Using Artificial Intelligence as a Melanoma Screening Tool in Self-Referred Patients.

INTRODUCTION: Early detection of melanoma requires timely access to medical care. In this study, we examined the feasibility of using artificial intelligence (AI) to flag possible melanomas in self-referred patients concerned that a skin lesion might be cancerous. METHODS: Patients were recruited for the study through advertisements in 2 hospitals in Halifax, Nova Scotia, Canada. Lesions of concern were initially examined by a trained medical student and if the study criteria were met, the lesions were then scanned using the FotoFinder System®. The images were analyzed using their proprietary computer software. Macroscopic and dermoscopic images were evaluated by 3 experienced dermatologists and a senior dermatology resident, all blinded to the AI results. Suspicious lesions identified by the AI or any of the 3 dermatologists were then excised. RESULTS: Seventeen confirmed malignancies were found, including 10 melanomas. Six melanomas were not flagged by the AI. These lesions showed ambiguous atypical melanocytic proliferations, and all were diagnostically challenging to the dermatologists and to the dermatopathologists. Eight malignancies were seen in patients with a family history of melanoma. The AI's ability to diagnose malignancy is not inferior to the dermatologists examining dermoscopic images. CONCLUSION: AI, used in this study, may serve as a practical skin cancer screening aid. While it does have technical and diagnostic limitations, its inclusion in a melanoma screening program, directed at those with a concern about a particular lesion would be valuable in providing timely access to the diagnosis of skin cancer.

Plasmacytoid dendritic cells in hypertrophic discoid lupus erythematosus: an objective evaluation of their diagnostic value.

BACKGROUND: Hypertrophic discoid lupus erythematosus (HDLE), a rare variant of lupus skin disease, is difficult to distinguish from squamous neoplasms and certain dermatoses microscopically. Recently, recognition of the pathogenetic significance of plasmacytoid dendritic cells (PDCS) in cutaneous lupus erythematosus (LE) and of their patterns of distribution in different manifestations of the disease prompted us to study their diagnostic value in the context of HDLE. METHODS: Using immunohistochemistry (CD123) to label the cells, we examined their quantities and patterns of distribution in 27 tissue samples of HDLE from nine patients compared with 39 inflammatory and neoplastic control samples from 36 patients. RESULTS: Using three parameters pertaining to PDCs: (i) their representation of 10% or more of the inflammatory infiltrate, (ii) their arrangement in clusters of 10 cells or more and (iii) their presence at the dermoepidermal junction, we found them to have significant diagnostic value, with accuracies of 77%, 74% and 71%, respectively. CONCLUSIONS: This study supports the careful descriptive observations of previous authors in the field. It also lends validity to the diagnostic step of mapping, immunohistochemically, the density and distribution of PDCs in suspected cases of HDLE.

Cutaneous manifestations of angioimmunoblastic T-cell lymphoma: clinical and pathological characteristics.

Angioimmunoblastic T-cell lymphoma (AITL), an uncommon variant of peripheral T-cell lymphoma, affects the skin in approximately 50% of cases. Its protean clinical and histopathological cutaneous manifestations pose a challenge in diagnosis, particularly when these precede the diagnosis of AITL on a lymph node biopsy. In this retrospective study, we compared 11 cases of AITL with cutaneous manifestations (mean age 67 years; male:female ratio 1:0.8; 24 skin biopsies) with 20 control cases of inflammatory and non-AITL lymphomatous diseases (mean age 52 years; male:female ratio 1:1.5; 26 skin biopsies). Clinical, histopathological, immunohistochemical, and molecular data were documented. New insights into the clinical evolution of cutaneous involvement by AITL (C-AITL), from early macular, through papular to nodular stages, were observed. Microscopically, a parallel increment in the density of the dermal infiltrate and in the detection of lymphocyte cytological atypia was noted over time. Identification and quantification of follicular T-helper cells (Tfh), the neoplastic lineage, by immunohistochemistry helped to separate cases of C-AITL from inflammatory controls, offering promise as a useful diagnostic adjunct. The presence of T-cell clonality did not have discriminatory value between the 2 groups. Our work suggests that the early maculopapular phase of C-AITL eludes identification on pathological grounds alone and that features such as cytological atypia and high endothelial venules lack diagnostic specificity. In the context of (1) a rash that simulates a drug/viral exanthem or an acute manifestation of a connective tissue disorder, but proves recalcitrant, (2) constitutional abnormalities and/or lymphadenopathy that persist, and (3) a Tfh cell-rich perivascular dermatitis, the diagnosis of early C-AITL can be suspected, but not confirmed, without the benefit of a lymph node biopsy. The later nodular phase of C-AITL occurring in a similar constitutional background, can usually be discerned as lymphomatous, clinically and pathologically. Here a Tfh cell-rich infiltrate is a clue to the specific diagnosis, but confirmation by a nodal evaluation remains mandatory. Despite the difficulty in establishing a diagnosis of C-AITL in its early stages, and speculation that the initial eruptions might be reactive in nature, our sequential data support the concept that these are lymphomatous ab initio. To address the diagnostic challenge presented by this disease, meaningful integration of clinical and pathological data is imperative.

