|
Johns Hopkins University School of Medicine
More than one-third of all people admitted to the hospital, and as many as 80% of all patients in an intensive care unit (ICU), develop delirium, a type of brain dysfunction marked by sudden bouts of confusion, inattention, paranoia, or even agitation and hallucinations. An intensivist at Johns Hopkins Medicine, in collaboration with Johns Hopkins University engineering students, report they have developed artificial intelligence (AI) algorithms that can detect the early warning signs of delirium and can predict—at any time during an ICU stay—a high risk of delirium for a significant number of patients.
"Being able to differentiate between patients at low and high risk of delirium is incredibly important in the ICU because it enables us to devote more resources toward interventions in the high-risk population," says Robert Stevens, M.D., associate professor of anesthesiology and critical care medicine at the Johns Hopkins University School of Medicine and senior author of the new study results, published in the Dec. 20 issue of the journal Anesthesiology. Stevens is also director of precision medicine and informatics, and co-director of the Johns Hopkins Precision Medicine Center of Excellence in Neurocritical Care.
Clinicians already knew that ICU delirium occurs more often in older and sicker patients, and that ICU patients who develop delirium are at higher risk of prolonged hospitalization, future dementia and death. Anti-delirium interventions such as care bundles, changing medications and earlier-than-usual occupational and physical therapy are effective, experts say, but limited time and resources, as well as the often unpredictable needs of ICU patients, prevent most ICUs from using them in every patient.
The new AI program, designed by undergraduate and master's level engineering students in a precision medicine class taught by Stevens, applied AI algorithms to a publicly available dataset covering more than 200,000 ICU stays at 208 hospitals around the country.
"The underlying idea was that this routinely collected data stored in patients' electronic health records contains signatures that are associated with delirium risk," says Kirby Gong, a recent master's degree graduate from the Johns Hopkins Department of Biomedical Engineering and first author of the new work.
Using the data, the team developed two computerized models to predict delirium risk. One, a so-called static model, takes a single snapshot of patient data shortly after admission—information about age, severity of illness, other diagnoses, physiologic variables and current medications—to predict delirium risk at any point during a hospital stay. The second, a so-called dynamic model, monitors information over hours and days, including repeat blood pressure, pulse and temperature readings—to provide the patient's continuously updated risk of delirium over the coming 12 hours.
Once the researchers developed the AI models, they tested them on two other sets of data from a Boston hospital, collectively covering more than 100,000 ICU stays. The area under the receiver operating characteristic curve (95% CI) for the first 24-hour model was 0.785, meaning that it was able to predict which patients would get delirium 78.5% of the time. The dynamic model performed even better, predicting delirium-prone patients up to 90% of the time.
Stevens says he is now testing the models on historical patient data from Johns Hopkins Medicine ICUs, and plans to design a clinical trial to test the use of the algorithms—and how they could shape clinical care—in patients newly admitted to an ICU. His lab is also applying similar artificial intelligence approaches—often in collaboration with engineering students and faculty—to predict stroke, heart failure, pulmonary embolisms and other emergent events seen in critical care medicine.
"For a lot of these physiological transitions, we think that there are early warning signs that may not be obvious to a clinician but can be picked up on using the kinds of artificial intelligence-supported pattern analysis that we used here," says Stevens.
|
|
Mayo Clinic / By Rick Thiesse
Winter months offer the opportunity for some athletes to rehab some of those nagging injuries. One injury common among runners and in sports centers is iliotibial band syndrome.
The iliotibial band, or IT, is a long, fibrous band of fascia tissue that runs from the outside of your hip down to the outside of your knee. It has a complex job description: it helps lift your leg to the front and to the side of your body, and it supports your knee during flexion and extension. When this hardworking tissue is injured or overworked, it can be a real pain in the leg.
"Repetitive motion, like running, rowing or cycling, typically is the culprit in IT band issues," says Jacob Erickson, D.O., Sports Medicine physician at Mayo Clinic Health System in Onalaska. "The IT band also is irritated when exercising on uneven surfaces, like trails or hiking downhill."
According to one study, iliotibial band syndrome is one of the most common injuries in runners presenting with lateral knee pain, with an incidence estimated between 5% and 14%
"The first warning sign of injury usually is pain on the outside of your knee, at the hip or down the side of your leg. You may notice the pain right after an exercise class or run. IT band problems can be experienced by active adults, children, and student and adult competitive athletes," explains Dr. Erickson.
Sudden increases in activity levels also can lead to iliotibial band syndrome. Although repeated tissue compression leading to irritation is best supported by recent evidence, there are several other trains of thought regarding the evolution of this condition.
"Weakness can be diagnosed with a simple test," offers Dr. Erickson. "For example, do a single-leg squat. If your knee tips in as you bend down, rather than pointing forward, be proactive and consider leg-strengthening exercises."
Dr. Erickson says younger athletes involved in sports are typically screened for this in hopes of identifying concerns before they begin. Not catching issues before sports activity, Dr. Erickson says, could result in injury midseason forcing athletes to take time away from their sport.
"The key is to keep a small problem small. Don't ignore the pain and try to push through it," adds Dr. Erickson. "Instead, take a rest from the activity you were doing for a few days. Patients can participate in other physical activities, such as swimming, that do not aggravate their symptoms to maintain their conditioning. If the pain persists, see a sports medicine specialist or athletic trainer, who often will prescribe physical therapy."
