Uncategorized

Duke Responsible AI Symposium: Content and Recordings Now Available

The recent 2025 Responsible AI Symposium, co-sponsored by The Society-Centered AI Initiative at Duke, the Duke Artificial Intelligence Master of Engineering, Duke AI Health, the Duke Office of Climate and Sustainability, and the Coach K Center for Leadership and Ethics (COLE), took place this past February and March at Duke University’s Karsh Alumni Center. The four-day event, which included industry and academic keynote talks, research talks, a poster session and a hackathon, convened a wide array of leaders, researchers, and students whose work is focused on society-centered AI and responsible AI.

Programming, speaker bios, event photos, and video from the 2025 Symposium are all available at the link below, where information about the planned 2026 event will posted when available. Abstracts from research talks are also available at the site.

LEARN MORE

Duke Responsible AI Symposium: Content and Recordings Now Available Read More »

photo of Engelhard and Kumar

NIH Pragmatic Trials Collaboratory Grand Rounds: Translating Clinic Notes for Patient with GPT-4

In a recent session of the weekly NIH Pragmatic Trials Collaboratory Grand Rounds series (recording and slides available at link below), Duke AI Health Faculty Affiliate Matthew Engelhard, MD, PhD, (left) and Anivarya Kumar, (right) a fourth-year medical student at Duke University School of Medicine, presented a talk titled “A Cross-Sectional Study of GPT-4–Based Plain Language Translation of Clinical Notes to Improve Patient Comprehension of Disease Course and Management.” In this presentation, Engelhard and Kumar described a project that employed the widely available GPT-4 large-language model to render physicians’ clinical notes into plain-language versions that would be more readily understood by patients.

LEARN MORE

NIH Pragmatic Trials Collaboratory Grand Rounds: Translating Clinic Notes for Patient with GPT-4 Read More »

presentation audience

AI Health Director Highlights Big Data & AI at Duke Orthopaedics Research Day

Duke Orthopaedics Department Research Day was celebrated on March 18 with standing-room-only attendance. This year’s theme, “BIG3: Big Ideas, Big Data, and Big Analysis,” sparked insightful conversations about the transformative potential of big data and artificial intelligence in addressing today’s most pressing challenges. Featured speakers included Michael Pencina, PhD, Chief Data Scientist for Duke Health, Vice Dean for Data Science, and Director of Duke AI Health; Elizabeth R. Skidmore, PhD, OTR/L, FAOTA, FACRM, from the University of Pittsburgh; and Duke University School of Medicine faculty Michael Bolognesi, MD; Maggie Horn, DPT, MPH, PhD; and Christian Pean, MD, MS. The event recording, photo gallery, full program booklet, and award recipients are available online.

LEARN MORE

AI Health Director Highlights Big Data & AI at Duke Orthopaedics Research Day Read More »

Duke medical center

PACE 2.0: Upgrading Duke’s Secure Research Computing & Invitation for Beta Testers

Duke’s Protected Analytics Computing Environment (PACE) is a secure platform for research teams working with sensitive health data. This year, thanks to the support of the School of Medicine, PACE will undergo a major upgrade to enhance computational power, security, and ease of use. PACE 2.0 will introduce a high-performance computing environment, GPU capabilities for AI research, and other new tools made accessible through Open OnDemand. Upgrades will roll out in late spring through the summer of 2025. Current PACE users at Duke University interested in beta testing PACE 2.0 are invited to sign up using the link below (log-in required).

LEARN MORE

PACE 2.0: Upgrading Duke’s Secure Research Computing & Invitation for Beta Testers Read More »

photo illustrating AI and circuits

Fostering Ethical Approaches to AI at Duke

A recent article* featured on Duke’s “Made for This” website highlights work by Duke computer science professor Nicki Washington and Duke AI Health Director Michael Pencina aimed at developing and promoting ethical approaches to building and implementing artificial intelligence.

“Both Pencina and Washington are committed to the idea that progress should not come at the expense of equity. At Duke, their work aligns to ensure that technological advancement, whether in health care or computer science, is both ethical and inclusive.”

*Original article by Mary-Russell Roberson, Leslie Gray Baker & Megan Hujber

READ MORE

Fostering Ethical Approaches to AI at Duke Read More »

Duke Electronic Health Records Study Design Workshop (EHR-SDW) 2024

Electronic poster for the Duke Electronic Health Records Study Design Workshop taking place December 2-6, 2024. Detailed information on the poster is contained in the body of the webpage.

Duke AI Health is pleased to announce the Duke Electronic Health Records Study Design Workshop (EHR-SDW) 2024. The workshop will be offered in December as a virtual five-day class that provides foundational lectures and hands-on studios on the fundamentals of working with and designing EHR-based studies.

The EHR-SDW is targeted toward individuals interested in learning about how to work with and conduct studies using edata from electronic health records (EHRs). EHR data are a widely available form of real-world data that are being used in different types of studies, spanning clinical trials, comparative effectiveness, risk prediction, population health, and more. The EHR-SDW will introduce learners to the components of EHR data and in considerations for designing effective studies. In addition to didactic lectures, participants will get hands-on experience in working with publicly available tools to facilitate EHR studies (e.g., RxNorm, CCS codes, geocoding), as well as feedback on effective study designs.

This course will be conducted virtually via Zoom.

