News Article | May 20, 2017
Doctors use that information to track your medical history and keep tabs on you in the hospital - but what if they could also use it to predict your future health? It's an idea inching closer to reality. This week, Google announced it's teaming up with University of Chicago Medicine to research ways to use machine learning to predict medical events - such as whether someone will be hospitalized, how long that hospitalization will last and whether a patient's health is deteriorating. Google has formed similar partnerships with Stanford Medicine and the University of California at San Francisco. Google and university researchers will try to discover patterns in patients' medical records but the records used in the research will be stripped of personally identifiable information to protect patient privacy. "There's so much health care data, especially with electronic health records being adopted over the last 10 years," said Katherine Chou, who's leading the project for Google Research. "The potential for using that data for predictions, people haven't really figured out how to harness it." University of Chicago Medicine has spent years working on ways to use data to predict health events. Researchers developed an algorithm called eCART that uses patient data to predict cardiac arrest, and if a patient is high-risk, nurses will perform extra checks on the patient. University of Chicago already uses eCART on its adult patients. Dr. Michael Howell, the medical center's chief quality officer, said he's confident eCART has helped reduce instances of cardiac arrest, but he said researchers are still collecting data on its effectiveness. The partnership with Google will help expand on such work, said Dr. Samuel Volchenboum, director of the Center for Research Informatics at University of Chicago Medicine. Chou said Google team members met the University of Chicago's Howell at a Harvard University medical training program, and Google saw how its ability to organize data and make it accessible could apply in health care. It's too early to tell whether Google could potentially develop a product or service using the technology, Google spokesman Jason Freidenfelds said in an email. At this point, Google is focused on demonstrating that the approach can improve patient care, he said. Chicago company Quant HC has already commercialized eCART, selling it to hospitals, including Amita Health Alexian Brothers Medical Center and some of NorthShore University HealthSystem's hospitals, said Dr. Dana Edelson, who helped develop eCART at the University of Chicago and is now CEO of Quant. "If you do more preventative care, then you have a win-win situation," Chou said. Explore further: The neighborhood effect: Sicker patients draw on shared resources
Mayampurath A.,Computation Institute |
Mayampurath A.,Center for Research Informatics |
Rogers M.R.,University of Chicago |
Wolfgeher D.J.,University of Chicago |
And 4 more authors.
Analytical Biochemistry | Year: 2016
The presence of the dense hydroxyapatite matrix within human bone limits the applicability of conventional protocols for protein extraction. This has hindered the complete and accurate characterization of the human bone proteome thus far, leaving many bone-related disorders poorly understood. We sought to refine an existing method of protein extraction from mouse bone to extract whole proteins of varying molecular weights from human cranial bone. Whole protein was extracted from human cranial suture by mechanically processing samples using a method that limits protein degradation by minimizing heat introduction to proteins. The presence of whole protein was confirmed by western blotting. Mass spectrometry was used to sequence peptides and identify isolated proteins. The data have been deposited to the ProteomeXchange with identifier PXD003215. Extracted proteins were characterized as both intra- and extracellular and had molecular weights ranging from 9.4 to 629 kDa. High correlation scores among suture protein spectral counts support the reproducibility of the method. Ontology analytics revealed proteins of myriad functions including mediators of metabolic processes and cell organelles. These results demonstrate a reproducible method for isolation of whole protein from human cranial bone, representing a large range of molecular weights, origins and functions. © 2016 Elsevier Inc.
Regnier S.M.,Committee on Molecular Metabolism and Nutrition |
Regnier S.M.,University of Chicago |
Kirkley A.G.,Section of Endocrinology |
Kirkley A.G.,University of Chicago |
And 23 more authors.
Endocrinology | Year: 2015
Environmental endocrine disruptors are implicated as putative contributors to the burgeoning metabolic disease epidemic. Tolylfluanid (TF) is a commonly detected fungicide in Europe, and previous in vitro and ex vivo work has identified it as a potent endocrine disruptor with the capacity to promote adipocyte differentiation and induce adipocytic insulin resistance, effects likely resulting from activation of glucocorticoid receptor signaling. The present study extends these findings to an in vivo mouse model of dietary TF exposure. After 12 weeks of consumption of a normal chow diet supplemented with 100 parts per million TF, mice exhibited increased body weight gain and an increase in total fat mass, with a specific augmentation in visceral adipose depots. This increased adipose accumulation is proposed to occur through a reduction in lipolytic and fatty acid oxidation gene expression. Dietary TF exposure induced glucose intolerance, insulin resistance,and metabolic inflexibility, while also disrupting diurnal rhythms of energy expenditure and food consumption. Adipose tissue endocrine function was also impaired with a reduction in serum adiponectin levels. Moreover, adipocytes from TF-exposed mice exhibited reduced insulin sensitivity, an effect likely mediated through a specific down-regulation of insulin receptor substrate-1 expression, mirroring effects of ex vivo TF exposure. Finally, gene set enrichment analysis revealed an increase in adipose glucocorticoid receptor signaling with TF treatment. Taken together, these findings identify TF as a novel in vivo endocrine disruptor and obesogen in mice, with dietary exposure leading to alterations in energy homeostasis that recapitulate many features of the metabolic syndrome. Copyright © 2015 by the Endocrine Society
News Article | October 28, 2016
