NeuroAge Therapeutics — Page-by-Page Analysis, Science Audit, and Lumosity Comparison

Prepared: August 2026
Subject: neuroagetx.com (NeuroAge Therapeutics, Inc., San Francisco)
Scope: (1) Site audit page by page, (2) product-by-product science and evidence grading, (3) comparison against Lumosity / Lumos Labs

0. Executive summary

What NeuroAge is. A 2022-founded, pre-seed/grant-stage San Francisco company selling a direct-to-consumer, cash-pay, multi-modal "biological brain age" assessment: brain MRI volumetrics, a proprietary 52-transcript blood RNA panel, whole-genome/genotype-based risk and pharmacogenomics, a Quest AD-Detect plasma amyloid/p-tau217 panel, and a light cognitive-testing layer called NeuroGames. Prices run $9.99/mo to $3,895. Founder/CEO Dr. Christin Glorioso (MD/PhD, Pitt/CMU MSTP, postdoc at MIT in Leonard Guarente's lab). Grant-funded in part by the Alzheimer's Drug Discovery Foundation ($250K). Berkeley SkyDeck alumnus.

The core finding on the science. NeuroAge's /our-science page is unusually good for a DTC company — ~40 real citations, correctly characterized, no obvious fabrications. But there is a systematic gap between the strength of the literature they cite and the strength of evidence for the product they sell:

The single sharpest observation for Lumos Labs: NeuroAge's cognitive product, NeuroGames, claims "up to 29% lower rates of dementia diagnosis" on the basis of the ACTIVE trial. NeuroGames is not the ACTIVE intervention. That is borrowed-evidence advertising of exactly the type the FTC fined Lumos Labs $2M for in January 2016 — and the resulting consent order still constrains Lumosity today while leaving NeuroAge free to make the claim. This is a regulatory asymmetry, not a scientific one.

The strategic read. NeuroAge and Lumosity are not currently competitors — they are mirror images. NeuroAge sells measurement with a weak training layer bolted on. Lumosity sells training with a light measurement layer bolted on. NeuroAge's evidence is broad but borrowed; Lumosity's is narrow but product-specific and now FDA 510(k) cleared (LumosityRx, adult ADHD, December 11, 2025). Where they collide is the future: NeuroAge's stated destination is a "digital twin" recommendation engine with cognitive training as an intervention, and Lumos Labs' pipeline lists MCI and Alzheimer's as proof-of-concept indications. Both are heading toward the same room from opposite doors.

1. Site audit — page by page

1.1 Site map

Two pages in the navigation (/products, /partnering, /resources) returned 404 at time of audit — the site is under active construction.

1.2 Home (/)

Headline: "Measure your brain age. Become optimally sharp." Three trust badges recur across the site:

• "Validated on data from 500,000+ individuals"
• "Supported by dozens of peer-reviewed publications"
• "Funded by the Alzheimer's Drug Discovery Foundation"

Read on the badges. All three are technically defensible and rhetorically misleading. "Validated on 500,000+ individuals" refers to the published literature the components draw on (UK Biobank, MyCogHealth cohorts, postmortem cohorts) — not to a validation of the NeuroAge product on 500,000 people. "Dozens of peer-reviewed publications" are overwhelmingly other people's papers about brain aging biology, not papers about NeuroAge's test. The ADDF funding is a ~$250K grant. This is the highest-leverage credibility-transfer move on the site, and it is the same move — "scientific studies proved these benefits" — that the FTC named in the Lumos Labs complaint.

Emotional framing is aggressive and worth noting: "Detect changes before symptoms appear—you may already be losing memory, just not noticing yet." That is anxiety-first acquisition copy aimed at the worried well.

HSA/FSA eligibility is flagged throughout — a deliberate price-softening device for a $1,400–$3,900 cash-pay purchase.

