Tag Archive for: data

Attendees at the inaugural symposium on AI in Pediatric Health and Rare Diseases

AI: The “single greatest tool” for improving access to pediatric healthcare

Attendees at the inaugural symposium on AI in Pediatric Health and Rare Diseases

The daylong event drew experts from the Food and Drug Administration, Pfizer, Oracle Health, NVIDIA, AWS Health and elsewhere to start building a community aimed at using data for the advancement of pediatric medicine.

The future of pediatric medicine holds the promise of artificial intelligence (AI) that can help diagnose rare diseases, provide roadmaps for safer surgeries, tap into predictive technologies to guide individual treatment plans and shrink the distance between patients in rural areas and specialty care providers.

These and dozens of other innovations were contemplated as scientists came together at the inaugural symposium on AI in Pediatric Health and Rare Diseases, hosted by Children’s National Hospital and the Fralin Biomedical Research Institute at Virginia Tech. The daylong event drew experts from the Food and Drug Administration, Pfizer, Oracle Health, NVIDIA, AWS Health and elsewhere to start building a community aimed at using data for the advancement of pediatric medicine.

“AI is the single greatest tool for improving equity and access to health care,” said symposium host Marius George Linguraru, D.Phil., M.A., M.Sc., principal investigator at the Sheikh Zayed Institute for Pediatric Surgical Innovation. “As a population, kids are vastly underrepresented in scientific research and resulting treatments, but pediatric specialties can use AI to provide medical care to kids more efficiently, more quickly and more effectively.”

What they’re saying

Scientists shared their progress in building digital twins to predict surgical outcomes, enhancing visualization to increase the precision of delicate interventions, establishing data command centers to anticipate risks for fragile patients and more. Over two dozen speakers shared their vision for the future of medicine, augmented by the power of AI:

  • Keynote speaker Subha Madhavan, Ph.D., vice president and head of AI and machine learning at Pfizer, discussed various use cases and the potential to bring drugs to market faster using real-world evidence and AI. She saw promise for pediatrics. “This is probably the most engaging mission: children’s health and rare diseases,” she said. “It’s hard to find another mission that’s as compelling.”
  • Brandon J. Nelson, Ph.D., staff fellow in the Division of Imaging, Diagnostics and Software Reliability at the Food and Drug Administration, shared ways AI will improve diagnostic imaging and reduce radiation exposure to patients, using more advanced image reconstruction and denoising techniques. “That is really our key take-home message,” he said. “We can get what … appear as higher dose images, but with less dose.”
  • Daniel Donoho, M.D., a neurosurgeon at Children’s National, introduced the audience to the potential of “Smart ORs”: operating rooms where systems can ingest surgery video and provide feedback and skill assessments. “We have to transform the art of surgery into a measurable and improvable scientific practice,” he said.
  • Debra Regier, M.D., chief of Genetics and Metabolism at Children’s National, discussed how AI could be used to diagnose and treat rare diseases by conducting deep dives into genetics and studying dysmorphisms in patients’ faces. Already, Children’s National has designed an app – mGene – that measures facial features and provides a risk score to help anyone in general practice determine if a child has a genetic condition. “The untrained eye can stay the untrained eye, and the family can continue to have faith in their provider,” she said.

What’s next

Linguraru and others stressed the need to design AI for kids, rather than borrow it from adults, to ensure medicine meets their unique needs. He noted that scientists will need to solve challenges, such as the lack of data inherent in rare pediatric disorders and the simple fact that children grow. “Children are not mini-adults,” Linguraru said. “There are big changes in a child’s life.”

The landscape will require thoughtfulness. Naren Ramakrishnan, Ph.D., director of the Sanghani Center for Artificial Intelligence & Analytics at Virginia Tech and symposium co-host, said that scientists are heading into an era with a new incarnation of public-private partnerships, but many questions remain about how data will be shared and organizations will connect. “It is not going to be business as usual, but what is this new business?” he asked.

