Comparative Analysis of AI Models for Atypical Pigmented Facial Lesion Diagnosis.

Diagnosing atypical pigmented facial lesions (aPFLs) is a challenging topic for dermatologists. Accurate diagnosis of these lesions is crucial for effective patient management, especially in dermatology, where visual assessment plays a central role. Incorrect diagnoses can result in mismanagement, delays in appropriate interventions, and potential harm. AI, however, holds the potential to enhance diagnostic accuracy and provide reliable support to clinicians. This work aimed to evaluate and compare the effectiveness of machine learning (logistic regression of lesion features and patient metadata) and deep learning (CNN analysis of images) models in dermoscopy diagnosis and the management of aPFLs. This study involved the analysis of 1197 dermoscopic images of facial lesions excised due to suspicious and histologically confirmed malignancy, classified into seven classes (lentigo maligna-LM; lentigo maligna melanoma-LMM; atypical nevi-AN; pigmented actinic keratosis-PAK; solar lentigo-SL; seborrheic keratosis-SK; and seborrheic lichenoid keratosis-SLK). Image samples were collected through the Integrated Dermoscopy Score (iDScore) project. The statistical analysis of the dataset shows that the patients mean age was 65.5 ± 14.2, and the gender was equally distributed (580 males-48.5%; 617 females-51.5%). A total of 41.7% of the sample constituted malignant lesions (LM and LMM). Meanwhile, the benign lesions were mainly PAK (19.3%), followed by SL (22.2%), AN (10.4%), SK (4.0%), and SLK (2.3%). The lesions were mainly localised in the cheek and nose areas. A stratified analysis of the assessment provided by the enrolled dermatologists was also performed, resulting in 2445 evaluations of the 1197 images (2.1 evaluations per image on average). The physicians demonstrated higher accuracy in differentiating between malignant and benign lesions (71.2%) than in distinguishing between the seven specific diagnoses across all the images (42.9%). The logistic regression model obtained a precision of 39.1%, a sensitivity of 100%, a specificity of 33.9%, and an accuracy of 53.6% on the test set, while the CNN model showed lower sensitivity (58.2%) and higher precision (47.0%), specificity (90.8%), and accuracy (59.5%) for melanoma diagnosis. This research demonstrates how AI can enhance the diagnostic accuracy in complex dermatological cases like aPFLs by integrating AI models with clinical data and evaluating different diagnostic approaches, paving the way for more precise and scalable AI applications in dermatology, showing their critical role in improving patient management and the outcomes in dermatology.

Novel imaging techniques for tumor margin detection in basal cell carcinoma: a systematic scoping review of FDA and EMA-approved imaging modalities.

Mohs micrographic surgery (MMS) is the gold standard for removing basal cell carcinomas (BCCs) due to its ability to guarantee 100% margin evaluation through frozen section histopathology, offering the highest cure rate among current treatments. However, noninvasive imaging technologies have emerged as promising alternatives to clinical assessment for defining presurgical margins. This systematic scoping review examines the efficacy of these imaging modalities, focusing on those approved for clinical use by the United States Food and Drug Administration (FDA) or the European Medicines Agency (EMA). A systematic search of EMBASE, Scopus, PubMed, and the Cochrane Public Library databases identified 11 relevant studies out of 2123 records, encompassing 644 lesions across five imaging techniques. The findings suggest that dermoscopy, high-frequency ultrasound (HFUS), optical coherence tomography (OCT), line-field optical coherence tomography (LC-OCT), and reflectance confocal microscopy (RCM) show potential in detecting BCC margins, which could enhance MMS by providing better preoperative planning, informing patients of expected defect size, aiding in reconstruction decisions, and reducing overall procedure costs. This review discusses the benefits and limitations of each technique, offering insights into how these innovations could influence the future of BCC management. Emerging imaging techniques could enhance MMS by improving BCC margin assessment and reducing costs. Their adoption will depend on price and ease of use.

Factors Associated with Severe Hidradenitis Suppurativa, Using Hurley Staging and Metascore.

