Create Jira Ticket
This idea cannot be sent to Jira.
VantiScope: Mapping Disease Burden, Research Investment, and Evidence Gaps in Invisible Illness
VantiScope helps researchers, funders, policymakers and patient advocates examine a practical question: How well does research address the needs of people living with invisible illnesses?
Developed by Hamad Al-Ibrahim MD, PhD and Chloe E. Bird, PhD, developed the platform, combining experience in software development, policy analysis, women’s health, population health and research evaluation. We translate fragmented public data into an accessible resource for researchers, funders, patient organizations, clinicians, and policymakers.
The working MVP connects disease burden, research investment, publications, and clinical trials across 15 conditions. It focuses on endometriosis, ME/CFS, POTS, Long COVID, and Chronic Kidney Disease, with ten comparison conditions providing broader context.
VantiScope offers three complementary experiences:
• The dashboard shows disease-burden estimates alongside funding, publication and trial activity.
• The Evidence Sandbox lets users ask a research question, inspect relevant passages and original records, and assemble an evidence brief.
• The Research Lab supports deeper analysis of research questions, connections between studies, patient priorities, trial populations, funding benchmarks and reported results. The Research Lab contains more than one million distinct PubMed records and over 60,000 ClinicalTrials.gov study records. Its core inclusion windows span 2015–2025, with source updates retained separately.
All three tools are publicly accessible from the same website. Users can move from an overview of a condition to individual records and examine the evidence behind a summary. The platform distinguishes what researchers proposed to study, what they investigated and what they reported.
VantiScope supports transparent research planning and evidence exploration. Its goal is to help decision-makers identify neglected questions, understand the available evidence, and direct attention toward patient needs.
VantiScope has received letters of endorsement from Christopher Steven Marcum, a consultant and former White House Assistant Director for Open Science and Data Policy; Carmela M. Roybal, Executive Director of the Native American Budget & Policy Institute at the University of New Mexico; and Liz Helms, President and CEO of the California Chronic Care Coalition. The letters describe its potential to support research planning, bring community needs into funding discussions and help patient advocates use evidence. All three letters accompany this submission.
Solution Overview (MVP Demonstration)
User-Facing Application
Live demo, prototype, or working product
Live platform: https://vantiscope.policytechinnovations.com
The website’s navigation provides access to the dashboard, Evidence Sandbox, Research Lab and Find Care. Start with the 90-second “What is VantiScope?” video: https://vantiscope.policytechinnovations.com/#demo
Suggested demonstration:
Select ME/CFS in the dashboard. Compare disease-burden context with research funding, publications and clinical trials.
Open the Evidence Sandbox and ask: “What research addresses post-exertional malaise in ME/CFS?” Read the relevant source passages, open the original records and select sources for an evidence brief.
Open the Research Lab’s evidence network. Follow connections between publications, trials and funded projects, and inspect whether each connection reflects a documented relationship or a similarity suggestion.
Explore patient priorities, trial demographics and study locations. Review the funding benchmarks and evidence-composition views, including links to citing clinical articles where available.
Open Results Availability. Distinguish posted registry results from candidate journal reports and records needing review, then inspect numerical outcomes and reported analyses where available.
Access instructions (if needed)
The dashboard, Evidence Sandbox, Research Lab and Find Care are public and do not require an account. A desktop or laptop browser is recommended for detailed tables and visualizations. Allow time for the initial condition data and the Sandbox’s semantic-search model to load.
Results for the American People
VantiScope serves people living with invisible illnesses, caregivers, patient organizations, researchers, clinicians, funders and policymakers in the United States.
For example, a person with endometriosis can explore research on non-invasive diagnosis, follow links to publications and trials, and review available findings. This can help them prepare questions for their clinician and contribute to discussions about what research is still needed.
A patient organization preparing for a funding meeting can begin with questions raised by its members, examine related funded projects and studies, and assemble a brief with links to the underlying records. A funder can use the same evidence to examine work already underway and identify questions that deserve closer attention.
Trial data help users examine who participated, where studies took place and which demographic details were not reported. Sourced patient priorities help users consider whether research addresses everyday concerns, such as diagnostic delays, symptom relief and the ability to work or care for family.
The immediate benefit is a shared basis for discussion, with patients and caregivers able to bring evidence and lived experience into the same conversation. By making research activity and potential gaps easier to examine, VantiScope can help communities make a clearer case for the questions they want researchers and funders to address.
Data, Tech & Evidence Driven Approach
VantiScope combines federal disease-burden data, NIH RePORTER, PubMed, ClinicalTrials.gov, NIH RCDC spending benchmarks and NIH iCite, supplemented by ISRCTN and documented patient-priority sources.
Across 15 condition cohorts, the Research Lab contains 1,064,601 distinct PubMed records and 60,153 ClinicalTrials.gov records. Publication coverage spans 2015–2025 (Long COVID: 2020–2025). Counts reflect recorded queries and source snapshots.
