Hopkins inHealth Pilot Project Discovery Program -- Awardee Announcement
The Johns Hopkins Individualized Health Initiative (Hopkins inHealth), a signature initiative of the Johns Hopkins University, Health System, and Applied Physics Laboratory, is pleased to announce eight new pilot projects as awardees of its inaugural Pilot Project Discovery Program. The selected projects, which represent the best of innovative thinking at Johns Hopkins, will bring the institution closer to achieving a vision where every personal health decision is informed by the latest scientific knowledge. The awardees will employ a variety of approaches to tackle health challenges ranging from cancer and cardiovascular disease to dementia and depression. Some projects will focus on the development of sophisticated methods to predict health outcomes; others will leverage mobile technologies to monitor patient conditions and advance clinical decision-making. All of the projects seek to advance individualized health in the US and beyond.
The Pilot Project Discovery Program was conceived to promote discoveries in biomedical and data science intended to improve health decisions and outcomes at more affordable costs. The program invited proposals that aimed to more precisely characterize an individual’s health status and likely health trajectory. Proposals that sought to augment clinical decision-making by taking into account the benefits and risks of health interventions were also solicited.
Faculty and staff from seven divisions across Johns Hopkins submitted a total of 95 applications. A pool of 35 reviewers, representing faculty and staff across a range of disciplines, ranked the proposals on scientific merit and potential to advance the mission of Hopkins inHealth. A final seven-member committee, consisting of leaders across Johns Hopkins, reviewed the top-ranked applications and selected the final awardees.
Each of the awarded projects will receive up to $75,000 for a 15-month funding period. Seven of the projects will be funded by Hopkins inHealth; one will be funded in partnership with Booz Allen Hamilton*. Hopkins inHealth will also provide scientific and technical support through its expertise cores in the areas of bioethics, study design and analysis, measurement, and database utilization.
2016 Hopkins inHealth Pilot Project Discovery Program Awardees:
1. Monitoring and Improving Patient Recovery after Cardiac Surgery Using Activity Monitors
Principal Investigator: Charles Brown, Anesthesiology and Critical Care Medicine, School of Medicine
Key Personnel: Jennifer Schrack, Epidemiology, School of Public Health; Vadim Zipunnikov, Biostatistics, School of Public Health; Scott Swetz, APL Senior Staff; Christopher Sciortino, Surgery, School of Medicine
Project Goal(s): To use activity monitors to characterize mobility in patients after cardiac surgery and identify the types and quantity of activity associated with good clinical outcomes. The project team will use this information to develop an intervention to improve mobility in patients with impaired activity. The team also plans to collaborate with systems engineers to identify the requirements and develop the systems concept necessary to automate the process through which the captured mobility data is transmitted to clinical staff.
2. Epileptic Seizure Watch
Principal Investigator: Nathan Crone, Neurology, School of Medicine
Key Personnel: Suchi Saria, Computer Science, Whiting School of Engineering; Gregory Krauss, Neurology, School of Medicine
Project Goal(s): To use data captured on patients with epilepsy by EpiWatch, an app available on the Apple Watch, to develop an algorithm that will optimize seizure detection based on patients’ prior seizures and their individual, seizure-related physiologic changes. The app will use sensors available on the watch to evaluate biological markers of seizures and will enable users to give feedback on whether a seizure occurred, allowing the team to continually improve the detection algorithm based on patient data.
3. Baltimore Falls Reduction Initiative Engaging Neighborhoods & Data (B'FRIEND)
Principal Investigator: Hadi Kharrazi, Health Policy and Management, School of Public Health, and Division of Health Sciences Informatics, School of Medicine
Key Personnel: Jonathan Weiner, Health Policy and Management, School of Public Health;
Joshua Sharfstein, Associate Dean for Public Health Practice and Training, School of Public Health
Project Goal(s): To use data collected by the state of Maryland to develop a risk score for older adults in Baltimore who will experience a fall requiring hospitalization. The project team will map the data across the city, allowing health officials to develop tailored, community-based interventions for city areas with high-risk scores.
4. Forecast of Future Events for Individualized Dementia Care: Dementia Forecast
Principal Investigator: Kenichi Oishi, Radiology and Molecular Radiation Sciences, School of Medicine
Key Personnel: Michael Miller, Biomedical Engineering, Whiting School of Engineering;
Constantine Lyketsos, Psychiatry, School of Medicine
Project Goal(s): To develop a statistical model, using neurological images and clinical assessments, that can predict the likelihood a patient with dementia will experience worsening cognition, behavioral problems, and falls. By creating this individualized risk prediction model, the project team will enable patients and their caregivers to make more informed care decisions.
5. Rapid Detection of Infection by Carbapenemase-Producing Organisms
Principal Investigator: Pranita Tamma, Pediatric Infectious Diseases, School of Medicine
Key Personnel: Karen Carroll, Pathology, School of Medicine; Patricia Simner, Pathology, School of Medicine
Project Goal(s): To use mass spectrometry to create a library of bacterial infections that produce an enzyme (carbapenemase) that renders bacteria highly drug resistant and, therefore, difficult to treat. By incorporating the information generated by the project into existing technologies, laboratories will be able to identify carbapenemase-producing infections about two days earlier than current practice, allowing clinicians to optimize antibiotic therapy sooner and limit the spread of highly drug resistant bacteria to other patients.
6. Personalized Risk Stratification for Sudden Cardiac Death Using Cardiac MRI and Virtual Heart Electrophysiologic Studies (PuRSUit-Virtual Heart)
Principal Investigator: Katherine Wu, Cardiology, School of Medicine
Key Personnel: Natalia Trayanova, Biomedical Engineering, Whiting School of Engineering;
Eliseo Guallar, Epidemiology, School of Public Health
Project Goal(s): To develop a new risk stratification approach to better predict sudden cardiac death among patients with non-ischemic cardiomyopathy (impairment of heart muscle function). The project team plans to integrate structural heart data using magnetic resonance imaging with electrophysiologic properties to create virtual whole heart models. These models will be used to individualize risk prediction to improve clinical decision-making.
7. Decoding Tumor Heterogeneity by Bayesian Statistical Models
*This project is jointly funded by Booz Allen Hamilton and Hopkins inHealth.
Principal Investigator: Yanxun Xu, Applied Mathematics and Statistics, Whiting School of Engineering
Key Personnel: Luigi Marchionni, Oncology, School of Medicine
Project Goal(s): To better characterize the heterogeneity inherent in the tumors of cancer patients by using state-of-the-art sequencing technology and statistical modeling. The project team will use their markers of tumor heterogeneity to predict patient survival and responsiveness to treatment, further advancing the individualization of cancer care.
8. Using Mobile Technology to Expand a Learning Health System for Depression
Principal Investigator: Peter Zandi, Mental Health, School of Public Health
Key Personnel: Fernando Goes, Psychiatry, School of Medicine
Project Goal(s): To improve the care of patients with depression by developing a phone app that uses captured data to continually adapt patient treatment plans. The app will monitor treatment adherence, efficacy, and safety in patients and transmit the data to clinical staff. The project team will test the app in a community clinic, evaluating its usage by and benefit to patients and clinicians.