Tag: fitness trackers

Categories : Paediatrics Surgeries & ProceduresTags :

Researchers Use Fitbits to Predict Children’s Surgery Complications

On By ModernMedia
Photo by Natanael Melchor on Unsplash

Although postoperative complications, such as infections, can pose significant health risks to children after undergoing surgical procedures, timely detection following hospital discharge can prove challenging.

A new study from Northwestern University, along with other institutions, is the first to use consumer wearables to quickly and precisely predict postoperative complications in children and shows potential for facilitating faster treatment and care. The study appears in Science Advances.

“Today, consumer wearables are ubiquitous, with many of us relying on them to count our steps, measure our sleep and more,” said senior author Arun Jayaraman, professor at Northwestern University Feinberg School of Medicine and a scientist at Shirley Ryan AbilityLab. “Our study is the first to take this widely available technology and train the algorithm using new metrics that are more sensitive in detecting complications. Our results suggest great promise for better patient outcomes and have broad implications for paediatric health monitoring across various care settings.”

How the study worked

As part of the study, commercially available Fitbit devices were given to 103 children for 21 days immediately after appendectomy, the most common surgery in children, which results in complications up to 38% of the time. Rather than just using the metrics automatically captured by the Fitbit to identify signs of complications (eg, low activity, high heart rate, etc.), Shirley Ryan AbilityLab scientists trained the algorithm using new metrics related to the circadian rhythms of a child’s activity and heart rate patterns. 

In the process, they found such metrics were more sensitive to picking up complications than the traditional metrics. In fact, in analysing the data, scientists were able to retrospectively predict postoperative complications up to three days before formal diagnosis with 91% sensitivity and 74% specificity. 

“Historically, we have been reliant upon subjective reporting from children – who often have greater difficulty articulating their symptoms – and their caregivers following hospital discharge. As a result, complications are not always caught right away,” said study author Dr Fizan Abdullah, who at the time of the study was an attending physician of paediatric surgery at Ann & Robert H. Lurie Children’s Hospital of Chicago and a professor at Feinberg. “By using widely available wearables, coupled with this novel algorithm, we have an opportunity to change the paradigm of postoperative monitoring and care – and improve outcomes for kids in the process.”

What’s next?

This research is part of a four-year National Institutes of Health-funded project. As a next step, scientists plan to transition this approach into a real-time (vs retrospective) system that analyses data automatically and sends alerts to children’s clinical teams. 

“This study reinforces wearables’ potential to complement clinical care for better patient recoveries,” said Hassan M.K. Ghomrawi, vice chair of research and innovation in the department of orthopaedic surgery at University of Alabama at Birmingham. “Our team is eager to enter the next phase of research exploration.”

Source: Northwestern University

Categories : Medical Research & Technology Metabolic DisordersTags :

For Obesity, Fitness Trackers Miss the Mark – but There’s a Fix

On By ModernMedia
Photo by Kamil Switalski on Unsplash

For many, fitness trackers have become indispensable tools for monitoring how many calories they’ve burned in a day. But for those living with obesity, who are known to exhibit differences in walking gait, speed, energy burned and more, these devices often inaccurately measure activity – until now.

Scientists at Northwestern University have developed a new algorithm that enables smartwatches to more accurately monitor the calories burned by people with obesity during various physical activities.

The technology bridges a critical gap in fitness technology, said Nabil Alshurafa, whose Northwestern lab, HABits Lab, created and tested the open-source, dominant-wrist algorithm specifically tuned for people with obesity. It is transparent, rigorously testable and ready for other researchers to build upon. Their next step is to deploy an activity-monitoring app later this year that will be available for both iOS and Android use.

“People with obesity could gain major health insights from activity trackers, but most current devices miss the mark,” said Alshurafa, associate professor of behavioral medicine at Northwestern University Feinberg School of Medicine.

Current activity-monitoring algorithms that fitness trackers use were built for people without obesity. Hip-worn trackers often misread energy burn because of gait changes and device tilt in people with higher body weight, Alshurafa said. And lastly, wrist-worn models promise better comfort, adherence and accuracy across body types, but no one has rigorously tested or calibrated them for this group, he said.

“Without a validated algorithm for wrist devices, we’re still in the dark about exactly how much activity and energy people with obesity really get each day — slowing our ability to tailor interventions and improve health outcomes,” said Alshurafa, whose team tested his lab’s algorithm against 11 state-of-the-art algorithms designed by researchers using research-grade devices and used wearable cameras to catch every moment when wrist sensors missed the mark on calorie burn.

The findings will be published June 19 in Nature Scientific Reports.

The exercise class that motivated the research

Alshurafa was motivated to create the algorithm after attending an exercise class with his mother-in-law who has obesity.

“She worked harder than anyone else, yet when we glanced at the leaderboard, her numbers barely registered,” Alshurafa said. “That moment hit me: fitness shouldn’t feel like a trap for the people who need it most.”

Algorithm rivals gold-standard methods

By using data from commercial fitness trackers, the new model rivals gold-standard methods of measuring energy burn and can estimate how much energy someone with obesity is using every minute, achieving over 95% accuracy in real-world situations. This advancement makes it easier for more people with obesity to track their daily activities and energy use, Alshurafa said.