INTRODUCTION: Hidradenitis suppurativa (HS) is a chronic inflammatory skin disease for which certain risk factors are well known: obesity and smoking (in particular). However, the factors associated with more severe conditions, and therefore potential aggravators of the disease, remain a matter of debate. Our study aims to determine the clinical factors associated with severe HS using several severity scores. METHODS: The data were obtained via the ERHS questionnaire from patients exclusively recruited at Erasme Hospital in Brussels. The severity of HS was firstly estimated by the Hurley score, and secondly by a metascore, a system combining the iHS4, HS-PGA, SAHS, and DLQI. Univariable and multivariable analyses were performed. RESULTS: Six hundred and forty-seven patients were included in the Hurley analysis, and 456 patients in the metascore analysis. In multivariable analysis, men have a more severe metascore than women (odds ratio [OR] = 1.89, p = 0.022), smoking was associated with a more severe disease according to metascore, especially in mild cases (OR = 0.76, p = 0.043), and an elevated body mass index was associated with having Hurley stage III disease compared to Hurley I or II disease (OR = 1.09, p = 0.001). A significant association is also shown between blood pressure and Hurley stage (OR = 0.97, p = 0.025). Self-reports of nonsteroidal anti-inflammatory drugs aggravating the disease is also a factor associated with greater severity according to the metascore (OR = 0.12, p = 0.008). Finally, several locations of HS lesions were associated with greater severity, in particular the armpits according to the metascore (OR = 0.29, p < 0.001), and the perianal area according to the Hurley score (OR = 0.15, p < 0.001). CONCLUSION: HS seems to be more severe in men; smoking seems to aggravate mild cases of HS, while increased body mass index plays a major role in the transition from Hurley II to Hurley III.

Line-Field Confocal Optical Coherence Tomography: A New Skin Imaging Technique Reproducing a "Virtual Biopsy" with Evolving Clinical Applications in Dermatology.

BACKGROUND: Line-field confocal optical coherence tomography is a novel technology able to reproduce a "virtual biopsy" of the skin. The aim of this review is to explore the application of line-field confocal optical coherence tomography (LC-OCT) in various skin diseases, covering skin cancers, inflammatory and infectious skin diseases, genetic diseases, cosmetic procedures, and less common disorders. METHODS: Study selection was conducted based on LC-OCT and using pertinent MeSh terms, following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines from inception to March 2024; to evaluate the quality and risk of bias of studies, Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) was used. RESULTS: the search retrieved 154 papers according to the selection criteria; after removing publications by one or more of the exclusion criteria, a total of 96 studies were found to be suitable for the analysis. CONCLUSIONS: Increasing evidence supports the use of LC-OCT as an adjunctive diagnostic tool for the in vivo diagnosis of a variety of skin tumors. As this device can be considered a "bridge" between dermoscopy and histopathology, widening applications in numerous fields of clinical dermatology, including inflammatory skin disease treatment, presurgical mapping, cosmetic procedures, and monitoring of non-invasive therapies, have been explored.

Line-field confocal optical coherence tomography for the differential diagnosis of porokeratosis from clinical simulators: a preliminary study.

Porokeratosis variants are relatively rare and can be clinically misdiagnosed with several common papulo-keratosic simulators. Line-field confocal optical coherence tomography (LC-OCT) is a new technology able to explore the skin in vivo up to 500µm depth. In this preliminary study we aimed to investigate the role of LC-OCT in the diagnosis of many porokeratosis variants. A total of 54 patients (28 was affected by one among 13 porokeratosis variants, 26 had a simulator condition) were examined at lesional and perilesional sites in vertical and horizontal view. We found an almost perfect interobserver agreement in LC-OCT images interpretation and a perfect correspondence with histologic slides. In addition, a series of morphologic in vivo and 3D features related to the cornoid lamella were detected by LC-OCT, not visible under histology. This device can be proposed for rapid bed-side non-invasive differentiation of porokeratosis variants from their simulators, possibly sparing incisional biopsy in doubtful cases.

The Role of Line-Field Confocal Optical Coherence Tomography in Detecting Extramammary Paget Disease Recurrences: A Pilot Diagnostic Study.