1.3 Our Science (/our-science) — the substantive page

Eleven sections, roughly 6,000 words, ~40 numbered citations with DOIs. Structure:

1. Premise — brain aging precedes symptoms by decades; dementia is not inevitable
2. Multi-modal > single-modality (Wang 2022, Brain Communications)
3. Biological brain age > chronological age (Glorioso 2019; Nguyen 2025; Liang 2022; Lancet Commission 2024; Chene 2025)
4. NeuroGames as a cognitive clock (Talboom 2021, 2019; Rentz 2023; Bilgel 2017; Bopp & Verhaeghen 2005; Edwards 2017)
5. MRI volumetrics (Qi 2020; Zhou 2022; Brown 2022; Wardlaw 2017; Vernooij 2007; Toh 2022)
6. RNA blood biomarkers (Glorioso 2019, 2010)
7. Genomics and Mendelian randomization (Andrews 2024; Liu 2024; Fan 2023)
8. Quest AD-Detect plasma biomarkers (Barthélemy 2024; Khalafi 2025; Racke 2024, 2025)
9. The ADDF clinical validation study (n=75, WCG IRB)
10. Reversibility evidence (Erickson 2011; Ten Brinke 2015; Ornish 2024)
11. How recommendations are generated — biomarker→intervention mapping with self-assigned evidence tiers

Assessment of the page as a document. This is the best-executed science page I have seen from a DTC brain-health company. Citations are real, accurately characterized, and mostly primary. The recommendation section even self-grades its own evidence tiers (Strong / Moderate / Emerging) — a genuinely honest touch that most competitors don't attempt. Two structural problems remain:

• Citation substitution. Nearly every citation supports a biological premise, not a product performance claim. The page reads as an argument that brain aging is measurable and modifiable — which is true — and lets the reader infer that NeuroAge measures it accurately, which is unestablished.
• No performance characteristics anywhere. No sensitivity, specificity, test-retest reliability, MAE of the brain age estimate, or confidence interval on any NeuroAge output is published on the site. For a product whose entire value proposition is a number, this is the most consequential omission.

1.4 About Us (/about-us)

Founder: Dr. Christin Glorioso, MD/PhD — Pitt/CMU Medical Scientist Training Program, postdoc at MIT (Guarente lab), formerly Head of AI at TeachAids and Chief Strategist at UCSF's Bakar Aging Research Institute. Co-founder Dr. Priyanka Joshi (CSO) per external sources. Origin story: grandmother died of Alzheimer's.

Team is small and junior-weighted: VP Engineering, one AI engineer, business development, ops coordinator, clinical administrator, and three ML engineering interns. There is no VP of Clinical Affairs, no regulatory lead, no biostatistician, and no medical director listed.

Advisory board is genuinely strong: Matt Kaeberlein (Optispan, one of the most credible names in geroscience), Ronjon Nag (Stanford Genetics adjunct), Lawrence Tanenbaum (former CTO of RadNet Imaging — a serious radiology credential), Joshua Kuluva (neurologist/psychiatrist), Salah Mahmoudi (Reneu Bio, ex-Pfizer/Alkahest).

The gap between advisory board strength and operating team depth is the single clearest signal of stage. This is a company with excellent scientific taste and very little clinical/regulatory infrastructure.

1.5 ADDF Study (/addf-study)

Free brain MRI, cognitive assessment, at-home phlebotomy, and (for some) an Oura ring for adults 60+, with or without MCI/early AD. n=75 (50 healthy controls aged 25–95, 25 MCI/early AD). WCG IRB approved. Powered to detect 5% score differences at p<0.05. Follow-up at 6-month intervals; extended arm at 12 and 24 months.

This page is simultaneously a research protocol and a customer acquisition funnel. The banner "Age 60 or older? Receive a free brain health assessment by participating in our research study" appears on every page of the site. That is not improper — it is IRB-approved recruitment — but it means the study doubles as a zero-CAC channel into their highest-value demographic.

The critical thing this page reveals: the study exists to answer whether the blood panel works in living people at all. It is a pilot feasibility study, n=75, single-arm, with the sponsor's own composite as the index test. They are selling the $899 blood test today while running the study that determines whether it measures what they say it measures.

1.6 Legal (/legal)

The most important finding of the site audit. The Legal page contains website terms of use, cookie policy, content licensing, and privacy language — and no medical disclaimer, no FDA statement, no CLIA/LDT disclosure, no "not intended to diagnose, treat, cure, or prevent any disease" language, and no statement of test limitations.

For a company selling an Alzheimer's-associated blood biomarker, whole-genome sequencing with pharmacogenomic results (CYP2C19, VKORC1, SLCO1B1, HLA-B*15:02 — variants with real prescribing consequences), and a brain MRI marketed to asymptomatic adults, the absence of consolidated medical/regulatory disclosure is a material compliance gap. A "not intended to diagnose" line appears buried in the NeuroGames product copy, but nowhere centrally.

