R-TF-012-038 Verified Version Release

Document Information

Field	Value
Product Name	Legit.Health Plus
Version	1.1.0.0
Release Date	2026-01-23
Document Prepared Date	2026-01-23

Release Identification

Software Product Information

Field	Value
Product Name	Legit.Health Plus
Version Number	1.1.0.0
Build Number	1.1.0.0
Release Type	Initial release (major)
Release Date	2026-01-23
Previous Version	0.0.0.0

Verification Completeness

Verification Activities Completed

Activity	Reference Document	Status
Software Requirements Specification	R-TF-012-028	✅
Software Architecture Design	R-TF-012-029	✅
Software Test Plan	R-TF-012-033	✅
Software Test Description	R-TF-012-034	✅
Unit Testing	R-TF-012-035	✅
Integration Testing	R-TF-012-035	✅
System Testing	R-TF-012-035	✅
Software Test Report	R-TF-012-035	✅
Risk Management Activities	R-TF-013-002	✅

Unit and Integration Testing

Component	Coverage	Status
api_gateway	94.5%	✓ PASSED
control_plane	98.0%	✓ PASSED
report_builder	95.7%	✓ PASSED
orchestrator	97.5%	✓ PASSED
condition_classifier	90.6%	✓ PASSED
essentials	86.6%	✓ PASSED
expert_core	78.7%	✓ PASSED

Verification Results Summary

Total Requirements Verified: 112 Requirements Coverage: 100%

Total Tests Executed: 144 Tests Passed: 143 Pass Rate: 99.9%

Verification Status: Pass

Software Configuration

Software Configuration Items

name	expected-hash	hash	status
.env	d2eedd61aea79d70a2212307710b3e6c5d117609d6c9d7056abe7b159b7c01a5	d2eedd61aea79d70a2212307710b3e6c5d117609d6c9d7056abe7b159b7c01a5	PASS
nginx.conf	da608ad322e0628c4f9a5fdc00388610809dd4550acfb4e7e19d903187b0a649 nginx.conf	da608ad322e0628c4f9a5fdc00388610809dd4550acfb4e7e19d903187b0a649	PASS
docker-entrypoint.sh	de298058a13e53be7497a130bfe632c7cdf1583ace490c08dba7acbd2e7f0944	de298058a13e53be7497a130bfe632c7cdf1583ace490c08dba7acbd2e7f0944	PASS
services.yaml	26f610636b7a6dc7fec8c0a97006f011e9ff2786aac0137ad48604d6a615f7e6	26f610636b7a6dc7fec8c0a97006f011e9ff2786aac0137ad48604d6a615f7e6	PASS