How the study measured energy burn

In one group, 27 study participants wore a fitness tracker and metabolic cart – a mask that measures the volume of oxygen the wearer inhales and the volume of carbon dioxide the wearer exhales to calculate their energy burn (in kilocalories/kCals) and resting metabolic rate. The study participants went through a set of physical activities to measure their energy burn during each task. The scientists then looked at the fitness tracker results to see how they compared to the metabolic cart results.

In another group, 25 study participants wore a fitness tracker and body camera while just living their lives. The body camera allowed the scientists to visually confirm when the algorithm over- or under-estimated kCals.

At times, Alshurafa said he would challenge study participants to do as many pushups as they could in five minutes.

“Many couldn’t drop to the floor, but each one crushed wall-pushups, their arms shaking with effort,” he said, “We celebrate ‘standard’ workouts as the ultimate test, but those standards leave out so many people. These experiences showed me we must rethink how gyms, trackers and exercise programs measure success – so no one’s hard work goes unseen.”

Source: Northwestern University

Categories : IT in Healthcare Surgeries & ProceduresTags :

AI Analyses Fitbit Data to Predict Spine Surgery Outcomes

On By ModernMedia
Photo by Barbara Olsen on Pexels

Researchers who had been using Fitbit data to help predict surgical outcomes have a new method to more accurately gauge how patients may recover from spine surgery.

Using machine learning techniques developed at the AI for Health Institute at Washington University in St. Louis, Chenyang Lu, the Fullgraf Professor in the university’s McKelvey School of Engineering, collaborated with Jacob Greenberg, MD, assistant professor of neurosurgery at the School of Medicine, to develop a way to predict recovery more accurately from lumbar spine surgery.

The results show that their model outperforms previous models to predict spine surgery outcomes. This is important because in lower back surgery and many other types of orthopaedic operations, the outcomes vary widely depending on the patient’s structural disease but also varying physical and mental health characteristics across patients. The study is published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.

Surgical recovery is influenced by both preoperative physical and mental health. Some people may have catastrophising, or excessive worry, in the face of pain that can make pain and recovery worse. Others may suffer from physiological problems that cause worse pain. If physicians can get a heads-up on the various pitfalls for each patient, that will allow for better individualized treatment plans.

“By predicting the outcomes before the surgery, we can help establish some expectations and help with early interventions and identify high risk factors,” said Ziqi Xu, a PhD student in Lu’s lab and first author on the paper.

Previous work in predicting surgery outcomes typically used patient questionnaires given once or twice in clinics that capture only one static slice of time.

“It failed to capture the long-term dynamics of physical and psychological patterns of the patients,” Xu said. Prior work training machine learning algorithms focus on just one aspect of surgery outcome “but ignore the inherent multidimensional nature of surgery recovery,” she added.

Researchers have used mobile health data from Fitbit devices to monitor and measure recovery and compare activity levels over time but this research has shown that activity data, plus longitudinal assessment data, is more accurate in predicting how the patient will do after surgery, Greenberg said.

The current work offers a “proof of principle” showing, with the multimodal machine learning, doctors can see a much more accurate “big picture” of all the interrelated factors that affect recovery. Proceeding this work, the team first laid out the statistical methods and protocol to ensure they were feeding the AI the right balanced diet of data.

Prior to the current publication, the team published an initial proof of principle in Neurosurgery showing that patient-reported and objective wearable measurements improve predictions of early recovery compared to traditional patient assessments. In addition to Greenberg and Xu, Madelynn Frumkin, a PhD psychological and brain sciences student in Thomas Rodebaugh’s laboratory in Arts & Sciences, was co-first author on that work. Wilson “Zack” Ray, MD, the Henry G. and Edith R. Schwartz Professor of neurosurgery in the School of Medicine, was co-senior author, along with Rodebaugh and Lu. Rodebaugh is now at the University of North Carolina at Chapel Hill.

In that research, they show that Fitbit data can be correlated with multiple surveys that assess a person’s social and emotional state. They collected that data via “ecological momentary assessments” (EMAs) that employ smart phones to give patients frequent prompts to assess mood, pain levels and behaviour multiple times throughout day.

We combine wearables, EMA -and clinical records to capture a broad range of information about the patients, from physical activities to subjective reports of pain and mental health, and to clinical characteristics,” Lu said.

Greenberg added that state-of-the-art statistical tools that Rodebaugh and Frumkin have helped advance, such as “Dynamic Structural Equation Modeling,” were key in analyzing the complex, longitudinal EMA data.

For the most recent study they then took all those factors and developed a new machine learning technique of “Multi-Modal Multi-Task Learning (M3TL)” to effectively combine these different types of data to predict multiple recovery outcomes.

In this approach, the AI learns to weigh the relatedness among the outcomes while capturing their differences from the multimodal data, Lu adds.

This method takes shared information on interrelated tasks of predicting different outcomes and then leverages the shared information to help the model understand how to make an accurate prediction, according to Xu.

It all comes together in the final package producing a predicted change for each patient’s post-operative pain interference and physical function score.

Greenberg says the study is ongoing as they continue to fine tune their models so they can take these more detailed assessments, predict outcomes and, most notably, “understand what types of factors can potentially be modified to improve longer term outcomes.”

Source: Washington University in St. Louis