Skip to main content
Companion Care
Boojee Companion Care · Clinical Research Program

From "uses validated instruments"
to "has evidence."

The honest path forward, in three stages. Using UCLA-3, PHQ-2/9, and GAD-7 is table stakes — the instruments are validated, but our conversational administration of them, and any outcome from the program, are not.

This is the study program that closes that gap: first prove the measurement holds, then look for a signal in an uncontrolled pilot, then — and only then — test whether it works in a randomized controlled trial. Each stage earns exactly one honest claim and nothing more.

SPIRIT 2013 protocols CONSORT 2010 trials STROBE observational Common Rule 45 CFR 46 ClinicalTrials.gov registration
01 — The Evidence Roadmap

Three stages. Each unlocks one claim.

Evidence is earned in order. Skipping a stage does not buy the claim — it just makes the claim wrong. The honesty rule: never state a claim a completed study cannot support.

Stage 1 · Fidelity / Equivalence

Does conversational scoring equal the validated screen?

Within-subjects, counterbalanced. The same older adults take each screen two ways — standardized self-report vs. the companion in conversation — and we test agreement (ICC, Bland–Altman, weighted κ) and equivalence (TOST) against pre-set margins.

Unlocks: "The companion's conversational scores are equivalent to the validated self-administered instruments."
Does NOT unlock any claim that the program helps anyone. Fidelity ≠ efficacy.
Stage 2 · Single-Arm Outcomes Pilot

Does loneliness/mood move — and can we run this safely?

~40 isolated older adults, 12 weeks, pre/post UCLA-3 + PHQ-9 with the Reliable Change Index, plus real engagement and safety data. No control group — by design.

Unlocks: "In an uncontrolled pilot, X% showed reliable improvement; the program was feasible and safe." An association + feasibility claim.
Does NOT unlock any claim that the companion caused the change. Pilot = association, not causation.
Stage 3 · Randomized Controlled Trial

Does the companion actually cause improvement vs. control?

Registered, randomized, controlled — ideally against an attention-matched control, because for a companionship product the honest question is "better than an equal amount of contact," not "better than nothing." Blinded outcome assessment; powered from the pilot's effect size.

Unlocks: the real efficacy claim — "in a randomized controlled trial, the companion reduced loneliness/depression vs. control." The evidence tier payers and regulators recognize.
Still limited by a single trial, one population, and durability — replication strengthens it.
Where we are today: pilot-stage, zero enrolled participants, zero results. The category benchmarks we cite elsewhere (ElliQ, Papa, Pyx impact reports) are those vendors' own program data, not peer-reviewed RCTs and not our results. These protocols are how we build our own evidence, honestly.
02 — Draft Protocol Documents

Four IRB-grade draft documents.

Each is a full draft protocol written to the standard an IRB and a payer's clinical team would expect: objectives, design, sample-size justification, analysis plan, safety provisions, and honest limitations.

Study 1 · Equivalence

Instrument-Fidelity Study

Answers the #1 objection: a score obtained in conversation is not automatically the validated score. This proves — or disproves — equivalence.

Design
Within-subjects, counterbalanced, 48h–7d washout
Sample
Target N≈120 (ICC-precision driven)
Margins
UCLA-3 ±1, PHQ-9/GAD-7 ±2 points (TOST)
Agreement
ICC ≥0.75, Bland–Altman limits, weighted κ ≥0.60
Safety
PHQ-9 item-9 concordance gated as a safety analysis
Study 2 · Pilot

Single-Arm Outcomes Pilot

The program's first honest data point: does loneliness and mood move over 12 weeks, and can we operate safely? Uncontrolled by design.

Design
Single-arm, pre/post; no control group
Sample
~N=40, isolated older adults (UCLA-3 ≥6), 12 weeks
Primary
UCLA-3 + PHQ-9 via Reliable Change Index
Secondary
Engagement + retention (≥70% target) + safety base rates
Registration
ClinicalTrials.gov registered before enrollment
Claim
Explicitly: association only, not causation
Study 3 · RCT

Randomized Controlled Trial — Outline

The eventual gold standard for a causal efficacy claim. Sequenced last, powered from the pilot. Confronts the hard attention/placebo problem head-on.

