This content is part of the Essential Guide: Digital transformation technologies power CX makeovers
Evaluate Weigh the pros and cons of technologies, products and projects you are considering.

6 uses of AI in healthcare: Image analysis, analytics and more

AI in healthcare has the potential to improve patient care and staff efficiency by assisting with medical image analysis and diagnosis.

We surround ourselves with technology that is able to help us in our daily lives. The success of autonomous cars,...

advancements in clinical research and personal digital assistants has shown the incredible potential of technology and how far it has come in recent decades. Despite the progress that many other industries have made, healthcare is likely to be the one market where AI can truly have an impact that goes beyond convenience and positively affects human lives.

Today, more than ever, many technology vendors are making significant investments in AI to ensure they are able to offer products and services that can use the technology. Microsoft, Google, Apple, IBM and Amazon, to name a few, have all adopted and fully committed to AI and are already providing these services to consumers.

Anytime a new technology enters healthcare, there are a number of challenges it faces. Common setbacks of AI in healthcare include a lack of data exchange, regulatory compliance requirements and patient and provider adoption. AI has come across all of these issues, narrowing down the areas in which it can succeed.

One of the most popular uses of AI in healthcare is in IBM's smart cloud, where Watson lives. The Watson platform has been used in a number of disciplines within healthcare including with payers, oncology and patient risk assessment.

There are a number of other applications within healthcare where AI can deliver incredible value, but healthcare executives must evaluate and see if they can adopt some or all of them in order to begin their journey in the AI space. The following are six uses of AI in healthcare that are gaining steam.

1. Personal health virtual assistant

With most of today's U.S. adolescents, adults and seniors owning a smartphone, they are likely to have access to an intelligent personal virtual assistant on their device. The likes of Cortana, Siri and Google Assistant are backed by powerful systems with strong AI capabilities. These systems have the potential to provide tremendous value when combined with healthcare apps.

Healthcare apps can be used to deliver medication alerts, patient education material and human-like interactions to gauge a patient's current mental state. The application of AI in the form of a personal assistant can have an incredible impact on monitoring and assisting patients with some of their needs when clinical personnel are not available.

2. Advanced analytics and research

The uses of AI in healthcare do not stop at understanding human commands and knowing what type of response is needed. For example, AI has been used in many advanced use cases in oncology to help detect abnormalities in X-rays and MRIs, in genomics to perform complex processing and in precision medicine to provide assistance in creating highly customized treatments for individual patients.

In the example of IBM Watson, the AI has successfully applied its capabilities to process structured and unstructured patient data. In the field of oncology, IBM Watson can provide evidence-based treatment recommendations for cancer patients.             

3. Personal life coach

Healthcare providers who treat patients with chronic diseases recognize the importance of maintaining contact with their patients outside of the exam room. Several hospitals have life coaching services as part of their overall care, but the cost of such services compared to the current shrinking reimbursements makes it difficult to sustain such programs.

However, with today's powerful AI capabilities and mobile apps, patients can receive feedback on a number of data elements captured on their phone or wearable devices. Whether it relates to medication adherence or is simply a motivational voice that encourages fitness activities and healthy habits, AI as a personal life coach creates a customized experience for each individual patient and offers proactive alerts that can be sent back to physicians.             

4. Healthcare bots

One of the areas of AI that is beginning to gain adoption is in the field of customer service, and healthcare bots are likely to be available soon as part of what healthcare providers offer. A bot is an AI application patients can interact with through a chat window on a website or via telephone to receive help with their requests. Bots can be used in situations such as scheduling follow-up appointments with a patient's provider online. Other examples include when a bot helps a patient with their medication or medical billing needs. These uses of AI in healthcare improve customer service; offer 24/7 assistance for basic requests, such as scheduling, billing and other clinical requests; and reduce the overall administrative costs for hospitals.

5. Medical imaging analysis and diagnosis assistance

One of the most valuable uses of AI in healthcare is in radiology. It can assist in the diagnostic processes by analyzing many of the medical images such as MRIs, X-rays and CT scans and providing feedback on what it can detect that the human eye may miss.

