All healthcare providers share the goal of treating more patients, cutting the cost of healthcare, and achieving better patient and business outcomes. With these goals in mind, many providers are now embracing solutions for artificial intelligence.
AI promises to help healthcare providers deliver better outcomes by improving preventive medicine, enhancing diagnostics and enabling clinicians to treat more patients. With AI applications and systems, healthcare providers can easily sift through large amounts of data to identify infections sooner, predict which patients are likely to have certain problems and identify needs in large groups of people.
At the same time, AI can help providers optimize the use of existing resources to improve productivity and contain costs. According to an Accenture analysis, the combination of key clinical AI applications could potentially create $150 billion in annual savings for the United States healthcare economy by 2026.1
Common use cases
To make this story more tangible, let’s look at some common use cases for AI in healthcare.
- Medical imaging — With AI, providers can use automated imagery analysis to increase diagnostic speed and accuracy. This isn’t to say that a machine is going to replace the specialists who review medical images to identify indicators of problems. Rather, the AI systems will do the heavy lifting to help the clinicians quickly see things they need to look at.
- Hospital workflows — AI can help healthcare organizations bring new efficiencies to routine workflows, planning, scheduling, and selecting exams and treatments. For example, AI-driven capabilities like voice-to-text transcription can greatly reduce the time required for everyday tasks, such as entering data in patient records and ordering prescriptions and tests.
- Clinical decision support — AI can help providers integrate electronic health records with other data, such as medical images, to add context to patient care and enhance the delivery of appropriate therapies. As the population ages, AI-driven clinical decision support systems will help providers treat growing numbers of patients with chronic diseases in a more cost-effective manner.
- Personalized medicine — AI allows healthcare providers to shift through enormous amounts of data to pinpoint the ideal treatment for a specific patient. For example, AI can be used to sift through thousands of genetic mutations in a sequenced cancer tumor to zero in on mutations that contribute to the growth of a cancer.2 Capabilities like these enable narrowly targeted therapies, instead of potentially less-effective one-size-fits-all approaches.
- Population health — AI allows healthcare and public health organizations to integrate and analyze large volumes of data to identify more effective disease prevention and treatment protocols for groups of people. With capabilities like deep learning, AI is uniquely capable of ferreting out the patterns and trends in disparate datasets to help healthcare providers and policymakers understand the needs of a population.
A case study
In a 2018 study published in the medical journal The Lancet Oncology, a team of medical researchers from Gustave Roussy, a leading European center for cancer research and care, and a few other institutions demonstrated that AI can process medical images to extract biological and clinical information to help with immunotherapy treatment.
In the study, the researchers used an algorithm they designed and developed to analyze CT scan images and create a “radiomic signature.” This signature defines the level of lymphocyte infiltration of a tumor — or the degree to which immune cells have moved from the blood into a tumor cell. The radiomic signature also provides a predictive score for the efficacy of immunotherapy in the patient.
In a news release on the study, Gustave Roussy notes that, in the future, physicians might be able to use imaging to identify biological phenomena in a tumor located in any part of the body without having to perform a biopsy.3 That’s a great example of the potential of AI to revolutionize healthcare.
With the power to predict emergency health conditions, support more accurate and timely clinical diagnoses, and streamline hospital operations, AI is opening exciting new frontiers in healthcare. Along the way, AI is putting us on the path to powerful solutions to some of today’s most pressing healthcare challenges — from the fallout of an aging population and a shortage of clinical specialists to an urgent need to contain rising costs.
The bottom line: While AI isn’t a miracle cure for the problems in our strained healthcare system, it is certainly a part of the remedy.
Ready to learn more?
For a look at the great things Gustave Roussy is doing in the fight against childhood cancers, read the case study “Cancer centre speeds up life-saving treatments” or watch the video “Gustave Roussy improves pediatric cancer treatments by speeding genomic analysis with Dell servers.”
1 Accenture, “Artificial Intelligence: Healthcare’s New Nervous System,” 2017.
2 JASON study for the U.S. Department of Health and Human Services, “Artificial Intelligence for Health and Health Care,” December 2017.
3 Gustave Roussy news release, “Predicting the response to immunotherapy using artificial intelligence,” August 27, 2018.