Scientific Evidence Dossier

The evidence behind Companion Care — stated honestly

A clinician-, IRB-, and payer-facing account of the psychometrics of every instrument we administer and an honest, cited review of whether AI and technology companionship actually reduces loneliness and depression in older adults. We separate what is well-validated (the instruments) from what is not yet proven (this product's efficacy) — and we never overstate.

The load-bearing distinction

Our instruments are validated. Our product is not. UCLA-3, PHQ-2/PHQ-9, and GAD-7 are well-established screeners with peer-reviewed psychometrics in older adults. That is a strong, defensible foundation for screening, monitoring, and routing to humans.

It is not evidence that Boojee Companion Care reduces loneliness or treats depression. No product like ours has demonstrated efficacy in a controlled trial, and the most-quoted consumer figures in this space (e.g., a "95% reduction in loneliness") come from non-randomized, self-report, response-biased data. Our path from validated instruments to a validated product runs through an IRB-reviewed controlled study — described here.

Part 1

Instrument psychometrics

Each instrument is public-domain / free-to-use, delivered using its exact validated item stems and response anchors. Below: derivation, scoring, older-adult cutoffs, and the honest limitations — including the caveats of repeated measurement and conversational delivery. Full detail in instrument-psychometrics.md.

UCLA-3 Three-Item Loneliness Scale Validated screener

Hughes, Waite, Hawkley & Cacioppo (2004), Research on Aging 26(6):655–672 — derived from the R-UCLA-20 (Russell 1996).

Items: Lack companionship / feel left out / feel isolated. Anchors 1 hardly ever · 2 some of the time · 3 often.
Score: Total 3–9 (higher = lonelier). Field convention: ≥6 = probable/meaningful loneliness (a convention, not a diagnostic cut).
Older adults: Built & tested in ~2,100 middle-aged/older adults (HRS); internal consistency α ≈ 0.72; acceptable concurrent & discriminant validity.
Admin: Designed for telephone/oral delivery — the one instrument here purpose-built for voice.

Limits: loneliness is self-reported, not a diagnosis (no true sensitivity/specificity); only 7 possible scores → coarse, real floor/ceiling & weak change-resolution; oral-script validation licenses fixed stems, not conversational paraphrase.

PHQ-2 & PHQ-9 Depression Validated screener

Kroenke, Spitzer & Williams — PHQ-9 (2001, J Gen Intern Med 16:606–613); PHQ-2 (2003, Med Care 41:1284–1292).

Score: PHQ-9 0–27, bands 5/10/15/20 (mild→severe). PHQ-2 0–6; ≥3 → administer PHQ-9.
Accuracy: PHQ-9 ≥10: sensitivity 88%, specificity 88% for major depression (general/primary care).
Older adults: Optimal cut runs LOWER in elders: ≥5 gave sens 100%/spec 81%; ≥10 spec 95% but sens fell to 71% (under-detects). Treat the 5–9 "mild" band as review-worthy, not reassurance.
Change: MID ≈5 points; reliable change (Jacobson–Truax) ≈≥6-point reduction; validated for treatment monitoring.
Item 9: Safety trigger only — routes to human + 988. NOT a suicide-risk assessment (low PPV; a "0" doesn't rule out risk).

Limits: somatic items overlap with normal aging/illness (score inflation); accuracy degrades with cognitive impairment; the 2-week window makes frequent re-administration autocorrelated (practice/response-set effects).

GAD-7 Anxiety Validated screener

Spitzer, Kroenke, Williams & Löwe (2006), Arch Intern Med 166(10):1092–1097.

Score: 0–21, bands 5/10/15; screen-positive ≥10.
Accuracy: ≥10: sensitivity 89%, specificity 82% for GAD (n=965); mostly unidimensional, α ≈ 0.89–0.92.
Older adults: Acceptable, widely used — but less geriatric-specific validation than PHQ-9; anxiety/depression overlap lowers discriminant precision.

Limits: no clean MID/reliable-change anchor like PHQ-9 → treat trends as directional signal, not calibrated change; somatic items overlap with cardiac/respiratory disease common in elders.

Part 2

The conversational-administration validation gap

Every psychometric number above was established under a standardized administration mode — paper/computer self-report for PHQ/GAD, a fixed telephone script for UCLA-3. Our companion delivers items conversationally, in dialogue. We preserve the verbatim stems and anchors, but conversational delivery is a genuine deviation that can move scores: rapport and demand effects, any paraphrase or reordering, voice pacing, and the fact that a warmly conversing AI is not a neutral administrator.

What the literature says — honestly, both directions. Early work is encouraging: a GPT-4o voice chatbot administering the PHQ-9 showed high concordance with self-administration (ICC ≈ 0.91, median absolute difference ≈ 1 point, no systematic bias), and paper/computer/mobile equivalence studies generally find rough agreement. But those studies are small, recent, not peer-reviewed at the level of our other citations, not in older adults, and not our product. Interview modes have also shown lower reliability (α ≈ 0.80) than self-report (α ≈ 0.87) in some comparisons — mode can matter.

Our position: conversational administration is plausibly near-equivalent, but it is not validated for our population and mode, and we will not claim equivalence until we run a within-subject concordance/fidelity study (ICC, mean bias, Bland–Altman limits of agreement) in older adults — reported before any efficacy claim.

Part 3

Does AI / tech companionship actually work?

GRADE-style read of the real literature. The problem is strongly evidenced; specific companion interventions range from a modest RCT signal (PARO for depression in dementia) to mixed-to-null for ICT reducing loneliness in elders. Full review in evidence-base.md.

Loneliness/isolation harms elder health

High

Established. NASEM 2020 + Holt-Lunstad: isolation's all-cause mortality risk rivals smoking/obesity; ~50% higher dementia risk. Justifies screening & connection — not any specific product.

