Elaine Nsoesie, PhD, is a research fellow at Boston Children’s Hospital’s HealthMap, Harvard Medical School and Virginia Bioinformatics Institute. In this post, which originally appeared on HealthMap’s Disease Daily, Nsoesie looks at the trend of detecting disease digitally by monitoring mentions on social media. She delves into one of the major limitations of this technique—namely telling those who are curious about a disease apart from those who actually have it.
There are plenty of studies about tracking diseases (such as influenza) using digital data sources, which is awesome! However, many of these studies focus solely on matching the trends in the digital data sources (for example, searches on disease-related terms, or how frequently certain disease-related terms are mentioned on social media over time, etc.) to data from official sources such as the Centers for Disease Control and Prevention. Although this approach is useful in telling us about the possible utility of these data, there are several limitations. One of the main limitations is the difficulty in distinguishing between data generated by healthy individuals and individuals who are actually sick. In other words, how can we tell whether someone who searches Google or Wikipedia for influenza is sick or just curious about the flu?
Researchers at Penn State University have developed a system that seeks to deal with this limitation. We spoke to the lead author, Todd Bodnar, about the study titled, On the Ground Validation of Online Diagnosis with Twitter and Medical Records. Full story »
What happens when you try to scale up a successful quality initiative? Eric Fleegler, MD, MPH, and Eugenia Chan, MD, MPH, are facing that challenge with ICISS, their web-based system that went quickly from ideation to adoption by 3,000 patients with attention deficit hyperactivity disorder (ADHD) and their families.
ICISS enables parents, teachers and patients to give online updates on medications, symptoms and school performance in close to real time, then packages that data for clinicians in a visual, actionable fashion. But tasked with introducing ICISS into four other clinics at Boston Children’s Hospital—autism, asthma, depression and epilepsy—a raft of practical, legal and philosophical questions came up about how to handle these patient-generated health data. For example:
- How should we inform families that they need to contact their provider directly with immediate concerns?
- What if a parent indicates that a child is at risk of self-harm, and how can we manage this in a timely manner?
- How can clinics afford to hire additional staff to screen and manage alerts from ICISS when this activity is non-reimbursable?
- What is the obligation of the provider if actionable data show up months in advance of the scheduled visit?
Fleegler and Chan discuss the challenges and lessons learned in our sister publication, Innovation Insider. We’d be interested to hear from others facing similar questions in handling patient-generated health data.
Cameron with Galina Lipton, MD
By the time Cameron Shearing arrived at the South Shore Hospital Emergency Department (ED) during a December snowstorm, he wasn’t breathing. He didn’t have much time. The two-year-old had aspirated a chocolate-covered pretzel, which sent tiny bits of material into his lungs.
The odds of a good outcome were not high. Pretzel is one of the worst foods to aspirate for two reasons: The small pieces can block multiple small airways, and the salt, which is very irritating, causes a lot of inflammation.
“Cameron was one of the sickest patients I ever cared for as an emergency physician. I did everything I could within my scope of practice, but he needed the tools and expertise of pediatric subspecialists,” recalls Galina Lipton, MD, from Boston Children’s Department of Emergency Medicine, who was staffing the South Shore Hospital emergency room that evening. Full story »
Last week, Boston Children’s Hospital’s Innovation Acceleration Program hosted a jam-packed Innovators’ Showcase where teams from around the hospital networked, traded ideas and showed off their projects. Here are a few Vector thinks are worth watching.
1. An imaging ‘biomarker’ after concussion
Thirty percent of people who suffer a mild traumatic brain injury—a.k.a. concussion—have ongoing symptoms that can last months or years. If patients at risk could be identified, they could receive early interventions such as brain cooling and anti-seizure medications. New MRI protocols that can measure free, non-directional diffusion of water, coupled with sophisticated analytics, are achieving unprecedented pictures of what happens inside the brain after injury. Full story »
Alexandra Pelletier is a manager in the Innovation Acceleration Programat Boston Children’s Hospital. She directs the FastTrack Innovation in Technology Program, a hospital initiative to accelerate, rapidly develop and deliver innovative clinical software solutions.
Do you know the feeling of opening a new box with technology in it? I’m not a tech geek, but when my Google Glass arrived, with its crisp and simple packaging, my visceral reaction was “this is really cool.” Nonetheless, I’m approaching Glass carefully, because even the best technologies still require humans to use them. That means that they must be easy to use, must connect with other systems seamlessly and must offer value that makes its adoption worthwhile.
