The role of machine learning in advancing diabetic foot: a review

Frontiers in Endocrinology, Journal Year: 2024, Volume and Issue: 15

Published: April 29, 2024

Background Diabetic foot complications impose a significant strain on healthcare systems worldwide, acting as principal cause of morbidity and mortality in individuals with diabetes mellitus. While traditional methods diagnosing treating these conditions have faced limitations, the emergence Machine Learning (ML) technologies heralds new era, offering promise revolutionizing diabetic care through enhanced precision tailored treatment strategies. Objective This review aims to explore transformative impact ML managing complications, highlighting its potential advance diagnostic accuracy therapeutic approaches by leveraging developments medical imaging, biomarker detection, clinical biomechanics. Methods A meticulous literature search was executed across PubMed, Scopus, Google Scholar databases identify pertinent articles published up March 2024. The strategy carefully crafted, employing combination keywords such “Machine Learning,” “Diabetic Foot,” Foot Ulcers,” Care,” “Artificial Intelligence,” “Predictive Modeling.” offers an in-depth analysis foundational principles algorithms that constitute ML, placing special emphasis their relevance sciences, particularly within specialized domain pathology. Through incorporation illustrative case studies schematic diagrams, endeavors elucidate intricate computational methodologies involved. Results has proven be invaluable deriving critical insights from complex datasets, enhancing both planning for management. highlights efficacy decision-making, underscored comparative analyses prognostic assessments applications care. Conclusion culminates prospective assessment trajectory realm We believe despite challenges limitations ethical considerations, remains at forefront paradigms management are globally applicable precision-oriented. technological evolution unprecedented possibilities opportunities patient

Language: Английский

---

A novel diabetic foot ulcer diagnostic model: identification and analysis of genes related to glutamine metabolism and immune infiltration

BMC Genomics, Journal Year: 2024, Volume and Issue: 25(1)

Published: Jan. 30, 2024

Abstract Background Diabetic foot ulcer (DFU) is one of the most common and severe complications diabetes, with vascular changes, neuropathy, infections being primary pathological mechanisms. Glutamine (Gln) metabolism has been found to play a crucial role in diabetes complications. This study aims identify validate potential Gln biomarkers associated DFU through bioinformatics machine learning analysis. Methods We downloaded two microarray datasets related patients from Gene Expression Omnibus (GEO) database, namely GSE134431, GSE68183, GSE80178. From GSE134431 dataset, we obtained differentially expressed Gln-metabolism genes (deGlnMRGs) between normal controls. analyzed correlation deGlnMRGs immune cell infiltration status. also explored relationship GlnMRGs molecular clusters Notably, WGCNA (DEGs) within specific clusters. Additionally, conducted GSVA annotate enriched genes. Subsequently, constructed screened best model. Finally, validated predictions' accuracy using nomogram, calibration curves, decision curve analysis (DCA), GSE80178 dataset. Results In both control groups, confirmed presence an activated response. 20 deGlnMRGs, including CTPS1, NAGS, SLC7A11, GGT1, GCLM, RIMKLA, ARG2, ASL, ASNS, ASNSD1, PPAT, GLS2, GLUD1, MECP2, ASS1, PRODH, CTPS2, ALDH5A1, DGLUCY, SLC25A12. Furthermore, were identified DFU. Immune indicated heterogeneity these established Support Vector Machine (SVM) model based on 5 (R3HCC1, ZNF562, MFN1, DRAM1, PTGDS), which exhibited excellent performance external validation datasetGSE134431, (AUC = 0.929). Conclusion five DFU, revealing novel therapeutic targets for immune-inflammatory cells plays progression

Language: Английский

---

Identifying and Validating GSTM5 as an Immunogenic Gene in Diabetic Foot Ulcer Using Bioinformatics and Machine Learning

Journal of Inflammation Research, Journal Year: 2023, Volume and Issue: Volume 16, P. 6241 - 6256

Published: Dec. 1, 2023

A diabetic foot ulcer (DFU) is a serious, long-term condition associated with significant risk of disability and mortality. However, research on its biomarkers still limited. This study utilizes bioinformatics machine learning methods to identify immune-related for DFU validates them through external datasets animal experiments.This used analyze microarray data from the Gene Expression Omnibus (GEO) database key genes DFU. Animal experiments were conducted validate these findings. employs GSE68183 GSE80178 retrieved GEO as training dataset building gene model, after conducting differential analysis data, this package glmnet e1071 construct LASSO SVM-RFE models, respectively. Subsequently, we validated model using set validation (GSE134431). We enrichment analysis, including GSEA GSVA, genes. also performed immune functional Finally, immunohistochemistry (IHC) genes.This identifies GSTM5 potential target in methods. Subsequent IHC confirms critical biomarker The may be T cells regulatory (Tregs) follicular helper, it influences NF-κB, GnRH, MAPK signaling pathway.This identified finding potentially provide therapy