PARO robot reduces depression in dementia

Low–Mod

RCT meta-analysis: significant depression effect (SMD ≈ −0.42), may ease loneliness; but small, mostly institutional/dementia samples, short follow-up, QoL effects inconsistent. A tactile robot pet — not conversational AI.

CBT chatbots reduce short-term depression/anxiety

Low

Woebot RCT (n=70, ages 18–28, 2 weeks) cut PHQ-9 vs psychoeducation — but young adults, tiny, brief, subclinical, and not consistently replicated. Not older adults, not loneliness.

ICT/tech reduces loneliness in older adults

Low → Null

RCT meta-analysis (6 RCTs, 391 pts): pooled SMD = −0.08 (95% CI −0.33 to 0.17, ns) — "little to no difference" vs control. No harm found. This is the category we most resemble; the honest read is the burden of proof is unmet.

Consumer AI companion (ElliQ-type) reduces loneliness

Very Low

Not an RCT. ElliQ (n=173 customer survey, 62% response; NY pilot n=107) reports the "95% reduction" figure from self-report with response/selection bias. The authors themselves say RCTs are still needed. Satisfaction data, not efficacy.

Boojee Companion Care reduces loneliness/depression

Untested

No evidence yet. Requires our own IRB-reviewed controlled trial before any efficacy claim. Instrument validity does not transfer to product efficacy.

Risks we name plainly: a compelling companion could displace human contact rather than bridge to it; friendly-companion demand bias can inflate our own self-report metrics (the very flaw that makes ElliQ-type numbers untrustworthy); and LLM companions can mishandle crisis disclosures — so crisis/item-9 handling must be deterministic and human-routed, never left to generative judgment.

Part 4

How we will measure outcomes honestly

Endpoints, meaningful-change thresholds, confounds, and — critically — what each study design can and cannot claim. Full plan in measurement-plan.md.

Endpoints. Primary: UCLA-3 change, PHQ-9 change. Secondary: GAD-7 (directional), engagement (a process measure, never an efficacy result). Safety: item-9 events, crisis-escalation completion, score deterioration.

Meaningful change. PHQ-9 has clean anchors — MID ≈5, reliable change ≈≥6 points (Jacobson–Truax). UCLA-3 and GAD-7 have no established individual-change value; we report change distributions and will not invent thresholds.

Why pre/post ≠ proof. A single-arm improvement is fully explained by regression to the mean + natural history + demand bias + attention effects without the product doing anything. Uncontrolled data is legitimate for feasibility, engagement, and safety signals — nothing more. Only a randomized, ideally attention-controlled trial with blinded outcome assessment can honestly support an efficacy claim on UCLA-3/PHQ-9 change.

Our sequence: (1) conversational-vs-standardized fidelity study → (2) IRB-reviewed feasibility single-arm (labeled non-causal) → (3) controlled trial before any efficacy claim reaches payers, marketing, or the public. Preregistered, intention-to-treat, per-participant responder analysis, all endpoints reported.

Part 5

What we can and cannot claim

We can honestly say

Loneliness & isolation are serious, well-evidenced health risks in older adults.
We use peer-reviewed, validated screening instruments (UCLA-3, PHQ-2/9, GAD-7).
We screen, monitor, and route positive findings to humans — a defensible measurement-based-care process.
Evidence for some companion technologies is promising but preliminary.

We must not claim

That the product "reduces loneliness by X%" — the ElliQ "95%" figure is the exact claim to avoid.
That it "improves mood," "treats depression," or is "clinically proven."
That validated instruments make the product validated — they do not.
Any efficacy claim before an IRB-reviewed controlled trial.

Appendix

Full analyses

Instrument Psychometrics

Per-instrument derivation, scoring, older-adult cutoffs, monitoring caveats, and the conversational-administration gap — fully cited.

Evidence Base Review

GRADE-style review of PARO, ElliQ, Woebot/Wysa, ICT meta-analyses, and NASEM 2020 — strength, gaps, and harms, honestly.

Measurement Plan

Endpoints, reliable-change/MID thresholds, confounds, and the design ladder mapping each study to the claim it can support.

Key references

Peer-reviewed sources

• Hughes, Waite, Hawkley & Cacioppo (2004), UCLA-3, Research on Aging — journals.sagepub.com · PMC2394670
• Kroenke, Spitzer & Williams (2001), PHQ-9, J Gen Intern Med — Wiley
• Kroenke, Spitzer & Williams (2003), PHQ-2, Med Care
• PHQ-9 in older adults (cutoff shifts) — PMC8559588 · cognitive impairment PMC3930057
• Spitzer, Kroenke, Williams & Löwe (2006), GAD-7, Arch Intern Med — reference PDF · psychometrics PMC6691128
• PHQ-9 monitoring / sensitivity to change (Löwe 2004) — PMID 15550799; RCI/MID — NovoPsych · Jacobson–Truax
• Chatbot PHQ-9 administration concordance (HopeBot) — arXiv 2507.05984
• NASEM (2020), Social Isolation & Loneliness — nationalacademies.org · PMC7742588
• PARO RCT meta-analysis — Int J Nurs Stud 2023
• ElliQ progress/lessons (2024) — PMC10917141
• Woebot RCT (Fitzpatrick 2017) — JMIR Ment Health
• ICT-for-loneliness RCT meta-analysis (2021) — PMC8692663

Prepared by the Boojee Estate desk for clinical, IRB, and payer review. The instruments cited are validated; Boojee Companion Care itself has not undergone independent clinical validation or a controlled trial, and this page makes no efficacy claim. Honesty commitments here are load-bearing — please hold us to them.

Trust & Evidence Center — full compliance & evidence status →