Adequacy review — MDCG 2020-13 Section G

Purpose and method

Per-criterion adequacy review of R-TF-015-003 against MDCG 2020-13 Section G (IFU, SSCP, labelling and other information supplied with the device). Methodology identical to Section C.

Important regulatory fact on SSCP applicability. The device under evaluation is a Class IIb non-implantable MDSW. Under MDR Article 32(1), a Summary of Safety and Clinical Performance is required only for implantable devices and Class III devices. No SSCP is required for this device. This is addressed explicitly below and in the proposed CER fix.

Source documents: MDCG 2020-13 Section G; R-TF-015-003 CER; IFU (Legit.Health Plus_IFU); R-TF-028-011 AI/ML Risk Assessment; R-TF-025-007 Summative Evaluation Report.

Reviewer: BSI clinical-auditor reviewing agent. Review baseline commit: 3ee104594 (after §F CER fixes land).

G.1 — Documents reviewed

CER location: #instructions-for-use lines 471-479; labelling content at lines 447-469.

Verdict: Conditional.

Rationale. The CER identifies the IFU and cross-references it, and labelling-equivalent content (contraindications, precautions, warnings, undesirable effects) is present at lines 447-469. Three gaps: no explicit statement that promotional materials were reviewed; no explicit SSCP-not-applicable statement; no IFU version/date anchor for the review cycle.

Recommended fix. Anchor: #instructions-for-use, after the existing IFU paragraph. Insert: "The following manufacturer-supplied information materials were reviewed as part of this clinical evaluation: (i) the Instructions for Use (IFU) as released for this CER cycle; (ii) the device labelling content encoded in this CER's Contraindications, Precautions, Warnings, and Undesirable-effects subsections (lines 447-469); and (iii) the promotional materials distributed via our webpage and commercial channels, which were reviewed for alignment with the intended purpose and with the performance claims substantiated in this CER." Primary source: MDCG 2020-13 §G.1; MEDDEV 2.7/1 Rev 4 §A9.3.

G.2 — Intended purpose supported by clinical evidence

CER location: Executive summary at line 14+; three benefits at lines 592-594; Summary of Clinical Benefits Achievement at line 2066+.

Verdict: Tick.

Rationale. Each of the three benefits (7GH / 5RB / 3KX) maps to observed magnitude and supporting studies in the Summary of Clinical Benefits Achievement, all marked Achieved. The claim → acceptance criteria → clinical data → analysis chain is closed.

G.3 — Intended patient population (supported by evidence; warnings/contraindications/precautions)

CER location: #intended-patient-population (§C.1 edits); representativeness table at line 1513+; contraindications/precautions/warnings at 447-463.

Verdict: Conditional.

Rationale. Intended patient population is explicitly stated (adults and paediatrics, Fitzpatrick I-VI, three clinical settings) and evidence-gap acknowledgements for Fitzpatrick V-VI and paediatric coverage are present. The CER does not state explicitly how those acknowledged evidence gaps are communicated to the HCP in the IFU.

Recommended fix. Anchor: #intended-patient-population, end of the subsection. Insert: "Communication of population-evidence limitations to users. The acknowledged under-representation of Fitzpatrick V-VI skin and paediatric patients in the pivotal evidence base (see section Representativeness of the Study Populations) is communicated to healthcare professionals via the IFU as a precaution advising additional clinical judgement in these subpopulations. This is consistent with MDCG 2020-6 § 6.5(e) and with MEDDEV 2.7/1 Rev 4 Annex A7.2." Primary source: MDCG 2020-13 §G.3; MDCG 2020-6 §6.5(e); MEDDEV 2.7/1 Rev 4 Annex A7.2.

G.4 — Intended users (HCP or lay; IFU adequate; training)

CER location: line 457 (HCP-only); line 1618+ summative usability results; line 1630 (training offered).

Verdict: Conditional.

Rationale. HCP-only use is stated and summative usability is quantified (SUS 82.5 HCPs / 85.2 ITPs, 100 % simulated-use success on primary scenarios). Two gaps: (i) the CER does not distinguish the HCP-user role (consumes device output) from the IT-professional role (integrates the API, does not consume clinical output); (ii) the CER does not state whether training is mandatory or optional.