Extramammary Paget disease (EMPD) is an uncommon adenocarcinoma of apocrine gland-rich areas, presenting significant diagnostic challenges due to its nonspecific clinical appearance and frequent misidentification as benign, inflammatory skin conditions. Traditional diagnostic methods such as biopsy are invasive and uncomfortable, often required repeatedly due to high recurrence rates. Dermoscopy and non-invasive imaging techniques have been used but provide limited diagnostic accuracy due to their constraints in depth penetration and resolution. Recent advancements in imaging technologies, such as line-field confocal optical coherence tomography (LC-OCT), show promise in enhancing diagnostic precision while minimizing invasive procedures. LC-OCT merges high-resolution imaging with deep penetration capabilities, capturing detailed horizontal and vertical skin images akin to histopathology. This study evaluated the diagnostic performance of LC-OCT in detecting EMPD and its recurrence in 17 clinically suspicious anogenital regions, belonging to six patients. Data were collected prospectively at the patient's bedside by an LC-OCT expert with poor training for EMPD, and, then, reviewed retrospectively by an independent LC-OCT expert with adequate training for EMPD and no concerns about time. The prospective examination yielded 64.7% accuracy (11 true results out of 17 total cases), 71.4% sensitivity (10 true positives out of 14 actual positives), and 33.3% specificity (1 true negative out of 3 actual negatives). The retrospective analysis achieved 94.1% accuracy (16 true results out of 17 total cases), 100% sensitivity (14 true positives out of 14 actual positives), and 66.7% specificity (2 true positives out of 3 actual positives), with the only false positive case being a difficult-to-diagnose concomitant presentation of a lichen sclerosus et atrophicus. Despite the need for specialized training, our results suggest that LC-OCT represents a valuable tool for accurately identifying EMPD and improving its management by reducing unnecessary biopsies. Further studies are needed to standardize its clinical application.

Pattern Analysis of Benign and Malignant Atypical Melanocytic Skin Lesions of Palms and Soles: Variations of Dermoscopic Features According to Anatomic Site and Personal Experience.

Background: The differential diagnosis of atypical melanocytic skin lesions localized on palms and soles represents a diagnostic challenge: indeed, this spectrum encompasses atypical nevi (AN) and early-stage melanomas (EN) displaying overlapping clinical and dermoscopic features. This often generates unnecessary excisions or delayed diagnosis. Investigations to date were mostly carried out in specific populations, focusing either on acrolentiginous melanomas or morphologically typical acquired nevi. Aims: To investigate the dermoscopic features of atypical melanocytic palmoplantar skin lesions (aMPPLs) as evaluated by variously skilled dermatologists and assess their concordance; to investigate the variations in dermoscopic appearance according to precise location on palms and soles; to detect the features with the strongest association with malignancy/benignity in each specific site. Methods: A dataset of 471 aMPPLs-excised in the suspect of malignancy-was collected from 10 European Centers, including a standardized dermoscopic picture (17×) and lesion/patient metadata. An anatomical classification into 17 subareas was considered, along with an anatomo-functional classification considering pressure/friction, (4 macroareas). A total of 156 participants (95 with less than 5 years of experience in dermoscopy and 61 with ≥than 5 years) from 17 countries performed a blinded tele-dermoscopic pattern analysis over 20 cases through a specifically realized web platform. Results: A total of 37,440 dermoscopic evaluations were obtained over 94 (20%) EM and 377 (80%) AN. The areas with the highest density of EM compared to AN were the heel (40.3% EM/aMPPLs) of the sole and the "fingers area" (33%EM/aMPPLs) of the palm, both characterized by intense/chronic traumatism/friction. Globally, the recognition rates of 12 dermoscopic patterns were non statistically different between 95 dermatology residents and 61 specialists: aMPPLs in the plantar arch appeared to be the most "difficult" to diagnose, the parallel ridge pattern was poorly recognized and irregular/regular fibrillar patterns often misinterpreted. Regarding the aMPPL of the "heel area", the parallel furrow pattern (p = 0.014) and lattice-like pattern (p = 0.001) significantly discriminated benign cases, while asymmetry of colors (p = 0.002) and regression structures (p = 0.025) malignant ones. In aMPPLs of the "plantar arch", the lattice-like pattern (p = 0.012) was significant for benignity and asymmetry of structures, asymmetry of colors, regression structures, or blue-white veil for malignancy. In palmar lesions, no data were significant in the discrimination between malignant and benign aMPPLs. Conclusions: This study highlights that (i) the pattern analysis of aMPPLs is challenging for both experienced and novice dermoscopists; (ii) the histological distribution varies according to the anatomo-functional classification; and (iii) different dermoscopic patterns are able to discriminate malignant from benign aMPPLs within specific plantar and palmar areas.

Understanding the Dermoscopic Patterns of Basal Cell Carcinoma Using Line-Field Confocal Tomography.

