Transcriptomic and machine learning analyses identify hub genes of metabolism and host immune response that are associated with the progression of breast capsular contracture

Machine Learning, Deep Learning, Artificial Intelligence and Aesthetic Plastic Surgery: A Qualitative Systematic Review

PURPOSE

This systematic review aims to assess the use of machine learning, deep learning, and artificial intelligence in aesthetic plastic surgery.

METHODS

This qualitative systematic review followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses reporting guideline. To analyze quality risk-of-bias assessment of all included articles, we used the ROBINS-I tool for non-randomized studies. We searched for studies with the following MeSH terms: Machine Learning OR Deep Learning OR Artificial intelligence AND Plastic surgery on MEDLINE/PubMed, EMBASE, and Cochrane Library, from inception until July 2024 without any filter applied.

RESULTS

A total of 2,148 studies were screened and 41 were fully reviewed. We conducted article extraction, screening, and full text review using the rayyan tool. Eighteen studies were ultimately included in this review, describing the use of machine learning, deep learning and artificial intelligence in aesthetic plastic surgery. All studies were published from 2019 to 2024. Articles varied regarding the population studied, type of machine learning (ML), Deep Learning Model (DLM), Artificial Intelligence (AI) used, and aesthetic plastic surgery type. Of the eighteen studies, we included the following aesthetic plastic surgeries: augmentation mastopexy, breast augmentation, reduction mammoplasty, rhinoplasty, facial rejuvenation surgery, including facelift surgery; blepharoplasty, and body contouring. Image-based with AI, ML, and DLMs algorithms were used in these studies to improve human decision-making and identified factors associated with postoperative complications.

CONCLUSION

AI, ML, and DL algorithms offer immense potential to transform the aesthetic plastic surgery field. By meticulously analyzing patient data, these technologies may, in the future, help optimize treatment plans, predict potential complications, and more clearly elucidate patient concerns, improving their ability to make informed decisions. The drawback, as with preoperative surgical simulation, is that patients may see an AI-generated image that is to their liking, but impossible to achieve; great care is needed when using such tools in order to not create unrealistic expectations. Ultimately, the old plastic surgery adage of ''under-promise and over-deliver'' will continue to hold true, at least for the foreseeable future.

LEVEL OF EVIDENCE III

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 . Study registration A review protocol for this systematic review was registered at PROSPERO CRD42024567461.

Comprehensive analysis and validation of TP73 as a biomarker for calcium oxalate nephrolithiasis using machine learning and in vivo and in vitro experiments

Calcium oxalate (CaOx) nephrolithiasis constitutes approximately 75% of nephrolithiasis cases, resulting from the supersaturation and deposition of CaOx crystals in renal tissues. Despite their prevalence, precise biomarkers for CaOx nephrolithiasis are lacking. With advances in high-throughput sequencing, we aimed to identify biomarkers of CaOx nephrolithiasis by combining two CaOx nephrolithiasis datasets (GSE73680 and GSE117518). Utilizing weighted gene co-expression network analysis (WGCNA) and four machine learning, we identified six hub genes (DLK2, BHLHA15, C12orf5, ICMT, LOXHD1, and TP73) as potential biomarkers. Additionally, CIBERSORT immune infiltration analysis suggested that these core genes may influence immune cell recruitment and infiltration in CaOx nephrolithiasis. Then, TP73 emerged as a significant hub gene in CaOx nephrolithiasis via receiver operating characteristic (ROC) analysis (AUC = 0.885). Furthermore, the role of TP73 was validated in CaOx nephrolithiasis rat models induced by 1% ethylene glycol, as well as clinical samples and renal tubular epithelial cell models treated with 1 mM oxalate. Immunohistochemistry, RNA-Sequencing, and RT-qPCR experiments demonstrated an increased expression of TP73 in CaOx nephrolithiasis rat models and clinical samples. After transfection with TP73 lentivirus, CCK-8 assays suggested that TP73 could inhibit the proliferation of HK-2 and NRK-52E cells. In oxalate-induced cell models, dihydroethidium staining and flow cytometry apoptosis assays indicated that TP73 could enhance ROS levels and cell apoptosis. In summary, our study preliminarily identified TP73 as a diagnostic biomarker and elucidated the promoting role of TP73 in CaOx nephrolithiasis, providing a deeper understanding of the clinical diagnosis and pathogenesis.

Applications of spatial transcriptomics and artificial intelligence to develop integrated management of pancreatic cancer

Cancer is a complex disease intrinsically associated with cellular processes and gene expression. With the development of techniques such as single-cell sequencing and sequential fluorescence in situ hybridization (seqFISH), it was possible to map the location of cells based on their gene expression with more precision. Moreover, in recent years, many tools have been developed to analyze these extensive datasets by integrating machine learning and artificial intelligence in a comprehensive manner. Since these tools analyze sequencing data, they offer the chance to analyze any tissue regardless of its origin. By applying this to cancer settings, spatial transcriptomic analysis based on artificial intelligence may help us understand cell-cell communications within the tumor microenvironment. Another advantage of this analysis is the identification of new biomarkers and therapeutic targets. The integration of such analysis with other omics data and with routine exams such as magnetic resonance imaging can help physicians with the earlier diagnosis of tumors as well as establish a more personalized treatment for pancreatic cancer patients. In this review, we give an overview description of pancreatic cancer, describe how spatial transcriptomics and artificial intelligence have been used to study pancreatic cancer and provide examples of how integrating these tools may help physicians manage pancreatic cancer in a more personalized approach.

Immunological profile of lactylation-related genes in Crohn's disease: a comprehensive analysis based on bulk and single-cell RNA sequencing data

BACKGROUND

Crohn's disease (CD) is a disease characterized by intestinal immune dysfunction, often accompanied by metabolic abnormalities. Disturbances in lactate metabolism have been found in the intestine of patients with CD, but studies on the role of lactate and related Lactylation in the pathogenesis of CD are still unknown.

METHODS

We identified the core genes associated with Lactylation by downloading and merging three CD-related datasets (GSE16879, GSE75214, and GSE112366) from the GEO database, and analyzed the functions associated with the hub genes and the correlation between their expression levels and immune infiltration through comprehensive analysis. We explored the Lactylation levels of different immune cells using single-cell data and further analyzed the differences in Lactylation levels between inflammatory and non-inflammatory sites.

RESULTS

We identified six Lactylation-related hub genes that are highly associated with CD. Further analysis revealed that these six hub genes were highly correlated with the level of immune cell infiltration. To further clarify the effect of Lactylation on immune cells, we analyzed single-cell sequencing data of immune cells from inflammatory and non-inflammatory sites in CD patients and found that there were significant differences in the levels of Lactylation between different types of immune cells, and that the levels of Lactylation were significantly higher in immune cells from inflammatory sites.

CONCLUSIONS

These results suggest that Lactylation-related genes and their functions are closely associated with changes in inflammatory cells in CD patients.