Patient care navigation and health copilot AI
Health-GPT
Health-GPT is a free mobile app from Omni Timeline LLC that turns uploaded medical documents, screenshots, and photos into a chronological health timeline, answers questions about the record in the user's preferred language, and generates questions to bring to the next doctor visit. The design is squarely patient-directed, with per-entry privacy controls, entry and account deletion within seven days, an explicit pledge not to train AI models on personal data, and a fictional sample record for trying the workflow before trusting it with real records. The profile stays a low-confidence draft because the AI provider and subprocessors are unnamed, the company has no public footprint beyond its website and app listings, the privacy policy lacks an effective date, jurisdiction, correction right, and export right, the Terms of Use could not be retrieved, and the iOS privacy label claims no data is collected while the policy describes retained server-side content.
Public-source research has been drafted, often with AI assistance. No comprehensive human review is recorded unless the profile provenance says so.
Summary judgment · 80% toward patient-directed
Potentially agency-expanding, with vendor-opacity and disclosure caveats
The patient chooses the app, supplies the records, controls per-entry privacy, and gets a comprehension-and-preparation loop that directly supports reflection and strategic action. The posture carries heavy caveats because the AI provider is unnamed, the anonymous vendor discloses no team or history, the privacy policy documents no correction or export rights, the Terms of Use returned a 404, and the iOS privacy label's 'Data Not Collected' claim conflicts with the vendor's own policy describing server-side retention of uploaded records.
Patient agency
How this tool changes agency
Turning scattered records into a readable timeline, answering questions in the user's own language, and generating questions for the next appointment are direct supports for critical reflection and strategic action.
Users can delete entries and mark them private, and original documents stay in the user's hands for comparison. No public materials document how to correct a wrong extraction, a misdated event, or a misread medication, and the privacy policy grants access and deletion but is silent on correction and export.
Patient-facing signals
Who does this AI serve?
Patients and caregivers choose the app, supply the records, and control which entries the AI may use. The vendor and its unnamed AI processors sit in the pipeline, and the free app's business model is undisclosed, so the economics behind the service cannot be evaluated.
Can patients tell AI is involved?
AI is the product's explicit identity, from the GPT-styled name to the marketed extraction and chat features. The specific models and providers behind it are not named, and the App Store listing notes the company is unaffiliated with OpenAI.
Can patients meaningfully choose?
Use is voluntary, the app is free with no in-app purchases listed, a fictional sample record allows a trial before real data is uploaded, and deletion works per entry and per account with permanent erasure within seven days. The undisclosed business model limits fully informed choice.
Can patients correct or challenge what the AI produces?
Users can delete entries and mark them private, and original documents stay in the user's hands for comparison. No public materials document how to correct a wrong extraction, a misdated event, or a misread medication, and the privacy policy grants access and deletion but is silent on correction and export.
Does it help patients understand or act?
Turning scattered records into a readable timeline, answering questions in the user's own language, and generating questions for the next appointment are direct supports for critical reflection and strategic action.
Text findings
Who is left out or burdened?
Digitization burden on the patient; several groups excluded
The patient must obtain and upload their own records. The app requires iOS 15.1 or later with an English-only interface even though answers are multilingual, is rated 17+, excludes children under 13, and declares itself unsuitable for mental health, wellness, and pregnancy-related care. Caregiver-oriented marketing is not matched by documented proxy or shared-access controls, and accessibility conformance is not disclosed.
What happens to patient data?
Clear no-training pledge above an opaque pipeline
The privacy policy states no AI training on personal data, encryption in transit, technical logs capped at thirty days, content retained until the user deletes it, and permanent account deletion within seven days, with private entries excluded from answer generation. It names no AI provider, subprocessors, jurisdiction, or effective date, and documents no export right. The iOS privacy label claims 'Data Not Collected,' which conflicts with the policy's description of server-side storage, and no HIPAA claim is made, which is likely accurate for a direct-to-consumer app.
Are the clinical boundaries clear?
Clear, with an unverified legal layer
The product repeats that it is not a substitute for professional medical advice, frames itself as informational visit preparation rather than diagnosis, and excludes mental health, wellness, and pregnancy use. The Terms of Use, where liability and dispute terms would live, returned a 404 during this review.
Who defined what good looks like?
Vendor-defined; no visible external input
No patient co-design, advisory input, independent evaluation, peer-reviewed evidence, or named team was found. The company's public footprint consists of its website, its app-store listings, and a support email address, with a single App Store rating at the time of review.
Review provenance
Criteria
Same HugoScore CAIHL-derived criteria for every tool; public criteria are displayed from site/data/criteria.json, with fuller method notes in SCORING_FRAMEWORK.md.
Reviewer
AI-assisted public-source draft prepared in Claude (Cowork); no named human reviewer recorded.
AI / model
Claude Fable 5 (claude-fable-5).
Human review
No comprehensive human review has been completed or claimed for this draft profile.
Review date
2026-08-15
Limitations
No account creation, document-upload test, extraction-accuracy inspection, vendor or user interview, security audit, accessibility audit, independent validation, or legal/regulatory determination. Terms of Use and Google Play listing could not be retrieved; FAQ answers render client-side and were not readable.
Review method
Public-source review of the health-gpt.org homepage, sample-record demo page, and privacy policy, plus the iTunes Store lookup record and App Store listing, and searches for press coverage, funding records, company registrations, and independent evaluations. The linked Terms of Use returned a 404 to automated retrieval; the Google Play listing could not be reliably retrieved; FAQ answers render client-side and were unreadable. No account creation, document-upload test, extraction-accuracy inspection, vendor interview, patient interview, security audit, accessibility audit, independent validation, or legal/regulatory determination.
Draft profile · Low draft, official sources only