, 3. precise surgery planning and navigation.

The solution is designed to be used as a supplemental tool to assist medical experts. The cool part is that this architecture leverages cloud, Azure to be specific, and have cloud APIs designed to integrate with third-party software solutions.

READ MORE: Artificial Intelligence Adds Pressure to Health IT Networks

Potentially, this is the future – where cloud, AI, and machine learning all work together to help with analysis of medical imaging and deliver new kinds of healthcare services.

Natural Language Processing

Working with NLP solutions has been a fascinating. I’ve seen all sorts of new solutions emerge to help with business and even consumer challenges. For example, startups like theMind allow users to get truly unbiased opinions on everything. And, it’s all secure and anonymous. Furthermore, there’s a lot of application of NLP solutions within healthcare as well. To clarify, NLP leverages solutions like AI/ML to work with interactions between computers and human (natural) languages. Specifically, the goal is to process vast amounts of natural language data to deliver effective, concise results and information.

When it comes to healthcare investment, recent findings from Transparency Market Research shows that the global healthcare natural language processing market is expected to be worth $4.3 billion by the end of 2024 as compared to $936 million in 2015. Startups aside, large organizations are actively investing in NLP solutions. According to the research, IBM Corporation, Apple, Inc., and Microsoft Corporation emerged as the leading players due to ongoing investments in research and development of NLP technologies for the healthcare sector.

The cool part here is that there are already some really interesting use-cases. Recently, French researchers leveraged the power of NLP to help with monitoring, detecting, and preventing hospital-acquired infections (HAI) among patients. According to the solution, it helps with the detection of specific combinations of events and underlining relations between symptoms, treatments, drugs, reactions, and biological parameters can allow automatic systems to identify potential adverse events. Alerts could then be sent to risk management teams to help them identifying events that require immediate action and correction measures.

There are even more applications here as well. Being able to correlate data based on human interaction and speech can vastly simplify healthcare processes. Plus, these types of solutions allow you to work with patients in a variety of new areas. As a recent HealthITAnalytics.com article points out, this could be summarizing lengthy blocks of narrative text, such as a clinical note or academic journal article, by identifying key concepts or phrases present in the source material. Or, converting data in the other direction from machine-readable formats into natural language for reporting and educational purposes.

READ MORE: Machine Learning Fortifies Digital Transformation for Analytics

It’s an exciting time to be in the healthcare world. We’re seeing emerging technologies improve healthcare services and safe more lives. Still, some of these new technologies will take investment and time to learn. For example, NLP solutions might struggle a bit with acronyms commonly used by healthcare practitioners. And, as mentioned earlier, some of these new innovative solutions might be expensive and require advanced, customized, development.

However, without investing in new and innovative solutions, you won’t experience growth and market differentiation. When you incorporate the solutions we discussed, you’ll get the chance to create a self-operating healthcare engine that’s poised for growth and revolutionizing the services you deliver.

X

Sign up for our free newsletter covering the latest IT technology for Hospitals:

Our privacy policy

no, thanks

Continue to site...