JHU WIT https://jhuwit.github.io/news/ quarto-1.10.18 Thu, 06 Aug 2026 04:00:00 GMT Minute-level NHANES step counts released on PhysioNet https://jhuwit.github.io/news/posts/2026-08-physionet-nhanes-steps.html Lily Koffman and John Muschelli released minute-level step counts and physical activity data for NHANES 2011–2014 on PhysioNet (doi:10.13026/d7sw-f662). The dataset applies five step counting algorithms and the ActiGraph Activity Count algorithm to the raw 80 Hz wrist accelerometry, and includes minute-level step counts, Activity Counts, MIMS, wear predictions, and wear flags for all participants who wore accelerometers. See our step counting research for the papers behind it.

]]> data software https://jhuwit.github.io/news/posts/2026-08-physionet-nhanes-steps.html Thu, 06 Aug 2026 04:00:00 GMT Lily Koffman joins the University of Virginia https://jhuwit.github.io/news/posts/2026-08-koffman-uva.html Lily Koffman has joined the University of Virginia School of Data Science as an Assistant Professor of Data Science. Lily’s PhD work with WIT focused on identity recognition and health prediction using high-resolution accelerometry, including walking fingerprinting and step counting in NHANES. Congratulations, Lily!

]]> alumni https://jhuwit.github.io/news/posts/2026-08-koffman-uva.html Sat, 01 Aug 2026 04:00:00 GMT Two papers on hemodynamics in cardiac surgery in the British Journal of Anaesthesia https://jhuwit.github.io/news/posts/2026-05-bja-hemodynamics.html With collaborators in Johns Hopkins Anesthesiology and Critical Care Medicine, WIT members Lily Koffman, Marina Hernandez, Angela Zhao, John Muschelli, and Ciprian Crainiceanu co-authored two papers using minute-level hemodynamic data recorded during cardiac surgery:

See our hemodynamics research for more.

]]> papers https://jhuwit.github.io/news/posts/2026-05-bja-hemodynamics.html Fri, 01 May 2026 04:00:00 GMT Joe Sartini completes PhD, joins Wake Forest https://jhuwit.github.io/news/posts/2026-05-sartini-wake-forest.html Joe Sartini completed a PhD in Biostatistics, with a dissertation on Bayesian methods for functional and longitudinal data, including continuous glucose monitoring. Joe is now a tenure-track Assistant Professor in the Department of Biostatistics and Data Science at Wake Forest University School of Medicine. Visit Joe’s site.

]]> alumni https://jhuwit.github.io/news/posts/2026-05-sartini-wake-forest.html Fri, 01 May 2026 04:00:00 GMT New preprint: Functional Moments Regression https://jhuwit.github.io/news/posts/2026-04-functional-moments-regression.html Mingyuan Li, Martin Lindquist, Edward Gunning, and Ciprian Crainiceanu posted Functional Moments Regression, a new approach to functional regression with applications to accelerometry data.

]]> papers https://jhuwit.github.io/news/posts/2026-04-functional-moments-regression.html Wed, 01 Apr 2026 04:00:00 GMT Fast Bayesian FPCA published in JCGS https://jhuwit.github.io/news/posts/2026-02-fast-bayesian-fpca.html Joe Sartini, Xinkai Zhou, Elizabeth Selvin, Scott Zeger, and Ciprian Crainiceanu published Fast Bayesian Functional Principal Components Analysis in the Journal of Computational and Graphical Statistics. FAST is a fully Bayesian FPCA that accounts for uncertainty in the estimated principal components, motivated by mealtime glucose variability in the DASH4D continuous glucose monitoring study. Code is available as supplementary material.

]]> papers https://jhuwit.github.io/news/posts/2026-02-fast-bayesian-fpca.html Wed, 11 Feb 2026 05:00:00 GMT New preprint: walking fingerprinting in NHANES https://jhuwit.github.io/news/posts/2025-06-nhanes-walking-fingerprinting.html Lily Koffman, John Muschelli, and Ciprian Crainiceanu posted Walking Fingerprinting Using Wrist Accelerometry During Activities of Daily Living in NHANES, which identifies individuals from their free-living walking patterns at population scale.

]]> papers https://jhuwit.github.io/news/posts/2025-06-nhanes-walking-fingerprinting.html Fri, 20 Jun 2025 04:00:00 GMT Video: the WIT Working Group https://jhuwit.github.io/news/posts/2025-05-wit-video.html The Department of Biostatistics released a short video about the WIT Working Group, in which Ciprian Crainiceanu describes how the group started, its focus on students, and how it works.

]]> group https://jhuwit.github.io/news/posts/2025-05-wit-video.html Mon, 12 May 2025 04:00:00 GMT Physical activity and incident Alzheimer’s disease in the UK Biobank https://jhuwit.github.io/news/posts/2024-12-alzheimers-ukb.html Angela Zhao and colleagues published Objectively Measured Physical Activity Using Wrist-Worn Accelerometers as a Predictor of Incident Alzheimer’s Disease in the UK Biobank in the Journals of Gerontology, Series A. Accelerometry-based activity summaries were among the strongest modifiable predictors of incident Alzheimer’s disease.

]]> papers https://jhuwit.github.io/news/posts/2024-12-alzheimers-ukb.html Sun, 01 Dec 2024 05:00:00 GMT Comparing step counting algorithms in NHANES https://jhuwit.github.io/news/posts/2024-11-step-counting-msse.html Lily Koffman, Ciprian Crainiceanu, and John Muschelli’s comparison of step counting algorithms for high-resolution wrist accelerometry in NHANES 2011–2014 was published in Medicine & Science in Sports & Exercise. The minute-level step counts behind the paper are openly available on PhysioNet.

]]> papers https://jhuwit.github.io/news/posts/2024-11-step-counting-msse.html Tue, 26 Nov 2024 05:00:00 GMT Evaluating step counting algorithms on sub-second wrist accelerometry https://jhuwit.github.io/news/posts/2024-07-step-counting-jmpb.html Lily Koffman and John Muschelli published Evaluating Step Counting Algorithms on Subsecond Wrist-Worn Accelerometry: A Comparison Using Publicly Available Data Sets in the Journal for the Measurement of Physical Behaviour (doi:10.1123/jmpb.2024-0008), benchmarking open-source and proprietary step counting algorithms against publicly available data with ground-truth steps.

]]> papers https://jhuwit.github.io/news/posts/2024-07-step-counting-jmpb.html Tue, 30 Jul 2024 04:00:00 GMT