Adequacy review — MDCG 2020-13 Overall Conclusions

Purpose and method

Per-criterion adequacy review of R-TF-015-003 against the Overall Conclusions section of MDCG 2020-13. Methodology identical to Section C.

Source documents: MDCG 2020-13 Overall Conclusions; R-TF-015-003 CER #conclusions (line 2432+).

Reviewer: BSI clinical-auditor reviewing agent. Review baseline commit: 0c26288f0 (after §G CER fixes land).

OC.1 — Summary of clinical benefits

Criterion: summarise the clinical benefits with meaningful and measurable patient-relevant clinical outcomes (including diagnosis-related outcomes); describe their positive impact on patient management or public health.

CER location: #benefit-7gh-improvement-in-diagnostic-accuracy (line 2440); #benefit-5rb-objective-severity-assessment (line 2450); #benefit-3kx-care-pathway-optimisation (line 2454).

Verdict: Tick.

Rationale. Each of the three claimed benefits is summarised with quantitative magnitudes against pre-specified acceptance criteria and with explicit links to supporting pivotal studies. Benefit 7GH reports accuracy improvements per user tier and per pathology tier; 5RB reports ICC / Kappa / RMAE per condition against expert reference standards; 3KX reports waiting-time reduction, referral optimisation, remote-care capacity, and expert-consensus utility. The chain from claim to measured outcome to impact on patient management (reduced missed malignancy, reduced waiting time, reduced unnecessary referral, improved severity-assessment consistency) is traceable on the face of the CER.

OC.2 — Summary of risks with clinical relevance

Criterion: summarise the risks with clinical relevance (uncertainties or limitations of clinical data, undesirable side-effects, potential for misuse) with incidence, severity, duration, vulnerable subgroups, and any dose-response relationship.

CER location: #gspr-compliance at line 2436 (compact benefit-risk narrative); #declared-acceptable-evidence-gaps at line 2458; #pediatric-population at line 2468; full risk detail at #risk-management-and-residual-risks-acceptability (line 2225+) and #safety-benchmarking-against-state-of-the-art (line 2277+), outside the Conclusions section.

Verdict: Conditional.

Rationale. The Conclusions section references residual risks qualitatively at line 2438 ("Residual risks have been mitigated to acceptable levels through the integrated image quality validator, probabilistic output design, visual explainability metadata, and dedicated IFU guidance") and enumerates three acceptable evidence gaps (line 2458-2466) with brief rationale each. The detailed residual-risk list (6 of 62 remaining, defence-in-depth architecture, P₂=1 constraint, quantitative benchmarking zero-over-800 with 0.375% upper 95% CI) lives in the benefit-risk body section. A reviewer reading the Conclusions only will not see the quantitative risk summary.

Recommended fix. Anchor: #gspr-compliance, append a concise risks-with-clinical-relevance paragraph. Insert: "Risks with clinical relevance. The risk management file identifies 62 risks, of which 8 residual risks remain after mitigation; these are classified by the risk management file under Usability (2 residual risks) and Product (6 residual risks) categories, and are all assessed at Severity 3 (Major) under the P₂=1 architectural severity constraint described in section Risk architecture. Across the pivotal-investigation portfolio (more than 800 patients), zero device-related adverse events, zero incidents, zero CAPAs, and zero FSCAs were recorded, with the upper 95% confidence bound on the true adverse-event rate of 0.375% per the rule of three (Hanley and Lippman-Hand 1983) — see section Safety Benchmarking against State of the Art. Uncertainties of clinical data comprise the three acceptable evidence gaps declared under MDCG 2020-6 § 6.5(e) and addressed by targeted PMCF activities: autoimmune dermatoses, genodermatoses, and Fitzpatrick V-VI representativeness. Vulnerable subgroups are paediatric patients (addressed by Activity F.1) and Fitzpatrick V-VI skin (addressed by Activity E.1); there is no dose-response relationship for a software-only MDSW." Primary source: R-TF-015-003 #risk-management-and-residual-risks-acceptability (line 2225+); #safety-benchmarking-against-state-of-the-art (line 2277+); MDCG 2020-13 Overall Conclusions; MEDDEV 2.7/1 Rev 4 §A7.2.

OC.3 — Discussion of the impact of risks in relation to clinical benefits

Criterion: discuss the impact of the risks (per OC.2) in relation to the clinical benefits, taking into account the factors described, particularly uncertainties in clinical data.

CER location: body-level benefit-risk assessment at #assessment-of-the-benefit-risk-profile (line 2366+); body-level risk-benefit narrative at lines 2225-2273; no explicit benefit-risk impact paragraph in the Conclusions section.

Verdict: Conditional.

Rationale. The benefit-risk assessment in the body of the CER is substantive and reaches a clear conclusion, but the Conclusions section does not contain a single paragraph discussing the impact of the risks (residual risks, undesirable side-effects, uncertainties in clinical data) against the three benefits. A reviewer working from Conclusions alone cannot see the final impact discussion.