Dr. Erickson says a physical therapist will develop a series of exercises for you that will treat your whole leg, including targeting and strengthening your core and larger gluteal muscles to relieve some of the IT band's workload. The therapist also may do some soft-tissue work or dry needling. Other treatments may include steroid injections or, in rare cases, surgery.
"In general, the best way to avoid having your IT band become a pain the leg, is to maintain your core, leg and gluteal muscle strength," Dr. Erickson says. |
|
|
MedicalXpress / By Cody Mello-Klein, Northeastern University
Don't throw away that Wii Fit Balance Board––it might be more valuable than you think. New research from a team at Northeastern University found that active video games––like Wii Fit and Dance Dance Revolution––are more effective for improving balance than conventional forms of physical therapy.
Led by Amy Lu, associate professor of communication studies at Northeastern, the team of researchers conducted a comprehensive review and meta analysis of thousands of studies focused on active video games. After narrowing their focus to a few hundred, they grouped the studies into different categories based on what they were measuring, from physical fitness to cognitive outcomes. The research on balance is just one of a series of papers the team has written based on their work.
"Personally speaking, I don't think active video games themselves can replace outdoor physical activities like soccer or basketball," Lu says. "It's a good alternative, however, in [this research], we have basically found that compared to those conventional treatments, active games actually work better."
Dagmar Sternad, university distinguished professor of biology at Northeastern who Lu recruited based on her expertise in balance, says, even looking conservatively, the findings indicate that "this automatized and supposedly more motivating and fun way of play and practice is at least as good as conventional training."
The findings are significant, especially in a field that can have lifesaving implications. Sternad says postural balance and falling are, even in healthy people, some of the "main risk factors that lead to immobility and then eventually mortality."
"Even for a 60-year-old woman falling with weak bones, if there is a fracture, the fracture confines her to be less mobile for three months," Sternad says. "Reduced mobility has an effect on overall health, and it's a downward slope."
In studies conducted so far, researchers found that active video games mainly benefit healthy people without medical conditions. Lu says it's indicative of how much more difficult balance work is for people with neurological conditions like multiple sclerosis, Parkinson's disease or cerebral palsy.
In looking at more than 100 studies, Lu and her team also found that active video game treatment had the greatest effect on children, followed by older adults. Lu hopes these findings can send a signal to the games industry, which has historically not marketed or designed to older adults.
"They really liked it and could benefit a lot from it, so just imagine if we actually are going to be able to switch some of the focus of the population to older adults," Lu says. "Probably we're going to see a lot more public health benefits for this population."
As for why active video games are so effective, Lu says they are, by design, more engaging and motivating than conventional forms of physical therapy. The Wii Fit Balance Board is not too different from traditional balance boards that are used in physical therapy. But the way Nintendo has designed the experience to gamify physical activity––a physical action leads to feedback in the game that helps you achieve a goal both in the game and in real life––can make it more engaging.
"It's really giving you this kind of immediate pleasurable feedback in real time based on your input," Lu says. "Gamification and game companies have done a lot of research on how to make this reward feel very satisfactory. Then, on top of that, I also feel that in terms of the design of the devices, over the years from Wii to [Microsoft] Kinect to VR, one of the things I feel the companies have been dedicating themselves to is to make this interactive process very effortless and smooth."
Sternad says the implications of these findings go beyond the games industry. She says the wider medical field could benefit from using active video games as another tool in the toolkit for physical therapy. In a field that is starting to explore physical distanced forms physical therapy, video games could be a boon for patients.
"Yes, you can provide [patients] with assistive devices, you can provide people with physical therapy, but all of that has huge downsides," Sternad says. "Physical therapy is expensive. How do people get to the physical therapy office, if you think of more rural populations? You need a caregiver, a partner who drives you there."
"The opportunity such active video games [provide] to have some kind of fun way to practice at home, self-guided, is huge," she adds. "If doctors feel there is scientific support to tell them to do this––maybe even insurance paying for such platforms––that would be a step in a good direction."
The research is published in the journal Archives of Physical Medicine and Rehabilitation. |
Study: Most Patients are Getting Small Doses of Rehab Therapy After Stroke
News Medical Life Sciences / By Emily Henderson, B.Sc.
Many patients don't receive much rehabilitation therapy following a stroke, despite strong evidence that higher amounts can reduce long-term disability, according to a new UCLA-led study that tracked over 500 patients across 28 acute care hospitals in their first year following a stroke.
The new research, published in the peer-reviewed journal Stroke, is the first U.S.-wide study to find that patients who had more severe strokes received higher amounts of rehabilitation therapy, a welcome finding. "But in the bigger picture, the findings reinforce that too many patients are missing out on a golden opportunity to maximize recovery during a critical period following a stroke," said the study's lead author, Steven Cramer, MD. Stroke is a leading cause of long-term disability in the United State and can affect speech, memory, and mobility, among other impairments.
Among the study's key findings:
--Many patients tracked in this study did not receive any rehabilitation therapy after their stroke. After three months, about one-third of patients had not received physical therapy, almost half had not received occupational therapy, and over 6 in 10 did not receive speech therapy.
--Those who did receive rehabilitation therapy typically had six to eight sessions by three months after their stroke – and between 0 and 1.5 sessions the rest of the year.
--Where patients were sent following hospitalization also mattered. Those who were discharged home had the lowest levels of rehabilitation therapy, regardless of the severity of their stroke.
--Hispanic patients received disproportionately lower amounts of physical therapy and occupational therapy.
Cramer said it is important for future research to examine the feasibility of providing higher therapy doses to stroke patients. |
|