Google Glass is gaining some real excitement in health care. Each day my Twitter feed lights up with a new report of a hospital or practice trying it out. Here at Boston Children’s, we too are investigating the use of this technology through the Google Glass Explorer Program (watch Vector for more to come). We see promising potential for Google’s head-mounted display technology to transform communication and access to real-time information. Full story »
The only time most of us ever look at an insurance claim is after a hospital or doctor visit, when we get a claim summary from our carrier. And then as far as we know, it gets filed away, never again to see the light of day.
But there’s a lot to be learned from these claims data.
As with electronic medical records (EMRs), behind every claim an insurer receives is a detailed record about symptoms, tests, diagnosis and treatment. Properly compiled and analyzed, claims data can be an excellent resource for taking population-level snapshots of disease, helping to identify trends and reveal or probe associations.
That’s why claims data recently caught the eye of Kenneth Mandl, MD, MPH, and Mei-Sing Ong, PhD, two researchers in Boston Children’s Informatics Program (CHIP). Using claims records for roughly 2.5 million Americans, they turned their attention to two conditions—epilepsy and asthma—with interesting results. Full story »
In 2012, Boston Children’s Hospital held the international CLARITY Challenge—an invitation to interpret genomic sequence data from three children with rare diseases and provide a meaningful, actionable report for clinicians and families. (Click for more background on the children, findings and winners.)
The full proceedings, published March 25 in Genome Biology, concluded that while the technical approaches were markedly similar from center to center, the costs, efficiency and scalability were not. Most variable, and most in need of future work, was the quality of the clinical reporting and patient consenting process. The exercise also underscored the need for medical expertise to bring meaning to the genomic data.
That was CLARITY 1. CLARITY 2, focusing on cancer genomics in children, promises to be exponentially more complex. Full story »
A clinician's-eye view of a patient with spinal muscular atrophy during a telemedicine visit.
The jury is still out on telemedicine. Proponents and many patients appreciate its ability to deliver virtual patient care and to extend the reach of experts beyond the brick-and-mortar setting of a hospital. But the real question about telemedicine is: Does it make it difference? Does is it improve care and if so, in what circumstances?
TeleCAPE, a small pilot project at Boston Children’s Hospital, inches the dial toward “yes” for some patients—in particular, home-ventilated patients.
Home-ventilated patients require an inordinate amount of health care resources for even minor conditions. Costs for a simple urinary tract or viral respiratory infection that might be managed without hospitalization can reach up to $83,000 because the child’s complex medical needs require ICU admission. Full story »
The people who deliver care are starting to think in terms of population health.
A growing number of health care professionals are looking at their patients not just as individuals with unique concerns but also as members of larger groups with common problems and needs. This broader, population-based framework could lead to better health outcomes for more people, according to Jonathan Finkelstein, MD, MPH
of Boston Children’s Hospital.
“The health care system is changing from one that’s more reactive to illness—you come see the doctor when you’re not well—to one that’s more responsible for the promotion of health for defined groups of people,” he explains. While individual patients will always be treated as, well, individuals, the concept of population health can help providers “figure out the most appropriate services within a set of limited resources for specific groups.” Full story »
Israel Green-Hopkins, MD, is a second-year fellow in Pediatric Emergency Medicine at Boston Children’s Hospital and a fierce advocate for innovation in health information technology, with a passion for design, mobile health, remote monitoring and more. Follow him on Twitter @israel_md.
A few months ago, I spent 15 minutes filling out a detailed health data form at the doctor’s office. The paper form contained multiple questions about my health, family history, medications and basic demographic information. I assumed that an administrative specialist would code it into the practice’s electronic medical record (EMR) to be put to use. So it came as a surprise when I spent another 5 minutes reviewing the form with my physician, who then proceeded to type this information into the EMR herself. I’m confident neither my physician nor I felt enabled by the experience.
Countless people have had a similar experience—or worse, filled out a form with no sign that any clinician ever saw the information. Though the industry has made outstanding progress in adopting EMRs, the practice of data acquisition from patients remains cloudy. Patient-generated health data (PGHD), a term encompassing all forms of data that patients provide on their own, is a relatively new concept in health care. It falls into two broad groups: historical data and biometric data. Full story »