Distinct 'pattern of autofluorescence' of acute ischemic stroke patients' skin and fingernails: A novel diagnostic biomarker for acute ischemic stroke
Wu, D.; Zhang, M.; Tao, Y.; Li, Y.; Zhang, S.; Zou, X.; Chen, X.; Ying, W.
Show abstract
AbstractEarly and economical diagnosis of acute ischemic stroke (AIS) is pivotal for therapeutic efficacy, particularly for the settings where medical imaging resource is deficient. We have obtained evidence supporting our hypothesis that collective properties of the green autofluorescence (AF) of the fingernails and certain skins positions may be a novel diagnostic biomarker for AIS: Both the green AF intensity and AF asymmetry of the AIS patients in their Index Fingernails and most examined skins positions were significantly higher than that of the healthy subjects and the Non-AIS subjects. ROC analyses and machine learning-based analyses on the AF properties showed that AUC was 0.93 and 0.87, respectively, for differentiating the AIS patients from the healthy subjects and for differentiating the AIS patients from the Non-AIS subjects. The AIS patients had significantly higher AF intensity and AF asymmetry at several examined positions, compared to those of the patients of Parkinsons disease, pulmonary infection and transient ischemic attack. The AUC was 0.79 - 0.88 for differentiating AIS patients from each of these diseases. There was evidence suggesting that the AF originates from keratins. Collectively, our study has indicated that the characteristic AISs Pattern of AF is a novel diagnostic biomarker for the disease. The Pattern of AF Technology holds excellent potential to become a new non-invasive, label-free and economical diagnostic approach for AIS, which is particularly valuable when MRI or CT imaging resource is deficient.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Mapping of single-cell landscape of acral melanoma and analysis of molecular regulatory network of tumor microenvironment 93%
- Single-cell Sequencing Highlights Heterogeneity and Malignant Progression in Actinic Keratosis and Cutaneous Squamous Cell Carcinoma 93%
- Derivation and Internal Validation of Prediction Models for Pulmonary Hypertension Risk Assessment in a Cohort Inhabiting Tibet, China 93%
Similar papers in this journal
- Multiscale Entropy Analysis of Retinal Signals Reveals Reduced Complexity in a Mouse Model of Alzheimer's Disease 92%
- Candidate genes associated with neurological manifestations of COVID-19: Meta-analysis using multiple computational approaches 92%
- Raman imaging analysis of microvesicular and macrovesicular lipid droplets in non-alcoholic fatty liver disease 92%
Similar papers in this journal
- Transcriptome analysis of sevoflurane exposure effects at the different brain regions 93%
- Identification of cuproptosis and ferroptosis-related subtypes and development of a prognostic signature in colon cancer 93%
- Research of the mechanism on miRNA193 in exosomes promotes cisplatin resistance in esophageal cancer cells 92%
Similar papers in this journal
- Empathic contagious pain and consolation in laboratory rodents: species and sex comparisons 90%
- Co-editing PINK1 and DJ-1 genes via AAV-delivered CRISPR/Cas9 system in adult monkey brains elicits classic Parkinsonian phenotypes 90%
- Feature-based Quality Assessment of Middle Cerebral Artery Occlusion Using 18F-fluorodeoxyglucose Positron Emission Tomography 89%
Similar papers in this journal
- The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis 90%
- Construction and Analysis of Protein-Protein Interaction Network of Non-Alcoholic Fatty Liver Disease 90%
- Systematic identification of A-to-I editing associated regulators from multiple human cancers 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.