To register for the EHR-SDW, please visit  https://events.duke.edu/ehr-sdw-2024

To request consideration for a scholarship, please visit https://duke.qualtrics.com/jfe/form/SV_a3Fs9TyyK82Bkr4

The deadline for registration is Thursday, November 21, 2024.

READ MORE


Duke Electronic Health Records Study Design Workshop (EHR-SDW) 2024 Read More »

Spark Initiative for AI in Medical Imaging Officially Launches at Duke

The Duke Spark Initiative for AI in Medical Imaging formally launches this week. Spark’s mission at Duke encompasses research into development and use of artificial intelligence in medical imaging, with an emphasis on collaborative work between physicians across different specialties and machine learning experts.

Portrait of Duke SPARK Director Maciej Mazurowski, PhD

“Spark represents the kind of collaboration that can realize the full potential of the diverse pool of knowledge, talent, and insight across the School of Medicine and the larger university community,” says Mary Klotman, MD, executive vice president for health affairs at Duke University and the dean of the Duke University School of Medicine. “As AI technologies are increasingly integrated into patient care and research, efforts like Duke Spark will be essential for ensuring that these tools yield meaningful benefits for patients and clinicians.”

An interdepartmental effort convened under the umbrella of Duke AI Health, Spark includes a team of faculty researchers and exceptional trainees drawn from the Departments of Radiology, Surgery, Orthopaedic Surgery, Medicine, Electrical and Computer Engineering, Computer Science, and Biomedical Engineering.

READ MORE


Spark Initiative for AI in Medical Imaging Officially Launches at Duke Read More »

Duke Researchers Receive NIH Grant to Use EHR Data to Explore Late Talking in Children

Portraits of Benjamin Goldstein, PhD (left) and Lauren Franz, MBChB (right)

Duke AI Health Director of Data Science Benjamin Goldstein, PhD, and Interim Director for Duke Center for Autism and Brain Development Lauren Franz, MBChB, have recently been awarded a grant from the National Institutes of Health to develop approaches for using existing sources of health data to better understand late language emergence in children, or “late talking.” Late talking often co-occurs with autism and is frequently “undercoded” in medical records, which can affect whether children and families receive referrals for early intervention. The R21 grant, which is part of the NIH’s cross-institute Tackling Acquisition of Language in Kids (TALK) Initiative, will support efforts at Duke to apply machine learning to compare coding data in electronic health records (EHRs) with free-text information in EHR notes to determine whether indications of late talking recorded there are matched by appropriate coding.

The work will also leverage longitudinal health data and NC-statewide sources of claims data to shed additional light on developmental pathways, including methods for analyzing co-occurring factors that may predispose children to late talking, as well as downstream effects of delayed language acquisition later in life. Another focus for the project will be the health equity dimensions of late talking, including differences across gender, language, and race and ethnicity.

READ MORE


Duke Researchers Receive NIH Grant to Use EHR Data to Explore Late Talking in Children Read More »

Duke AI Health Welcomes Michael Zavlanos as Director in Healthcare System Optimization

Picture of Michael Zavlanos, PhD and the text "“We are very excited about the unique insights Dr. Zavlanos will bring to challenges that directly affect the performance of our health system and the experiences of our patients and the clinicians and staff who care for them.” – Duke AI Health Director Michael Pencina, PhD"

Duke AI Health has recently welcomed Michael Zavlanos, PhD, as Director in Healthcare System Optimization for Duke AI Health. In this newly created role, Dr. Zavlanos will direct efforts focused on developing and implementing machine learning, optimization, and other algorithmic tools to increase operational efficiency and resource use in health care at Duke.

Currently a professor in the Thomas Lord Department of Mechanical Engineering and Materials Science at Duke University’s Pratt School of Engineering and an Amazon Scholar with Amazon Robotics, Dr. Zavlanos received his doctorate in electrical and systems engineering from the University of Pennsylvania, where he specialized in robotics and autonomous control systems. More recently, at Duke, Dr. Zavlanos has begun to explore the potential for using data gathered from “real-world” clinical settings to solve problems with a direct impact for patients.

READ MORE


Duke AI Health Welcomes Michael Zavlanos as Director in Healthcare System Optimization Read More »

Ricardo Henao Rejoins Duke in New Role as DCRI Associate Director of Clinical Trials AI

Duke Clinical Research Institute and AI Health are delighted to announce the return of Dr. Ricardo Henao to Duke, starting July 1! After a leave of absence at the King Abdullah University of Science and Technology (KAUST) in Saudi Arabia, Dr. Henao has returned to North Carolina as Associate Director of Clinical Trials AI for the Duke Clinical Research Institute (DCRI) and as a member of AI Health’s Faculty Council. Dr. Henao is Associate Professor in the Department of Biostatistics and Bioinformatics at Duke University School of Medicine.

“We are very excited about Dr. Henao’s return to Duke given his enormous contributions both to teaching and to developing novel methods for applying probabilistic modeling to deep learning algorithms,” notes Duke AI Health Director Michael Pencina, PhD. “Ricardo’s innovative work has been key to multidisciplinary efforts at Duke and beyond to improve predictive modeling for clinical outcomes,” he continues, noting that Henao’s gifts as a collaborator, methodologist, and teacher will be in high demand.

READ MORE


Ricardo Henao Rejoins Duke in New Role as DCRI Associate Director of Clinical Trials AI Read More »