Skinformatics: Navigating the big data landscape of dermatology.

Big data and associated approaches to analyse it are on the rise, especially in healthcare settings. This growth is also seen with unique applications in the field of dermatology. While big data offer a plethora of opportunity for improving our current understanding of disease and ability to deliver care, as with any technology innovation, the potential pitfalls should be addressed. In this piece, we highlight opportunities and challenges associated with big data in dermatology. Opportunities include large and novel data sources that may offer a wealth of information, automated detection, classification and diagnostics and improved public health monitoring. Challenges include data quality, issues of interpretability and disparities within artificial intelligence (AI) training data sets. Clinicians and researchers in the field should be aware of these developments within the field of big data to understand how best it may be used toward improving patient care and health outcomes, particularly in the field of dermatology.

Dermoscopy aids in differentiating café-au-lait macules from congenital melanocytic nevi in patients with darker skin phototypes.

Dermoscopy aids in the diagnosis and management of pigmented growths and disorders of pigmentation in children. However, there is limited literature on the dermoscopic appearance of café-au-lait macules (CALMs) and congenital melanocytic nevi in patients with dark skin. We report two cases of young children with dark skin and many hyperpigmented patches in whom dermoscopy was utilized to accurately diagnose CALMs and facilitate testing for neurofibromatosis.

DEL-Thyroid: deep ensemble learning framework for detection of thyroid cancer progression through genomic mutation.

Genes, expressed as sequences of nucleotides, are susceptible to mutations, some of which can lead to cancer. Machine learning and deep learning methods have emerged as vital tools in identifying mutations associated with cancer. Thyroid cancer ranks as the 5th most prevalent cancer in the USA, with thousands diagnosed annually. This paper presents an ensemble learning model leveraging deep learning techniques such as Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Bi-directional LSTM (Bi-LSTM) to detect thyroid cancer mutations early. The model is trained on a dataset sourced from asia.ensembl.org and IntOGen.org, consisting of 633 samples with 969 mutations across 41 genes, collected from individuals of various demographics. Feature extraction encompasses techniques including Hahn moments, central moments, raw moments, and various matrix-based methods. Evaluation employs three testing methods: self-consistency test (SCT), independent set test (IST), and 10-fold cross-validation test (10-FCVT). The proposed ensemble learning model demonstrates promising performance, achieving 96% accuracy in the independent set test (IST). Statistical measures such as training accuracy, testing accuracy, recall, sensitivity, specificity, Mathew's Correlation Coefficient (MCC), loss, training accuracy, F1 Score, and Cohen's kappa are utilized for comprehensive evaluation.

Synchronizing smart city nodes using Skew Integrated Timestamp (SIT).

Time synchronization among smart city nodes is critical for proper functioning and coordinating various smart city systems and applications. It ensures that different devices and systems in the smart city network are synchronized and all the data generated by these devices is consistent and accurate. Synchronization methods in smart cities use multiple timestamp exchanges for time skew correction. The Skew Integrated Timestamp (SIT) proposed here uses a timestamp, which has time skew calculated from the physical layer and uses just one timestamp to synchronize. The result from the experiment suggests that SIT can be used in place of multiple timestamp exchanges, which saves computational resources and energy.

Noninfectious causes of alopecia in the pediatric population.

PURPOSE OF REVIEW: To highlight recent advances in the knowledge base surrounding noninfectious causes of alopecia in the pediatric population. RECENT FINDINGS: Recent developments in the literature included assessments of treatment efficacy, diagnostic utility of trichoscopy, and retrospective studies characterizing the clinical picture of pediatric cases. SUMMARY: These findings will equip practitioners with the recent advances in the field's understanding of noninfectious causes of alopecia in the pediatric population.

Anticoagulation Versus Antiplatelets in Spontaneous Cervical Artery Dissection: A Systematic Review and Meta-Analysis.