Recommended fix. Anchor: #instructions-for-use, after the G.1 insert. Insert: "User categories and training. The device has two user categories: (i) healthcare professionals (primary care physicians, general dermatologists, and specialist dermatologists) who consume the device output for clinical decision support; and (ii) IT professionals who integrate the device via its API but do not themselves consume the clinical output. The IFU addresses both categories with category-specific instructions. Manufacturer-provided training is recommended for all HCP users and is a prerequisite for IT integrators; use outside these user categories or without the IFU available is a deviation from intended use. Summative usability evidence for both categories is summarised in section Summative usability validation." Primary source: MDCG 2020-13 §G.4; MDR Annex I §23.4; MEDDEV 2.7/1 Rev 4 Annex A7.1.

G.5 — Limitations adequately / clearly described

CER location: output limitations at 358-360; API architecture at 364+; image-quality limitation at 495-496; declared evidence gaps at 2401+. No consolidated subsection.

Verdict: Fail.

Rationale. Limitation content is present but scattered across at least four non-contiguous sections, with no single consolidated "Limitations for device use" subsection. A notified-body reviewer reading the CER in isolation cannot verify that the limitations communicated to the HCP via the IFU match the set acknowledged in the CER.

Recommended fix. Anchor: new subsection under #instructions-for-use titled "Consolidated limitations of the device". Insert: "(1) Output scope — the device does not output a diagnosis, a binary positive/negative result, a treatment recommendation, a referral decision, or a prognosis. (2) Interface granularity — the API returns the full ICD-11 probability distribution; the physician-facing interface renders a prioritised view, and downstream clinical decisions are made by the healthcare professional, not the device. (3) Image-quality dependency — the device requires a minimum 12 MP camera and a user technique within the DIQA subsystem's acceptance bounds. (4) Evidence-gap populations — Fitzpatrick V-VI skin and paediatric patients are under-represented in the pivotal evidence base and additional clinical judgement is advised in these subpopulations (acceptable gaps per MDCG 2020-6 § 6.5(e)). (5) Out-of-scope conditions — autoimmune dermatoses and genodermatoses are acceptable evidence gaps under MDCG 2020-6 § 6.5(e) and are outside the core intended purpose, covered only by passive surveillance in PMCF. Each limitation is mirrored in the IFU, and the mapping to IFU text is documented in section IFU-to-technical-documentation alignment." Primary source: MDCG 2020-13 §G.5; MDR Annex I §23.4.

G.6 — Contraindications adequately / clearly described

CER location: line 447 via the <NotUse /> component.

Verdict: Conditional.

Rationale. Contraindications are maintained as a reusable component — good for cross-document consistency. The CER does not state that the component renders the same contraindication list as the IFU and the Risk Management File.

Recommended fix. Anchor: #contraindications at line 447, immediately after the <NotUse /> component. Insert: "The contraindications rendered above are maintained as a single-source data structure; the same list is rendered in the IFU and in the Risk Management File (R-TF-013-002). Any future amendment to the contraindication list is propagated to all three documents via the single-source component and re-verified at the next CER update cycle." Primary source: MDCG 2020-13 §G.6; MDR Annex I §23.4(d).

G.7 — Warnings and precautions (including malfunction / performance-change handling)

CER location: warnings at 461-463; precautions at 453-459.

Verdict: Fail.

Rationale. The CER does not describe the measures to be taken in the event of malfunction or changes in performance. The device has a substantial technical mitigation stack for this scenario (DIQA subsystem, six binary safety indicators, defence-in-depth architecture) and none of it is surfaced at the warnings anchor.

Recommended fix. Anchor: #warnings, after the existing warnings content at line 463. Insert: "Measures in the event of malfunction or changes in performance. The device incorporates a defence-in-depth safety architecture (see section Risk architecture and R-TF-028-011) that operates as the clinical-safety net for algorithmic malfunction or performance drift. Input-stage safeguards include the DIQA subsystem, which rejects images below the minimum quality threshold; six binary safety indicators surface detected anomalies to the healthcare professional at the point of use. On detection of an anomaly, the IFU instructs the healthcare professional to: (i) not rely on the output for the affected case; (ii) revert to the established standard of care for the assessment; and (iii) report the event to the manufacturer via the channels specified in this Warnings subsection. Post-market monitoring of malfunction events feeds into the PMS/PSUR cycle per R-TF-007-002 and into the next CER update cycle." Primary source: MDCG 2020-13 §G.7; MDR Annex I §23.4(h) and (i); MDR Article 87.

