12 ways AI will revolutionize healthcare in the next year
AI Slide 0.jpg
Expectations are high for the impact that artificial intelligence can play in healthcare, but most experts admit that the industry is still early in the process of researching one-off uses for AI in healthcare settings. Still, many predict that many opportunities will soon emerge to take full advantage of advanced computing technologies.

Recently, faculty members of Partners HealthCare ranked artificial intelligence-enabled technologies that will have the greatest impact on medicine in the next 12 months. More than 60 in-person and telephone interviews were conducted with Partners HealthCare faculty to nominate the breakthrough innovations. To be considered for the annual ranking, nominated healthcare innovations had to have strong potential for significant clinical impact and patient benefit in comparison to current medical practices, as well as be on the market by 2020.
Reimagining medical imaging
Radiology-CROP.jpg
Researchers are using AI-based approaches to increase the power of mammography, transforming it to a more targeted tool for assessing breast cancer risk. For example, a team in Massachusetts is leveraging machine learning in multiple ways to improve breast cancer screening. The researchers developed an AI-based method, now in clinical use at a large hospital for slightly more than a year that can automatically determine breast density using mammograms.
Improving predictions of suicide risk
AI Slide 2.jpg
Researchers in Washington, Virginia and other states, as well as teams based at major social media companies, are using natural language processing and machine learning methods to create algorithms that can detect the early warning signs of suicide. Such tools could form the basis of an app or other technology-based system that parents, other caregivers and medical providers can use to alert them when an adolescent in their care is contemplating suicide.
Streamlining diagnosis
AI Slide 3.jpg
Clinical imaging has become increasingly digitized, paving the way for AI-based approaches that could bring efficiencies to clinical operations and decision making. For example, AI offers the prospect of prioritizing patients’ images for analysis, moving them to the top of the virtual stack for radiologists, based on the likelihood of an abnormal and potentially life-threatening finding. For example, researchers in California recently developed a deep-learning-based algorithm that can distinguish normal chest X-ray images from abnormal ones.
Automating malaria detection
microscope-foto-365.jpg
With the help of deep learning methods, a research group in Washington has developed an approach that automates malaria diagnosis. Their tool can detect and quantify malaria parasites with 90 percent accuracy and specificity, matching the level of performance of human experts. Researchers packaged their algorithm within an inexpensive automated digital microscope. The system has yielded impressive results in field tests in Thailand and Peru, and it’s now undergoing more testing and is in commercial development.
Offering a window on the brain
AI Slide 5.jpg
Progress is being made toward real-time monitoring and analysis of brain health. For example, a team of researchers in Boston has annotated some 30 terabytes of EEG data from thousands of patients, and they’ve mined the data to create deep learning algorithms that can automatically detect seizures in the critically ill, regardless of the underlying cause of illness. These tools are now under development and will be deployed in the coming year at a large hospital in the region, making real-time analysis of EEG a reality.
Using AI for eye health and disease
AI Slide 6.png
In 2018, the Food and Drug Administration took a historic step with the approval of a new AI-based system for the detection of diabetic retinopathy. Researchers based in Iowa recently examined the clinical use of this tool for diabetic retinopathy through a large prospective analysis. Meanwhile, research teams in the United Kingdom have been working to design AI-based tools that are more generalizable and not geared to a single eye disease, but able to detect within a single imaging modality features used in the diagnosis of more than 50 common eye conditions, including age-related macular degeneration.
Amplifying FHIR’s use in health information exchange
Provider data show B.jpg
A new data standard, known as the Fast Healthcare Interoperability Resources (FHIR) is gaining popularity and has become the de facto standard for sharing medical and other health-related information. With its web-based approach to health information exchange, FHIR promises to enable a new world of possibilities rooted in patient-centered care. Perhaps the most trailblazing aspect of FHIR is the new realm of patient-controlled data sharing it will create.
Reducing the burden of healthcare administration
p19pg50iqkjslm0gj651smv1cata.jpg
AI could have a sizeable impact on medical coding and billing. To help streamline the process of medical coding, teams across the country are harnessing AI to develop automated approaches. For example, a Boston-based startup has created a suite of machine learning algorithms that can analyze the doctors’ notes from patients’ electronic health records and automatically generate the proper diagnostic and procedure codes.
Enabling a revolution in acute stroke care
AI Slide 9.jpg
Massachusetts researchers have developed a set of AI-based algorithms that can help determine whether or not there is bleeding within the brain. The algorithms, which were trained on some 2,000 head CT images, can automatically review a patient’s head CT scan to identify a cerebral hemorrhage, help localize its source and determine the volume of brain tissue that is affected. Currently, the team is working to expand these tools by creating additional AI-based methods that similarly automate the subsequent steps of ischemic stroke diagnosis.
Narrowing gaps in mental healthcare
AI Slide 12.jpg
Research teams across the country are harnessing technology, including AI-based methods, to help narrow the gaps in mental healthcare. For example, researchers in Massachusetts are developing an app for patients with opioid, alcohol and other forms of drug addiction, which provides a virtual form of integrated group therapy, a highly effective treatment that teaches patients behaviors and skills to manage their own recovery and prevent relapse.
Bringing voice-first technology to healthcare
p1909l9eks1dc815ilpj119t1br19.jpg
AI-powered voice-first technology is coming to the clinic. Using speech recognition and natural language processing, several vendors are developing tools that are designed to help clinicians deliver better care and also give them more quality time with patients. For example, a host of healthcare technology companies are working on voice assistants that can help reduce physicians’ data entry burdens.
Unmasking potential intimate partner violence
AI Slide 10.jpg
Researchers are working to develop AI-enabled tools that can help alert clinicians if a patient’s injuries likely stem from intimate partner violence (IPV). Their goal is to create an integrated, AI-based system that can analyze a patient’s clinical and radiological data and automatically alert radiologists and clinicians if the injuries are likely to be associated with IPV. A research team in Boston recently conducted a pilot study that analyzed the electronic health records and imaging exams of nearly 200 patients with a known history of IPV as well as a control set of more than 550 non-abused patients.