BACKGROUND: It is uncertain whether antiplatelets or anticoagulants are more effective in preventing early recurrent stroke in patients with cervical artery dissection. Following the publication of the observational Antithrombotic for STOP-CAD (Stroke Prevention in Cervical Artery Dissection) study, which has more than doubled available data, we performed an updated systematic review and meta-analysis comparing antiplatelets versus anticoagulation in cervical artery dissection. METHODS: The systematic review was registered in PROSPERO (CRD42023468063). We searched 5 databases using a combination of keywords that encompass different antiplatelets and anticoagulants, as well as cervical artery dissection. We included relevant randomized trials and included observational studies of dissection unrelated to major trauma. Where studies were sufficiently similar, we performed meta-analyses for efficacy (ischemic stroke) and safety (major hemorrhage, symptomatic intracranial hemorrhage, and death) outcomes using relative risks. RESULTS: We identified 11 studies (2 randomized trials and 9 observational studies) that met the inclusion criteria. These included 5039 patients (30% [1512] treated with anticoagulation and 70% [3527]) treated with antiplatelets]. In meta-analysis, anticoagulation was associated with a lower ischemic stroke risk (relative risk, 0.63 [95% CI, 0.43 to 0.94]; P=0.02; I2=0%) but higher major bleeding risk (relative risk, 2.25 [95% CI, 1.07 to 4.72]; P=0.03, I2=0%). The risks of death and symptomatic intracranial hemorrhage were similar between the 2 treatments. Effect sizes were larger in randomized trials. There are insufficient data on the efficacy and safety of dual antiplatelet therapy or direct oral anticoagulants. CONCLUSIONS: In this study of patients with cervical artery dissection, anticoagulation was superior to antiplatelet therapy in reducing ischemic stroke but carried a higher major bleeding risk. This argues for an individualized therapeutic approach incorporating the net clinical benefit of ischemic stroke reduction and bleeding risks. Large randomized clinical trials are required to clarify optimal antithrombotic strategies for management of cervical artery dissection.

The use of biologics and JAK inhibitors in the management of moderate to severe Hidradenitis Suppurativa treatment: a scoping review.

This scoping review aims to characterize the use of biologics and Janus Kinase inhibitors (JAKi) in the treatment of Hidradenitis Suppurativa (HS), which is a chronic inflammatory condition. A comprehensive literature search was conducted in PubMed/NCBI, Embase, Web of Science databases, and the Clinicaltrials.gov register. The search included interventional trials assessing the use of biologics or JAKi in HS, with no geographic or time restrictions. Secukinumab and adalimumab were identified as the only two drugs approved by the FDA for treating moderate to severe HS in adults. Several other drug classes showed promising results based on clinical studies reviewed. IL-12/23 inhibitor ustekinumab demonstrated improvements in disease severity scores and HiSCR rates in small trials. IL-17 inhibitors such as brodalumab, bimekizumab, and CJM112 showed preliminary positive responses in early-phase clinical studies and case reports. While evidence was mixed, some TNF-α inhibitors such as infliximab provided benefits according to a randomized controlled trial, though etanercept trials yielded non-significant or inconsistent findings. Larger, well-designed studies are required to further establish their efficacy and safety, but biologics and JAKis show potential as alternative treatment options for moderate to severe HS. The findings of this review contribute to the growing interest among patients and to enhancing the understanding of physician's regarding potential alternative therapeutic options for HS and provide a basis for further research in this field.

Skin and Syntax: Large Language Models in Dermatopathology.

This literature review introduces the integration of Large Language Models (LLMs) in the field of dermatopathology, outlining their potential benefits, challenges, and prospects. It discusses the changing landscape of dermatopathology with the emergence of LLMs. The potential advantages of LLMs include a streamlined generation of pathology reports, the ability to learn and provide up-to-date information, and simplified patient education. Existing instances of LLMs encompass diagnostic support, research acceleration, and trainee education. Challenges involve biases, data privacy and quality, and establishing a balance between AI and dermatopathological expertise. Prospects include the integration of LLMs with other AI technologies to improve diagnostics and the improvement of multimodal LLMs that can handle both text and image input. Our implementation guidelines highlight the importance of model transparency and interpretability, data quality, and continuous oversight. The transformative potential of LLMs in dermatopathology is underscored, with an emphasis on a dynamic collaboration between artificial intelligence (AI) experts (technical specialists) and dermatopathologists (clinicians) for improved patient outcomes.

