Congratulations to Rimma Pivovarov-Perotte for winning the first annual dissertation award for her thesis entitled, “Electronic Health Record Summarization over Heterogeneous and Irregularly Sampled Clinical Data.” Great job, and it reflects greatly on the department!
And thanks to Ted Shortliffe for initiating this award series.
Congratulations to Andrew Chiang for winning the National Library of Medicine annual training meeting (i.e., for our training grant) Best Talk for day one. It was on, “Correlates of Cognitive Phenotype Severity in Autism Spectrum Disorders.”
The American College of Medical Informatics (ACMI) will present the 2017 Morris F. Collen Award of Excellence to Professor Carol Friedman, PhD, during the Opening Session of AMIA’s Annual Symposium in Washington, D.C. AMIA’s Annual Symposium is taking place Nov. 4-8.
In honor of Morris F. Collen, a pioneer in the field of medical informatics, this prestigious award is presented to an individual whose personal commitment and dedication to medical informatics has made a lasting impression on the field. The award is determined by ACMI’s Awards Committee.
Dr. Carol Friedman is a Professor of Biomedical Informatics at Columbia University and Director of the Department’s Graduate Training Program. She received her M.A. and Ph.D. in Computer Science from the Courant Institute of Mathematics at New York University, where her research focused on the natural language processing (NLP) of complex language structures. After receiving her Ph.D. degree, Dr. Friedman joined the Department of Biomedical Informatics at Columbia as an Assistant Professor.
Dr. Friedman is a recognized pioneer in NLP within the biomedical domain with an established national and international reputation. Her current research is devoted to the use of NLP methodology to obtain executable data and knowledge from clinical reports and biomedical text, to be employed for discovery and patient care, with a special focus on pharmacovigilance and medication safety. Dr. Friedman was one of the first researchers to demonstrate the value of NLP for a broad range of clinical and biomedical applications that include decision support, automated encoding, vocabulary development, clinical research, data mining, discovery, error detection, genomics research, and pharmacovigilance. She also was one of the first to demonstrate that a general NLP system could be used to improve actual patient care. She developed MedLEE, a comprehensive natural language extraction and encoding system for the clinical domain, which has been used at New York-Presbyterian Hospital (NYP) in collaboration with Dr. George Hripcsak and has been shown to produce results similar to medical experts. She adapted MedLEE to develop GENIES in collaboration with Dr. Andrey Rzhetsky and BioMedLEE in collaboration with Dr. Yves Lussier. GENIES extracts biomolecular relations from journal articles, and BioMedLEE extracts a broad range of genotypic-phenotypic relations from the literature. In her early work, Dr. Friedman helped design the Clinical Patient Repository, which is still in use at NYP.
Dr. Friedman has more than 120 publications consisting of journal articles, conference proceedings, and book chapters, and also holds several patents associated with NLP technology. She is a fellow of the American College of Medical Informatics and the American Academy of Medicine. She has served on the editorial boards of several journals in the biomedical field, and was a member of the Board of Regents and the Board of Counselors of the National Library of Medicine. In 2010, she received the Donald A. B. Lindbergh Award for Innovation in Biomedical Informatics from the American Medical Informatics Association.
President of the American College of Medical Informatics, Christopher Chute, MD, DrPH, FACMI, the Bloomberg Distinguished Professor of Health Informatics, Johns Hopkins University, said, “ I am delighted to announce that Carol Friedman, PhD, has been selected as the recipient of the 2017 Morris F. Collen Award, which will be given during the opening session of the AMIA Annual Symposium. She was selected from an incredibly competitive pool of nominees and I look forward to celebrating Carol’s achievements with you in Washington, DC.”
AMIA’s Annual Symposium is the premier educational event in the field. The symposium presents leading-edge scientific research on biomedical and health informatics and over 100 scientific sessions. The Symposium presents work from across the spectrum of the informatics field — translational bioinformatics, clinical research informatics, clinical informatics, consumer health informatics and public health informatics.