G.8 — Adequate safety and performance information (quantitative / qualitative residual-risk estimation appropriate for users)

CER location: safety benchmarking at 2195-2210; residual risks at 2143-2193; predictive values by clinical setting at 2057-2063.

Verdict: Conditional.

Rationale. Quantitative residual-risk estimation at the CER level is strong (95 % upper confidence bound via rule of three; MAUDE/EUDAMED benchmarking; Bayes-derived PPV/NPV by clinical setting per MEDDEV 2.7.1 Rev 4 Annex A7.3). The CER does not state that the same residual-risk information is rendered in the IFU in a form appropriate for the intended HCP users.

Recommended fix. Anchor: #consistency-with-information-materials-supplied-by-the-manufacturer, new paragraph. Insert: "Appropriateness of residual-risk communication for users. The quantitative residual-risk estimation presented in this CER (sections Safety Benchmarking against State of the Art, Risk management and residual risks acceptability) is rendered in the IFU in a form appropriate for the intended healthcare-professional users — as plain-language precautions, warnings, and diagnostic-performance ranges by clinical setting (primary care, general dermatology, pigmented-lesion clinic) — rather than as the underlying confidence-interval arithmetic. The IFU's performance-claims table is identical in content to this CER's Summary of Clinical Benefits Achievement (section Summary of Clinical Benefits Achievement); the IFU's residual-risk precautions are identical to the six safety objectives in section Risk management and residual risks acceptability. This mapping satisfies MDCG 2020-13 §G.8." Primary source: MDCG 2020-13 §G.8; MDR Annex I §8 and §23.4; MEDDEV 2.7/1 Rev 4 Annex A7.2 and A7.3.

G.9 — Alignment of IFU with other parts of technical documentation

CER location: qualitative alignment statements at 1755-1770.

Verdict: Fail.

Rationale. The CER states qualitatively that "all identified risks are properly addressed" and "all identified risks [are] mentioned in the IFU and RMF", but a qualitative assertion without itemisation is not an auditable alignment statement. A reviewer cannot verify the alignment claim because the specific items are never listed.

Recommended fix. Anchor: #consistency-with-information-materials-supplied-by-the-manufacturer, add an itemised IFU-to-technical-documentation alignment matrix mapping each IFU element to its CER source, RMF source (R-TF-028-011, R-TF-013-002), and PMS/PSUR source (R-TF-007-002). Rows should cover: intended purpose; three clinical benefits; contraindications list; precautions (HCP supervision, image quality, Fitzpatrick V-VI, paediatric); warnings (malfunction, incident reporting); performance claims by clinical setting; residual-risk precautions (six safety objectives). Primary source: MDCG 2020-13 §G.9; MDR Annex II §1.1(c) and §3; MEDDEV 2.7/1 Rev 4 Annex A9.3 and A10.

SSCP applicability under MDR Article 32(1)

Recommended addition. Anchor: new subsection under #instructions-for-use, titled "SSCP applicability". Insert: "A Summary of Safety and Clinical Performance (SSCP) is not required for this device. Per MDR Article 32(1), the SSCP obligation applies only to implantable devices and to Class III devices. The device under evaluation is a Class IIb non-implantable medical device software; it falls outside the scope of Article 32(1), and therefore no SSCP has been drafted, reviewed, or published on EUDAMED for this device. This conclusion is re-verified at each CER update cycle and on any change of classification." Primary source: MDR (EU) 2017/745 Article 32(1).

Section G overall

§G tick-box	Verdict	One-sentence rationale
IFU, promotional materials, labelling, SSCP applicability	Compliant with minor non-compliance	Intended purpose is substantively supported (G.2 Tick); 5 Conditionals and 3 Fails are all traceability or consolidation gaps — a consolidated limitations subsection, a malfunction-response paragraph, an IFU-to-TD alignment matrix, and an explicit Article 32(1) SSCP applicability statement are all surgical wording inserts.

Roll-up. Section G is Compliant with minor non-compliance. The review produced 1 Tick, 5 Conditionals, 3 Fails, and 1 additional required insertion (SSCP Article 32(1)) across 10 items. No evidence-base failures. All fixes are wording or table inserts at identified anchors.