Multimodal CNN-DDI: using multimodal CNN for drug to drug interaction associated events.

Drug-to-drug interaction (DDIs) occurs when a patient consumes multiple drugs. Therefore, it is possible that any medication can influence other drugs' effectiveness. The drug-to-drug interactions are detected based on the interactions of chemical substructures, targets, pathways, and enzymes; therefore, machine learning (ML) and deep learning (DL) techniques are used to find the associated DDI events. The DL model, i.e., Convolutional Neural Network (CNN), is used to analyze the DDI. DDI is based on the 65 different drug-associated events, which is present in the drug bank database. Our model uses the inputs, which are chemical structures (i.e., smiles of drugs), enzymes, pathways, and the target of the drug. Therefore, for the multi-model CNN, we use several layers, activation functions, and features of drugs to achieve better accuracy as compared to traditional prediction algorithms. We perform different experiments on various hyperparameters. We have also carried out experiments on various iterations of drug features in different sets. Our Multi-Modal Convolutional Neural Network - Drug to Drug Interaction (MCNN-DDI) model achieved an accuracy of 90.00% and an AUPR of 94.78%. The results showed that a combination of the drug's features (i.e., chemical substructure, target, and enzyme) performs better in DDIs-associated events prediction than other features.

Transcarotid Arterial Revascularization of Symptomatic Internal Carotid Artery Disease: A Systematic Review and Study-Level Meta-Analysis.

BACKGROUND: Transcarotid artery revascularization (TCAR) is an interventional therapy for symptomatic internal carotid artery disease. Currently, the utilization of TCAR is contentious due to limited evidence. In this study, we evaluate the safety and efficacy of TCAR in patients with symptomatic internal carotid artery disease compared with carotid endarterectomy (CEA) and carotid artery stenting (CAS). METHODS: A systematic review was conducted, spanning from January 2000 to February 2023, encompassing studies that used TCAR for the treatment of symptomatic internal carotid artery disease. The primary outcomes included a 30-day stroke or transient ischemic attack, myocardial infarction, and mortality. Secondary outcomes comprised cranial nerve injury and major bleeding. Pooled odds ratios (ORs) for each outcome were calculated to compare TCAR with CEA and CAS. Furthermore, subgroup analyses were performed based on age and degree of stenosis. In addition, a sensitivity analysis was conducted by excluding the vascular quality initiative registry population. RESULTS: A total of 7 studies involving 24 246 patients were analyzed. Within this patient cohort, 4771 individuals underwent TCAR, 12 350 underwent CEA, and 7125 patients underwent CAS. Compared with CAS, TCAR was associated with a similar rate of stroke or transient ischemic attack (OR, 0.77 [95% CI, 0.33-1.82]) and myocardial infarction (OR, 1.29 [95% CI, 0.83-2.01]) but lower mortality (OR, 0.42 [95% CI, 0.22-0.81]). Compared with CEA, TCAR was associated with a higher rate of stroke or transient ischemic attack (OR, 1.26 [95% CI, 1.03-1.54]) but similar rates of myocardial infarction (OR, 0.9 [95% CI, 0.64-1.38]) and mortality (OR, 1.35 [95% CI, 0.87-2.10]). CONCLUSIONS: Although CEA has traditionally been considered superior to stenting for symptomatic carotid stenosis, TCAR may have some advantages over CAS. Prospective randomized trials comparing the 3 modalities are needed.

FLAIR signal intensity ratio predicts small subcortical infarct early neurologic deterioration: a cross-sectional study.