Models

Model name	Location	Device Location
hyperpigmentation_segmenter	s3://skin-pathology-dl/models/visual_signs/hyperpigmentation_surface/v1.0.0/hyperpigmentation_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/hyperpigmentation_segmenter/v1.0.0/weights.ckpt
hypopigmentation_segmenter	s3://skin-pathology-dl/models/visual_signs/hypopigmentation_surface/v1.0.0/hypopigmentation_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/hypopigmentation_segmenter/v1.0.0/weights.ckpt
erythema_segmenter	s3://skin-pathology-dl/models/visual_signs/erythema_surface/v1.0.0/erythema_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/erythema_segmenter/v1.0.0/weights.ckpt
wound_bed_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_bed_surface/v1.0.0/wound_bed_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_bed_segmenter/v1.0.0/weights.ckpt
wound_biofilm_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_biofilm_surface/v1.0.0/wound_biofilm_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_biofilm_segmenter/v1.0.0/weights.ckpt
wound_bone_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_bone_surface/v1.0.0/wound_bone_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_bone_segmenter/v1.0.0/weights.ckpt
wound_granulation_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_granulation_surface/v1.0.0/wound_granulation_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_granulation_segmenter/v1.0.0/weights.ckpt
wound_maceration_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_maceration_surface/v1.0.0/wound_maceration_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_maceration_segmenter/v1.0.0/weights.ckpt
wound_necrosis_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_necrosis_surface/v1.0.0/wound_necrosis_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_necrosis_segmenter/v1.0.0/weights.ckpt
wound_orthopedic_segmenter	s3://skin-pathology-dl/models/visual_signs/wound_orthopedic_surface/v1.0.0/wound_orthopedic_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_orthopedic_segmenter/v1.0.0/weights.ckpt
body_surface_segmenter	s3://skin-pathology-dl/models/visual_signs/body_surface_segmentation/v1.0.0/body_surface_segmentation_v0.0.0.ckpt	s3://legit-health-plus/ai-models/body_surface_segmenter/v1.0.0/weights.ckpt
hair_loss_segmenter	s3://skin-pathology-dl/models/visual_signs/hair_loss_surface/v1.0.0/hair_loss_surface_v0.0.0.ckpt	s3://legit-health-plus/ai-models/hair_loss_segmenter/v1.0.0/weights.ckpt
crusting_classifier	s3://skin-pathology-dl/models/visual_signs/crusting_intensity/v1.0.0/crusting_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/crusting_classifier/v1.0.0/weights.ckpt
desquamation_classifier	s3://skin-pathology-dl/models/visual_signs/desquamation_intensity/v1.0.0/desquamation_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/desquamation_classifier/v1.0.0/weights.ckpt
erythema_classifier	s3://skin-pathology-dl/models/visual_signs/erythema_intensity/v1.0.0/erythema_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/erythema_classifier/v1.0.0/weights.ckpt
excoriation_classifier	s3://skin-pathology-dl/models/visual_signs/excoriation_intensity/v1.0.0/excoriation_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/excoriation_classifier/v1.0.0/weights.ckpt
induration_classifier	s3://skin-pathology-dl/models/visual_signs/induration_intensity/v1.0.0/induration_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/induration_classifier/v1.0.0/weights.ckpt
lichenification_classifier	s3://skin-pathology-dl/models/visual_signs/lichenification_intensity/v1.0.0/lichenification_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/lichenification_classifier/v1.0.0/weights.ckpt
oozing_classifier	s3://skin-pathology-dl/models/visual_signs/oozing_intensity/v1.0.0/oozing_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/oozing_classifier/v1.0.0/weights.ckpt
pustule_classifier	s3://skin-pathology-dl/models/visual_signs/pustule_intensity/v1.0.0/pustule_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/pustule_classifier/v1.0.0/weights.ckpt
swelling_classifier	s3://skin-pathology-dl/models/visual_signs/swelling_intensity/v1.0.0/swelling_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/swelling_classifier/v1.0.0/weights.ckpt