The science-policy interface

We can do better: Lessons learned on COVID-19 data sharing can inform future outbreak preparedness

Since COVID-19 emerged late last year, there’s been an enormous amount of research produced on this novel coronavirus disease. But the content publicly available for this data and the format in which it’s presented lack consistency across different countries’ national public health institutes, greatly limiting its usefulness, Children’s National Hospital scientists report in a new study. Their findings and suggestions, published online August 19 in Science & Diplomacy, could eventually help countries optimize their COVID-19-related data — and data for future outbreaks of other diseases — to help further new research, clinical decisions and policy-making around the world.

Recently, explains study senior author Emmanuèle Délot, Ph.D., research faculty at Children’s National Research Institute, she and her colleagues sought data on sex differences between COVID-19 patients around the world for a new study. However, she says, when they checked the information available about different countries, they found a startling lack of consistency, not only for sex-disaggregated data, but also for any type of clinical or demographic information.

“The prospects of finding the same types of formats that would allow us to aggregate information, or even the same types of information across different sites, was pretty dismal,” says Dr. Délot.

To determine how deep this problem ran, she and colleagues at Children’s National, including Eric Vilain, M.D., Ph.D., the James A. Clark Distinguished Professor of Molecular Genetics and the director of the Center for Genetic Medicine Research at Children’s National, and Jonathan LoTempio, a doctoral candidate in a joint program with Children’s National and George Washington University, surveyed and analyzed the data on COVID-19.

The research spanned data reported by public health agencies from highly COVID-19 burdened countries, viral genome sequence data sharing efforts, and data presented in publications and preprints.

PubMed entries with coronavirus

Publications with the term “coronavirus” archived in PubMed over time.

At the time of study, the 15 countries with the highest COVID-19 burden at the time included the US, Spain, Italy, France, Germany, the United Kingdom, Turkey, Iran, China, Russia, Brazil, Belgium, Canada, the Netherlands and Switzerland. Together, these countries represented more than 75% of the reported global cases. The research team combed through COVID-19 data presented on each country’s public health institute website, looking first at the dashboards many provided for a quick glimpse into key data, then did a deeper dive into other data on this disease presented in other ways.

The data content they found, says LoTempio, was extremely heterogeneous. For example, while most countries kept running totals on confirmed cases and deaths, the availability of other types of data — such as the number of tests run, clinical aspects of the disease such as comorbidities, symptoms, or admission to intensive care, or demographic information on patients, such as age or sex — differed widely among countries.

Similarly, the format in which data was presented lacked any consistency among these institutes. Among the 15 countries, data was presented in plain text, HTML or PDF. Eleven offered an interactive web-based data dashboard, and seven had comma-separated data available for download. These formats aren’t compatible with each other, LoTempio explains, and there was little to no documentation about where the data that supplies some formats — such as continually updated web-based dashboards — was archived.

The science-policy interface

Graphic representation of the science-policy interface.

Dr. Vilain says that a robust system is already in place to allow uniform sharing of data on flu genomes — the World Health Organization’s (WHO) Global Initiative on Sharing All Influenza Data (GISAID) — which has been readily adapted for the virus that causes COVID-19 and has already helped advance some types of research. However, he says, countries need to work together to develop a similar system for harmonized sharing other types of data for COVID-19. The study authors recommend that COVID-19 data should be shared among countries using a standardized format and standardized content, informed by the success of GISAID and under the backing of the WHO.

In addition, the authors say, the explosion of research on COVID-19 should be curated by experts who can wade through the thousands of papers published on this disease since the pandemic began to identify research of merit and help merge clinical and basic science.

“Identifying the most useful science and sharing it in a way that’s usable to most researchers, clinicians and policymakers, will not only help us emerge from COVID-19 but could help us prepare for the next pandemic,” Dr. Vilain says.

Other researchers who contributed to this study include D’Andre Spencer, MPH, Rebecca Yarvitz, BA, and Arthur Delot-Vilain.