-
Clinics in Dermatology Jun 2024Psoriasis is an immune-mediated skin disease affecting approximately 3% of the global population. Proper management of this condition necessitates the assessment of the...
Psoriasis is an immune-mediated skin disease affecting approximately 3% of the global population. Proper management of this condition necessitates the assessment of the Body Surface Area (BSA) and the involvement of nails and joints. Recently, the integration of Natural Language Processing (NLP) with Electronic Medical Records (EMRs) has shown promise in advancing disease classification and research. This study evaluates the performance of ChatGPT-4, a commercial AI platform, in analyzing unstructured EMR data of psoriasis patients, particularly in identifying affected body areas.
PubMed: 38909857
DOI: 10.1016/j.clindermatol.2024.06.018 -
The Journal of Investigative Dermatology Jun 2024Federated Learning (FL) enables multiple institutes to train models collaboratively without sharing private data. Current FL research focuses on communication...
Federated Learning (FL) enables multiple institutes to train models collaboratively without sharing private data. Current FL research focuses on communication efficiency, privacy protection, and personalization and assumes that the data of FL have already been ideally collected. In medical scenarios, however, data annotation demands both expertise and intensive labor, which is a critical problem in FL. Active learning (AL), has shown promising performance in reducing the number of data annotations in medical image analysis. We propose a federated AL (FedAL) framework in which AL is executed periodically and interactively under FL. We exploit a local model in each hospital and a global model acquired from FL to construct an ensemble. We use ensemble-entropy-based AL as an efficient data-annotation strategy in FL. Therefore, our FedAL framework can decrease the amount of annotated data and preserve patient privacy while maintaining the performance of FL. To our knowledge, this FedAL framework applied to medical images has not been previously reported. We validated our framework on real-world dermoscopic datasets. Using only 50% of samples, our framework was able to achieve state-of-the-art performance on a skin-lesion classification task. Our framework performed better than several state-of-the-art AL methods under FL and achieved comparable performance to full-data FL.
PubMed: 38909844
DOI: 10.1016/j.jid.2024.05.023 -
Computers in Biology and Medicine Jun 2024Melanoma, one of the deadliest types of skin cancer, accounts for thousands of fatalities globally. The bluish, blue-whitish, or blue-white veil (BWV) is a critical...
Melanoma, one of the deadliest types of skin cancer, accounts for thousands of fatalities globally. The bluish, blue-whitish, or blue-white veil (BWV) is a critical feature for diagnosing melanoma, yet research into detecting BWV in dermatological images is limited. This study utilizes a non-annotated skin lesion dataset, which is converted into an annotated dataset using a proposed imaging algorithm (color threshold techniques) on lesion patches based on color palettes. A Deep Convolutional Neural Network (DCNN) is designed and trained separately on three individual and combined dermoscopic datasets, using custom layers instead of standard activation function layers. The model is developed to categorize skin lesions based on the presence of BWV. The proposed DCNN demonstrates superior performance compared to the conventional BWV detection models across different datasets. The model achieves a testing accuracy of 85.71 % on the augmented PH2 dataset, 95.00 % on the augmented ISIC archive dataset, 95.05 % on the combined augmented (PH2+ISIC archive) dataset, and 90.00 % on the Derm7pt dataset. An explainable artificial intelligence (XAI) algorithm is subsequently applied to interpret the DCNN's decision-making process about the BWV detection. The proposed approach, coupled with XAI, significantly improves the detection of BWV in skin lesions, outperforming existing models and providing a robust tool for early melanoma diagnosis.
PubMed: 38905895
DOI: 10.1016/j.compbiomed.2024.108758 -
JMIR Medical Informatics Jun 2024Dermoscopy is a growing field that uses microscopy to allow dermatologists and primary care physicians to identify skin lesions. For a given skin lesion, a wide variety...
BACKGROUND
Dermoscopy is a growing field that uses microscopy to allow dermatologists and primary care physicians to identify skin lesions. For a given skin lesion, a wide variety of differential diagnoses exist, which may be challenging for inexperienced users to name and understand.
OBJECTIVE
In this study, we describe the creation of the dermoscopy differential diagnosis explorer (D3X), an ontology linking dermoscopic patterns to differential diagnoses.
METHODS
Existing ontologies that were incorporated into D3X include the elements of visuals ontology and dermoscopy elements of visuals ontology, which connect visual features to dermoscopic patterns. A list of differential diagnoses for each pattern was generated from the literature and in consultation with domain experts. Open-source images were incorporated from DermNet, Dermoscopedia, and open-access research papers.
RESULTS
D3X was encoded in the OWL 2 web ontology language and includes 3041 logical axioms, 1519 classes, 103 object properties, and 20 data properties. We compared D3X with publicly available ontologies in the dermatology domain using a semiotic theory-driven metric to measure the innate qualities of D3X with others. The results indicate that D3X is adequately comparable with other ontologies of the dermatology domain.
