Prevention Adoption Initiative · Data infrastructure pillar

Colorectal screening — completion work queue

The behaviorally-configured registry the initiative would install: it ranks overdue patients by an explainable non-completion risk, recommends the next-best action, and tracks completion, cost, and the equity gap. Work the reds first — mark one complete and watch the numbers move.

Highest-priority patients

Ranked by non-completion risk = care gap + prior no-shows + SDOH barriers + language mismatch. Each score shows its contributions.

Completion funnel

Where the panel is right now.

Equity — completion by language

Watched as a fairness guardrail, not an afterthought.

Why this is state-of-the-art — and honest

Explainable risk

The score is decomposable — every point traces to a driver (a SHAP-style contribution breakdown). In production the additive score is replaced by a trained model (logistic regression → gradient boosting) with the same explainability.

Next-best action

Not just "who is high-risk," but which action most changes completion for this person — an uplift / contextual-bandit policy over channel and message.

FHIR integration

Ingest overdue panels and results via Bulk FHIR / SMART-on-FHIR; write actions back as FHIR Communication / Task resources. Phase 1 runs on a flat export; deep write-back is Phase 2.

Fairness monitoring

The equity gap is a first-class metric, tracked so automation never widens disparities for patients with unstable contact or low portal access.

Full panel

All 30 synthetic patients.

Patient	Lang	ZIP	Payer	Barriers	Risk	Status

A demonstration of the Prevention Adoption Initiative (an HSREP initiative in development). Synthetic data; no real patients, no PHI, no EHR connection. Illustrative only.