6. Dictation assistance with NLP

In order to help reduce the time spent by health professionals capturing documentation, natural language processing extracts data from dictated notes and enters the information into the EHR. Another use of NLP that has been recently is around the analysis of existing clinical documentation. Modern NLP systems are able to sort through the existing content of the charts and highlight the relevant data for the clinical team.   

While healthcare is not ready to fully trust AI to independently diagnose patient diseases, advancements in machine learning and big data have contributed to healthcare by assisting in processing data and discovery insights much faster than humans can. Working alongside experienced clinicians, AI is likely to continue to be the current course for many healthcare organizations for some time. Until we can prove that AI has what it takes to accurately diagnose patients, the expansion of its current use in healthcare is likely to be a careful and well-planned process.

But by adopting uses of AI in healthcare, hospitals can deliver on a number of key goals such as improving patient outcomes and increasing staff efficiency. Over time, more innovations in AI will drive its adoption further.

Next Steps

To treat behavioral health, balance technology and human interaction

Corporations, academia respond to White House request for AI development

Virtual assistants can help improve patient engagement

AI applications often fall short of expectations

Dig Deeper on Health care business intelligence systems

Join the conversation


Send me notifications when other members comment.

Please create a username to comment.

Which use of AI in healthcare would be the most beneficial for your hospital or practice?
These uses of AI would make a great difference for sure! Some of the functions, such as analysis, research and assistance are already in use and will only become more advanced. What is an even more interesting question is what else can we use these functions for? There are many predictions for the use of AI and robots.
Some of our SearchHealthIT staff just got back from the HIMSS conference, and it sounds like AI has some potential for cybersecurity -- for example, using AI algorithms to learn near malware attack patterns.
Yes, Netrolix the first SD-WAN provider to leverage machine learning and AI to just what you described. I'm excited about this technology, especially for healthcare provider organizations.
AI in healthcare for engagement is an area of great interest. However, payors and providers alike should take time to learn what has or has not worked in the consumer world. That is what are the limitations of a chatbot solely utilizing FAQ'S or knowledge base. We all talk about Siri, Alexa etc. but are they really fully conversational.
Fair point about Siri. My kids will ask detailed NFL questions to Siri and then they don't understand why Siri can't come up with an answer. At this point, I would be uncomfortable asking a virtual assistant a semi-urgent medical question not because the idea of the assistant is bad, but because I wouldn't trust the answer. 
It's great to see AI more frequently adopted in the healthcare space. Obviously huge benefits for both healthcare professionals and their patients. It's important to consider the infrastructure behind it though and how this high tech adoption affects the IT behind the scenes.

Leaning out waste and inefficiencies in the delivery of hospital-based patient care, estimated by the Institute of Medicine in 2009 to account for over $200 billion in non-value added friction that can now be addressed by emerging "hospital command operations center - think NASA" cognitive and interoperable IoT platform.

Commercialized last year and in early deployment in a Texas-based IDN that can streamline and improve operational efficiencies.


Orders of magnitude more affordable, and much faster to implement it leapfrogs legacy RFID tracking systems that connect “Things” but lack analytics to revolutionize decision making and harness the power of big data and analytics.        


Interoperable across all existing BLE and Bluetooth enabled RFID - RTLS systems and with enterprise grade beacons and gateways, for location, temperature, relative humidity, geofencing and, acceleration allows the hospital to connect all of their, patients, staff, and visitors people to make all of their unconnected” assets smart and connected.  

The IoT Dashboard - provides real-time visibility into the precise location and status of all connected physical assets and staff, patients and visitors with alerts and triggers that provide “command center” visibility helping to improve the quality, and the safety of the patient experience while reducing cost.

AI-based networks have vast potential in healthcare imaging. We have also seen that the system could distinguish between viral and bacterial pneumonia in children by examining X-rays. While viral pneumonia may require no treatment, a patient with bacterial pneumonia requires prompt antibiotic treatment to prevent serious complications of the disease.
“We’re seeing a variety of medical fields where artificial intelligence is being used more and more,” as per everydayhealth. “I think it’s a very exciting time for the field of artificial intelligence and its applications in medicine.”