First-of-its-kind, personalized glucose forecasting tool may make meal planning simpler for type 2 diabetes patients
Columbia University researchers have developed a personalized algorithm that predicts the impact of particular foods on an individual’s blood sugar levels. The algorithm has been integrated into an app, Glucoracle, that will allow individuals with type 2 diabetes to keep a tighter rein on their glucose levels—the key to preventing or controlling the major complications of a disease that affects 8 percent of Americans.
The findings were published online today in PLoS Computational Biology.
Medications are often prescribed to help patients with type 2 diabetes manage their blood sugar levels, but exercise and diet also play an important role.
“While we know the general effect of different types of food on blood glucose, the detailed effects can vary widely from one person to another and for the same person over time,” said lead author David Albers, PhD, associate research scientist in biomedical informatics at Columbia University Medical Center (CUMC). “Even with expert guidance, it’s difficult for people to understand the true impact of their dietary choices, particularly on a meal-to-meal basis. Our algorithm, integrated into an easy-to-use app, predicts the consequences of eating a specific meal before the food is eaten, allowing individuals to make better nutritional choices during mealtime.”
The algorithm uses a technique called data assimilation, in which a mathematical model of a person’s response to glucose is regularly updated with observational data—blood sugar measurements and nutritional information—to improve the model’s predictions, explained co-study leader George Hripcsak, MD, MS, the Vivian Beaumont Allen Professor and chair of biomedical informatics at Columbia. Data assimilation is used in a variety of applications, notably weather forecasting.
“The data assimilator is continually updated with the user’s food intake and blood glucose measurements, personalizing the model for that individual,” said co-study leader Lena Mamykina, PhD, assistant professor of biomedical informatics at Columbia, whose team designed and developed the Glucoracle app.
Glucoracle allows the user to upload fingerstick blood measurements and a photo of a particular meal to the app, along with a rough estimate of the nutritional content of the meal. This estimate provides the user with an immediate prediction of post-meal blood sugar levels. The estimate and forecast are then adjusted for accuracy. The app begins generating predictions after it has been used for a week, allowing the data assimilator to learn how the user responds to different foods.
The researchers initially tested the data assimilator on five individuals using the app, including three with type 2 diabetes and two without the disease. The app’s predictions were compared with actual post-meal blood glucose measurements and with the predictions of certified diabetes educators.
For the two nondiabetic individuals, the app’s predictions were comparable to the actual glucose measurements. For the three subjects with diabetes, the app’s forecasts were slightly less accurate, possibly due to fluctuations in the physiology of patients with diabetes or parameter error, but were still comparable to the predictions of the diabetes educators.
“There’s certainly room for improvement,” said Dr. Albers. “This evaluation was designed to prove that it’s possible, using routine self-monitoring data, to generate real-time glucose forecasts that people could use to make better nutritional choices. We have been able to make an aspect of diabetes self-management that has been nearly impossible for people with type 2 diabetes more manageable. Now our task is to make the data assimilation tool powering the app even better.”
Encouraged by these early results, the research team is preparing for a larger clinical trial. The researchers estimate that the app could be ready for widespread use within two years.
Congratulations to Noémie Elhadad for receiving a grant from the Endometriosis Foundation of America for her Citizen Endo project (citizenendo.org) to phenotype endometriosis through citizen science and data science.
In addition, the Health Natural Language Processing (hNLP) Center is a new initiative founded by Noémie Elhadad (Columbia University), Martha Palmer (Colorado Boulder), and Guergana Savova (Boston Children’s Hospital). The Center’s primary activities are to (1) provide a repository and a data curation, distribution and management point for health-related language resources; (2) support sponsored research programs and health-related language-based technology evaluations; (3) engage in collaborations with US and foreign researchers, institutions and data centers; and (4) host and participate in various workshops. More at http://center.healthnlp.org.