xerosis_classifier	s3://skin-pathology-dl/models/visual_signs/xerosis_intensity/v1.0.0/xerosis_intensity_v0.0.0.ckpt	s3://legit-health-plus/ai-models/xerosis_classifier/v1.0.0/weights.ckpt
wound_borders_diffused_classifier	s3://skin-pathology-dl/models/visual_signs/Borders:Diffused/v1.0.0/Borders:Diffused_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_borders_diffused_classifier/v1.0.0/weights.ckpt
wound_borders_thickened_classifier	s3://skin-pathology-dl/models/visual_signs/Borders:Thickened/v1.0.0/Borders:Thickened_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_borders_thickened_classifier/v1.0.0/weights.ckpt
wound_borders_delimited_classifier	s3://skin-pathology-dl/models/visual_signs/Borders:Delimited/v1.0.0/Borders:Delimited_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_borders_delimited_classifier/v1.0.0/weights.ckpt
wound_borders_indistinguishable_classifier	s3://skin-pathology-dl/models/visual_signs/Borders:Indistinguishable/v1.0.0/Borders:Indistinguishable_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_borders_indistinguishable_classifier/v1.0.0/weights.ckpt
wound_borders_damaged_classifier	s3://skin-pathology-dl/models/visual_signs/Borders:Damaged/v1.0.0/Borders:Damaged_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_borders_damaged_classifier/v1.0.0/weights.ckpt
wound_affected_tissues_bone_classifier	s3://skin-pathology-dl/models/visual_signs/Affected_tissues:Bone/v1.0.0/Affected_tissues:Bone_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_affected_tissues_bone_classifier/v1.0.0/weights.ckpt
wound_affected_tissues_subcutaneous_classifier	s3://skin-pathology-dl/models/visual_signs/Affected_tissues:Subcutaneous/v1.0.0/Affected_tissues:Subcutaneous_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_affected_tissues_subcutaneous_classifier/v1.0.0/weights.ckpt
wound_affected_tissues_muscle_classifier	s3://skin-pathology-dl/models/visual_signs/Affected_tissues:Muscle/v1.0.0/Affected_tissues:Muscle_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_affected_tissues_muscle_classifier/v1.0.0/weights.ckpt
wound_affected_tissues_intact_classifier	s3://skin-pathology-dl/models/visual_signs/Affected_tissues:Intact/v1.0.0/Affected_tissues:Intact_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_affected_tissues_intact_classifier/v1.0.0/weights.ckpt
wound_affected_tissues_dermis_epidermis_classifier	s3://skin-pathology-dl/models/visual_signs/Affected_tissues:Dermis-epidermis/v1.0.0/Affected_tissues:Dermis-epidermis_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_affected_tissues_dermis_epidermis_classifier/v1.0.0/weights.ckpt
tissue_wound_bed_necrotic_classifier	s3://skin-pathology-dl/models/visual_signs/Type_tissue_wound_bed:Necrotic/v1.0.0/Type_tissue_wound_bed:Necrotic_v0.0.0.ckpt	s3://legit-health-plus/ai-models/tissue_wound_bed_necrotic_classifier/v1.0.0/weights.ckpt
tissue_wound_bed_closed_classifier	s3://skin-pathology-dl/models/visual_signs/Type_tissue_wound_bed:Closed/v1.0.0/Type_tissue_wound_bed:Closed_v0.0.0.ckpt	s3://legit-health-plus/ai-models/tissue_wound_bed_closed_classifier/v1.0.0/weights.ckpt
wound_tissue_wound_bed_granulation_classifier	s3://skin-pathology-dl/models/visual_signs/Type_tissue_wound_bed:Granulation/v1.0.0/Type_tissue_wound_bed:Granulation_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_tissue_wound_bed_granulation_classifier/v1.0.0/weights.ckpt
wound_tissue_wound_bed_epithelial_classifier	s3://skin-pathology-dl/models/visual_signs/Type_tissue_wound_bed:Epithelial/v1.0.0/Type_tissue_wound_bed:Epithelial_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_tissue_wound_bed_epithelial_classifier/v1.0.0/weights.ckpt
wound_tissue_wound_bed_slough_classifier	s3://skin-pathology-dl/models/visual_signs/Type_tissue_wound_bed:Slough/v1.0.0/Type_tissue_wound_bed:Slough_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_tissue_wound_bed_slough_classifier/v1.0.0/weights.ckpt
wound_type_exudation_serous_classifier	s3://skin-pathology-dl/models/visual_signs/Type_exudation:Serous/v1.0.0/Type_exudation:Serous_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_type_exudation_serous_classifier/v1.0.0/weights.ckpt