CONCLUSIONS
The D3X ontology is a resource that can link and integrate dermoscopic differential diagnoses and supplementary information with existing ontology-based resources. Future directions include developing a web application based on D3X for dermoscopy education and clinical practice.
PubMed: 38904996
DOI: 10.2196/49613 -
Frontiers in Microbiology 2024The concept of a sterile uterus was challenged by recent studies that have described the microbiome of the virgin and pregnant uterus for species including humans and...
INTRODUCTION
The concept of a sterile uterus was challenged by recent studies that have described the microbiome of the virgin and pregnant uterus for species including humans and cattle. We designed two studies that tested whether the microbiome is introduced into the uterus when the virgin heifer is first inseminated and whether the origin of the microbiome is the vagina/cervix.
METHODS
The uterine microbiome was measured immediately before and after an artificial insemination (AI; Study 1; = 7 AI and = 6 control) and 14 d after insemination (Study 2; = 12 AI and = 12 control) in AI and non-AI (control) Holstein heifers. A third study (Study 3; = 5 Holstein heifers) that included additional negative controls was subsequently conducted to support the presence of a unique microbiome within the uterus despite the low microbial biomass and regardless of insemination. Traditional bacteriological culture was performed in addition to 16S rRNA gene sequencing on the same samples to determine whether there were viable organisms in addition to those detected based on DNA sequencing (16S rRNA gene sequence).
RESULTS AND DISCUSSION
Inseminating a heifer did not lead to a large change in the microbiome when assessed by traditional methods of bacterial culture or metataxonomic (16S rRNA gene) sequencing (results of Studies 1 and 2). Very few bacteria were cultured from the body or horn of the uterus regardless of whether an AI was or was not (negative control) performed. The cultured bacterial genera (e.g., , and ) were typical of those found in the soil, environment, skin, mucous membranes, and urogenital tract of animals. Metataxonomic sequencing of 16S rRNA gene generated a large number of amplicon sequence variants (ASV), but these larger datasets that were based on DNA sequencing did not consistently demonstrate an effect of AI on the abundance of ASVs across all uterine locations compared with the external surface of the tract (e.g., perimetrium; positive control samples for environment contamination during slaughter and collection). Major genera identified by 16S rRNA gene sequencing overlapped with those identified with bacterial culture and included , and .
PubMed: 38903779
DOI: 10.3389/fmicb.2024.1385505 -
Frontiers in Chemistry 2024This work provides a brief comparative analysis of the influence of heat creation on micropolar blood-based unsteady magnetised hybrid nanofluid flow over a curved...
This work provides a brief comparative analysis of the influence of heat creation on micropolar blood-based unsteady magnetised hybrid nanofluid flow over a curved surface. The Powell-Eyring fluid model was applied for modelling purposes, and this work accounted for the impacts of both viscous dissipation and Joule heating. By investigating the behaviours of Ag and TiO nanoparticles dispersed in blood, we aimed to understand the intricate phenomenon of hybridisation. A mathematical framework was created in accordance with the fundamental flow assumptions to build the model. Then, the model was made dimensionless using similarity transformations. The problem of a dimensionless system was then effectively addressed using the homotopy analysis technique. A cylindrical surface was used to calculate the flow quantities, and the outcomes were visualised using graphs and tables. Additionally, a study was conducted to evaluate skin friction and heat transfer in relation to blood flow dynamics; heat transmission was enhanced to raise the Biot number values. According to the findings of this study, increasing the values of the unstable parameters results in increase of the blood velocity profile.
PubMed: 38903202
DOI: 10.3389/fchem.2024.1397066 -
DrugSK: A Stacked Ensemble Learning Framework for Predicting Drug Combinations of Multiple Diseases.Journal of Chemical Information and... Jun 2024Combination therapy is an important direction of continuous exploration in the field of medicine, with the core goals of improving treatment efficacy, reducing adverse...
Combination therapy is an important direction of continuous exploration in the field of medicine, with the core goals of improving treatment efficacy, reducing adverse reactions, and optimizing clinical outcomes. Machine learning technology holds great promise in improving the prediction of drug synergy combinations. However, most studies focus on single disease-oriented collaborative predictive models or involve excessive feature categories, making it challenging to predict the majority of new drugs. To address these challenges, the DrugSK comprehensive model was developed, which utilizes SMILES-BERT to extract structural information from 3492 drugs and trains on reactions from 48,756 drug combinations. DrugSK is an integrated learning model capable of predicting interactions among various drug categories. First, the primary learner is trained from the initial data set. Random forest, support vector machine, and XGboost model are selected as primary learners and logistic regression as secondary learners. A new data set is then "generated" to train level 2 learners, which can be thought of as a prediction for each model. Finally, the results are filtered using logistic regression. Furthermore, the combination of the new antibacterial drug Drafloxacin with other antibacterial agents was tested. The synergistic effect of Drafloxacin and Isavuconazonium in the fight against has been confirmed, providing enlightenment for the clinical treatment of skin infection. DrugSK's prediction is accurate in practical application and can also predict the probability of the outcome. In addition, the tendency of Drafloxacin and antifungal drugs to be synergistic was found. The development of DrugSK will provide a new blueprint for predicting drug combination synergies.