Basal cell carcinoma (BCC) is the most frequent malignancy in the general population. To date, dermoscopy is considered a key tool for the diagnosis of BCC; nevertheless, line-field confocal optical coherence tomography (LC-OCT), a new non-invasive optical technique, has become increasingly important in clinical practice, allowing for in vivo imaging at cellular resolution. The present study aimed to investigate the possible correlation between the dermoscopic features of BCC and their LC-OCT counterparts. In total, 100 histopathologically confirmed BCC cases were collected at the Dermatologic Clinic of the University of Siena, Italy. Predefined dermoscopic and LC-OCT criteria were retrospectively evaluated, and their frequencies were calculated. The mean (SD) age of our cohort was 65.46 (13.36) years. Overall, BCC lesions were mainly located on the head (49%), and they were predominantly dermoscopically pigmented (59%). Interestingly, all dermoscopic features considered had a statistically significant agreement with the LC-OCT criteria (all p < 0.05). In conclusion, our results showed that dermoscopic patterns may be associated with LC-OCT findings, potentially increasing accuracy in BCC diagnosis. However, further studies are needed in this field.

Belgian Patients of the European Registry for Hidradenitis Suppurativa (ERHS-Be): Data, Scores, and Phenotypes since 2015.

INTRODUCTION: Hidradenitis suppurativa (HS) is a chronic inflammatory skin disease, characterized by painful and recurrent lesions in apocrine gland-bearing skin areas. It is a heterogeneous disease, which makes assessment and data collection difficult. Questionnaires with detailed items, such as the Belgian European Registry for Hidradenitis Suppurativa (ERHS-Be), are useful to study HS and its associated comorbidities. The aim of this registry was to uncover new factors associated with HS and understand HS patients' clinical profiles and efficacy of treatments. MATERIAL AND METHODS: The ERHS-Be registry is based on questionnaires, with sections for sociodemographic data, medical and HS history, clinical examination, and treatment plan. It allows identification of different clinical phenotypes and automatic calculation of severity scores. RESULTS: At present, 606 patients are included in the ERHS-Be (67% women, 33% men). The mean age at the first visit is 38.5 years. Tobacco use is present in 72.6% of patients. A family history of HS is noted in 42% of patients. Comorbidities are documented in this cohort: depression is present in 43.8% of patients, arthritis in 27.8%, obesity in 31.5%, hypertension in 10.6%, diabetes mellitus in 6.4%, and dyslipidemia in 12.4%. Moreover, 7.7% of patients suffer from IBD and 27.4% have a pilonidal sinus. History of severe acne is found in 32.1% of patients and psoriasis in 9.3%. Thirteen percent of women in our cohort suffer from polycystic ovarian syndrome. Severity of disease is quantified in 533 patients: for instance, Hurley I, II, and III scores proportions are, respectively, 32.3%, 52.7%, and 15%, while the mean IHS4 score is 5.2. This registry also enables determination of relative phenotype proportions in our cohort, according to different classifications. CONCLUSION: The ERHS-Be questionnaires allow systematic and larger data collection, including detailed comorbidities, phenotypes, and severity of disease. Analysis of this large database will contribute to a better understanding and management of HS, at a time where new therapeutic options are becoming available.

Line-Field Confocal Optical Coherence Tomography Evaluation of Eyelid Skin Lesions.

BACKGROUND: Periocular malignancies may be clinically different from the examples arising at other sites, with possible delayed diagnosis and greater challenges for treatment and repair. Line-field confocal optical coherence tomography (LC-OCT) is a recently developed technique characterized by an unprecedented capacity to acquire high-definition images in vertical and horizontal modes. In this study, we aimed to investigate the LC-OCT morphological features of a series of eyelid skin lesions, correlating them to histopathological findings. METHODS: Patients with biopsy-proven equivocal skin lesion in the eyelid area, previously investigated by means of LC-OCT, were included in the study. Percentage overall agreement was estimated for LC-OCT and histopathological diagnosis for study cases. RESULTS: A total of 51 patients (28 women, 23 men; mean age 66.4 years old), for a total of 51 skin lesions, were assessed. The histopathological diagnosis consisted of 30 malignant and 21 benign tumors. Different entities were characterized by peculiar findings in LC-OCT, alike to histopathological features, allowing for an accurate "in vivo" classification in almost all cases, with a diagnostic concordance with histopathology of 92.1% (47/51). CONCLUSIONS: By integrating this new imaging technique into the assessment of suspicious tumors in this area, diagnostic accuracy may increase, improving strategies adopted in multidisciplinary meetings and patient-centered care.

Line-Field Confocal Optical Coherence Tomography (LC-OCT) for Skin Imaging in Dermatology.