Language: Английский

---

A hydrogen generator composed of poly (lactic-co-glycolic acid) nanofibre membrane loaded iron nanoparticles for infectious diabetic wound repair

Journal of Colloid and Interface Science, Journal Year: 2024, Volume and Issue: 672, P. 266 - 278

Published: May 31, 2024

Language: Английский

---

Identification and validation of mitochondrial dynamics-related genes in patients with acute myocardial infarction-a bioinformatics analysis

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 2, 2025

Recent studies highlight the link between cardiovascular disease and mitochondrial dynamics. This study sought biomarkers of dynamics in acute myocardial infarction (AMI) to guide more precise clinical management. AMI-related datasets (GSE62646 GSE59867) 50 dynamics-related genes (MD-RGs) were derived from public databases. Firstly, based on MD-RGs, AMI samples GSE62646 classified into high- low-scoring groups by single-sample gene set enrichment analysis. The differentially expressed (DEGs) incorporated machine learning algorithms. Subsequent expression level receiver operating characteristic (ROC) analyses identified biomarkers. Furthermore, relationship was analyzed analysis, immune infiltration correlation analysis m6A regulators. Finally, biomarker verified reverse transcription quantitative PCR (RT-qPCR). In this study, COX7B SNORD54 as associated with AMI. ROC curves showed that two could better differentiate control samples, subsequent nomogram created integrating highly accurate predicting revealed co-enrich pathways for included “oxidative phosphorylation” “Notch signaling pathway”. Notably, six regulators (HNRNPC, KIAA1429, METTL3, WTAP, YTHDC1, YTHDC2) found be significantly under-expressed samples. RT-PCR demonstrated levels downregulated compared controls. recognized AMI, presenting potential applications advance understanding

Language: Английский

---

Metrnl Ameliorates Ferroptosis in Model of Diabetic Foot Ulcer Through the Inhibition of Mitochondrial Damage via LKB1/AMPK Signaling

Experimental and Clinical Endocrinology & Diabetes, Journal Year: 2025, Volume and Issue: 133(03), P. 120 - 132

Published: March 1, 2025

Abstract Diabetic foot ulcer (DFU) represents a severe complication of diabetes, mainly caused by peripheral vascular occlusion and infection, presenting significant clinical challenges in treatment potentially resulting gangrene, amputation, or even fatality. This study aimed to investigate the involvement underlying mechanisms Meteorin-like (Metrnl) pathogenic process DFU. Mice underwent diabetes induction streptozotocin, while human umbilical vein endothelial cells (HUVECs) were exposed 5.5, 10, 20 40 mM glucose. HUVECs transfected with negative Metrnl si-nc si-Metrnl plasmids via Lipofectamine 2000. The expression was down-regulated both patients murine model Elevated glucose levels diminished through enhanced ubiquitination. suppression exacerbated mouse alleviated oxidative stress ferroptosis DFU inhibiting mitochondrial damage. induced liver kinase B1 (LKB1)/AMP-activated protein (AMPK) signaling model. LKB1 attenuated effects on data cumulatively demonstrate that ameliorates damage LKB1/AMPK signaling, suggesting targeting may emerge as potential preventive approach against other diabetes.

Language: Английский

---

Research progress on and molecular mechanism of vacuum sealing drainage in the treatment of diabetic foot ulcers

Frontiers in Surgery, Journal Year: 2024, Volume and Issue: 11

Published: Feb. 23, 2024

Diabetic foot ulcers (DFUs) are common chronic wounds and a complication of diabetes. The is the main site diabetic ulcers, which involve small medium-sized arteries, peripheral nerves, microcirculation, among others. DFUs prone to coinfections affect many patients. In recent years, interdisciplinary research combining medicine material science has been increasing achieved significant clinical therapeutic effects, application vacuum sealing drainage (VSD) in treatment typical representative this progress, but mechanism action remains unclear. review, we integrated bioinformatics literature found that ferroptosis an important signaling pathway through VSD promotes healing System Xc-GSH-GPX4 NAD(P)H-CoQ10-FSP1 axes pathway, speculate most likely inhibit promote DFU above axes. addition, some classical pathways, such as TNF, NF-κB, Wnt/β-catenin also involved VSD-mediated promotion healing. We compiled reviewed progress from studies on VSD, information provides reference for study DFUs.