LOGICOIL--multi-state prediction of coiled-coil oligomeric state.

MOTIVATION: The coiled coil is a ubiquitous α-helical protein-structure domain that directs and facilitates protein-protein interactions in a wide variety of biological processes. At the protein-sequence level, the coiled coil is readily recognized via a conspicuous heptad repeat of hydrophobic and polar residues. However, structurally coiled coils are more complicated, existing in a wide range of oligomer states and topologies. As a consequence, predicting these various states from sequence remains an unmet challenge. RESULTS: This work introduces LOGICOIL, the first algorithm to address the problem of predicting multiple coiled-coil oligomeric states from protein-sequence information alone. By covering >90% of the known coiled-coil structures, LOGICOIL is a net improvement compared with other existing methods, which achieve a predictive coverage of ∼31% of this population. This leap in predictive power offers better opportunities for genome-scale analysis, and analyses of coiled-coil containing protein assemblies. AVAILABILITY: LOGICOIL is available via a web-interface at http://coiledcoils.chm.bris.ac.uk/LOGICOIL. Source code, training sets and supporting information can be downloaded from the same site.

Correction to "Insights into the Effects of Violating Statistical Assumptions for Dimensionality Reduction for Chemical "-omics" Data with Multiple Explanatory Variables".

[This corrects the article DOI: 10.1021/acsomega.3c01613.].

Insights into the Effects of Violating Statistical Assumptions for Dimensionality Reduction for Chemical "-omics" Data with Multiple Explanatory Variables.

Biological volatilome analysis is inherently complex due to the considerable number of compounds (i.e., dimensions) and differences in peak areas by orders of magnitude, between and within compounds found within datasets. Traditional volatilome analysis relies on dimensionality reduction techniques which aid in the selection of compounds that are considered relevant to respective research questions prior to further analysis. Currently, compounds of interest are identified using either supervised or unsupervised statistical methods which assume the data residuals are normally distributed and exhibit linearity. However, biological data often violate the statistical assumptions of these models related to normality and the presence of multiple explanatory variables which are innate to biological samples. In an attempt to address deviations from normality, volatilome data can be log transformed. However, whether the effects of each assessed variable are additive or multiplicative should be considered prior to transformation, as this will impact the effect of each variable on the data. If assumptions of normality and variable effects are not investigated prior to dimensionality reduction, ineffective or erroneous compound dimensionality reduction can impact downstream analyses. It is the aim of this manuscript to assess the impact of single and multivariable statistical models with and without the log transformation to volatilome dimensionality reduction prior to any supervised or unsupervised classification analysis. As a proof of concept, Shingleback lizard (Tiliqua rugosa) volatilomes were collected across their species distribution and from captivity and were assessed. Shingleback volatilomes are suspected to be influenced by multiple explanatory variables related to habitat (Bioregion), sex, parasite presence, total body volume, and captive status. This work determined that the exclusion of relevant multiple explanatory variables from analysis overestimates the effect of Bioregion and the identification of significant compounds. The log transformation increased the number of compounds that were identified as significant, as did analyses that assumed that residuals were normally distributed. Among the methods considered in this work, the most conservative form of dimensionality reduction was achieved through analyzing untransformed data using Monte Carlo tests with multiple explanatory variables.

SCORER 2.0: an algorithm for distinguishing parallel dimeric and trimeric coiled-coil sequences.

