BerufsGuard AI — Scientific Brochure
ODIOSOFT DERMATOLOGY

BerufsGuard AI

AI-powered occupational dermatology suite with 6 modules — contact dermatitis detection, skin barrier damage, occupational UV exposure, chemical allergen matching, occupational disease suspicion documentation and occupational physician teleconsultation (German BK list reference).

Occupational Skin Protection & BK Suspicion Assistant
ContactGuardBarrierGuardUV-WorkGuardChemGuardWorkTrendTeleConsult
CONTENTS
1Platform Overview
2Technology & Architecture
3Modules & Clinical Flow
4Clinical Value & BK Integration
5ESG & Sustainability
6References
VISION
Detect and document occupational skin diseases early — every worker can track their occupational skin burden with objective AI scores.
USAGE
Mobile, hardware-independent. Upload a skin photo, enter occupation and exposure — AI assesses dermatitis, barrier damage, UV risk and BK suspicion.
1
OVERVIEW

Platform Overview

BerufsGuard AI — BerufsGuard AI is an AI-powered mobile suite for occupational dermatology based on the German occupational disease list (BKV).

Six modules cover the most important occupational skin diseases: contact dermatitis, skin barrier damage (wet work), occupational UV exposure, chemical allergen matching, occupational history with BK suspicion and occupational physician teleconsultation.

Core Capabilities

  • ContactGuard — irritant-toxic vs. allergic, ICDRG severity
  • BarrierGuard — TEWL proxy, fissure, wet-work tracking
  • UV-WorkGuard — erythema, light damage, skin cancer risk proxy
  • ChemGuard — occupational allergen matching with patient profile
  • WorkTrend — BK suspicion per BK 5101/5102
  • TeleConsult-Beruf — BK suspicion report for accident insurance carrier
Why BerufsGuard AI?
Combines AI image analysis with occupational-disease-specific documentation — from detection to BK report in one suite.
2
TECHNOLOGY

Technology & Architecture

Mobile, hardware-independent. AI image analysis + structured JSON output. German occupational disease list (BKV) as reference.

Clinical Flow

  • Upload skin photo + enter occupation/exposure
  • AI assesses dermatitis/barrier/UV/allergens
  • WorkTrend: causal assessment & BK suspicion
  • TeleConsult: BK suspicion report documentation
  • Trend analysis across shift/season cycles

Architecture Components

AI Image Analysis
Dermatitis, barrier, UV damage — structured scores
BK Reference
German occupational disease list (BK 5101, 5102)
Allergen Matching
PatientAllergenProfile integration
Trend Infrastructure
Longitudinal tracking
3
MODULES

Modules & Clinical Flow

Six analytical modules + trend analysis for comprehensive occupational skin monitoring.

ContactGuard
Contact dermatitis — irritant-toxic vs. allergic, ICDRG severity, occupational substance exposure
BarrierGuard
Skin barrier damage — TEWL, desquamation, fissure for wet-work occupations
UV-WorkGuard
Occupational UV exposure — erythema, light damage, skin cancer risk, ITA°
ChemGuard
Chemical allergen matching — chromate, nickel, rubber accelerators, formaldehyde
WorkTrend
Occupational history — BK suspicion BK 5101/5102, causal assessment
TeleConsult-Beruf
Occupational physician consultation — BK suspicion report for accident insurance carrier

Clinical Outputs

  • Dermatitis type + ICDRG severity
  • Barrier damage score + wet-work hours
  • Skin cancer risk proxy + ITA° trend
  • Allergen match + safe protective glove recommendation
  • BK suspicion + causal assessment
  • BK suspicion report documentation
4
CLINICAL VALUE

Clinical Value & BK Integration

Objective AI scores + BK-specific documentation for occupational dermatology.

Early Detection
AI image analysis before BK report
BK Documentation
Suspicion report per BK 5101/5102
Allergen Protection
Patient-profile-based protective glove recommendation

Safety

  • AI assessment — not a clinical diagnosis
  • BK suspicion to be confirmed by occupational physician
  • Patient data RLS-isolated
  • GDPR compliance

Integration

Guard Architecture
Same infrastructure as WoundGuard/PhotoGuard
German BK List
Berufskrankheiten-Verordnung (BKV)
5
ESG

ESG & Sustainability

Digital occupational skin health — accessibility and prevention.

Prevention
Early detection before BK development
Accessibility
Mobile — also for SME businesses
Documentation
Paperless BK suspicion report

Roadmap

Phase 1
6 modules + BK suspicion
Phase 2
Occupational physician workflow
Phase 3
Accident insurance carrier integration
6
SCIENTIFIC SOURCES

References

BerufsGuard AI is based on dermatological and occupational medicine standards.

