Working smarter with AI
Imagine a future in which the wristband you’re wearing can nudge your doctor by indicating you’ve been in the exam room for half an hour. Or where the clinic is wired for sensors that recognize you when you walk in the door, taking your temperature and blood pressure and recording your height and weight.
Far from science fiction, these clinic scenarios are real artificial intelligence (AI) projects currently being developed at UT Southwestern’s Medical Artificial Intelligence and Automation (MAIA) Laboratory.
“AI is going to transform health care. Nothing is comparable,” says Dr. Steve Jiang, Professor of Radiation Oncology and Director of the MAIA lab. “Almost everything we do in health care will be impacted by artificial intelligence – to improve the efficiency and quality of the work. AI helps humans do a better job, faster.”
Dr. Jiang, who is also Vice Chair of the Department of Radiation Oncology and Director of the Division of Medical Physics and Engineering, began working on machine learning 15 years ago.
“AI can learn from human experience and by itself by interacting with the environment,” Dr. Jiang says. “AI can improve patient safety by automatically detecting and preventing errors. The machine is never tired and will check everything, every detail. And it will learn from data from previously treated patients and become smarter and smarter from learning continuously.”
Dr. Jiang and his team of MAIA medical physicists are busy developing intelligent medical devices and computer algorithms for UT Southwestern clinicians to improve treatment and patient safety. Among its many projects, the group has been working to incorporate artificial intelligence into the fabric of a medical clinic.
The team’s Real Time Location System (RTLS) uses sensors based on Bluetooth technology to track the location of patients, clinical staff, and equipment in order to improve workflow and patient safety.
“Almost everything we do in health care will be impacted by artificial intelligence – to improve the efficiency and quality of the work. AI helps humans do a better job, faster.”
“We’ve been working on this for a couple of years,” Dr. Jiang says. “The first step is to give a patient a wristband with a sensor in it to wear during their clinic visit. We can then track the patient – just like a GPS. We can also verify the patient’s identity using the sensor.”
If a patient has been waiting in an exam room for, say, 15 minutes, the system can send a text or other reminder to staff. If the patient is still waiting 15 minutes or a half-hour later, the system can send a stronger reminder.
“We think future hospitals should be really smart – with a lot sensors in the building, on the walls, in the ceiling, on the patient, and on the equipment collecting data. AI can then analyze that data to create the best workflow and patient monitoring,” he says.
The MAIA team is also working to more accurately pinpoint the location of patients inside a clinic or hospital. Integrating facial and posture recognition technologies, the AI system would automatically measure and analyze patients’ weight, height, and other vital signs. Such tracking would require patient consent, he notes.
Dr. Jiang’s team has been testing the system and estimates that by year-end, MAIA researchers will be ready to track patients and staff in UTSW’s Radiation Oncology Building, which opened in April 2017.
Turning to specific treatments, another MAIA project uses artificial intelligence to increase the resolution quality in magnetic resonance spectroscopic imaging (MRSI). The National Cancer Institute defines MRSI as a noninvasive method that provides information about cellular activity (metabolism) in addition to the shape and size information available from standard magnetic resonance imaging.
“For many clinical applications, higher MRSI resolution is desired,” Dr. Jiang says. “So we came up with the idea to use artificial intelligence to get high resolution from low resolution. This kind of work is called super-resolution.”
By combining a low-resolution MRSI with a regular resolution magnetic resonance image, the team found a novel way of producing super-resolution spectroscopic images of the human brain, Dr. Jiang says. The team then used simulation data to create a model that has been investigated with a few volunteers, says Dr. Jiang, who holds the Barbara Crittenden Professorship in Cancer Research. The next step is to expand the data set.
“This is an important project because higher-resolution MRSI has a lot of clinical applications,” Dr. Jiang says. “We are working with a group in Vienna, Austria, to get more patients. Right now, based on what we have, this is a very promising approach.”
He adds: “AI is changing the world and also changing health care – that’s what we’re working on. We’re trying to use AI to solve important clinical problems.”