Vanessa Geneva Ahern

home

authors

vanessa-geneva-ahern

When Seattle Children’s Hospital researchers set out to examine how to identify social complexity risk factors in children using various state data, they hoped that pinpointing kids with notable challenges early on could lead to better health supports, helping families build resilience and addressing unmet needs.

Soon, investigators turned to data on emergency department visits, confident that the numbers might provide insights into how these populations were using the facilities and how healthcare stakeholders could better serve them.

Looking at emergency department visits, they theorized, could confirm that social complexity risk factors—like homelessness, involvement with the child welfare system, and mental health issues in their parents&mdash;were associated with adverse outcomes, says Kimberly C. Arthur, MPH, a clinical research scientist at the hospital and a co-author on the corresponding study.

The team of researchers, which included pediatricians, looked at emergency department visits that were non-urgent and didn’t result in hospital stays, homing in on issues that might have been best addressed in a primary care setting. That stood to reveal whether kids with social risk factors face an increased risk of going to the ED for non-urgent visits. Nine of the 11 risk factors, it turned out, were associated with greater emergency department use.

“You can think of interventions that can reduce emergency department use, but more importantly, because we saw that association, we know that there are issues that need to be addressed because the children likely need extra support with getting better access to care or managing a chronic condition,” Arthur notes.

The resultant study also offered a possible solution: If a primary care physician were to see a flag on a patient’s electronic medical record highlighting a child’s social complexity risk factors, then the doctor would be better positioned to take action to help the patient and family. The particular social risk factor information would not need to be disclosed in such an arrangement, according to the researchers.

But by knowing that a social risk factor exists, a primary care physician could schedule a longer appointment to allow for a more fruitful discussion. For an acute care appointment, meanwhile, a doctor could see whether a child was up to date on all necessary vaccinations and the like, a critical opportunity since these kids may not visit doctors often, according to the researchers.

Still, the data might not be enough to get such a program off the ground. It could require a significant investment of time, money, and resources for states to develop this comprehensive identification system, meaning that such a set of disparate data and point-of-care notification might remain elusive.

Arthur says collaboration between the public health sector and practices must increase regardless. “A team approach where you potentially have a care coordinator, a social worker, and a nurse or a community health worker providing support is a way to make this more doable,” she adds. “It’s not that it all has to be on the [primary care physician]. It really takes a team. Considering the constraints of a single visit, it is important to look at what those strategies are and what is learned about family situations after having a conversation in primary care.”

 in the January/February 2018 issue of the journal 

Articles

Why Seattle Children’s Hospital researchers say electronic medical records can help doctors provide better care to at-risk children.

What Do Emergency Department Visit Data Say About Risk?

Imagine going about your daily life, working, shopping, and driving, knowing that you might have a seizure at any moment. But relief is on the horizon, as researchers from the University of Melbourne in Victoria, Australia have developed a potentially life-saving deep learning tool that can predict when an epileptic seizure is about to happen.

 last month. The deep learning-based prediction system “achieved mean sensitivity of 69% and mean time warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%,” according to the findings.

Dean Freestone, PhD, senior research fellow at the department of medicine at St. Vincent’s Hospital at the University of Melbourne, says the tech could be contained in a chip inside a wearable device such as a wristband or bracelet, “incorporating a person’s behavior, environment, and physiology.” He and fellow co-author Mark J. Cook, MD, chair of medicine at St. Vincent’s Hospital, have launched a company named 

 to pursue this technology. They hope to implant patients with the technology later this year.

“The technology is now proven. We have shown seizure prediction is possible in our previous paper published in 

 and in a Kaggle contest. This new study is just further backup,” Freestone says.

The advance could change the lives of many people with epilepsy, who worry about looming seizures while they are doing everyday activities. Patients who have tested the technology reported that they felt more in control when they used the wearable device and were more confident doing novel activities. They also claimed to have benefited from improved sleep and decision making.

The new forecasting technology would be best suited for someone having seizures once per week, according to the architects. If someone has seizures every hour, or if the seizures are too infrequent, it is difficult to train the algorithms, Freestone notes.

The way the predictive technology works is similar to Facebook’s facial recognition software. Instead of people in photos, the researchers have trained the algorithms to recognize patterns in the electrical activity of the brain that preempt seizures. “It is software that learns from example. The electrical patterns are very subtle and are invisible to the human eye, but the computer algorithms can identify them. The circadian patterns then help to boost the algorithms performance,” Freestone says.

“Patients can take action to actually prevent seizures. This could be in the form of a medication or even just a change in behavioral. We have also learnt a lot about the mechanisms of seizure, such as the strong influence of circadian cycles,” he adds.

Although significant cost and risk comes with new trials of medical devices, researchers are excited about the changes they can make. “We are working toward a system that will constantly provide a person with a risk level of seizure susceptibility,” Freestone says. “It will be a gauge that outputs a probability. We will incorporate as many aspects of a person’s behavior, environment and physiology as we can acquire from wearable technologies and other sensors.”

The findings came about, in part, thanks to the University of Melbourne’s large, long-term data set, which is unique and apt for exploring deep learning for seizure forecasting.

Why an algorithm might restore confidence and control to patients.