Custom software retrieves and deduplicates records, standardizes identifiers, links annual NIH narratives to financial records, extracts outcomes and demographics, and applies documented rules to screen research topics. Semantic AI ranking runs in the user’s browser to retrieve relevant passages in the Sandbox. Numerical summaries are calculated from source data.
Automated trial-representation checks examined 6,064 posted-results records and 12,571 demographic tables. Checks identify overlapping groups and unclear denominators; pooling rules limit which records contribute to combined summaries.
Source identifiers, retrieval dates, queries and links allow users to check the analysis. Documented relationships are distinguished from similarity suggestions. Available abstracts, title-only records and public project narratives retain distinct labels; coverage does not include all relevant research or universal full-text access.
Patient priorities require documented sources. A topic match identifies related work, not an answered question. Missing registry results do not establish that a study was never published.
Execution, Efficiency & Delivery:
The MVP is live: users can search, inspect source passages, follow related records and create an evidence brief within one workflow.
Bringing disease burden, funding, publications and trials together shows where research effort is concentrated and where reported evidence appears limited. Users can follow a question from funded aims to related studies and reported findings, then examine potential gaps in topics, populations or results availability that are harder to see in separate databases.
Records are processed in advance, with data loaded by condition. This reduces repeated retrieval and record matching, letting users focus on interpreting evidence and checking original sources. Source-linked briefs give researchers, funders and patient organizations a common basis for discussion.
Delivery checks cover identifiers, date filters, annual funding matches, numerical trial results and data-loading routes. Missing information is labeled, and documented relationships are distinguished from suggested links so users can see what needs review.
The intended gain is less time spent searching across separate systems and assembling evidence for research and funding decisions. Time savings, return on investment and health outcomes have not yet been measured. Structured user testing will assess task completion, time to prepare a brief, accuracy of supporting sources and ease of use.
Scalability, Reuse & Societal Impact:
VantiScope uses a common data structure and analytical views across 15 conditions. The next phase targets all 300-plus NIH RCDC research, condition and disease categories, with validated searches and mappings across sources.
We also plan to add AHRQ’s Healthcare Cost and Utilization Project (HCUP) data to examine hospital use, costs and patterns of care, subject to access and data-use requirements. This would let users consider research investment alongside the burden on patients and health services.
The browser-based platform loads data by condition. Source links and structured exports support reuse by universities, patient organizations, funders and public research programs, with potential for workspaces tailored to individual organizations.
Expansion will require reliable source access, comparable measures and review by condition experts and patient representatives. New sources will undergo checks for duplicate records, coding differences and gaps in coverage.
Next steps include user testing, accessibility review, scheduled refreshes and expert review of candidate study links and reported outcomes. A generative conversational assistant is planned, with answers grounded in retrieved records and links to supporting sources.
The aim is to make neglected questions visible across a wider range of conditions and help communities and funders set research priorities.
Hi Hamad, the way VantiScope separates what researchers proposed to study, what they investigated and what they reported is exactly the kind of care that makes an evidence map trustworthy.
My entry looks at a related question from the other side: not where research effort goes, but which burdens each study actually measures. My tool turns published Lyme and Long COVID papers into runnable simulators and sorts each study’s results into 16 burden categories. Your page names diagnostic delays and the ability to work or care for family as everyday patient concerns. In my library of 25 papers, six report a diagnostic-delay result and six report work and income, but none report caregiving and household labor (chart attached). The tags are assigned by an AI model and checked by code, and the 25 papers aren’t a systematic sample, so this describes my library and not all research. It makes me think the two approaches could complement each other.
My entry is here if you’d like to look: https://invisibleillness.crowdicity.com/post/896844
Thank you for sharing your work, and good luck with the user testing.
Users tagged:
Reply 0
Thanks for this — the part that stood out to me is how clearly you separate what was proposed, what was actually investigated, and what was finally reported. Too many gap analyses blur those together, so keeping funded aims, abstracts, title-only records, and posted registry results under different labels feels like the right discipline.
Two things I'm curious about: for the Results Availability view, how will expert review work for candidate journal links, and will users be able to see which links have actually been reviewed? And with burden varying so much by population and measurement, will subgroup and missing-demographic flags show up in the dashboard itself, not just in the Research Lab? Your checks on 6,064 posted-results records and 12,571 demographic tables suggest you've already thought hard about overlapping groups and unclear denominators — I'm wondering how visible that caution will be to someone just looking at the headline dashboard.
Reply 0
VantiScope project is an impressive and forward-thinking initiative that bridges artificial intelligence, medical research, and unmet patient needs. As an advocate of regenerative medicine and clinical research, I see significant potential in this platform to identify research gaps, guide future clinical studies, and accelerate evidence-based medical innovation. I believe VantiScope could become a valuable resource for researchers and healthcare institutions worldwide.
Reply 0