PubMed: 38900583
DOI: 10.1021/acs.jcim.4c00296 -
Medical Image Analysis Jun 2024Although the U-shape networks have achieved remarkable performances in many medical image segmentation tasks, they rarely model the sequential relationship of...
Although the U-shape networks have achieved remarkable performances in many medical image segmentation tasks, they rarely model the sequential relationship of hierarchical layers. This weakness makes it difficult for the current layer to effectively utilize the historical information of the previous layer, leading to unsatisfactory segmentation results for lesions with blurred boundaries and irregular shapes. To solve this problem, we propose a novel dual-path U-Net, dubbed IU-Net. The newly proposed network encourages historical information re-usage and re-exploration through rich information interaction among the dual paths, allowing deep layers to learn more comprehensive features that contain both low-level detail description and high-level semantic abstraction. Specifically, we introduce a multi-functional information interaction module (MFII), which can model cross-path, cross-layer, and cross-path-and-layer information interactions via a unified design, making the proposed IU-Net behave similarly to an unfolded RNN and enjoying its advantage of modeling time sequence information. Besides, to further selectively and sensitively integrate the information extracted by the encoder of the dual paths, we propose a holistic information fusion and augmentation module (HIFA), which can efficiently bridge the encoder and the decoder. Extensive experiments on four challenging tasks, including skin lesion, polyp, brain tumor, and abdominal multi-organ segmentation, consistently show that the proposed IU-Net has superior performance and generalization ability over other state-of-the-art methods. The code is available at https://github.com/duweidai/I2U-Net.
PubMed: 38897032
DOI: 10.1016/j.media.2024.103241 -
Annals of Plastic Surgery Jun 2024Hyperpigmentation is a skin disorder characterized by a localized darkening of the skin due to increased melanin production. When patients fail first line topical...
BACKGROUND
Hyperpigmentation is a skin disorder characterized by a localized darkening of the skin due to increased melanin production. When patients fail first line topical treatments, secondary treatments such as chemical peels and lasers are offered. However, these interventions are not devoid of risks and are associated with postinflammatory hyperpigmentation. In the quest for novel therapeutic potentials, this study aims to investigate computational methods in the identification of new targeted therapies in the treatment of hyperpigmentation.
METHODS
We used a comprehensive approach, which integrated text mining, interpreting gene lists through enrichment analysis and integration of diverse biological information (GeneCodis), protein-protein association networks and functional enrichment analyses (STRING), and plug-in network centrality parameters (Cytoscape) to pinpoint genes closely associated with hyperpigmentation. Subsequently, analysis of drug-gene interactions to identify potential drugs (Cortellis) was utilized to select drugs targeting these identified genes. Lastly, we used Deep Learning Based Drug Repurposing Toolkit (DeepPurpose) to conduct drug-target interaction predictions to ultimately identify candidate drugs with the most promising binding affinities.
RESULTS
Thirty-four hyperpigmentation-related genes were identified by text mining. Eight key genes were highlighted by utilizing GeneCodis, STRING, Cytoscape, gene enrichment, and protein-protein interaction analysis. Thirty-five drugs targeting hyperpigmentation-associated genes were identified by Cortellis, and 29 drugs, including 16 M2PK1 inhibitors, 11 KRAS inhibitors, and 2 BRAF inhibitors were recommended by DeepPurpose.
CONCLUSIONS
The study highlights the promise of advanced computational methodology for identifying potential treatments for hyperpigmentation.
PubMed: 38896860
DOI: 10.1097/SAP.0000000000004007 -
Science Advances Jun 2024Skin-like soft optical metamaterials with broadband modulation have been long pursued for practical applications, such as cloaking and camouflage. Here, we propose a...
Skin-like soft optical metamaterials with broadband modulation have been long pursued for practical applications, such as cloaking and camouflage. Here, we propose a skin-like metamaterial for dual-band camouflage based on unique Au nanoparticles assembled hollow pillars (NPAHP), which are implemented by the bottom-up template-assisted self-assembly processes. This dual-band camouflage realizes simultaneously high visible absorptivity (~0.947) and low infrared emissivity (~0.074/0.045 for mid-/long-wavelength infrared bands), ideal for visible and infrared dual-band camouflage at night or in outer space. In addition, this self-assembled metamaterial, with a micrometer thickness and periodic through-holes, demonstrates superior skin-like attachability and permeability, allowing close attachment to a wide range of surfaces including the human body. Last but not least, benefiting from the extremely low infrared emissivity, the skin-like metamaterial exhibits excellent high-temperature camouflage performance, with radiation temperature reduction from 678 to 353 kelvin. This work provides a new paradigm for skin-like metamaterials with flexible multiband modulation for multiple application scenarios.
PubMed: 38896621
DOI: 10.1126/sciadv.adl1896