Antonia Reimer-Taschenbrecker

Clinical data for rare diseases are sparse, noisy, and heterogeneous, complicating calibration of ordinary differential equation (ODE) models. Thus, we introduce a noise-robust calibration in latent space that combines expert-derived ODEs with learned latent representations. Our approach leverages synthetic ODE trajectories, augmenting our scarce observations to train a model-specific autoencoder representation and imputer. During calibration, observed and ODE-generated trajectories are compared in latent space, and ODE parameters are updated by minimizing their latent distance. In a controlled ABCDE simulation model, the imputer outperformed a carry-forward baseline for moderate parameter shifts, parameter recovery remained stable under random missingness, calibration remained robust to additional noise variables despite reduced downstream identifiability, and distinct dynamics formed visually separable latent trajectories. On a custom developed ODE model for real Epidermolysis Bullosa patients, the calibrated phenomenological model reproduced patient-level trajectories from sparse observations. Thus, we conclude that our latent-space calibration approach supports rare-disease modeling.

Background/Objectives: Trichoscopy is an important diagnostic tool for hair and scalp disorders, but it requires significant expertise. Publicly available large language models (LLMs) are becoming more popular among both physicians and patients, yet their usefulness in trichology is unknown. We aimed to evaluate the diagnostic accuracy of four publicly available LLMs when interpreting trichoscopic images, as well as to compare their performance with that of dermatology residents, board-certified dermatologists, and trichology experts. Method: In this prospective comparative study, a preprocessed set of trichoscopic images was assessed in an online image-based survey. To reduced recognition bias from public image repositories, all images were structurally transformed while preserving diagnostic features. Fifteen dermatologists (five residents, four board-certified dermatologists, six trichology experts) provided a suspected diagnosis (SD), and up to three the differential diagnoses (DD). Four LLMs (ChatGPT-4o, Claude Sonnet 4, Gemini 2.5 Flash, and Grok-3) evaluated the images under the same conditions. Results: The overall diagnostic accuracy among 15 dermatologists was 58.1% (95% CI, 53.0–63.0) for SD and 68.3% (95% CI, 63.4–72.8) for SD + DD. Experts significantly outperformed residents and board-certified dermatologists. AI models achieved an accuracy of 18.2% (95% CI, 11.8–26.9) for SD and 44.4% (95% CI, 35.0–54.3) for SD + DD. Gemini 2.5 Flash performed best, with an accuracy of 62.5% for SD + DD. Agreement among dermatologists increased with experience (AC1 up to 0.65 for experts), while agreement among AI models was moderate to good (AC1 up to 0.70). Agreement between AI models and dermatologists was only slight to fair (AC1 = 0.06 for SD and 0.21 for SD + DD). All human-AI differences were statistically significant (p < 0.001). Conclusions: In trichology, publicly available LLMs currently underperform compared to human experts, especially in providing a single correct diagnosis. These models require further development and specialized training before they can reliably assist with trichological diagnoses in routine care.

Introduction: Artificial intelligence (AI) has developed into an increasingly important tool in dermatology. While new technologies integrated within laser devices are emerging, there is a lack of data on the applicability of publicly available AI models. Methods: The prospective study used an online questionnaire where participants evaluated diagnosis and treatment for 25 dermatological cases shown as pictures. The same questions were given to AI models: ChatGPT-4o, Claude Sonnet 4, Gemini 2.5 Flash, and Grok-3. Results: Dermatologists outperformed AI in diagnostic accuracy (suspected primary diagnosis-SD 75.6%) in pooled dermatologists vs. pooled AI (SD 57.0%), with laser specialists achieving the highest accuracy (SD 82.0%) and residents the lowest (SD 66.0%). There was a high heterogeneity across AI models. Gemini approached dermatologist performance (SD 72.0%), while Claude showed a low accuracy (SD 40.0%). While AI models reached near 100% accuracy in some classic/common diagnoses (e.g., acne, rosacea, spider angioma, infantile hemangioma), their accuracy dropped to near 0% on rare or context-dependent cases (e.g., blue rubber bleb nevus syndrome, angiosarcoma, hirsutism, cutaneous siderosis). Inter-rater agreement was high among laser experts in terms of diagnostic accuracy and treatment choice. Agreement between residents and AI models was highest for diagnostic accuracy and treatment choice, while it was lowest between experts and AI models. Conclusions: Before AI-based tools can be integrated into daily practice, particularly regarding diagnosis and appropriate laser treatment recommendations, specific supervised medical training of the AI model is necessary, as open-source platforms currently lack the ability to contextualize presented data.

