Clinical evidence
This section compiles the evidence behind the automated hidradenitis suppurativa scoring provided by Legit.Health: the peer-reviewed publication of the automated IHS4 (AIHS4) and the foundational references for the scores it reports. Together they document the scientific basis of the automated IHS4 and how it is validated for use as a clinical trial endpoint.
Validation status and reproducibility
The automated IHS4 methodology was published in Skin Research and Technology in 2023.
Severity scoring has no objective gold standard. IHS4 depends on how each assessor identifies and classifies every lesion, and telling an abscess from a nodule, or spotting a tunnel opening, is where dermatologists disagree most. The reference is therefore the consensus of independent expert dermatologists, the same standard the FDA and EMA accept for dermatology trials. Matching that consensus is the realistic performance ceiling for any rater, human or AI.
Two properties are decisive for endpoint use in a trial:
- Reproducibility: the AI's first read is deterministic. The same image yields the same detections at every site and every visit, with no calibration drift, and the investigator then confirms them after examining the patient; see investigator review.
- Counts as the foundation: the AI detects and classifies each lesion, and every score is derived from those counts. The lesion counts are reported in their own right, so the same capture supports IHS4 and any other count-based measure the protocol specifies.
The device is CE-marked as a medical device, meaning a Notified Body has independently assessed it against the safety and performance requirements of the EU Medical Device Directive (MDD 93/42/EEC) and authorised its use on the EU market. Beyond the EU, the device is registered with the MHRA for the United Kingdom market and has obtained ANVISA approval in Brazil. Real-world performance is monitored continuously through the manufacturer's post-market surveillance and post-market clinical follow-up (PMCF) programme under MDR Annex XIV. Study-specific agreement and reproducibility metrics are available on request to support protocol design.
Legit.Health is a clinical decision support device: the automated scores provide diagnostic support and do not replace the healthcare professional's assessment.
Automated IHS4
Automatic International Hidradenitis Suppurativa Severity Score System (AIHS4): A novel tool to assess the severity of hidradenitis suppurativa using artificial intelligence. Hernández Montilla I, Medela A, Mac Carthy T, et al. Skin Research and Technology. 2023;29(6):e13357. DOI: 10.1111/srt.13357 | PMID: 37357665
The foundational publication for the automated IHS4. It describes the deep learning lesion detection model behind the score and its training on hidradenitis suppurativa images annotated by six specialists, whose labels were unified into a single consensus reference. With the dataset available at the time, the automated score assessed HS severity with performance comparable to that of the most expert physician on the board.
Manual IHS4 requires an investigator to find, classify and count every nodule, abscess and draining tunnel across every affected region at every visit. Automated IHS4 gives every investigator the same starting point, a consistent first read of the photographs that they confirm after examining the patient, with three properties manual scoring cannot offer:
- A reproducible first read: the same image always produces the same detections, with zero intra-rater variability, at every site and every visit.
- No investigator training drift: performance does not depend on how recently a site was trained or on which rater is on shift that day.
- Less noise in IHS4 change from baseline, which can support smaller sample sizes or greater statistical power to detect treatment response.
The published study reports the model as it stood at submission, and the detection algorithm has been improved since. It has been trained on a larger, newly annotated image set, and its bounding boxes can now take any orientation, so they follow the shape of elongated lesions such as tunnels instead of enclosing them in an upright rectangle.
Image quality for hidradenitis suppurativa scoring (DIQA)
Dermatology Image Quality Assessment (DIQA): Artificial intelligence to ensure the clinical utility of images for remote consultations and clinical trials. Hernández Montilla I, Mac Carthy T, Aguilar A, et al. Journal of the American Academy of Dermatology. 2023;88(4):927–928. DOI: 10.1016/j.jaad.2022.11.002 | PMID: 36526082
Reliable IHS4 scoring depends on the quality of the input photographs. DIQA is the image quality assessment algorithm that acts as a quality gate in the hidradenitis suppurativa imaging workflow, checking every image against consistent quality criteria across investigator sites before it reaches the lesion detection model. The dependency is sharp in hidradenitis suppurativa, where lesions sit in skin folds and a blurred or poorly lit image can hide a nodule or a tunnel opening and lower the count.
Image quality is the hidden failure point of multi-site imaging. DIQA screens every photograph for clinical utility before it reaches the scoring algorithms, so unusable images are caught at capture rather than surfacing as missing data at database lock.
Foundational IHS4 and HiSCR references
The platform does not introduce a new, unvalidated scale. It automates the lesion counts behind IHS4 and HiSCR, the severity and response measures clinicians and regulators already accept, so the endpoint your protocol specifies is the endpoint the algorithm reports.
- Zouboulis, C. C. et al. Development and validation of the International Hidradenitis Suppurativa Severity Score System (IHS4), a novel dynamic scoring system to assess HS severity. British Journal of Dermatology, 177(5), 1401–1409 (2017). The original IHS4 development and validation paper.
- Kimball, A. B. et al. Assessing the validity, responsiveness and meaningfulness of the Hidradenitis Suppurativa Clinical Response (HiSCR) as the clinical endpoint for hidradenitis suppurativa treatment. British Journal of Dermatology, 171(6), 1434–1442 (2014). The validation paper for HiSCR, the response endpoint derived from the same lesion counts.
For the full list of clinical evidence across all indications, see the clinical validation section.
Accelerate your trials
Join pharmaceutical companies, biotechs, and CROs reaching the market 4-6 months faster with superior data quality. Fill in the form to discuss your study requirements.