AllerSens — Scientific Brochure
AllerSens
AI-Assisted Skin Allergy & Atopic Dermatitis Module Suite

AllerSens

Skin Allergy Tracking Platform

Lesion severity segmentation, personalized ingredient safety scanning and product-lesion cross-analysis — under one AI-assisted dermatology intelligence roof.

Developed by Dr. Siyra Seren.
EczemaTrackAllerGuardAllerTrackHuman-in-the-loop
Contents
1What is AllerSens?
2Technology: Segmentation + OCR + LLM
3EczemaTrack — Atopic Dermatitis Tracking
4AllerGuard — Ingredient Scanner
5AllerTrack — Cross-Analysis
6Clinical Value & Safety
7ESG & Roadmap
8Scientific References
Vision
A hardware-independent AI dermatology module suite that produces clinically meaningful skin allergy assessments from consumer devices (smartphone, tablet).
Usage
Atopic dermatitis severity tracking, cosmetic ingredient safety scanning, cross-matching with patch-test results and product-lesion causality analysis.
1
Section 1

What is AllerSens?

Skin Allergy Tracking Platform — AllerSens is an AI-assisted digital module suite for skin allergy and atopic dermatitis tracking. It offers lesion severity, ingredient safety and product-lesion cross-analysis under one roof with three integrated modules.

The modules run on photo-based AI segmentation, OCR ingredient reading and large language model (LLM) clinical commentary. All results support clinical decisions; they do not replace a medical diagnosis.

Three Integrated Modules

  • EczemaTrack: BSA, erythema/edema/exudate/lichenification scores, PO-SCORAD/EASI from a lesion photo
  • AllerGuard: Barcode/label OCR + cross-matching with patient allergens + risk level
  • AllerTrack: Product label and lesion analyzed together → per-ingredient risk and mechanism
  • Shared infrastructure: image segmentation, OCR engine, LLM clinical commentary
Clinical Positioning
The system is a screening and decision-support tool; it does not replace a definitive medical diagnosis. AI models can make errors; results are produced to support a physician's clinical assessment. Final diagnosis and treatment decisions belong to the specialist.
2
Section 2

Technology: Segmentation + OCR + LLM

The platform combines image processing (segmentation), optical character recognition (OCR) and large language model (LLM) multimodal inference. The lesion is segmented by AI, the product label is read via OCR, and both are placed in clinical context by the LLM.

Workflow

  • Image capture & quality check (lesion sharpness, label legibility)
  • Lesion segmentation + label OCR reading
  • Multimodal LLM inference: scores, ingredient list, risk, mechanism, clinical commentary
  • Longitudinal tracking & trend comparison

Software-Centric Architecture

Hardware-Independent
Runs with the device's built-in camera; no extra medical hardware required.
Web-Based (SaaS)
API-first architecture; integrates with EMR/clinical systems.
Multimodal AI
Image segmentation + OCR + LLM for structured clinical output.
Telemedicine-Ready
Records stored digitally; remote consultation and longitudinal tracking.
3
Section 3

EczemaTrack — Atopic Dermatitis Tracking

EczemaTrack automatically produces BSA involvement percentage, erythema/edema/exudate/lichenification scores and PO-SCORAD/EASI indices from lesion photos via AI segmentation.

PO-SCORAD formula: A/100×6 + (7×B/2) + C. A = extent (0-100→0-6), B = sum of 6 signs (0-18), C = subjective (0-20.7). EASI = region weight × (erythema+edema+exudate+lichenification) × BSA.

BSA
Involvement percentage (0-100)
Erythema
Redness (0-3)
Edema
Papulation (0-3)
Exudate
Crust/oozing (0-3)
Lichenification
Skin thickening (0-3)
PO-SCORAD
Index (0-103)
EASI
Index (0-72)
Longitudinal Value
A patient's severity changes over time are compared with trend charts and AI clinical commentary; flare early warning and treatment response monitoring are supported.
4
Section 4

AllerGuard — Personalized Ingredient Scanner

AllerGuard reads cosmetic/skincare product barcodes or ingredient labels via OCR, cross-matches them with the patient's known allergens from patch testing and flags risky products.

The barcode (EAN/UPC) is read from the image; product name and brand are confirmed via an online database. Flagged allergens are ranked by patient profile and safe alternatives are suggested.

Label/Barcode
OCR ingredient reading from image
Cross-Match
Compare with patient allergens
Risk Level
Low / Medium / High
Safe Products
Alternative suggestions

Risk Scale

  • Low: no flagged allergens
  • Medium: 1-2 flagged allergens
  • High: 3+ flagged allergens or strong sensitizer
5
Section 5

AllerTrack — Product-Lesion Cross-Analysis

AllerTrack analyzes the product label and lesion photo together; AI evaluates the ingredient's possible contribution to the lesion.