2. Product-by-product: what it is, the science, and how strong the science is

Grading scale used throughout:

• A — Multiple independent RCTs, regulatory-grade validation, or replicated meta-analytic evidence for this specific use
• B — Strong, replicated observational or mechanistic evidence; validated in independent cohorts, but not for this specific consumer application
• C — Plausible and supported, but limited, single-lab, indirect, or with unresolved generalization problems
• D — Preliminary, unvalidated, or the claim relies on evidence from a different product/population

2.1 NeuroGames — $9.99/month

What it is. Five validated cognitive tests (memory, processing speed, visuospatial, executive function, attention) completed online in ~30 minutes, plus a ~10-minute/day speed-of-processing training game. Produces age- and sex-normed scores, a trend line, a brain age estimate that updates with play, and personalized recommendations.

The science cited.

• Talboom et al., 2021, npj Aging (n>75,000, ages 18–85): reaction time and memory closely linked; family history of AD, diabetes, stroke, smoking independently predicted slower RT and worse memory. Solid, large, real.
• Talboom et al., 2019, eLife: family history of AD associated with lower paired-associate learning four decades before typical onset; attenuated by education and absence of diabetes. Solid.
• Rentz et al., 2023, Alzheimer's & Dementia: face-name associative memory (Dr. Dorene Rentz, Harvard), validated in ARMADA; in a 257-participant amyloid-biomarker cohort achieved "acceptable" discrimination of amyloid-positive vs negative. Real, but "acceptable discriminatory accuracy" is a weak descriptor — likely AUC in the 0.6–0.7 range.
• Bilgel et al., 2017, J Alzheimers Dis (n>3,100, two longitudinal cohorts): digit span working memory was the first measure to decline, while individuals were still cognitively normal. Strong and genuinely important — this is the best scientific justification for testing working memory early.
• Bopp & Verhaeghen, 2005: meta-analysis of 123 studies on working memory span and aging. Strong.
• Edwards et al., 2017 (ACTIVE): up to 29% lower dementia rates after speed-of-processing training, 10-year follow-up, n=2,802.

Evidence grade: assessment layer = B. Training layer / dementia-reduction claim = D.

Why the split. The measurement side is well-founded: these are validated paradigms drawn from real cohorts, and the Bilgel finding that digit span moves first is a legitimate scientific rationale for a consumer product. The training side is where the problem is:

1. The ACTIVE 29% figure is being borrowed. ACTIVE's speed-of-processing arm used the Useful Field of View (UFOV) task, which was commercialized as Double Decision by Posit Science/BrainHQ, not by NeuroAge. NeuroGames is a different product. Claiming a 29% dementia reduction on the basis of a trial of someone else's intervention is exactly the inferential leap the FTC prohibited.
2. The ACTIVE dementia finding itself is contested. Dementia was not a pre-specified primary outcome of ACTIVE; the original trial's headline result was that training improved the trained ability with minimal far transfer to daily function. The dementia analysis was a long-follow-up secondary analysis with proxy-based ascertainment, and the effect was concentrated in participants who returned for booster sessions (i.e., a self-selected adherent subgroup). Memory and reasoning training arms showed no significant effect.
3. "Brain age estimate that updates with ongoing play" conflates practice effects with biological change. If the score improves because the user got better at the game, the product is measuring familiarity, not brain aging. Nothing on the site addresses practice-effect correction — a first-order methodological requirement for any repeat-administered cognitive assessment.

Bottom line: NeuroGames is the weakest product in the lineup and the one carrying the most aggressive claim. It is also, at $9.99/mo, the funnel entry point.

2.2 Brain MRI — $1,398 new scan / $999 (or $399, listed inconsistently) for upload; +$1,299 full-body

What it is. Non-contrast structural brain MRI through a partner imaging network, processed by the BrainKey platform for volumetrics across 25+ regions (the Essentials page claims 100+), a brain age estimate against age/sex norms, 3D visualizations, and radiologist review for incidental findings.

The science cited.

• Hippocampal volume — the earliest and best-established structural marker of AD. Grade A as a risk marker.
• White matter hyperintensities — Qi et al., 2020 meta-analysis, 36 prospective studies, >19,000 participants: higher WMH burden associated with +14% all-cause dementia, +25% AD, +73% vascular dementia. Zhou 2022: 49% increased progression risk. Grade A.
• WMH reversibility — Brown et al., 2022, Neurology: WMH regression documented in up to a third of participants; Wardlaw et al., 2017: WMH decreased in 37% of 190 adults within one year, with baseline BP predicting resolution. Grade B, and genuinely underappreciated — this is a legitimately motivating finding for a consumer.
• Incidental findings — Vernooij et al., 2007, NEJM (n=2,000): 1.8% asymptomatic cerebral aneurysm, 1.6% benign primary brain tumor. Toh 2022 meta-analysis (n=40,777): ~1% neoplastic incidental findings. Grade A for prevalence; the interpretation is where it gets contentious.

