HDS

The COVID-19 pandemic has produced a staggering array of challenges that clinicians, public health experts, and policy makers are struggling to meet. Data scientists and quantitative experts across the globe have gone into overdrive as they work to analyze a flood of information, seeking not only to better understand, track, and predict the disease, but also to help guide the response to it and ensure that timely, accurate, and trustworthy information is readily available for everyone from scientists and clinicians to communities and members of the public.

This urgent need to bridge the worlds of data science, clinical research, and public health was the driving force behind this summer’s COVID + Data Science Virtual Seminars. Sponsored by Duke Plus Data Science (+DS), the 8-week series in summer 2020 was devoted to exploring data science methods with direct applications to the COVID-19 pandemic.

The series of 12 lectures attracted more than 1,500 virtual attendances, with many participants joining across multiple weeks and topics. The series, which wrapped up in late August, provided the opportunity for audiences both within Duke and beyond to hear directly from experts on topics spanning data analysis and visualization, deep learning, statistical methods, natural language processing, molecular methodology, and more.

Read the full story at the Center for Computational Thinking website: https://computationalthinking.duke.edu/2020/11/03/plus-ds-covid-2020-summer-seminars/

BLOG: “As we advance into the era of learning health systems, we need to systematize a process for how clinicians and data scientists can work together to solve important problems with EHR data.” – Andrew Olson, MPP, and Scott Kollins, PhD

READ MORE

The +DS program held a student showcase on Wednesday, December 4, 2019 from 4:30-6:00 PM in the Energy Hub Atrium (first floor of Gross Hall). More than 30 student posters were presented.

27 teams with 62 students presented from the +DS fall 2019 course POE 190.01/POE 790.01 “Introduction to Machine Learning Methods and Practice.” This mini-class has introduced students to machine learning methods that have become increasingly useful in practice, specifically deep learning and neural networks. The student have produced their end-of-semester projects with applications of machine learning to a problem of relevance to their field of study or major.

5 teams with 8 students presented from the +DS Advanced Projects. Students who have previously completed the +DS curriculum are eligible to apply for the Advanced Projects, typically structured as an independent study project, where they are mentored by experts in data science partnered within clinicians in areas of focus including dermatology, ophthalmology, pathology, radiology, and cardiology.

These +DS project-based learning teams offer Duke students, both undergraduate and graduate, the opportunity to be a part of teams applying advanced data science methods and machine learning to real-world problems, and as a means of learning the important field of machine learning in a manner that is accessible and adaptive to all Duke students.

Students, faculty, and staff from across Duke recently assembled for the Data Science Student Showcase, held at the Gross Hall Atrium on the morning of April 25th. Put together by the +DS Projects in Medicine and the DCRI-Forge HDS Internship Program(link is external), the event served as a platform for students to present the projects that they have been immersed in during the spring semester.

“The students have an important opportunity to learn through these experiences,” said Lisa Wruck, PhD, director of the Center for Predictive Medicine, who delivered the introductory remarks at the event. “We appreciate the contributions of the mentors, program coordinators, and the hard work of the students themselves.”

The Showcase featured the efforts of nine students with the DCRI-Forge HDS Internship Program. Through brief “lightning talks,” they were able to highlight the methods and initial findings of their research. Twelve student teams with the +DS Projects in Medicine also presented posters about their applied projects, for a total of 71 student participants.

“It’s not just applying machine learning models, but also about having a more immersive experience with real data, provenance, and applications,” said Ricardo Henao, PhD, Duke Forge principal data scientist and assistant professor in the Department of Biostatistics and Bioinformatics, who provided the closing remarks. “With +DS, we establish a solid background in machine learning. Then with the HDS interns, we are addressing real problems and developing the pipeline.”

The +DS Projects in Medicine is an eight-month program where students get a chance to apply state-of-the-art deep learning technology to image analysis, with the goal of assisting clinicians in making decisions on diagnosis and delivery of care. During the fall 2018 semester, students received training in deep learning with a particular focus on image analysis, constituted via the online +DS learning modules and through complementary in-person learning experiences. Thirteen student teams were formed in the spring of 2019, mentored by leading Duke Faculty involved in data science research with areas of focus in dermatology, ophthalmology, pathology, radiology, and cardiology.

The HDS Internship Program is a partnership between the Duke Clinical Research Institute (DCRI) and Duke Forge. The projects that the interns are introduced to through the internship are part of the Forge Demonstration Program in which transdisciplinary teams use advanced data science methods to “demonstrate the art of the possible.” The HDS internship program is structured as a 17-month program with interns working under the direction of quantitative experts, paired with biostatistician staff mentors primarily from the Center for Predictive Medicine, and receiving dedicated technical and professional skills training.

“Our goal is to offer Duke students, both undergraduate and graduate, the important opportunity to be a part of research teams,” said Larry Carin, PhD, Duke University Vice Provost for Research.