Linus Health vs Neurotrack
The most AI native product in the category against the most deployable, and they barely overlap. Linus Health derives signal from behaviour, the drawing process and speech acoustics, and uses it to predict amyloid status, earning A grades on AI centrality, model transparency, evidence, and governance, the fullest technical record of the four. Neurotrack keeps the AI light on purpose and competes on reach: cloud based on any device with no hardware, integrating with all major EHRs in weeks, sized for the Medicare Annual Wellness Visit, with the broadest distribution and the only published SOC 2 of the four. The honest asymmetry is that these solve different problems, one predicts pathology for the treatment era, the other screens a population inside existing workflows. If your failure mode is identifying who carries amyloid pathology, start with Linus, and confirm which claims are cleared versus research. If your failure mode is getting a validated screen in front of an entire panel without friction, start with Neurotrack, understanding it is registered rather than cleared.
- Genuinely AI native: the DCTclock analyses the drawing process, stylus dynamics and speech acoustics with no paper equivalent, graded A on AI centrality where Neurotrack's standardised digital delivery grades C, and A on model transparency for peer reviewed method disclosure where Neurotrack grades B.
- Biomarker prediction is the capability: DCTclock correlated with amyloid PET in cognitively normal people and the DCR predicting PET status in the 930 participant Bio-Hermes-001 study, graded A on clinical evidence where Neurotrack grades B, addressing treatment eligibility rather than screening alone.
- The best governance posture in this sweep: the team names the cultural and educational bias failure mode directly and publishes the uncomfortable findings, including a South Asian cohort, graded A where Neurotrack designs for inclusivity but publishes no subgroup data at B.
- Population scale deployment with no hardware friction: cloud based, runs on any device, no specialised hardware or training, graded A on deployment where Linus requires an iPad with Apple Pencil and grades B.
- The broadest distribution and interoperability in the category: integrates with all major EHRs deploying in weeks, feeding Annual Wellness Visit and RADV workflows, graded A on interoperability where Linus offers integration without naming EHRs and grades B.
- The only published security attestation of the four: SOC 2 and HIPAA stated directly on the product, graded B where Linus has none located, with named health system customers across primary care, virtual, and home settings.
Side-by-Side
| Axis | L Linus Health |
N Neurotrack |
|---|---|---|
| AI Centrality | ||
| Autonomy and Oversight Model | ||
| Model and Technology Transparency | ||
| Clinical and Operational Evidence | ||
| AI Safety and PHI Stewardship | ||
| HIPAA and BAA Posture | ||
| Security Certifications and Trust Center | ||
| FDA and Regulatory Status | ||
| AI Governance and Bias Disclosure | ||
| EHR and Interoperability Depth | ||
| Deployment Model and Data Residency | ||
| Commercial Transparency | ||
| Setting and Specialty Coverage |
These are the opposite ends of the category on AI and on deployment. Linus is the model driven product, graded A on AI centrality, model transparency, evidence, and governance, its signal derived from behaviour rather than digitised scoring. Neurotrack is the distribution product, graded A on deployment, interoperability, and setting coverage, its moat the workflow fit and health system reach rather than the algorithm; notably its own earlier eye tracking work, which involved genuine digital phenotyping, was removed from the clinician suite, which is why it grades C on AI centrality today. Two cautions cut in opposite directions: Linus is cleared for cognitive assessment while its commercial claim is amyloid prediction, much of it in conference abstracts, and it publishes no security attestation; Neurotrack is FDA registered rather than cleared and its evidence base partly predates its current product. Neither publishes pricing.