Evidence grade: underlying markers = A. The "brain age" number derived from them = C. The screening-of-asymptomatic-adults use case = C/D.

The three problems.

1. Brain age models don't generalize well to individuals. The 2025 literature is blunt about this: brain age models show marked performance drops on external datasets, systematically over- or under-estimate depending on training-set age skew, produce estimates not centered on zero in cognitively normal subjects, and vary considerably between software packages on the same scans. Recent work supports brain age gap as a group-level biomarker while explicitly flagging that bias correction is required before individual clinical use. NeuroAge sells an individual number.

2. BrainKey's regulatory status is not disclosed. Competing volumetric packages — NeuroQuant, VUNO Med-DeepBrain, CorticoMetrics THINQ, icometrix — hold FDA 510(k) clearances and say so. I found no evidence of a BrainKey 510(k), and the NeuroAge site makes no clearance claim. A Y Combinator–backed Stanford spinout with AI models trained on "tens of thousands of scans" is a reasonable technical bet, but it is not the same as a cleared device, and the site does not draw that line for the customer.

3. The incidental-findings pitch cuts both ways. NeuroAge frames incidental findings as a benefit ("caught an aneurysm another provider missed") and cites the 30–40% rupture mortality figure. That's real. But the base rates cited are the argument against population screening: at ~1.8% aneurysm prevalence in asymptomatic adults, most detected aneurysms are small, will never rupture, and generate surveillance imaging, anxiety, and occasionally a procedure with its own morbidity. The literature on DTC whole-body MRI finds 40–50% of scans produce at least one incidental finding, and one 1,000-person series found 180 required workup to identify 2 tumors — a positive predictive value of ~0.011. No professional society recommends brain MRI screening in asymptomatic adults. NeuroAge presents only the upside.

This is nonetheless the strongest product in the lineup — NeuroAge says so themselves, and correctly: "MRI volumetrics is currently the most predictive single component in the NeuroAge panel." Non-contrast MRI is genuinely safe and repeatable, and hippocampal volume and WMH are the two structural markers with the best predictive track record.

2.3 Blood Biomarkers Test (52-transcript RNA panel) — $899

What it is. NeuroAge's proprietary and only truly differentiated asset: a 52-transcript blood RNA panel positioned as a brain-specific aging clock, mapping to five hallmarks — metabolic dysfunction, neuroinflammation, synaptic decline, cellular senescence, stress response. Explicitly positioned as not an Alzheimer's pathology test but a measure of upstream aging biology. Site claim: "NeuroAge's RNA blood biomarker panel is proprietary, and no other company offers it."

The science cited.

• Glorioso et al., 2019, Life Science Alliance — "Rate of brain aging and APOE ε4 are synergistic risk factors for Alzheimer's disease." Transcriptome analysis of 673 postmortem brain samples across four/five cohorts, ages 25–97, free of neurological disease. Established a transcriptome-based molecular brain age gauge that correlates well with DNA methylation clocks; showed APOE ε4 accelerates molecular brain aging synergistically. This is a real, well-regarded paper.
• Glorioso, Oh, Douillard, Sibille, 2010 (Sibille lab, Pitt) — characterized the molecular aging signature across four brain regions.
• The site's stated foundation for the blood proxy: blood transcriptomics from postmortem cohorts predicted brain biological age from 23 blood transcripts at p<10⁻⁶.
• Irmady et al., 2023, Nature Communications — precedent that postmortem Parkinson's brain transcriptome patterns are detectable in antemortem peripheral blood.

Evidence grade: D (with a credible path to B).