1.McMullen E, et al. (2024). Diagnosing contact dermatitis using machine learning: A review. Contact Dermatitis, 91(3), 185–194. https://doi.org/10.1111/cod.14588
2.Kim JH, et al. (2025). Evaluation of artificial intelligence-assisted diagnosis of skin irritation and patch test reactions using the YOLOv5x framework. Contact Dermatitis, 93(2), 112–121. https://doi.org/10.1111/cod.14720
3.Chan S, et al. (2021). Using deep learning and convolutional neural networks to accurately diagnose allergic contact dermatitis and patch-test reactions from clinical photographs. Dermatitis, 32(5), 310–317. https://doi.org/10.1097/DER.0000000000000754
4.Patel S, Wang JV, Motaparthi K, Lee JB. (2021). Artificial intelligence in dermatology for the clinician. Clinics in Dermatology, 39(4), 667–672. https://doi.org/10.1016/j.clindermatol.2021.03.012
5.Thyssen JP, et al. (2022). European Society of Contact Dermatitis (ESCD) guidelines for diagnostic patch testing – digital tools and methodological updates. Contact Dermatitis, 86(2), 75–84. https://doi.org/10.1111/cod.14002
6.Garg S, et al. (2024). Machine learning in allergic contact dermatitis: Identifying hidden patterns among occupational risks, demographics, and polysensitization. Current Research in Toxicology, 4, 100125. https://doi.org/10.1016/j.crtox.2024.100125
7.Skudlik C, et al. (2023). Secondary and tertiary individual prevention of occupational skin diseases: Current status and digital transformation models. Journal der Deutschen Dermatologischen Gesellschaft (JDDG), 21(6), 591–599. https://doi.org/10.1111/ddg.15044
8.John SM, et al. (2022). Interventions for preventing occupational irritant hand dermatitis: An overview of systematic reviews and digital monitoring solutions. Cochrane Database of Systematic Reviews, 2022(8), CD004414. https://doi.org/10.1002/14651858.CD004414.pub4
9.Linder M, et al. (2023). Automated image analysis and computer vision in contact dermatitis: A critical appraisal of current datasets and convolutional models. Contact Dermatitis, 88(1), 15–24. https://doi.org/10.1111/cod.14220
10.Bauer A, et al. (2021). Digital health applications and artificial intelligence in occupational dermatology: Opportunities and challenges for prevention and management. Contact Dermatitis, 85(4), 379–387. https://doi.org/10.1111/cod.13895
11.Karagounis TK, Cohen DE. (2023). Occupational hand dermatitis. Current Allergy and Asthma Reports, 23(4), 201–212. https://doi.org/10.1007/s11882-023-01070-5
12.Olesen CM, Agner T, Ebbehøj NE, Carøe TK. (2019). Factors influencing prognosis for occupational hand eczema: new trends. British Journal of Dermatology, 181(6), 1280–1286. https://doi.org/10.1111/bjd.17870
13.Jacobsen G, Rasmussen K, Bregnhøj A, Isaksson M, Diepgen TL, Carstensen O. Causes of irritant contact dermatitis after occupational skin exposure: a systematic review. Int Arch Occup Environ Health. 2022 Jan;95(1):35-65. doi: 10.1007/s00420-021-01781-0. Epub 2021 Oct 19.
14.Lee J, Lin R, Maderal A. (2024). Update on occupational dermatitis: reviewing toxic substances from OSHA standards. International Journal of Dermatology, 64(1), 72–78. https://doi.org/10.1111/ijd.17413
15.Papadatou Z, Williams H, Cooper K. Effectiveness of interventions for preventing occupational irritant hand dermatitis: a quantitative systematic review. JBI Database System Rev Implement Rep. 2018 Jun;16(6):1398-1417. doi: 10.11124/JBISRIR-2017-003405.
16.Jungbauer FH, van der Vleuten P, Groothoff JW, Coenraads PJ. Irritant hand dermatitis: severity of disease, occupational exposure to skin irritants and preventive measures 5 years after initial diagnosis. Contact Dermatitis. 2004 Apr;50(4):245-51. doi: 10.1111/j.0105-1873.2004.00347.x.
17.Friis UF, Menné T, Schwensen JF, Flyvholm MA, Bonde JP, Johansen JD. Occupational irritant contact dermatitis diagnosed by analysis of contact irritants and allergens in the work environment. Contact Dermatitis. 2014 Dec;71(6):364-70. doi: 10.1111/cod.12290. Epub 2014 Oct 10.
BerufsGuard AI
Odiosoft Dermatology — AI-powered occupational dermatology