Improving healthcare is a critical application for big data analytics and artificial intelligence (AI). Think of all that available patient information—from medical records, health monitoring devices, drug trials, genetics databases—there is no dearth of data. What is often lacking is a way to aggregate that trove of information and sort through it in a way that makes it useful.
If that can be accomplished, patient outcomes could be improved. Given the incentives insurance companies have to keep people healthy (i.e. out of the hospital) and prevent former patients from being readmitted, the stakes are high. If all that data could be used to make intelligent predictions about where a particular person is headed in terms of health, that could be a huge deal.
The advent of electronic health records, mandated over the last few years, has helped with patient care, but it's not enough. "Now at least you can access data, but it's still hard to make sense out of it," Ashish Atreja, chief technology innovation and engagement officer for medicine at Mount Sinai's Icahn School of Medicine told Fortune. "The health ecosystem lacks tools that can be used generally to make sense of that data."
"A patient may spend one to two hours in an outpatient facility in a year, but then there are 5,000 waking hours spent outside the hospital, which is where outcomes can be affected. What we need is one tool to check on them at home," he noted.
Towards this end, New York's Mount Sinai Hospital plans to use CloudMedx Clinical AI Platform to help craft care for people who have—or might develop—congestive heart failure (CHF), a condition affecting an estimated 5 million Americans. CloudMedx is already working with Sutter Physician Services, a Sacramento-based healthcare organization to apply its AI services to patient care.
Patient information—whether it's from a hospital systems' Epic or Cerner (cern) electronic medical records (EMR) systems, or from personal fitness devices (think Fitbit (fit) or Jawbone), implantable medical devices or home monitors)—needs to be gathered and queried. CHF can be a chronic condition that is often managed with drugs, diet, exercise, blood pressure and respiratory function as measured by devices at home. If data from about these management approaches could be ingested into the CloudMedx system for processing.
Public clouds, like Amazon (amzn)Web Services and Microsoft @msft(msft)Azure, provide the muscle to run huge data crunching jobs on Hadoop or some other data processing tool. CloudMedx runs on both AWS and Azure, adding its specialized analytics and algorithms that allow clinicians or researchers ask questions and get answers from all that data.
Based on that output, doctors can assess which patients are at risk of developing a disease or seeing their existing condition worsen, and prioritize what care needs to be administered immediately. It's AI-assisted triage. The company says its system can process a variety of factors to predict which patients are most likely to be back in the hospital and help the clinician fine-tune treatment to keep that from happening.
For more on data-driven healthcare, read: IBM Uses Watson to Help Workers Find Cancer Treatment
CloudMedx, which competes with IBM (ibm) Watson in this field, is becoming part of the Mt. Sinai Hospital Systems' connected healthcare platform which helps physicians see if a patient's condition—whether it is CHF or diabetes or something else—is being adequately controlled.
"We need tools to mine text data to figure out who needs the most proactive care and CloudMedx helps there," Atreja said. That, in conjunction with other technology including Mt. Sinai's in-house technology—like its secure text messaging system and telemedicine applications—provide a fuller picture of the patient even when the patient is at home.
For more on high-tech healthcare, watch:
"If their blood pressure or weight goes up we get that data to our nurses and doctors," he noted. And, to CloudMedx as well.