Demonstration Projects Funding Program
Co-Sponsored by the Johns Hopkins Data Science and AI Institute
The Malone Center for Engineering in Healthcare and the Johns Hopkins Data Science and AI Institute are proud to announce the launch of the Demonstration Projects Funding Program, aimed at accelerating the development and deployment of data science and artificial intelligence tools in critical applications. This program is oriented towards translational efforts rather than fundamental research.
The funding program will support long-term demonstration projects on high-impact translational projects that bring researchers, engineers, and/or clinicians across the institution and potentially external partners together. The demonstration projects are expected to demonstrate the substantial gains that can be achieved by developing, implementing, and deploying data science or AI within a research program that is already externally funded. The program is expected to accelerate translation and lead to strong additional external funding, philanthropic support, and new partnerships.
Learn more and apply here.
The Malone Center for Engineering in Healthcare and Johns Hopkins Hospital Internship
Position Summary: We are seeking one or two enthusiastic data science interns who are interested in the application of mathematical and computational techniques to solve real-world problems in health care. This internship is a collaboration between the Whiting School of Engineering, the School of Medicine, and Rubicon Health.
The ideal candidate will have strong data science skills (modeling and coding) and a background in microbiology (or willingness to learn). Our collaboration is focused on creating analytics and cognitive aids to help clinicians and clinical teams treat critically ill children. Sepsis is a syndrome, triggered by an infection, with life-threatening organ dysfunction caused by a dysregulated host immune response. Annually in the U.S., 1.7 million adults and 75,000 children have sepsis and about 20% of those adults and 10% of those children die. Antibiotic administration delays are common and associated with increased mortality. Once started, broad-spectrum antibiotic therapy for sepsis is often unnecessarily prolonged. Current electronic health record (EHR) based clinical decision supports (CDS) have not improved sepsis care.
We are leveraging the JHU Precision Medicine Analytics Platform (PMAP) to develop an innovative extensible comprehensive CDS software package to assist the clinical team in:
- Differentiating bacterial from viral infections so antibiotic use can be minimized; and
- When antibiotics are prescribed, using all available data to determine whether there has been a measurable clinical improvement attributable to the antibiotics.
The first project will take all the microbiology test results and, with census block-level geocodes, map where infections are occurring and use spatial time-series analyses to allow the geocoded data to add features to an antibiotic decision algorithm. There is substantial work necessary to clean the data and, collaborating with pediatric infectious diseases colleagues, create logical microbiological hierarchies of the 2.5 million results. We will then work with collaborators at the Bloomberg School of Public Health to map the data and look for clusters. Finally, we will work with collaborators at Morgan State University (and elsewhere) to include environmental data to see if we can predict and/or prevent infections.
The second project is more complex. We are guessing that in a typical pediatric intensive care unit, about half of all antibiotics are given for infections that are not antibiotic-responsive (e.g., viral infections) or sometimes for conditions that are not caused by an infection. The first step would be to work with time-series data and correlate physiological responses to doses of antibiotics. The second step would be to annotate the dataset with labels indicative of what type of infection, if any, the patient actually suffered.
Accepted students can expect an experience like a lab rotation, as well as exposure to operational and clinical workflows relevant to translational medical research. The internships will start as soon as possible and are expected to last 16 weeks upon satisfactory performance. There is a possibility of extension depending on the performance of the student and the needs of the project.
Benefits for the Student: This internship is ideally suited to students with strong analytic skills and an interest in pursuing health care-oriented entrepreneurship or careers in industry or academia. Interns will acquire theoretical and practical training in advancing the practice of medicine and health care delivery using data science and systems engineering, with a particular focus on EHR data and optimization techniques. Interns will have access to faculty and staff in the Malone Center for Engineering in Healthcare, the Center for Systems Science and Engineering, the Department of Anesthesiology and Critical Care Medicine, and Rubicon Health and will work in interdisciplinary teams. The project is led by James “Jim” Fackler—the director of safety, quality, and logistics at the Johns Hopkins Pediatric Intensive Care Unit—and John C. Malone Assistant Professor of Civil and Systems Engineering Kimia Ghobadi. Experiences gained will be highly informative and advantageous to students who plan to pursue further training (e.g., graduate or medical school), expand their interdisciplinary skills and knowledge, or work in this arena after graduation. The project will prepare students to showcase their skills in data analytics, analytical thinking, and operations research.
Compensation: Class credit. Compensation may be available in special cases.
Required Education: Undergraduate or master’s students in systems engineering, computer science, applied mathematics and statistics, biomedical engineering, or relevant fields. No previous research/industry experience required.
Desired knowledge, skills, and abilities:
- Excellent high-level communication skills
- Strong critical thinking and analytical reasoning skills
- Ability to execute assigned project tasks within an established schedule
- Sound documentation skills (i.e., writes and communicates clearly and concisely)
- Proficiency with multiple programming languages (e.g., Python, R, Julia)
- Strong data sciences, data analytics, and AI skills and knowledge
- Prior experience in health care-oriented research desired but not necessary
- Experience in spatiotemporal analysis and software desired but not necessary
Application Process: Please send your resume, a one-page cover letter (describing relevant course work, research experience, and/or plans for your industry/research career) and contact information for one letter of recommendation/professional reference (only the contact information, we will request the letters ourselves for select candidates). Email applications to Jim Fackler with the subject line “MCEH Internship Application.”
Application Status: Open
Strategic Initiatives
Identifying Mechanisms Responsible for Inequitable Health Outcomes for COVID-19
The COVID-19 pandemic has exposed longstanding health inequities in United States; evidence is mounting that some ethnic groups are suffering far worse outcomes, including mortality, compared to others. Precise mechanisms driving these disparities are not currently well understood, and may include socioeconomic factors, prevalence of important comorbidities, or even other mechanisms such as differential adherence to government interventions.
In this proposed study, the team will leverage modern causal inference methodology to investigate mechanisms behind observed disparities associated with causal pathways mediated by by socioeconomic factors, biological factors, or differences in care. Their findings will be made available to the scientific and legislative communities as soon as possible to help guide continued research and political intervention to mitigate the causes of inequitable health outcomes in COVID-19.
This project is a continuation of work started at the center’s 2021 symposium, “Disparities and COVID-19: A Two Day Virtual Workshop on Data Science for Social Good.”