Arms
Companion vs. attention-control (or 3-arm) vs. usual care
Blinding
Blinded outcome assessment; participants cannot be blinded
Primary
UCLA loneliness; power from pilot effect size
Standards
CONSORT + prospective ClinicalTrials.gov registration
Oversight
Full independent DSMB
Cross-cutting · Safety

Human-Subjects Safety Plan

Governs all three studies. Suicidality escalation, adverse-event reporting, elder-abuse disclosure, consent & capacity, and data safety.

Crisis
PHQ-9 item-9 / risk language → 988 + clinician alert, logged
AE/SAE
AE/SAE definitions + IRB reporting timelines
DSMB
Mini-DSMB (pilot) → full DSMB + stopping rules (RCT)
Consent
Capacity-to-consent screen for older adults
Reporting
Elder-abuse mandatory reporting; HIPAA data safety
03 — Safety Monitoring Plan

Crisis care always overrides research.

These studies enroll isolated older adults and screen for depression and suicidal ideation. Safety is not an afterthought — it is the precondition for running at all. In every study, including the pure measurement study, a positive suicidality signal triggers the standing crisis pathway immediately, independent of any research procedure.

Standing escalation rule. PHQ-9 item 9 > 0, or any suicidal statement in any mode, triggers immediate 988 Suicide & Crisis Lifeline resources (call or text 988), a real-time clinician alert, an audit-logged escalation event, and — for imminent risk — emergency services per the clinical director's SOP. No data point is worth a missed escalation.
Crisis pathway

PHQ-9 Item 9 + Suicidality

Item 9 > 0 or any expressed suicidal ideation → immediate 988 resources surfaced, real-time clinician alert, audit log. Imminent risk → emergency services per clinical director SOP.

Adverse events

AE / SAE Definitions & Reporting

Adverse events and serious adverse events defined per protocol. IRB reporting timelines followed. All AEs logged regardless of relatedness to the intervention.

Data safety oversight

DSMB — Staged

Pilot: mini-DSMB with pre-specified stopping rules. RCT: full independent Data Safety Monitoring Board with interim analyses and formal stopping rules.

Consent

Capacity-to-Consent Screen

All older-adult participants receive a capacity-to-consent evaluation prior to enrollment. Legally authorized representatives may provide consent where capacity is limited, per IRB approval.

Mandatory reporting

Elder-Abuse Disclosure

Study staff are mandatory reporters. Any suspected elder abuse or neglect disclosed during participation is reported per applicable state law, independent of confidentiality provisions.

Data protection

HIPAA Data Safety

All participant health information handled under HIPAA. De-identified data only for analysis. IRB-approved data security plan; breach notification per regulatory requirements.

04 — What This Program Does Not Claim

The honest ceiling of each stage.

These are not caveats buried in footnotes. They are the actual epistemic bounds of a responsibly-staged evidence program.

  • No results exist yet. Nothing here has been run; we claim no outcomes.
  • Fidelity ≠ benefit. Proving conversational scores match validated ones says nothing about whether the program helps.
  • The pilot cannot prove causation. With no control arm, change may be regression to the mean, natural course, seasonality, attention, or measurement reactivity.
  • Companionship placebo is hard. Much of any benefit may be non-specific attention; only an attention-controlled RCT isolates the companion's specific effect.
  • Participants cannot be blinded. Behavioral-trial limit; we blind assessment and analysis instead, and say so.
  • Findings are build-specific. Any change to the production model or prompt re-opens fidelity — results are pinned to a build hash.
  • Scope is bounded. English-language, capacity-intact older adults; other languages and advanced cognitive impairment require their own studies.

Trust & Evidence Center — full compliance & evidence status →