Deep Learning Device Can Predict Epileptic Seizures

This bot sees what doctors sometimes cannot. Emory University researchers have created a “Sepsis Expert” algorithm that works in real time to predict the onset of sepsis, the deadly condition that often takes hold in healthcare settings. Banking on information from 31,000 patients admitted to 2 hospitals and data on 52,000 intensive care unit (ICU) patients from a public database, the researchers used machine learning to build an artificial intelligence (AI) technology that they hope will save lives.

According to the CDC, more than 1.5 million people in the United Sates contract sepsis every year, resulting in 250,000 deaths. But, until now, that knowledge has not translated to insights for the individual. “What we lack is ‘situation awareness,’ which is perceiving data, comprehending data, and projecting those data into the future to see whether there is an evolving threat to the patient,” says Timothy George Buchman, PhD, MD, director of Emory’s critical care center and co-author of 

He says the Sepsis Expert is sensitive to pattern detection over time, using layers of data that can project into the future. It acts like a smartphone pop-up notification, which 

 to appear when you are craving a donut—and when you are “vulnerable” and conveniently close to a coffee shop.

The AI-guided Sepsis Expert predicted the onset of patients in the ICU between “4 and 12 hours before clinical recognition,” the researchers found. Time is crucial, as for patients who have severe sepsis—an infection along with dropping blood pressure&mdash;each delayed hour of treatment raises the chance of mortality by about 7%, according to experts. The algorithm is designed to identify those people and begin their treatments early on.

“Recognizing and initiating treatment early not only saves lives, but also tends to mitigate those longer-term problems that plague older folks who don’t have much reserve and yet survive the sepsis episode,” Buchman says. “Finding and fixing a problem before it becomes catastrophic seems to make a difference. That said, it is the comorbidities that exist prior to sepsis that have the greatest influence on function among sepsis survivors.”

So far, Sepsis Expert is only compatible with adults, even though children are also vulnerable to sepsis. The AI must be tuned to kids, as they respond to sepsis differently than adults.

With all the bedside alarms already in place in hospital settings, researchers were concerned that Sepsis Expert might be perceived as another nuisance to ignore. Buchman says healthcare professionals are bombarded with device alarms, drug interaction alerts, and critical lab value notifications, but the team at Emory has spent considerable time and thought on how the alerts will be adjudicated, who does the adjudication, and what professionals at the bedside want to and need to know. He sees an increased trust in AI, though a future study may examine the clinical utility of the Sepsis Predictor model.

“An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU,”

Big data fueled the real-time sepsis forecasting algorithm.

AI Can Predict Sepsis to Save Lives

How does a patient with type 2 diabetes stay motivated to be active and eat healthy foods? Since the invention of wearable self-monitoring technology a decade ago, exercise researchers have examined the implications of how receiving real-time feedback on activity—steps, heart rate, calories burned&mdash;can influence a person’s behavior. But they have yet to reach a clear, catchall consensus.

Researchers recently set out to record the response of a diabetic’s brain to getting instant information on glucose levels and physical activity. More than 30 adults underwent MRI scans and then followed up 2 weeks later to monitor their physical fitness, sedentary time, and glucose levels. The wearable technology showed that the participants had been less sedentary—more stand-ups, more steps&mdash;than when the study began. The School of Sport, Exercise, Health, and Sciences at Loughborough University in the United Kingdom conducted the study, which was published in the 

Although the researchers acknowledged the limitations of the unnatural nature of the MRI machine, the results were promising enough to suggest that “wearable technologies presenting personalized glucose feedback may be useful to employ in future interventions.” Researchers found that participants who had access to their glucose levels and other personal stats were more likely to activate the superior frontal gyrus, the area of the brain that regulates positive behavior changes.

“One key ‘suggestion’ from these pilot data is that people have a desire to understand how their body’s acute physiology changes in response to lifestyle choices,” explains Dale Esliger, PhD, program director of Exercise as Health, MSc, School of Sport, Exercise and Health Sciences at Loughborough University. “If this turns out to be a solid finding, then it may act to prime the digital health technologies industries (i.e., wearables sector) to invest in the development of hybrid sensors that continuously measure a user’s acute physiology … alongside the more typically measured physical activity behaviors.”

Does this mean that physicians will soon add wearable technology to their diabetic patients’ prescriptions in the future? Maxine Whelan, BSc, who led the data collection on the study, thinks so. “This pilot work relates most directly to the prevention of type 2 diabetes, but in the future healthcare professionals may incorporate wearable technology as a way to help prevent other chronic diseases, as well,” she says. The technology simultaneously empowers patients and appears to encourage them to make positive choices, like taking a stroll after a meal, after viewing and digesting the physiciological consequences of their lifestyle choices, Whelan notes.

“Who knows? One day we may be able to easily and objectively quantify the acute health benefits of washing the car or taking the stairs or parking further away,” Esliger adds. “On the other side of the physical activity continuum, we may be able to overtly see the health risks of too much sedentary time. For example, binge-watching episodes of your favorite Netflix programs.”

But for now, it is clear that wearable fitness trackers hold a great deal of promise, and researchers say the health benefits are worth exploring.

Why wearable fitness trackers hold great potential to prompt positive behaviors.

Vanessa Geneva Ahern

Articles

What Do Emergency Department Visit Data Say About Risk?

Deep Learning Device Can Predict Epileptic Seizures

AI Can Predict Sepsis to Save Lives

Real-Time Health Data Help Patients With Diabetes Take Action