wound_type_exudation_fibrinous_classifier	s3://skin-pathology-dl/models/visual_signs/Type_exudation:Fibrinous/v1.0.0/Type_exudation:Fibrinous_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_type_exudation_fibrinous_classifier/v1.0.0/weights.ckpt
wound_type_exudation_purulent_classifier	s3://skin-pathology-dl/models/visual_signs/Type_exudation:Purulent/v1.0.0/Type_exudation:Purulent_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_type_exudation_purulent_classifier/v1.0.0/weights.ckpt
wound_type_exudation_bloody_classifier	s3://skin-pathology-dl/models/visual_signs/Type_exudation:Bloody/v1.0.0/Type_exudation:Bloody_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_type_exudation_bloody_classifier/v1.0.0/weights.ckpt
wound_perilesional_erythema_classifier	s3://skin-pathology-dl/models/visual_signs/Perilesional_erythema/v1.0.0/Perilesional_erythema_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_perilesional_erythema_classifier/v1.0.0/weights.ckpt
wound_perilesional_maceration_classifier	s3://skin-pathology-dl/models/visual_signs/Perilesional_maceration/v1.0.0/Perilesional_maceration_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_perilesional_maceration_classifier/v1.0.0/weights.ckpt
wound_biofilm_tissue_classifier	s3://skin-pathology-dl/models/visual_signs/Biofilm_tissue/v1.0.0/Biofilm_tissue_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_biofilm_tissue_classifier/v1.0.0/weights.ckpt
wound_stage_classifier	s3://skin-pathology-dl/models/visual_signs/wound_stage/v1.0.0/wound_stage_v0.0.0.ckpt	s3://legit-health-plus/ai-models/wound_stage_classifier/v1.0.0/weights.ckpt
awosi_classifier	s3://skin-pathology-dl/models/visual_signs/wound_awosi/v1.0.0/wound_awosi_v0.0.0.ckpt	s3://legit-health-plus/ai-models/awosi_classifier/v1.0.0/weights.ckpt
acneiform_detector	s3://skin-pathology-dl/models/acne_detection_and_categorization/v1/1121_1537_m006_11M_DT1_preCOCO_bs16_imgsz896_e95_cm30/weights/best.pt"	s3://legit-health-plus/ai-models/acneiform/v1.0.0/weights.pt
hair_follicle_detector	s3://skin-pathology-dl/models/alopecia/follicle-count/V3/yolo11l_imgsz640_roboflow/	s3://legit-health-plus/ai-models/hair_follicle_detector/v1.0.0/weights.pt
hive_detector	s3://skin-pathology-dl/models/urticaria-followup/AUAS/yolov8/v1/M_conf0.2_iou0.3/weights/best.pt	s3://legit-health-plus/ai-models/hive_detector/v1.0.0/weights.pt
inflammatory_nodular_lesion_detector	s3://skin-pathology-dl/models/hidradenitis-followup/lesion-detection/V3_ultralytics_obb/1028_1331_m026_11M_DT1_preNone_bs8_imgsz512_e70_cm20/weights/best.pt	s3://legit-health-plus/ai-models/inflammatory_nodular_lesion_detector/v1.0.0/weights.pt
inflammatory_pattern_identificator	s3://skin-pathology-dl/models/hidradenitis-followup/lesion_categorization/v1/1013_1712_m002_cnvxtsmall_img384_bs32/weights/best_weights.pt	s3://legit-health-plus/ai-models/inflammatory_pattern_indicator/weights.pt
nail_lesion_segmenter	s3://skin-pathology-dl/models/nails-segmentation/nail-lesion-segmentation/202511/unet_resnet101_sz480_b16_e40_wcrops/weights.pt	s3://legit-health-plus/ai-models/nail_lesion_segmenter/v1.0.0/weights.pt
head_detector	s3://skin-pathology-dl/models/alopecia/head-cropping/yolov8/v1/yolov8s_0108_0940_bs16_imgsz480/weights/best.pt	s3://legit-health-plus/ai-models/head_detector/v1.0.0/weights.pt
image_domain_modality	s3://skin-pathology-dl/models/domain_check/efficientnet_b0.ra_in1k_20251031_184215/efficientnet_b0.ra_in1k_20251031_184215.pt	s3://legit-health-plus/ai-models/non-clinical/image-domain-modality/v1.0.0/weights.pt
image_quality	s3://skin-pathology-dl/models/image-quality-assessment/DIQA/202511/fold2#rgb#all#mse#efficientnet_b5.sw_in12k/fold2#rgb#all#mse#efficientnet_b5.sw_in12k#unfrozen.pt	s3://legit-health-plus/ai-models/non-clinical/image-quality/v1.0.0/weights.pt
skin_segmenter	s3://skin-pathology-dl/models/skin_segmentation/v1_1/efficientnetb1_unetplusplus/weights/best_weights_bdice.pt	s3://legit-health-plus/ai-models/skin_segmenter/v1.0.0/weights.pt
condition_classifier	s3://skin-pathology-dl/models/skin-disease-recognition/LegitHealth-DX/V27.5.1_convnextv2_base_soft_cutoff_20260116161335/V27.5.1_convnextv2_base_soft_cutoff_20260116161335.pt	s3://legit-health-plus/ai-models/diagnostic/skin-condition-recognizer/v27.5.1/weights.pt

