PeopleofSuperintelligence

Researcher

Joshua T Vogelstein

Joshua T Vogelstein is a machine-learning researcher whose work links brain science and artificial intelligence. He earned degrees in biomedical engineering, applied mathematics and statistics, and neuroscience, then developed methods and shared tools for analyzing large brain datasets. His work spans spike inference, open connectomics, prospective learning for changing environments, and MIGHT, a method for measuring uncertainty in AI-assisted cancer screening. Since December 2025, he is a co-founder of Flourish while on leave from his Johns Hopkins associate professor role.

Now at
Johns Hopkins University and Flourish
Born
1981
Works
550
Citations
12,196
h-index
48
Badges

Years link to their sources. Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 1998–2009

    Engineering and neuroscience training

    He earns a BA in biomedical engineering at Washington University in St. Louis in 2002. At Johns Hopkins, he completes an MS in applied mathematics and statistics and a PhD in neuroscience in 2009; his thesis, OOPSI, develops spike-inference algorithms for neural connectivity from population calcium imaging.

  2. 2009

    Inferring neural spikes

    In 2009, he coauthors a paper that uses sequential Monte Carlo particle filters and biophysical models to infer spike trains and calcium dynamics from fluorescence. The method estimates when spikes occur within each image frame.

  3. 2011

    Open Connectome Project

    In 2011, he co-founds the Open Connectome Project. He works with neuroscience datasets that grow from tens of terabytes to hundreds.

  4. 2018

    NeuroData's cloud ecosystem

    In 2018, he and his coauthors describe NeuroData's open-source computational ecosystem for large neuroscience datasets. They move its custom software stack to a community-built system in the commercial cloud that reuses components across datasets.

  5. 2020–2025

    An NSF CAREER project

    He leads an NSF CAREER project from 2020 to 2025 on statistical theory and methods for populations of attributed connectomes. The project aims to help scientists infer structure in brain networks and compare connectivity patterns.

  6. 2024

    Prospective learning

    In 2024, he coauthors Prospective Learning: Learning for a Dynamic Future, a framework for machine learning when data and goals change over time. Its Prospective ERM method returns predictors for future data.

  7. 2025

    MIGHT for medical decisions

    In 2025, he coauthors MIGHT, a method for measuring uncertainty in AI predictions and controlling specific kinds of errors. The team applies it to circulating cell-free DNA data from people with and without cancer.

  8. Since December 2025

    Co-founding Flourish

    Since December 2025, he is a co-founder of Flourish, a neuroscience-grounded AI company, and is on leave from his associate professor role in biomedical engineering at Johns Hopkins. In February 2026, he joins the university's Data Science and AI Institute as faculty, and his research uses nonlinear machine learning to study natural and artificial intelligence through biomedical data.

Career

  1. Since 2026Johns Hopkins UniversityAssociate Professor
  2. Since 2025FlourishCo-founder
  3. 2011–2015Duke University
  4. 2011–2020Child Mind Institute

Education

  1. 2009Johns Hopkins UniversityMS in applied mathematics and statistics
  2. 2002Washington University in St. LouisBA in biomedical engineering

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Detection and localization of surgically resectable cancers with a multi-analyte blood test2018 · Science · 2,771 citations
  2. Differential connectivity and response dynamics of excitatory and inhibitory neurons in visual cortex2011 · Nature Neuroscience · 468 citations
  3. Fast Nonnegative Deconvolution for Spike Train Inference From Population Calcium Imaging2010 · Journal of Neurophysiology · 449 citations
  4. The connectome of an insect brain2023 · Science · 432 citations
  5. Imaging human connectomes at the macroscale2013 · Nature Methods · 419 citations

From OpenAlex, as of 21 October 2026.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Johns Hopkins University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Johns Hopkins University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. Google has the highest combined h-index among AI organizationsIncludes Johns Hopkins University. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Johns Hopkins University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Joshua T Vogelstein yet. Send us a free-licensed photo.

  1. Joshua Vogelstein, Ph.D. neurodata.io. Checked 20 October 2026.
  2. Spike Inference from Calcium Imaging Using Sequential Monte Carlo Methods pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.
  3. A community-developed open-source computational ecosystem for big neuro data nature.com. Checked 20 October 2026.
  4. Prospective Learning: Learning for a Dynamic Future arxiv.org. Checked 20 October 2026.
  5. Minimizing and quantifying uncertainty in AI-informed decisions: Applications in medicine pmc.ncbi.nlm.nih.gov. Checked 20 October 2026.