This is the central finding of the whole audit. The most expensive recurring test, the one product no competitor has, the one thing that makes NeuroAge a company rather than a reseller of Quest and BrainKey — has never been validated in living humans. The evidence chain is:

Postmortem brain tissue (n=673) → a molecular clock ✅ well-established
Postmortem paired blood samples → 23 transcripts predict brain age at p<10⁻⁶ ✅ promising, but postmortem blood
Living people's blood → 52 transcripts predict their brain age ❓ this is what the n=75 ADDF study is testing right now

Their own science page states this openly: the study's purpose is "to determine whether blood-based transcriptomic and methylation signatures can predict biological brain age as accurately in living people as they do in postmortem brain-blood paired cohorts." That is an admission that the answer is not yet known — and to their credit, it's stated plainly rather than hidden.

Additional concerns:

• Postmortem blood transcriptomes are not equivalent to living blood transcriptomes. Agonal state, hypoxia, post-mortem interval, and terminal illness all reshape the transcriptome. The 23→52 transcript expansion is also unexplained on the site.
• Blood RNA is extremely labile. Whole-blood transcriptomes shift with acute infection, time of day, fasting state, recent exercise, stress, and medication. The COVID literature shows transcriptomic age shifting by up to 21 years during acute infection and reverting on recovery. NeuroAge markets the panel's responsiveness to lifestyle as a feature — "the RNA panel can detect whether biological changes are actually occurring" — but the same lability that makes it responsive makes single measurements noisy. No pre-analytical protocol, test-retest reliability, or biological-variation data is published.
• "Brain-specific" is doing heavy lifting. Blood cells are not brain cells. The claim is that these 52 transcripts were selected for correlation with brain tissue aging, which is a defensible selection strategy, not a demonstration of brain specificity in circulation.
• The forward-looking claim is honest about being forward-looking. "As the NeuroAge dataset grows... the data will eventually make it possible to identify... which specific processes are driving that acceleration." The pathway-level readout is explicitly a future capability, not what the $899 buys today.

If the ADDF study reads out positive with a reasonable effect size and it replicates in an independent cohort, this becomes a genuinely valuable asset — a modifiable, repeatable, upstream brain-aging biomarker is something the field actually lacks, and their argument that amyloid-focused biomarkers are useless for monitoring non-amyloid therapeutics is correct and well-made. n=75 single-arm is a feasibility pilot, not validation.

2.4 Genetic Resilience Analysis — $249 (analysis) / +$550–799 (30× whole-genome sequencing)

What it is. APOE genotype plus a 41-variant Alzheimer's polygenic risk score; eight longevity/resilience variants (Klotho KL-VS, APOE ε2, FOXO3, CETP, IGF1R, IL-6, mTOR, PCSK9); six medically actionable pharmacogenomic genes (MTHFR, CYP2C19, CYP2C9, SLCO1B1, VKORC1, HLA-B*15:02); and PRS for eight other conditions (CAD, AF, osteoporosis, colorectal and ovarian cancer, glaucoma, psoriasis, Crohn's).

The science. Component by component:

Evidence grade: PGx = A. APOE = A. Everything else = C/D.

The real issue is delivery, not validity. Returning APOE ε4 homozygous status — a 10–15× Alzheimer's risk — to a consumer, alongside HLA-B*15:02 and VKORC1 results with direct prescribing consequences, is genetic counseling territory. The site's only framing is "Inherited risk does not determine your future, but it can tell you where to pay closer attention." The Essentials Bundle includes one 30-minute virtual consultation; the standalone $249 genetic product does not appear to include any. There is no listed genetic counselor on the team.

To their credit, the contextualization principle is sound and well-stated: "A lower overall NeuroAge score is associated with reduced neurological disease risk even in individuals with lower genetic resilience" — i.e., genes are not destiny, and current-state biomarkers matter more. That's the right message.

2.5 AD-Detect Blood Test — $799 (Quest Diagnostics)

What it is. A resold Quest Diagnostics panel: plasma Aβ42/40 ratio plus phosphorylated tau (p-tau217, and p-tau181 per the product page), combined into Quest's proprietary AD-Detect Likelihood Score.

The science cited.

• Barthélemy et al., 2024, Nature Medicine: plasma p-tau217 clinically equivalent or superior to FDA-approved CSF tests for classifying amyloid and tau PET status. Grade A. This is real and important.
• Khalafi et al., 2025, Alzheimer's & Dementia: meta-analysis of 30 studies, p-tau217 82% sensitivity / 86% specificity for amyloid PET positivity. Grade A.
• Racke et al., 2024 (AB255): low baseline Aβ42/40 increases progression risk to dementia ~70%. Grade B.
• Racke et al., 2025, Neurology Clinical Practice: real-world analysis of >4,000 specimens; 42% classified high likelihood, 15% indeterminate (10% with ApoE). Grade B.
• Quest's combined Likelihood Score: 91% sensitivity / 91% specificity, validated in the 1Florida ADRC cohort. Grade B — sponsor-validated, single cohort.