PURPOSE: Prior studies have used the fluid-attenuated inversion recovery sequence signal intensity ratio (FLAIR-SIR) to predict those with an incomplete infarct that may safely receive acute thrombolytics. Clinical early neurologic deterioration (END) of small subcortical infarcts (SSIs) is suspected to occur due to delayed infarct completion. We aimed to understand if a lower FLAIR-SIR, suggestive of an incomplete infarct, would have a higher likelihood of SSI-related END. METHODS: A cross-sectional retrospective study was performed of those with an acute SSI (anterior or posterior circulation) without significant parent vessel steno-occlusive disease. END was defined as a new or worsened disabling neurologic deficit during the index hospitalization. Standard-of-care brain MRIs were reviewed from the hospitalization, and a FLAIR-SIR cutoff of ≤ 1.15 was used based on prior studies. Adjusted logistic regression models were used for analysis. RESULTS: We identified 252 patients meeting inclusion criteria: median (IQR) age 68 (12) years, 38.5% (97/252) female, and 11% (28/252) with END. Tobacco use was more common in those without END (32%) compared with END (55%, p = 0.03). In adjusted analyses, a FLAIR-SIR cutoff of ≤ 1.15 yielded an odds ratio of 2.8 (95% CI 1.23-6.13, p = 0.012) of early neurological deterioration. CONCLUSION: Those with a FLAIR-SIR ≤ 1.15 are nearly threefold more likely to develop SSI-related END.

An ensemble-based deep learning model for detection of mutation causing cutaneous melanoma.

When the mutation affects the melanocytes of the body, a condition called melanoma results which is one of the deadliest skin cancers. Early detection of cutaneous melanoma is vital for raising the chances of survival. Melanoma can be due to inherited defective genes or due to environmental factors such as excessive sun exposure. The accuracy of the state-of-the-art computer-aided diagnosis systems is unsatisfactory. Moreover, the major drawback of medical imaging is the shortage of labeled data. Generalized classifiers are required to diagnose melanoma to avoid overfitting the dataset. To address these issues, blending ensemble-based deep learning (BEDLM-CMS) model is proposed to detect mutation of cutaneous melanoma by integrating long short-term memory (LSTM), Bi-directional LSTM (BLSTM) and gated recurrent unit (GRU) architectures. The dataset used in the proposed study contains 2608 human samples and 6778 mutations in total along with 75 types of genes. The most prominent genes that function as biomarkers for early diagnosis and prognosis are utilized. Multiple extraction techniques are used in this study to extract the most-prominent features. Afterwards, we applied different DL models optimized through grid search technique to diagnose melanoma. The validity of the results is confirmed using several techniques, including tenfold cross validation (10-FCVT), independent set (IST), and self-consistency (SCT). For validation of the results multiple metrics are used which include accuracy, specificity, sensitivity, and Matthews's correlation coefficient. BEDLM gives the highest accuracy of 97% in the independent set test whereas in self-consistency test and tenfold cross validation test it gives 94% and 93% accuracy, respectively. Accuracy of in self-consistency test, independent set test, and tenfold cross validation test is LSTM (96%, 94%, 92%), GRU (93%, 94%, 91%), and BLSTM (99%, 98%, 93%), respectively. The findings demonstrate that the proposed BEDLM-CMS can be used effectively applied for early diagnosis and treatment efficacy evaluation of cutaneous melanoma.

Off-Label Use of Baricitinib in Dermatology.

The current US Food and Drug Administration (FDA) indications for baricitinib include alopecia areata, rheumatoid arthritis, and COVID-19. However, increasing evidence indicates that baricitinib is effective in treating a variety of dermatological conditions. This review article comprehensively presents the available literature on this topic and will be of interest to practitioners in the field. These disorders may be broadly classified as connective tissue diseases, eczematous dermatoses, alopecias, vascular disorders, granulomatous diseases, neutrophilic dermatoses, vitiligo, psoriasis, lichenoid disorders, and other miscellaneous disorders. Shah A, Yumeen S, Qureshi A, et al. Off-label use of baricitinib in dermatology. J Drugs Dermatol. 2023;22(8):795-801. doi:10.36849/JDD.7360.