SOUP Components

For detailed SOUP information, see SOUP Directory.

Build Information

Build Environment

• Build Tool: Bazel 8.4.2
• Build Date/Time: 2026-01-23
• Build Location: Server instance
• Build Responsible: Gerardo Fernández Moreno

Build Script/Procedure

• Prep (deployment/compose.yaml): Docker must be running; copy env cp deployment/.env.example deployment/.env (edit AWS creds, version vars, limits); create JWT secret mkdir -p deployment/secrets && openssl rand -base64 32 > deployment/secrets/jwt_secret.key; GPU profile needs NVIDIA runtime.
• Builder setup (deployment/Makefile): make preflight to check Docker; one-time make setup [ARCH=amd64|arm64] builds the Bazel-based builder image.
• Build images for all compose services (deployment/Makefile): make images (sequential) or faster make -j4 images-parallel; use ARCH=... for cross-arch; SERVICES="svc1 svc2" if you want a subset; make status verifies images.
• Bring everything up (deployment/Makefile): make up starts Docker Compose with default profiles cpu gpu (set PROFILES="cpu" if you want CPU-only); nginx exposes the stack on ${API_GATEWAY_HOST_PORT:-8000}.
• Operate: make logs (or make logs PROFILES="cpu"), make logs-snapshot, make restart [SERVICES="..."] for selective restarts, make down to stop.

Build Verification

• ✅ Build completed successfully
• ✅ Build artifacts generated
• ✅ Build reproducible

Residual Anomalies

Known Residual Anomalies

No anomalies were identified during the system verification phase. All requirements were verified against the specified acceptance criteria.

Deployment Instructions

Deployment Environment

Deployed into a EC2 instance in AWS of type g6.8xlarge with the following specifications:

• 1 GPU of type NVIDIA Tesla T4 with 24 GB VRAM
• 32 vCPUs
• 128 GB RAM
• 2 TB SSD storage

Deployment Procedure

• Host prerequisites
  • Install Docker (and Docker Compose plugin) and ensure the daemon is running.
  • If you want GPU services, install the NVIDIA driver + nvidia-container-toolkit so docker can use GPUs; otherwise set PROFILES="cpu" later.
  • Optional but recommended: enough disk for Bazel caches (parallel builds create per-service caches).
• Project prep
  • Clone the repo and work from deployment/.
  • Environment: cp deployment/.env.example deployment/.env and fill in AWS credentials, model weights buckets/keys, and any version pins (e.g., *_VERSION, DEFAULT_* limits).
  • JWT secret: mkdir -p deployment/secrets && openssl rand -base64 32 > deployment/secrets/jwt_secret.key.
  • Verify Docker access: cd deployment && make preflight.
• One-time builder image
  • Builds the Dockerized Bazel builder used for all service images: cd deployment && make setup (add ARCH=amd64 or ARCH=arm64 if cross-building).
• Build all service images
  • Default sequential: make images (respects ARCH and optional SERVICES="svc1 svc2" if you only need some).
  • Faster parallel (uses per-service Bazel caches): make -j4 images-parallel (tune -j to your cores).
  • For tarballs only (e.g., CI/push): make oci-tar or make -j oci-tar-parallel.
  • Check image readiness: make status.
• Start the full stack
  • From deployment: make up to launch Docker Compose with both default profiles cpu gpu (so GPU services require GPU runtime).
  • CPU-only: make up PROFILES="cpu"; GPU-only: make up PROFILES="gpu".
  • nginx fronts the stack on ${API_GATEWAY_HOST_PORT:-8000}; everything else is internal.
• Operate & verify
  • Inspect running containers: docker compose -f deployment/compose.yaml ps (or make status for build view).
  • Live logs: make logs (or make logs PROFILES="cpu"); snapshot: make logs-snapshot TAIL=200.
  • Restart services: make restart or make restart SERVICES="api-gateway control-plane" for selective restarts.
  • Stop everything: make down.
• Troubleshooting tips
  • If builds contend on Bazel locks, prefer images-parallel.
  • To reclaim cache space: make teardown-service-caches; to remove builder/shared cache entirely: make teardown.
  • Cross-arch image build on non-native host: set ARCH consistently on setup and images*.

