In partnership with
Find your next winning ad creative in seconds with AI
Most AI tools promise you thousands of ads at the click of a button. But do you really need more ads—or just better ones?
Kojo helps you cut through the noise. We analyze your paid social data to uncover the ideas with the highest chance of success. Then, our AI predicts which concepts will perform best, so you don’t waste budget testing what won’t work.
Instead of drowning in endless variations, Kojo sends your best idea straight to a real human creator who makes it engaging, authentic, and ready to win on social. The entire process takes less than 20 seconds, giving you certainty before you spend and better performance without the waste.
Why gamble on guesswork or settle for AI spam when you can launch ads proven to work, made by people, and backed by data?
Executive Summary
Medical Affairs organizations are judged increasingly on patient impact, not activity volume. The winning move is to target physicians according to the unmet medical needs (UMNs) within their actual patient panels—and then measure how effectively those needs are closed.
Core premise: Medical Affairs teams that systematically identify, prioritize, engage, and measure UMNs will outperform broadcast models on outcomes, efficiency, and credibility.
Framework: A five-pillar operating system—(1) UMN assessment, (2) physician influence mapping, (3) engagement optimization, (4) impact analytics, (5) compliance and audit—implemented via privacy-by-design data, transparent logic, and explainable AI.
The Strategic Context: Why This Is Now Mission-Critical
What holds Medical Affairs back
Activity-based KPIs: Counting emails, events, and visits obscures whether patients benefited.
Broad segmentation: Specialty and geography miss practice-level realities.
Regulatory complexity: Ambiguity around educational vs promotional boundaries increases risk.
Physician expectations: Clinicians want practice-specific, high-utility scientific support.
Market forces you can harness
Value-based care: Outcome-tied incentives align with UMN-first engagement.
Real-world evidence: Demonstrable effects on treatment patterns strengthen your scientific mandate.
Analytics & AI: Data now make practice-level UMNs objectively visible and actionable.
System consolidation: Evidence-backed engagement helps physicians advocate inside integrated delivery networks.
Pillar 1 — Define and Quantify Unmet Medical Need (UMN)
Working definition
An unmet medical need exists where a measurable gap separates evidence-based care from real-world practice inside a physician’s panel.
Must-have characteristics
Measurable: Based on objective, reproducible indicators.
Evidence-anchored: Mapped to guidelines or peer-reviewed standards.
Patient-specific: Derived from de-identified, practice-level data.
Actionable: Addressable via education, process change, or resource support.
UMN classification (examples chosen to avoid company-specific therapies)
UMN Type | Definition | Illustrative Example (neutral) |
|---|---|---|
Treatment Gap | Eligible patients not receiving guideline-supported therapy | Patients with persistent asthma symptoms lacking any maintenance regimen |
Optimization Opportunity | Patients on therapy but not at recommended targets | Dyslipidemia patients on low-intensity statins despite high risk |
Diagnostic Delay | Long interval from first suggestive code to diagnosis | Sleep-disordered breathing symptoms without formal evaluation |
Adherence Challenge | Early discontinuation or erratic fills | Chronic therapy stopped within 60–90 days without alternative |
Calculating an Unmet Need Index (UNI)
Let Eligible be patients meeting objective criteria; Unaddressed those untreated, undertreated, delayed, or non-persistent.
Weighted UNI (severity & urgency)
Severity and Urgency use 1–5 scales tied to clinical consequences and time-sensitivity.
Data inputs (de-identified where patient-level):
Claims/administrative (de-identified per the Health Insurance Portability and Accountability Act [HIPAA]): diagnosis/procedure timelines, hospital/ER encounters, prescription fills and discontinuations.
Practice context: National Provider Identifier (NPI) registry for identity; affiliations; public quality indicators where available.
Engagement signals: Scientific inquiries, webinar participation, website interactions (consented).
Evidence layer: Guidelines and real-world evidence to define Eligible and Unaddressed criteria.