The label is read via OCR, the lesion is segmented by AI; each ingredient is evaluated for lesion mechanism (irritant, sensitizer, barrier disruptor) and per-ingredient risk percentage, role, confidence score and mechanism suggestion are provided.

Mechanism Categories

Irritant
Barrier-disrupting, acute irritant dermatitis
Sensitizer
Type IV delayed hypersensitivity (allergic contact)
Barrier Disruptor
TEWL increase, lipid layer damage
6
Section 6

Clinical Value & Safety

The platform supports clinical workflows as a screening and decision-support tool. Lesion scores, ingredient risk assessment and cross-analysis provide the physician with structured, reproducible and comparable data.

Screening
Non-invasive skin allergy and atopic dermatitis screening support.
Decision Support
Structured scores + ingredient risk + clinical AI commentary.
Tracking
Longitudinal trend and product exposure monitoring.

Safety Architecture (Human-in-the-loop)

  • AI output is not a diagnosis; it is information supporting the physician's assessment
  • AI commentary contains no prescription/treatment advice
  • Per-patient data isolation (RLS) and KVKK/GDPR-compliant sensitive data approach
  • Physician approval required for high-risk findings
7
Section 7

ESG & Roadmap

The software-centric architecture is compatible with EU carbon-reduction and ESG goals. Hardware independence brings medical consumable use close to zero.

Zero Hardware
Eliminates dermatology device manufacturing-to-disposal carbon.
Zero Consumables
No single-use probes/apparatus; clinical waste near zero.
Digital Logistics
Web-based analysis makes the patient's clinic trip unnecessary.

Roadmap

Phase 1
Clinical rollout of the three modules.
Phase 2
Automatic exposure-correlation and flare early warning.
Phase 3
Personalized allergy tracking and predictive analysis suite.
8
Section 8

Scientific References

The following studies demonstrate the clinical validity of atopic dermatitis scoring, contact dermatitis and ingredient allergenicity assessment.

1.Severity scoring of atopic dermatitis: the SCORAD index. Consensus Report of the European Task Force on Atopic Dermatitis. Dermatology. 1993;186(1):23-31. DOI: 10.1159/000248038
2.Kunz B, Oranje AP, Labrèze L, Stalder JF, Ring J, Taïeb A. Clinical validation and guidelines for the SCORAD index: consensus report of the European Task Force on Atopic Dermatitis. Dermatology. 1997;195(1):10-19. DOI: 10.1159/000246474
3.Hanifin JM, Thurston M, Omoto M, Cherill R, Tofte SJ, Graeber M. The Eczema Area and Severity Index (EASI): assessment of reliability in atopic dermatitis. Exp Dermatol. 2001;10(1):11-18. DOI: 10.1034/j.1600-0625.2001.100102.x
4.Stalder JF, Barbarot S, et al. PO-SCORAD: a self-assessment tool for atopic dermatitis. J Eur Acad Dermatol Venereol. 2011;25(1):36-40. DOI: 10.1111/j.1468-3083.2010.03726.x
5.Johansen JD, Aalto-Korte K, Agner T, et al. European Society of Contact Dermatitis guideline for diagnostic patch testing. Contact Dermatitis. 2015;73(4):195-221. DOI: 10.1111/cod.12432
6.Wilkinson M, Gonçalo M, Aerts O, et al. The European baseline series and recommendations for patch testing. Contact Dermatitis. 2019;80(1):7-14. DOI: 10.1111/cod.13055
7.Diepgen TL, Ofenloch RF, Bruze M, et al. Prevalence of contact allergy in the general population in different European regions. Br J Dermatol. 2016;174(2):319-329. DOI: 10.1111/bjd.14167
8.Thyssen JP, Linneberg A, Menné T, Johansen JD. The epidemiology of contact allergy in the general population—prevalence and main findings. Contact Dermatitis. 2007;57(5):287-297. DOI: 10.1111/j.1600-0536.2007.01220.x
9.De Groot AC. Patch Testing: Test Concentrations and Vehicles. Contact Dermatitis. CRC Press; 2008.
10.Peiser M, Tralau T, Heidemeier M, et al. Allergic contact dermatitis: epidemiology, molecular mechanisms, in vitro methods and regulatory approaches. Arch Toxicol. 2012;86(8):1153-1156. DOI: 10.1007/s00204-012-0867-9
11.Lepoittevin JP, Leblond I. Dictionary of Contact Allergens: Structure-Activity Relationships. Springer; 2013.
12.Natsch A, Gfeller H. LC-MS-based characterization of the peptide reactivity of chemicals to model the skin sensitization mechanism. Chem Res Toxicol. 2008;21(2):337-344. DOI: 10.1021/tx700385q
AllerSens — Skin Allergy Tracking Platform
Developed by Dr. Siyra Seren · AI decision support · odiosoft.tech