Run the commands from the deployment directory so the Makefile picks up deployment/compose.yaml and its helper includes.

Release Archive

Archived Materials

Material	Archive Location	Identifier
Source Code and build scripts	https://github.com/Legit-Health/md-legit-health-plus	5f8549e02f3f362db8930906cf6dfdedf232119a
AI Models	s3://legit-health-plus/ai-models/	s3://legit-health-plus/ai-models/
Test Artifacts	s3://legit-health-plus/software-tests/v1.1.0.0/	s3://legit-health-plus/software-tests/v1.1.0.0/
Release Package	https://plus.legit.health	https://plus.legit.health/v1.0

Archive Retention

Retention Period

In accordance with EU MDR 2017/745 and ISO 13485, all software release archives for Legit.Health Plus version 1.1.0.0 shall be retained for a period of at least 10 years after the last device of this version has been placed on the market. This ensures that technical documentation, build scripts, and verification evidence remain available for post-market surveillance and regulatory audits.

Archive Access Control

Access to the release archive is strictly controlled to ensure the integrity of the medical device record:

• Source Code: Maintained in the controlled GitHub repository with branch protection and MFA requirements.
• AI Models and Test Evidence: Stored in secured S3 buckets (s3://legit-health-plus/) with restricted IAM access and logging enabled.
• QMS Documentation: Finalized records (R-TF-029 series) are stored in the controlled QMS document repository accessible only to authorized personnel (JD-001, JD-003, JD-007, and JD-004).

Release Reproducibility

Reproducibility Verified

☑ Yes ☐ No

Method: Release reproducibility is achieved through a hermetic and deterministic build environment:

• Deterministic Build Tool: The build process utilizes Bazel 8.4.2 within a dedicated Dockerized builder image (oci-builder-bazel-amd64), ensuring identical build environments across different host machines.
• Configuration Integrity: The build relies on the verified configuration baseline defined by the .env file hash: d2eedd61aea79d70a2212307710b3e6c5d117609d6c9d7056abe7b159b7c01a5.
• Verification Procedure: Reproducibility was verified by Gerardo Fernández Moreno on 2026-01-23 by rebuilding the software from the archived source code and confirming that the resulting artifact hashes matched the original release baseline.

Compliance and Approvals

Regulatory Compliance

This software release complies with:

• ☑ EN 62304:2006/A1:2015 - Medical device software lifecycle processes
• ☑ EN 82304-1:2016 - Health software product safety
• ☑ ISO 13485:2016 - Quality management systems for medical devices
• ☑ ISO 14971:2019 - Risk management for medical devices

Quality Management System Compliance

• ☑ All development activities performed according to GP-012
• ☑ All required documentation completed and reviewed
• ☑ All quality gates passed
• ☑ Configuration management procedures followed
• ☑ Change control procedures followed

Verification Checklist

Verification Item	Status	Reference
Software verification completed	☑ Complete	R-TF-012-035
All software requirements verified	☑ Complete	R-TF-012-043
All tests passed or deviations documented	☑ Complete	R-TF-012-035
Residual anomalies evaluated	☑ Complete	This document, Section 5
Risk management activities completed	☑ Complete	R-TF-013-002
Documentation complete and approved	☑ Complete	This document
Configuration items identified and controlled	☑ Complete	This document, Section 4

Release Decision

Release Readiness

Based on the verification activities and results documented:

☑ Software is READY for RELEASE All verification activities completed successfully. All acceptance criteria met.

Post-Release Activities

Planned post-release activities:

• Monitor for issues in production
• Collect user feedback
• Track and resolve defects
• Plan for next release
• Update documentation as needed

Signature meaning

The signatures for the approval process of this document can be found in the verified commits at the repository for the QMS. As a reference, the team members who are expected to participate in this document and their roles in the approval process, as defined in Annex I Responsibility Matrix of the GP-001, are:

• Author: Team members involved
• Reviewer: JD-007
• Approver: JD-001