Recommended fix. Anchor: #gspr-compliance, after the Risks with clinical relevance paragraph proposed in OC.2. Insert: "Impact of risks in relation to clinical benefits. The residual-risk profile is bounded by the defence-in-depth safety architecture (upstream DIQA input gate plus five downstream clinical barriers; see section Risk architecture), which imposes the P₂=1 architectural severity constraint on the device: the device cannot directly cause physical harm to the patient because its output is always mediated by a supervising healthcare professional. Weighed against the clinical benefits substantiated in this CER — 7GH diagnostic-accuracy improvements of +15 to +27 percentage points in the intended-use settings, 5RB severity-assessment concordance with expert consensus across four dermatological conditions, and 3KX waiting-time reduction of 50-60% and unnecessary-referral reduction of 38% — the residual risks are considered acceptable, and the uncertainties associated with the acceptable evidence gaps are justified under MDCG 2020-6 § 6.5(e) with documented PMCF closure plans. The overall benefit-risk profile is favourable." Primary source: #assessment-of-the-benefit-risk-profile (line 2366+); #risk-architecture (line 2253+); MDCG 2020-13 Overall Conclusions; MEDDEV 2.7/1 Rev 4 §10.1.

OC.4 — Completeness of risk identification in the clinical evaluation

Criterion: have all risks that could have a significant impact on the benefit-risk analysis been identified in the clinical evaluation?

CER location: body-level consistency analysis at line 1749-1772 (Consistency between SotA, clinical data, and RMF; Consistency with information materials; No new safety concerns); the §F.1.b + §F.2 fixes that documented the legacy-device PMS fitness-of-purpose.

Verdict: Conditional.

Rationale. The body of the CER explicitly concludes "no new clinical safety concerns" (line 1772) and "no gaps or discrepancies were identified" between SotA, clinical data, RMF, and information materials (line 1757-1761). The Conclusions section does not repeat this declaration in a CEAR-aligned form.

Recommended fix. Anchor: #gspr-compliance, after the Impact of risks paragraph proposed in OC.3. Insert: "Completeness of risk identification. All risks that could have a significant impact on the benefit-risk analysis have been identified in this clinical evaluation. The cross-analysis between the State of the Art, the available clinical data, the Risk Management File (R-TF-013-002 and R-TF-028-011), and the information materials supplied by the manufacturer identified no new safety concerns, no gaps, and no residual uncertainties beyond the three evidence gaps declared as acceptable under MDCG 2020-6 § 6.5(e). This conclusion is re-verified at each scheduled CER update and on any unscheduled update triggered by PMS or PMCF findings." Primary source: R-TF-015-003 #consistency-between-the-state-of-the-art-the-available-clinical-data-and-the-risk-management-documentation (line 1749+); #new-safety-concerns (line 1768+); MDCG 2020-13 Overall Conclusions.

OC.5 — Alignment between risk management and clinical evaluation

Criterion: is there alignment between the risk management and clinical evaluation?

CER location: body-level alignment at #risk-management-and-residual-risks-acceptability safety-objectives table (line 2225+, six safety objectives with observed performance) and #safety-benchmarking-against-state-of-the-art (line 2277+); no explicit alignment statement in Conclusions.

Verdict: Conditional.

Rationale. The body of the CER contains an explicit six-row safety-objective table mapping each identified residual risk to a measurable objective and an observed outcome from the pivotal studies (line 2225+). The Conclusions section does not state that this alignment exists and that it is evidenced by the table.

Recommended fix. Anchor: #gspr-compliance, after the Completeness of risk identification paragraph proposed in OC.4. Insert: "Alignment between risk management and clinical evaluation. The six safety objectives defined in the Risk Management File are each mapped to a measurable clinical outcome in this CER, and each has been met in the pivotal investigation portfolio (zero cases reported across the applicable risk categories; see the safety-objectives table in section Risk management and residual risks acceptability). The Risk Management File and this Clinical Evaluation Report are therefore aligned on the set of residual risks, their acceptance criteria, and their observed-versus-claimed outcomes; any future amendment to the residual-risk list is propagated to both documents at the next CER update cycle." Primary source: #risk-management-and-residual-risks-acceptability (line 2225+, safety-objectives table); MDCG 2020-13 Overall Conclusions; ISO 14971:2019 §7.5.

Overall Conclusions roll-up

Overall-Conclusions tick-box	Verdict	One-sentence rationale
Benefit-risk conclusions and risk-management / clinical-evaluation alignment	Compliant with minor non-compliance	OC.1 (benefit summary) is Tick; four Conditionals (OC.2 risks summary, OC.3 benefit-risk impact discussion, OC.4 risk-identification completeness, OC.5 risk-management alignment) are wording inserts at a single anchor (#gspr-compliance), each reproducing content already present in the body of the CER in Conclusions-section form.

Roll-up. Overall Conclusions is Compliant with minor non-compliance. The review produced 1 Tick and 4 Conditionals across 5 criteria. All four Conditional fixes are consolidation paragraphs at the same anchor — they surface content already present in the body of the CER into the Conclusions section so that a notified-body reviewer reading Conclusions in isolation can answer each CEAR tick-box without opening the CER body.