Evidence grade: the biomarkers themselves = A. This use case (asymptomatic consumers) = D.

This is the most defensible assay and the least defensible application in the entire lineup. p-tau217 is arguably the biggest advance in Alzheimer's diagnostics in twenty years. The problem is who it's being sold to.

1. It is a laboratory-developed test. It is not FDA cleared or approved. Quest's own materials say so. NeuroAge's site does not.
2. The Alzheimer's Association's 2025 Clinical Practice Guideline on blood-based biomarkers explicitly excludes cognitively unimpaired individuals, "given the current lack of clinical relevance for blood-based biomarker use in this population," and also excludes primary care settings. The guideline covers specialists testing people with objective cognitive impairment. NeuroAge markets this to asymptomatic adults purchasing online, outside of specialty care. That is squarely outside guideline-recommended use.
3. Base rates destroy the positive predictive value in this population. 91%/91% in an enriched memory-clinic cohort does not translate to a 55-year-old with no symptoms, where amyloid positivity prevalence might be 10–15%. At those base rates a large fraction of positives are false, and the sensitivity/specificity figures quoted on the site materially overstate what an asymptomatic buyer should expect.
4. Quest's DTC launch of this test in 2023 drew unusually sharp criticism from Alzheimer's researchers and clinicians — described in trade press as opening a "Pandora's box," with concerns about false positives, patient comprehension, and unjustified anxiety; one report quoted neurologists calling the consumer-initiated version "an absolute catastrophe." Quest subsequently added a clinical-involvement requirement. NeuroAge's product page states only that it "does not replace physician-led diagnosis."

NeuroAge's own framing is the best argument against buying it from them: they explicitly say the RNA panel targets "the upstream biological aging process," positioning AD-Detect as the downstream-pathology complement. If that's true, AD-Detect is the least aligned product with their own thesis — and it's the one product a customer could just as easily get through their physician.

2.6 Essentials Bundle — $1,398/year (from $1,746, 20% off)

Brain MRI with 3D dashboard + preventative screening, Genetic Resilience analysis, NeuroGames, full score interpretation, personalized recommendations, one 30-minute virtual consultation. Add-ons: genome sequencing +$799, RNA blood test +$899, full-body MRI +$1,299.

Claims: "Dementia starts 20–30 years before the first symptom" (defensible), "40% of dementia cases are potentially preventable" (the 2020 Lancet Commission figure; the 2024 update says 45%, and their science page correctly uses 45% — the bundle page is stale), "trained on data from over 500,000 people" (the credibility-transfer issue again).

Note the bundle is priced annually. A $1,398/year subscription implies annual MRI in asymptomatic adults. Non-contrast MRI is safe to repeat, but there is no evidence base supporting annual structural brain MRI as surveillance in healthy people, and the year-over-year change in hippocampal volume in a healthy adult is on the order of the measurement error of most volumetric pipelines. The recurring-revenue model is ahead of the measurement science.

2.7 Coaching Program — $280 per 50-minute session (1, 4, or 12 sessions)

One-on-one with Dr. Glorioso herself, organized around "the 9 Pillars of Healthy Brain Aging." Helps interpret MRI, genetic, blood, and cognitive results; builds a prevention plan.

Grade: N/A as science; this is a service. Two observations: (1) it does not scale — the CEO of the company is the delivery unit, which caps this at a boutique revenue line; (2) it is, in practice, the clinical-interpretation layer the rest of the product line lacks. The company has effectively priced genetic and biomarker counseling as a premium add-on rather than building it into the products that generate results requiring interpretation.

2.8 NeuroAge Test Ultra — $3,895

"The full multi-modal workup" — all modalities combined. No dedicated page found; referenced from the routing quiz and homepage. This is the anchor price that makes the $1,398 bundle look moderate.

2.9 Summary scorecard

Overall verdict on NeuroAge's science: intellectually serious, commercially premature. The founder is a real physician-scientist with real publications, the citations are honest, the biological thesis (brain aging as an upstream, modifiable, measurable substrate for neurodegeneration) is scientifically live and arguably correct, and the self-graded evidence tiers show good faith. But not one of the products has published performance characteristics for its intended use, the flagship differentiator is explicitly unvalidated in living humans, and the composite "NeuroAge Score" — the number the entire brand is built on — has no published validation of any kind.