Privacy & governance: Use HIPAA-compliant de-identification, data use agreements, audit logs, and role-based access. Document sources, transformation, and versioning.
Pillar 2 — Map Physician Influence and Reach
Augment UMN with a multi-dimensional picture of physician leverage.
Influence dimensions & sample metrics
Clinical reach: Active panel size in condition; consult volumes (claims, NPI).
Decision autonomy: Therapeutic variety; formulary flexibility (pattern analysis).
Peer recognition: Publications, invited talks, committee roles (public sources).
Educational role: Teaching appointments, mentoring.
Innovation adoption: Uptake of new standards when indicated.
Quality leadership: Involvement in improvement initiatives.
Create an Influence Score tailored to your objectives. Keep weights transparent and review annually.
Pillar 3 — Orchestrate Targeted, Channel-Savvy Engagement
Use UNI + Influence Score + Engagement history to determine who hears what, when, and how.
Targeting matrix
Tier 1 (High UNI, High Influence):
Medical science liaison (MSL) scientific exchange; protocol/process consultations; advisory roles; real-world evidence collaborations.Tier 2 (Low UNI, High Influence):
Thought leadership, peer best-practice forums, guideline dissemination, innovation updates.Tier 3 (High UNI, Low Influence):
Case-based digital education, interactive modules, virtual boards, on-demand consults.Tier 4 (Low UNI, Low Influence):
Automated newsletters, resource hubs, self-service micro-learning.
Channel assignment logic
Begin with policy-as-code: enforce the Controlling the Assault of Non-Solicited Pornography and Marketing (CAN-SPAM) Act for commercial email, U.S. Food and Drug Administration (FDA) communication rules, and Pharmaceutical Research and Manufacturers of America (PhRMA) Code limits.
Use per-channel propensity and uplift models to select the next best channel/content.
Apply capacity and fairness constraints (e.g., MSL bandwidth; geographic equity).
Pillar 4 — Measure Impact with Causal Discipline
Core outcome formulas
UMN Closure Rate
Time-to-Appropriate-Treatment (TTAT) Improvement
Persistence/Adherence Improvement (≥6 months)
Diagnostic Latency Reduction
Attribution
Maintain holdouts by segment; run geo-experiments where possible.
Use difference-in-differences or CUPED to adjust for baseline variance.
Report point estimates with confidence intervals; document confounders and limitations.
Operational metrics to manage the machine: MSL time to case resolution, scientific inquiry depth, content match quality, cost per UMN addressed.
Pillar 5 — Compliance, Documentation, and Audit Readiness
Design so you can pass an audit today.
HIPAA (Health Insurance Portability and Accountability Act): Use de-identified patient data only; document de-identification provenance.
CAN-SPAM Act: Accurate headers, truthful subject lines, physical address, and rapid opt-out processing for any commercial email.
FDA guidance: Educational vs promotional boundaries; “consistent with labeling” for product communications; procedures for unsolicited requests.
PhRMA Code: Appropriate interactions with healthcare professionals (HCPs).
Centers for Medicare & Medicaid Services (CMS) Open Payments: Use for transparency checks and conflict-of-interest workflows.
Audit trail architecture
Data input validation: Source, privacy status, quality checks.
Decision rationale: Model versions, parameters, human overrides, policy checks.
Outcome measurement: Metric changes, statistical significance, attribution method.
All steps time-stamped, user-attributed, and version-controlled.
Implementation Roadmap (Phase-Gate)
Phase 1 (Months 1–6) – Foundation
Stand up secure data platform; connect National Provider Identifier (NPI) registry; codify policies.
Define eligibility rules and UMN algorithms with Medical/Compliance.
Pilot one therapeutic area and limited geographies.
Phase 2 (Months 7–12) – Pilot & Learn
Deploy Tier 1–3 playbooks; run controlled tests; refine models and thresholds.
Publish executive dashboards; conduct interim compliance audit.