Language: Английский

---

Identification and validation of biomarkers associated with mitochondrial dysfunction and ferroptosis in rat spinal cord injury

Frontiers in Neurology, Journal Year: 2025, Volume and Issue: 16

Published: March 17, 2025

Mitochondrial dysfunction and ferroptosis have been implicated in the pathophysiological processes following spinal cord injury (SCI), with evidence suggesting their interplay influences neuronal cell survival repair mechanisms. This study seeks to identify mitochondria- ferroptosis-related biomarkers through comprehensive bioinformatics analysis. Mitochondria- ferroptosis-associated differentially expressed genes (DEGs) were identified integration of differential expression analysis weighted gene co-expression network Two machine learning algorithms, least absolute shrinkage selection operator (LASSO) Boruta, employed isolate SCI-associated feature genes. Biomarkers subsequently by analyzing levels. An artificial neural (ANN) diagnostic model was constructed predict SCI likelihood based on these biomarkers. Further evaluations performed using enrichment analysis, immune infiltration profiling, molecular modulation assessment, drug prediction. The biomarkers' levels validated RT-qPCR. In this study, two biomarkers, Hcrt Cdca2, linked mitochondrial function SCI, found be highly samples. Tissue-specific from GTEx database revealed brain tissues. ANN model, accurately discriminated between control Enrichment highlighted several co-enriched pathways for including "ubiquitin-mediated proteolysis," "endocytosis," "neurotrophin signaling pathway." Immune Wilcoxon test, demonstrated significant differences T follicular helper levels, which lower samples compared controls. Notably, cells exhibited a positive correlation negative Cdca2. Furthermore, seven transcription factors, CEBPB, FOXC1, GATA2, as potential co-regulators Drug prediction stable interactions Cdca2 pinosylvin, zinc acetate dihydrate, hydroquinone, lucanthone, dasatinib. RT-qPCR validation confirmed patterns alignment dataset, showing statistically differences. identifies related providing new insights diagnosis mechanistic understanding SCI.

Language: Английский

---

The mechanistic study of codonopsis pilosula on laryngeal squamous cell carcinoma based on network pharmacology and experimental validation

Frontiers in Pharmacology, Journal Year: 2025, Volume and Issue: 16

Published: April 25, 2025

Laryngeal squamous cell carcinoma (LSCC) is a common malignant tumor of the head and neck, with poor prognosis for advanced patients, there an urgent need to find new treatment strategies. Codonopsis pilosula, traditional Chinese medicinal herb, possesses various pharmacological activities, but its antitumor effects mechanisms in LSCC are still unclear. The aim this study was systematically investigate potential mechanism pilosula LSCC. In study, we screened effective compounds targets by TCMSP, ETCM BATMAN-TCM databases, related combining DisGeNET, GeneCards database Cytoscape software. KEGG pathway enrichment analysis utilized explore signaling pathways. core were further based on TCGA GEO analysis, molecular docking carried out predict their binding ability compounds. presence key verified LC-MS, MAPK3 expression detected qPCR tissues, knockdown proliferation, migration, invasion, cycle, apoptosis cells evaluated cellular function assays. 22 that might regulate network pharmacology. showed pilosula-LSCC mainly involved HIF-1, TNF, IL-17 FoxO Based identified as target pilosula-LSCC. results variety from had strong abilities MAPK3, among them, Caprylic Acid, Emodin Luteolin have been confirmed LC-MS. QPCR indicated highly expressed tissues. significantly inhibits migration invasion. It also suppresses growth blocking cycle inducing apoptosis. exerts through regulation multiple pathways, providing theoretical basis clinical application.

Language: Английский

---

The role of programmed cell death in diabetic foot ulcers

International Wound Journal, Journal Year: 2023, Volume and Issue: 21(2)

Published: Sept. 22, 2023

Diabetic foot ulcer, is a chronic complication afflicting individuals with diabetes, continue to increase worldwide, immensely burdening society. Programmed cell death, which includes apoptosis, autophagy, ferroptosis, necroptosis and pyroptosis, has been increasingly implicated in the pathogenesis of diabetic ulcer. This review based on an exhaustive examination literature 'programmed death' 'diabetic ulcers' via PubMed. The findings revealed that natural bioactive compounds, noncoding RNAs certain proteins play crucial roles healing ulcers through various forms programmed including ferroptosis pyroptosis.

Language: Английский

---