3. Lumosity / Lumos Labs — comparison and contrast

3.1 What Lumosity is today

3.2 Head-to-head

3.3 The five contrasts that matter

1. Borrowed evidence vs. owned evidence. This is the deepest difference and it runs opposite to intuition. NeuroAge looks far more scientific — a physician-scientist founder, 40 citations, postmortem transcriptomics, ADDF funding. Lumosity looks like a game company. But NeuroAge's citations establish that brain aging is real and measurable; they do not establish that NeuroAge measures it accurately. Lumosity's evidence base is smaller in scope but tested on the actual shipping product, by an independent regulator, against a sham control, double-blind. NeuroAge has more science about the world; Lumosity has more science about its product. For a buyer, the second kind is what matters.

2. The regulatory asymmetry is a live business risk for NeuroAge, not a Lumosity disadvantage. Lumos Labs cannot say "reduces dementia risk." NeuroAge effectively does. That looks like a NeuroAge advantage today and is actually the reverse: the FTC's 2016 theory of the case maps almost exactly onto NeuroAge's ACTIVE-trial citation, and the FDA's LDT enforcement posture plus the professional backlash against DTC Alzheimer's blood testing put NeuroAge in a category regulators are actively watching. Lumosity has already paid this bill and rebuilt around it. The consent order that looked like a scar is now a moat.

3. Measurement vs. modification — and neither has closed the loop. NeuroAge measures well and intervenes weakly (supplements, generic lifestyle advice, and a training game with no evidence of its own). Lumosity intervenes with cleared evidence in one narrow indication and measures broadly but only in the cognitive domain. Neither company can currently say: "we measured your brain, we intervened, and the measurement moved." NeuroAge is closer conceptually — that's what the digital-twin vision describes — but is furthest from having the validated measurement to close it with. Lumosity is closer operationally, because it has a cleared intervention and a validated assessment, but has never tied training outcomes to biological markers.

4. Unit economics are inverted, and it shapes everything. NeuroAge needs roughly 17 customers to match the annual revenue of 250 Lumosity subscribers. That justifies high-touch sales, coaching, and clinical partnerships — but it caps TAM at people who will pay $1,400–3,900 out of pocket, a segment already crowded by Function Health, Neko Body Scan, Prenuvo, InsideTracker, and every longevity clinic. Lumosity's economics require scale and retention and are pressured by free alternatives — which is precisely why the prescription channel matters: a cleared PDT reaches payers and prescribers, where price is not set by the App Store.

5. What each is really building. NeuroAge's endgame is stated openly and is not a diagnostics company: cell-culture and animal studies on two therapeutics targeting master regulators of brain aging, with the biomarker panel as the companion monitoring tool. Read that way, the DTC business is a data-and-cash-generation machine for a drug program — which explains the aggressive consumer marketing of an unvalidated panel more charitably than a pure-diagnostics reading would. Lumos Labs' endgame is a portfolio of cleared digital therapeutics and digital biomarkers across 11 indications, monetized through healthcare rather than app stores. Both are using a consumer business to fund a medical business. NeuroAge is earlier and less hedged.

3.4 Where they overlap, compete, and could complement

Direct competition today: minimal. Different price points, different buyers, different jobs to be done. A Lumosity subscriber is not choosing between $60/yr of games and a $1,398 MRI.

Where they collide in 2–4 years:

• MCI screening and monitoring. Lumos Labs lists MCI as a proof-of-concept indication with 5 publications; NeuroAge's entire funnel is early detection. Both will end up pitching health systems and payers on "detect cognitive change early." Lumosity arrives with normative data on 130K people and a cleared-device track record; NeuroAge arrives with biology.
• The cognitive assessment layer. NeuroGames is NeuroAge's weakest asset and it sits in the exact domain where Lumosity has 7.5 billion data points and a published, validated instrument.
• Longevity-clinic and concierge-medicine channels, where both a validated cognitive battery and a biological panel get bundled.