Phase 3 (Months 13–18) – Scale
Expand indications/geographies; automate orchestration; add uplift models and constrained optimizers.
Establish external validation (academic/third-party) for credibility.
Change management essentials
Executive sponsorship tied to outcome KPIs.
Cross-functional operating cadence (Medical, Legal/Compliance, Data/IT, Field).
Role-specific upskilling (MSLs on needs-based consultation; analysts on causal methods).
Business Case: Why Boards Should Back This
Patient outcomes: Faster appropriate therapy, fewer preventable events.
Physician trust: Partnership fueled by objective need and scientific utility.
Organizational efficiency: Resources flow to highest-impact practices.
Regulatory resilience: Traceable, explainable, compliant decisions.
Enterprise value: Medical Affairs evolves into the evidence-to-impact engine.
Risks & Mitigations (Condensed)
Privacy risk → HIPAA de-identification, privacy impact assessments, third-party audits.
Model bias → Fairness constraints; periodic equity reviews by geography/specialty/site-of-care.
Low physician adoption → Show practice-level value; close the loop with outcome feedback.
Data quality → Source validation, drift monitoring, and corrective workflows.
Regulatory uncertainty → Conservative interpretations; pre-launch legal review; living policy-as-code.
Conclusion
Volume is yesterday’s scoreboard. Unmet medical need is today’s mandate.
By identifying UMNs with discipline, matching physicians to channels with precision, and measuring closure with causal rigor, Medical Affairs earns its seat as the strategic steward of patient outcomes—and the boardroom’s trust.
FAQ: The Questions Behind the Questions
1. What qualifies as an “Unmet Medical Need (UMN)” in this framework?
An unmet medical need is a measurable, evidence-based gap between recommended clinical practice and real-world treatment within a physician’s patient panel. Examples include untreated eligible patients, delayed diagnoses, suboptimal therapy regimens, or low persistence with therapy.
2. How does UMN targeting differ from traditional physician targeting?
Traditional targeting: based on specialty, geography, or prescription volume.
UMN targeting: based on objective, practice-specific patient gaps that can be improved through education and scientific exchange.
This ensures Medical Affairs resources are deployed where they matter most.
3. What data sources are required?
Public: National Provider Identifier (NPI) registry, CMS Open Payments.
Optional (contracted, HIPAA-compliant): De-identified claims, prescription data, referral networks.
Internal: Scientific inquiry logs, webinar participation, website interactions, MSL call notes.
4. How do we measure whether unmet needs are being closed?
By tracking:
The percentage of patients moving from “untreated” to “appropriately treated.”
Reductions in time from diagnosis to initiation of evidence-based therapy.
Improvements in persistence and adherence to therapy.
Shorter diagnostic timelines for conditions with established pathways.
5. What’s the role of Medical Science Liaisons (MSLs)?
MSLs are deployed strategically to physicians with high unmet need and high influence, where in-depth scientific exchange can meaningfully improve patient care. Their role evolves from information delivery to practice transformation partner.
6. How does this framework ensure compliance and audit readiness?
Every targeting decision is backed by:
Documented rationale and data sources.
Immutable logs of decisions, models, and human review.
Built-in safeguards to enforce FDA, HIPAA, CAN-SPAM, and PhRMA standards.
7. What risks exist with this approach?
Privacy risks: mitigated with HIPAA-compliant de-identification.
Model bias: reduced through fairness checks and equity reviews.
Physician skepticism: addressed by showing practice-specific value.
Regulatory ambiguity: managed through conservative interpretation and proactive review.
8. How does this align with value-based healthcare trends?
Value-based systems reward outcomes, not volume. By focusing on closing unmet needs, Medical Affairs supports physicians in achieving better outcomes, aligns with payer expectations, and strengthens credibility as a scientific partner.
9. How quickly can this be implemented?
Lean pilot: 3–6 months using simple unmet need scoring and 1–2 channels.
Enterprise rollout: 12–18 months with full data integration, weighted scoring, optimization, and dashboards.