MOTIVATION: The coiled coil is a ubiquitous α-helical protein structure domain that directs and facilitates protein-protein interactions in a wide variety of biological processes. At the protein-sequence level, coiled coils are quite straightforward and readily recognized via the conspicuous heptad repeats of hydrophobic and polar residues. However, structurally they are more complicated, existing in a range of oligomer states and topologies. Here, we address the issue of predicting coiled-coil oligomeric state from protein sequence. RESULTS: The predominant coiled-coil oligomer states in Nature are parallel dimers and trimers. Here, we improve and retrain the first-published algorithm, SCORER, that distinguishes these states, and test it against the current standard, MultiCoil. The SCORER algorithm has been revised in two key respects: first, the statistical basis for SCORER is improved markedly. Second, the training set for SCORER has been expanded and updated to include only structurally validated coiled coils. The result is a much-improved oligomer state predictor that outperforms MultiCoil, particularly in assigning oligomer state to short coiled coils, and those that are diverse from the training set. AVAILABILITY: SCORER 2.0 is available via a web interface at http://coiledcoils.chm.bris.ac.uk/Scorer. Source code, training sets and Supporting Information can be downloaded from the same site.

Etanercept-induced cutaneous and pulmonary sarcoid-like granulomas resolving with adalimumab.

A 59-year-old female with rheumatoid arthritis on etanercept therapy presented with a 7-cm-large subcutaneous forearm mass. Multiple smaller nodules subsequently developed on the upper and lower extremities. Except for a new cough, the patient was systemically well. Biopsy of the mass showed sarcoidal type granulomatous inflammation with nodular aggregations of non-necrotizing epithelioid histiocytes in the subcutis. A chest computed tomography (CT) scan showed mediastinal adenopathy consistent with pulmonary sarcoidosis. Etanercept was discontinued, and the patient was started on adalimumab for rheumatoid arthritis control. The cutaneous nodules fully resolved in 6 months with no additional treatment. A 4-month follow-up CT scan showed significant regression of mediastinal adenopathy. The patient has since been maintained on adalimumab therapy for 2 years with no recurrence of sarcoid-like manifestations. Biologic response modifiers targeting tumor necrosis factor alpha (TNFα) are effective treatments of chronic inflammatory conditions such as rheumatoid arthritis and psoriasis. TNFα represents a major cytokine in granuloma formation, and TNFα inhibitors are sometimes efficacious in the treatment of sarcoidosis. Paradoxically, there is a small volume of literature implicating TNFα inhibitors in the development of sarcoid-like disease. We present this case to promote the recognition of TNFα inhibitor-induced sarcoidosis and to illustrate the wide clinicopathologic differential of sarcoidal type granulomas.

Casework applications of probabilistic genotyping methods for DNA mixtures that allow relationships between contributors.

In both criminal cases and civil cases there is an increasing demand for the analysis of DNA mixtures involving relationships. The goal might be, for example, to identify the contributors to a DNA mixture where the unknown donors may be related, or to infer the relationship between individuals based on a DNA mixture. This paper applies a new approach to modelling and computation for DNA mixtures involving contributors with arbitrarily complex relationships to two real cases from the Spanish Forensic Police.

Acute onset of blisters in an infant with acrodermatitis enteropathica: A case report.

We represent a pediatric case of the congenital disorder caused by zinc malabsorption, acrodermatitis enteropathica, presenting with acute onsetof blisters. Although blisters can be seen in this condition, it is not always a key feature and can therefore be overlooked when considering a differential diagnosis of acute blistering in infancy. We therefore review the common and less common features of this cutaneous eruption as well as provide an extensive differential diagnosis for acute blistering in infancy. We also emphasize the importance of lifelong treatment with zinc supplementation in these children.

Granulomatous vasculitis in Crohn's disease: a clinicopathologic correlate of two unusual cases.

Cutaneous complications occur not uncommonly in patients with Crohn's disease (CD). Gastrointestinal CD often shows non-caseating granulomas and a rare cutaneous finding in CD is a sterile granulomatous infiltrate not contiguous with the GI tract, termed extraintestinal CD (ECD). The clinical presentation of ECD is diverse. The most common histopathological presentation is a superficial and deep granulomatous infiltrate that often accompanies a mixed perivascular infiltrate. Here we report two patients with CD and skin lesions characterized on microscopy by granulomatous vasculitis. A 29-year-old female presented with papules and ulcerated nodules above the ankle. The biopsy showed dermal and superficial subcutaneous involvement by a vasocentric infiltrate of mononuclear and multinucleated histiocytes as well as mural fibrin deposition. A 35-year-old male presented with two tender indurated erythematous plaques with punched-out centers on the lower leg. Histopathologically, a granulomatous vasculitis of small and medium-sized vessels in the dermis and subcutis was evident. These two cases represent the rarely described phenomenon of cutaneous granulomatous vasculitis in CD. Previously reported examples of this entity are reviewed.

