Turning anonymous symptom descriptions into structured biological signals with OpenGenome
Accuracy and Calibration of Evidence-Grounded Biomedical Signal Extraction From Free-Text Symptom Descriptions: A Prospective Observational Registry Using the OpenGenome Automated Research Instrument
This project tries to turn adults' anonymous free-text symptom descriptions submitted to OpenGenome into structured, literature-grounded biological signals using PubMed and ClinicalTrials.gov sources and a constrained reasoning model.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 1000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | OpenGenome Research network |
| Locations | 1 site (Friedrichshain, State of Berlin) |
| Trial ID | NCT07578610 on ClinicalTrials.gov |
What this trial studies
OpenGenome collects anonymized free-text symptom descriptions from consenting adults and sends parallel queries to PubMed and ClinicalTrials.gov to retrieve up to 16 real sources per submission. A constrained reasoning model operating under a strict output schema extracts a primary biological signal, up to five secondary signals, a plain-language correlation explanation, and two integer scores (confidence and signal strength from 0–100). All outputs include source identifiers (PMID or NCT) that are directly linkable for independent verification, and no participant contact occurs. The registry analyzes aggregate anonymized outputs to characterize internal consistency of signals, calibration of confidence scores by dataset size and symptom specificity, and population-level distributions of biological signal categories.
Who should consider this trial
Good fit: Ideal participants are adults who voluntarily submit meaningful, health-related free-text symptom descriptions on the OpenGenome platform and are not automated or rate-limited submissions.
Not a fit: People seeking direct medical care, personalized treatment recommendations, minors, or submissions that are automated/contain no health-related content are unlikely to get benefit from this registry.
Why it matters
Potential benefit: If successful, this could give people clearer, literature-linked summaries of what their symptoms might signal and help researchers and clinicians generate hypotheses faster.
How similar studies have performed: Related natural-language and knowledge-extraction efforts have shown promise, but the live linkage of each free-text submission to up-to-date PubMed and ClinicalTrials.gov sources under a strict schema is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
* Automated or programmatically generated submissions detected by rate limiting * Submissions containing no discernible symptom or health-related content
Where this trial is running
Friedrichshain, State of Berlin
- OpenGenome — Friedrichshain, State of Berlin, Germany (Recruiting)
Study contacts
- Study coordinator: Richard Koch
- Email: richard@opengenome.bio
- Phone: +491634168231
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.