Line-field confocal optical coherence tomography (LC-OCT) is a non-invasive optical imaging technique based on a combination of the principles of optical coherence tomography and reflectance confocal microscopy with line-field illumination, which can generate cell-resolved images of the skin in vivo. This article reports on the LC-OCT technique and its application in dermatology. The principle of the technique is described, and the latest technological innovations are presented. The technology has been miniaturized to fit within an ergonomic handheld probe, allowing for the easy access of any skin area on the body. The performance of the LC-OCT device in terms of resolution, field of view, and acquisition speed is reported. The use of LC-OCT in dermatology for the non-invasive detection, characterization, and therapeutic follow-up of various skin pathologies is discussed. Benign and malignant melanocytic lesions, non-melanocytic skin tumors, such as basal cell carcinoma, squamous cell carcinoma and actinic keratosis, and inflammatory and infectious skin conditions are considered. Dedicated deep learning algorithms have been developed for assisting in the analysis of LC-OCT images of skin lesions.

Where Artificial Intelligence Can Take Us in the Management and Understanding of Cancerization Fields.

Squamous cell carcinoma and its precursor lesion actinic keratosis are often found together in areas of skin chronically exposed to sun, otherwise called cancerisation fields. The clinical assessment of cancerisation fields and the correct diagnosis of lesions within these fields is usually challenging for dermatologists. The recent adoption of skin cancer diagnostic imaging techniques, particularly LC-OCT, helps clinicians in guiding treatment decisions of cancerization fields in a non-invasive way. The combination of artificial intelligence and non-invasive skin imaging opens up many possibilities as AI can perform tasks impossible for humans in a reasonable amount of time. In this text we review past examples of the application of AI to dermatological images for actinic keratosis/squamous cell carcinoma diagnosis, and we discuss about the prospects of the application of AI for the characterization and management of cancerization fields.

Line-Field Confocal Optical Coherence Tomography for the Diagnosis of Skin Carcinomas: Real-Life Data over Three Years.

Line-field confocal optical coherence tomography (LC-OCT) can help the clinical diagnosis of skin diseases. The present study aimed to evaluate the sensitivity, specificity, and diagnostic accuracy of LC-OCT for the diagnosis of the most frequent non-melanoma skin cancers (NMSCs), i.e., basal cell carcinoma (BCC) and squamous cell carcinoma (SCC). Comparing LC-OCT diagnostic performances with those of dermoscopy, histopathological examination was used as a gold standard. For every study endpoint, the diagnostic ability of LC-OCT revealed superiority over the dermoscopic examination. In particular, a significant increase in specificity was observed. Sensitivity, specificity, and diagnostic accuracy of dermoscopy and LC-OCT for the diagnosis of malignancy were, respectively, 0.97 (CI 0.94-0.99), 0.43 (CI 0.36-0.51), and 0.77 (CI 0.72-0.81) for dermoscopy and 0.99 (CI 0.97-1.00), 0.90 (CI 0.84-0.94), and 0.96 (CI 0.93-0.97) for LC-OCT. The positive predictive value (PPV) resulted in 0.74 (CI 0.69-0.78) for dermoscopy and 0.94 (CI 0.91-0.97) for LC-OCT, and the negative predictive value (NPV) was 0.89 (CI 0.81-0.95) for dermoscopy and 0.98 (CI 0.95-1.00) for LC-OCT. Finally, our real-life study showed a potentially important role of LC-OCT in the non-invasive diagnosis of NMSCs, especially BCC. The real-time imaging technique could spare unnecessary biopsies with an increased sensitivity, a much higher specificity, and better accuracy than clinical assessment with dermoscopy alone.

Dermoscopy of atypical pigmented lesions of the face: Variation according to facial areas.

Atypical pigmented facial lesions (aPFLs)-including lentigo maligna (LM) and lentigo maligna melanoma (LMM), solar lentigo (SL), pigmented actinic keratosis (PAK), atypical nevi (AN), seborrheic keratosis (SK) and lichen planus-like keratosis (LPLK)-can exhibit clinical and dermoscopic overlapping features. We aimed to investigate if and how 14 dermoscopic features suggestive for the aforementioned aPFLs vary according to six facial sites among 1197 aPFLs cases (excised to rule out malignancy) along with lesion and patients' metadata. According to distribution and association analysis, aPFLs on the forehead of a male patient aged > 69 years displaying the obliterated follicular openings pattern, appear to be more at risk of malignancy. Of converse, aPFLs of the orbital/cheek/nose area with evident and regular follicular openings with diameter < 10 mm in a female aged below 68 are probably benign. The obliterated follicular openings, keratin plugs, evident and regular follicular openings and target-like pattern features differed significantly among six facial areas in all aPFLs cases. Lesion of the nose may show both features suggestive of malignancy and benignity (e.g. many SL and PAK may display target-like pattern and some LM/LMM cases display keratin plugs and evident and follicular openings), making these features less specific.