Cocaine-related retiform purpura: evidence to incriminate the adulterant, levamisole.

The term 'cocaine-induced pseudovasculitis' was coined to encompass a constellation of clinical and laboratory findings which mimics a systemic vasculitis but lacks confirmatory evidence of vasculitis on biopsy. Antineutrophil cytoplasmic antibodies reacting with human neutrophil elastase (HNE) have been reported to distinguish the cocaine-related syndrome from a true autoimmune vasculitis. Published cases of retiform purpura related to cocaine use are rare and an etiologic role for levamisole, a common adulterant of cocaine, has been postulated. We describe two female patients aged 39 and 49 years with cocaine-related retiform purpura, mainly affecting the legs. The initial clinical and serological profile in case 1 led to a suspicion of anti-phospholipid syndrome and in case 2 to Wegener's granulomatosis with an unexplained associated neutropenia. Skin biopsies revealed a mixed pattern of leukocytoclastic vasculitis and microvascular thrombosis in case 1 and pure microvascular thrombosis in case 2. Identification of anti-HNE antibodies in both patients linked their disease to cocaine. The mixed vasculopathic pattern in case 1 and the associated neutropenia in case 2, both known adverse effects of levamisole, point to this as the true etiologic agent. Urine toxicology shortly after a binge of cocaine use in each case was positive for levamisole.

Inference from genome-wide association studies using a novel Markov model.

In this paper we propose a Bayesian modeling approach to the analysis of genome-wide association studies based on single nucleotide polymorphism (SNP) data. Our latent seed model combines various aspects of k-means clustering, hidden Markov models (HMMs) and logistic regression into a fully Bayesian model. It is fitted using the Markov chain Monte Carlo stochastic simulation method, with Metropolis-Hastings update steps. The approach is flexible, both in allowing different types of genetic models, and because it can be easily extended while remaining computationally feasible due to the use of fast algorithms for HMMs. It allows for inference primarily on the location of the causal locus and also on other parameters of interest. The latent seed model is used here to analyze three data sets, using both synthetic and real disease phenotypes with real SNP data, and shows promising results. Our method is able to correctly identify the causal locus in examples where single SNP analysis is both successful and unsuccessful at identifying the causal SNP.

Enumerating the decomposable neighbours of a decomposable graph under a simple perturbation scheme.

Given a decomposable graph, we characterize and enumerate the set of pairs of vertices whose connection or disconnection results in a new graph that is also decomposable. We discuss the relevance of this results to Markov chain Monte Carlo methods that sample or optimize over the space of decomposable graphical models according to probabilities determined by a posterior distribution given observed multivariate data.

Bayesian refinement of protein functional site matching.

BACKGROUND: Matching functional sites is a key problem for the understanding of protein function and evolution. The commonly used graph theoretic approach, and other related approaches, require adjustment of a matching distance threshold a priori according to the noise in atomic positions. This is difficult to pre-determine when matching sites related by varying evolutionary distances and crystallographic precision. Furthermore, sometimes the graph method is unable to identify alternative but important solutions in the neighbourhood of the distance based solution because of strict distance constraints. We consider the Bayesian approach to improve graph based solutions. In principle this approach applies to other methods with strict distance matching constraints. The Bayesian method can flexibly incorporate all types of prior information on specific binding sites (e.g. amino acid types) in contrast to combinatorial formulations. RESULTS: We present a new meta-algorithm for matching protein functional sites (active sites and ligand binding sites) based on an initial graph matching followed by refinement using a Markov chain Monte Carlo (MCMC) procedure. This procedure is an innovative extension to our recent work. The method accounts for the 3-dimensional structure of the site as well as the physico-chemical properties of the constituent amino acids. The MCMC procedure can lead to a significant increase in the number of significant matches compared to the graph method as measured independently by rigorously derived p-values. CONCLUSION: MCMC refinement step is able to significantly improve graph based matches. We apply the method to matching NAD(P)(H) binding sites within single Rossmann fold families, between different families in the same superfamily, and in different folds. Within families sites are often well conserved, but there are examples where significant shape based matches do not retain similar amino acid chemistry, indicating that even within families the same ligand may be bound using substantially different physico-chemistry. We also show that the procedure finds significant matches between binding sites for the same co-factor in different families and different folds.