Die hereditäre Epidermolysis bullosa (kurz EB) ist eine Gruppe seltener genetischer Hauterkrankungen, die sich durch eine erhöhte Hautfragilität als Folge von strukturellen Veränderungen in der dermo-epidermalen Junktionszone auszeichnet. Aufgrund einer reduzierten Stabilität zwischen den verschiedenen Hautschichten besteht eine eingeschränkte Widerstandsfähigkeit gegenüber mechanischer Belastung, so dass selbst leichte Traumata oder milde Scherkräfte zu Blasenbildung und Ablösungen an der Haut und, je nach Subtyp, auch an Schleimhäuten von Mund, Auge und Magen-Darm-Trakt führen können.

L’épidermolyse bulleuse congénitale (EB) est un groupe de maladies génétiques rares qui se caractérise par une fragilité accrue de la peau, due à des modifications structurelles de la zone de jonction dermo-épidermique. En raison d’une stabilité réduite entre les différentes couches de la peau, la résistance aux sollicitations mécaniques est amoindrie, de sorte que même des traumatismes ou frottements légers peuvent provoquer la formation de bulles et le décollement de la peau et, selon le sous-groupe, aussi des muqueuses buccale, des yeux et du tube digestif.

Background: Systemic inflammation is considered a major player in the pathogenesis of epidermolysis bullosa (EB), but its pattern has only been described in small heterogeneous cohorts. There is controversy if and how systemic inflammation should be therapeutically targeted.Methods: We examined serum proinflammatory, anti‐inflammatory, and itch related cytokines in a paediatric cohort of 29 patients with junctional and dystrophic EB. The cytokine that emerged as the most relevant was measured in a validation cohort of 42 patients during follow‐up visits over 2 years.Results: IL‐6 showed the most consistent and highest aberration dominating systemic inflammation. IL‐6 correlated with wound body surface area (BSA) in both, finding and validation cohorts. Patients with less than 3% wound BSA had normal IL‐6, while IL‐6 levels significantly increased at more than 5% and 10% of wound BSA. TGF‐β was only marginally elevated in patients with severe recessive dystrophic EB, while TNF‐α, IFN‐γ and IL‐1β varied inconsistently. Patients reporting itch showed elevations in type 2 immunity (IgE, TSLP, IL4 and/or IL‐31, respectively).Conclusions: Our data suggest a dominant skin barrier and wound healing inflammatory pattern in junctional and dystrophic EB that depends on the wound area and not on the EB type. In EB, itch mediators may be similar to other pruritic disorders.

A trio exome sequencing study identified a previously unreported NLRP1 gene variant resulting in a p.Leu813Pro substitution of the LRR (leucine-rich repeats) domain of the NLRP1 protein (NACHT, LRR and PYD domains-containing protein 1). This homozygous mutation was shared by two sisters with different clinical presentation: the younger sister had generalized inflammatory nodules with keratotic plugs, clinically resembling multiple keratoacanthomas, while the older had manifestations of familial keratosis lichenoides chronica. To analyse the consequences of this NLRP1 variant in two siblings with a different clinical spectrum of severity. To demonstrate the pathogenicity, p.Leu813Pro was recombinantly expressed, and its effect on inflammasome assembly was assessed. Exome sequencing and RNA-Seq were performed to identify factors with potentially modifying effects on the severity of the skin manifestation between each sibling. The variant p.Leu813Pro triggered activation of the NLRP1 inflammasome leading to ASC (apoptosis-associated speck-like protein containing a CARD) speck formation and interleukin (IL)-1β release. The more severely affected sister had several additional genomic variants associated with atopy and psoriasis that were not present in her sibling. IL-5 and IL-17 emerged as dominant cytokines driving prominent inflammation in the skin of the severely affected sibling. To the best of our knowledge, this is the first report of a NLRP1 variant that leads to a different clinical spectrum of severity within the same sibship. IL-5 and IL-17 were the main cytokines expressed in the inflammatory lesions of the severely affected patient and might be regarded as disease modifying factors, and therefore may be considered as therapeutic targets.