Where they're complementary — and this is the interesting part. NeuroAge's largest scientific gap is the cognitive layer: unvalidated brain-age-from-gameplay, no practice-effect correction, borrowed efficacy evidence. Lumosity's largest gap is biological grounding: it can show a training effect on a cognitive score but cannot show it on brain structure or biology. The NCPT is the instrument NeuroGames is trying to be, and a biological panel is the outcome measure Lumosity has never had. There is a real partnership shape here — Lumosity as the validated cognitive measurement and intervention layer inside a multi-modal biological assessment — and it would strengthen both. It would also give Lumos Labs something it currently lacks: a biological anchor for training claims that the FTC order otherwise makes unsayable.

3.5 If you're at Lumos Labs, the takeaways

1. NeuroAge is not a competitive threat; it's a competitive signal. It demonstrates that a segment will pay $1,400–3,900 for brain-health measurement with no validated product behind it. Lumosity has the validated measurement asset (NCPT) and no premium measurement SKU. That gap is worth more attention than NeuroAge itself.

2. The ACTIVE-trial claim is a case study to circulate internally. A competitor is currently making the precise claim Lumos Labs was fined $2M for, citing a trial of a third party's intervention. Whatever happens to NeuroAge, this is the clearest available illustration of why the claims discipline exists — and worth watching, because if the FTC acts, the category-level chill affects everyone.

3. FDA clearance is now the differentiator, and it should be said louder. As of December 2025 Lumos Labs holds something no brain-health consumer company has: a 510(k)-cleared cognitive intervention backed by a double-blind sham-controlled trial in 560 people. NeuroAge's entire "peer-reviewed science" positioning is weaker than that single fact, and the market does not yet know it.

4. The measurement-plus-intervention loop is the open position. Neither company has closed it. Lumos Labs is closer than it looks: a validated instrument, a cleared intervention, a proof-of-concept MCI pipeline, and FNIH biomarker consortium membership. What's missing is the biological endpoint. Whether that's built, partnered, or acquired, it's the thing that turns "brain training" into "brain medicine."

5. Watch NeuroAge's ADDF readout. If the n=75 study shows blood transcriptomic signatures predicting MRI- and cognition-derived brain age in living people with a meaningful effect, the RNA panel becomes a real asset and NeuroAge becomes a credible partner or acquisition target. If it doesn't, the company's differentiation collapses to reselling Quest and BrainKey.

4. Caveats on this analysis

• Content was captured from the live site in August 2026 via automated page fetch and summarization. Prices for Brain MRI upload were reported inconsistently across pages ($999 on the product page, $399 on the routing quiz) and one fetch of the pricing page returned a corrupted price table; treat all figures as indicative.
• /products, /partnering, and /resources returned 404 during the audit — the therapeutics pipeline and partnership model could not be assessed from the site directly and are reconstructed from /our-science and third-party coverage.
• Evidence grades are my judgment against the stated intended use of each product, not a formal systematic review. I did not attempt to obtain full texts of the ~40 cited papers; citation accuracy was spot-checked on the load-bearing ones (Glorioso 2019, Edwards 2017, Barthélemy 2024, the 2025 AA blood-biomarker guideline).
• Lumosity details are drawn entirely from public sources. Anything internal — roadmap, unpublished data, LumosityRx commercialization plans — is not reflected here.

Sources

NeuroAge: Our Science · Home · NeuroGames · Brain MRI · Blood Biomarkers · Genetic Resilience · AD-Detect · Essentials Bundle · Coaching · ADDF Study · About Us · What test is right for you

Company background: Crunchbase · Longevity.Technology · Propel(x)

Key science: Glorioso et al. 2019, Life Science Alliance · Edwards et al. 2017 (ACTIVE) · Vernooij et al. 2007, NEJM · AA Clinical Practice Guideline on blood-based biomarkers, 2025 · AAIC 2025 guideline release

Brain age limitations: Brain age software clinical validity comparison, eBioMedicine 2025 · Bias and generalizability of brain age models · Distribution bias in brain age research · Brain age gap as predictive biomarker, Communications Medicine 2025

AD-Detect / DTC criticism: Quest AD-Detect test directory · Alzforum: DTC Alzheimer's blood test opens Pandora's box · 360Dx: experts raise concerns · Being Patient

MRI screening: Incidental findings on brain MRI, MedLink · DTC whole-body MRI screening outcomes

Lumosity / Lumos Labs: Lumosity Science · Lumos Labs Digital Medicine · FDA clears LumosityRx, Medical Device Network · LumosityRx clearance, Psychiatry Advisor · FTC settlement, January 2016 · Science coverage of FTC fine · NCPT reliability and validity · NCPT massive dataset, Scientific Data