A risk-scoring model for the differential diagnosis of lentigo maligna and other atypical pigmented facial lesions of the face: The facial iDScore.

BACKGROUND: Due to progressive ageing of the population, the incidence of facial lentigo maligna (LM) of the face is increasing. Many benign simulators of LM and LMM, known as atypical pigmented facial lesions (aPFLs-pigmented actinic keratosis, solar lentigo, seborrheic keratosis, seborrheic-lichenoid keratosis, atypical nevus) may be found on photodamaged skin. This generates many diagnostic issues and increases the number of biopsies, with a subsequent impact on aesthetic outcome and health insurance costs. OBJECTIVES: Our aim was to develop a risk-scoring classifier-based algorithm to estimate the probability of an aPFL being malignant. A second aim was to compare its diagnostic accuracy with that of dermoscopists so as to define the advantages of using the model in patient management. MATERIALS AND METHODS: A total of 154 dermatologists analysed 1111 aPFLs and their management in a teledermatology setting: They performed pattern analysis, gave an intuitive clinical diagnosis and proposed lesion management options (follow-up/reflectance confocal microscopy/biopsy). Each case was composed of a dermoscopic and/or clinical picture plus metadata (histology, age, sex, location, diameter). The risk-scoring classifier was developed and tested on this dataset and then validated on 86 additional aPFLs. RESULTS: The facial Integrated Dermoscopic Score (iDScore) model consisted of seven dermoscopic variables and three objective parameters (diameter ≥ 8 mm, age ≥ 70 years, male sex); the score ranged from 0 to 16. In the testing set, the facial iDScore-aided diagnosis was more accurate (AUC = 0.79 [IC 95% 0.757-0.843]) than the intuitive diagnosis proposed by dermatologists (average of 43.5%). In the management study, the score model reduced the number of benign lesions sent for biopsies by 41.5% and increased the number of LM/LMM cases sent for reflectance confocal microscopy or biopsy instead of follow-up by 66%. CONCLUSIONS: The facial iDScore can be proposed as a feasible tool for managing patients with aPFLs.

Treatment of Acne with Isotretinoin Should Be Avoided in Patients with Hidradenitis Suppurativa "Conglobata Phenotype".

BACKGROUND: Acne conglobata (AC) and nodulocystic acne have long been confused clinically, despite the presentation and the response to treatment being different. AC and hidradenitis suppurativa (HS) resemble each other; a subtype of HS called "conglobata phenotype" has recently been reported in a large Dutch cohort. Acne vulgaris and HS are often associated. Isotretinoin is typically ineffective in treating HS and may even aggravate it, but it is often indispensable in treating acne vulgaris. OBJECTIVE: The aim of the study was to assess whether isotretinoin may be used safely in adults with both HS and acne vulgaris and when it might be contraindicated. MATERIALS AND METHODS: Belgian HS patients from the European Registry for Hidradenitis Suppurativa Registry (ERHS) reporting a history of severe acne of the face and/or the back, and who have ever used isotretinoin for their acne, were all selected. Patients whose acne worsened on isotretinoin were compared to patients whose acne did not worsen (improvement or no change). RESULTS: Among the 82 selected patients, 10 (12.2%) report that their acne was aggravated while taking isotretinoin, while 72 (87.8%) report that their acne was not aggravated on isotretinoin. Of the 10 HS patients whose acne worsened with isotretinoin, 9 (90%) were men (p = 0.04) and 8 (80%) were HS "conglobata phenotype" (p < 0.001). In contrast, 47 (65.3%) of the 72 patients whose acne did not worsen on isotretinoin belonged to the HS "regular phenotype" (p = 0.01). On multivariate analysis, the item most strongly associated with poor response to isotretinoin was the HS "conglobata phenotype," followed by body mass index (BMI) (worse response to isotretinoin if BMI >25 kg/m2). Additionally, of 26 patients who received isotretinoin while their HS had already started, only 6 (23.1%) reported isotretinoin effectiveness on their HS. CONCLUSION: Subject to confirmation by larger studies, our study suggests that isotretinoin should be avoided in the treatment of acne in HS patients with the HS "conglobata phenotype," as it may worsen the acne, likewise being male or having a BMI above 25 seems to increase this risk of a bad therapeutic outcome. Patients with an HS "regular phenotype" appear to be at a reduced risk of isotretinoin treatment worsening their acne.