Litmus Health, a clinical data science platform focused on health-related quality of life, today launched into public beta. The company uses data collected at the point of experience from wearables, smart devices, and home sensors to inform clinical endpoints and guide trial management. Litmus is initially focused on Phase I/II clinical trials. The decision faced by pharma to move forward from Phase II to Phase III is an expensive one, as several hundred million dollars usually hang in the balance. The goal is to get breakthrough treatments to market faster by putting health-related quality of life at the forefront of clinical development. Too often researchers press forward having collected little data on what’s happening outside the clinic, and even then, only across a few dimensions. “The answers we need are everywhere around us,” said Dr. Samuel Volchenboum, Chief Science Officer of Litmus, and Director of the Center for Research Informatics at the University of Chicago. “We need a better way to collect data in clinical research. Smartphones, wearables, and home sensors present a unique opportunity. Most researchers understand the value of patient-generated information collected at the point of experience, but they have no good way to harness those data. The ability to measure outcomes in multiple dimensions, remotely, is key. Litmus helps research teams and their sponsors make more confident go / no-go decisions.” The Litmus platform supports more than 200 data sources that describe patients’ behavior and environments. The company also draws from a library of validated patient surveys and can easily add new instruments. Researchers are able to customize their data sources and build their unique trial, combining traditional validated surveys with patient-generated remote data. The result is a comprehensive indication of a patient’s health and quality of life at any point in time. Once data are collected, Litmus uses machine learning and other algorithms to align time-series data, integrate multiple orthogonal data sources, and look for correlations between behavior, environment, and patient outcomes. The Litmus dashboard displays data that indicate each study’s progress and surfaces population trends. Researchers can view individual participants’ data. The Litmus trial companion mobile app is available for iOS and Android. It serves as a clearing house for device data, which it gathers and sends back to the platform. “These devices are already in the hands of consumers,” said Daphne Kis, CEO of Litmus. “The challenge is to credibly accommodate the data they collect. We have the opportunity to help researchers understand patients and their quality of life as we never have before, and the market is ready. These data are going to have huge implications for the healthcare ecosystem and for how we use patient data both in the clinical trials setting and beyond. In the not too distant future, the entire world will be one big clinical trial.” Litmus’ platform is currently being piloted at the University of Chicago in a clinical trial run by gastroenterologist Dr. David Rubin on the effects activity, sleep, and diet on Inflammatory Bowel Disease (IBD) patients. “We all want to collect higher quality, more accurate data from patients in our clinical trials,” said Rubin. “Litmus is the first platform I’ve seen that actually delivers.” Litmus was founded by an interdisciplinary team of healthcare, bioinformatics, and software engineering experts. The team is led by Daphne Kis, CEO, and Dr. Samuel Volchenboum, Chief Science Officer. The Litmus platform meets the standards for collecting and storing data according to HIPAA regulations and is 21 CFR Part 11 compliant. The data the company collects are ready for submission in CDISC’s CDASH format, as mandated by the FDA. Litmus is a clinical data science platform focused on health-related quality of life. We use data collected at the point of experience from wearables, smart devices, and home sensors to guide management and to inform trial endpoints. Continuously measuring outcomes in multiple dimensions leads to faster, more efficient drug-development pipelines. The answers we need are all around us. Learn more at: http://www.litmushealth.com.
News Article | December 27, 2016
In a research letter published Dec. 27, 2016, in JAMA, University of Chicago physicians describe a new concern for patients in the hospital: distractions caused by the misfortune of other patients. The researchers found that when one patient on a typical 20-bed hospital unit took a turn for the worse - a cardiac arrest, for example, or being transferred to an intensive-care unit - the other patients on that ward were at increased risk for their own setbacks. In the six hours after a critical-illness event, the odds that a second patient in the same unit would undergo a comparable crisis increased by about 18 percent. If there were two such events during a six-hour time period, the risk of yet another occurrence went up by about 53 percent. Risks were slightly higher when the initial critical illness events occurred at night. Cardiac arrests, urgent ICU transfers or patient deaths were also associated with delayed discharge from the hospital for the other patients on the same unit. "This should serve as a wake-up call for hospital-based physicians," said study author Matthew Churpek, MD, MPH, PhD, assistant professor of medicine at the University of Chicago. "Our data suggests that after caring for a patient who becomes critically ill on the hospital wards, we should routinely check to see how the other patients on the unit are doing," Churpek said. "Following these high-intensity events, our to-do list should include a thorough assessment of the other patients on the unit, to make sure none of them are at risk of slipping through the cracks." Luckily, such events were relatively rare. Nearly 84,000 adult patients were admitted to non-ICU beds at the University of Chicago Medicine from 2009 to 2013. About five percent of those patients were subsequently transferred to an intensive-care unit (4,107) or experienced an in-hospital cardiac arrest (179). Patients who had a cardiac arrest or required ICU transfer tended to be a few years older and male. They had been in the hospital, on average, for 13 days, four times longer than patients who did not have a critical-illness event. "We suspected this phenomenon based on our own anecdotal experience," said co-author Samuel Volchenboum, MD, PhD, associate professor of pediatrics at the University of Chicago and director of the University's Center for Research Informatics. "But until we had access to a large, well-curated research-data warehouse, we couldn't perform a study like this." "Very few academic centers have access to the kinds of high-quality data needed to perform this type of investigation," he added. The study was designed to detect and quantify any increased risk to neighboring patients. The researchers speculate that one potential factor may be that doctors and nurses could have been "temporarily diverted to help care for critically ill patients," Volchenboum said. "Further study is needed to determine the causes of this effect." The study was funded by the National Heart Lung and Blood Institute. Additional authors were Anoop Mayampurath, Gözde Göksu-Gürsoy, Dana P. Edelson and Michael D. Howell, all from the University of Chicago.