The purpose of this study was to verify the usefulness of machine learning (ML) for selection of risk factors and development of predictive models for patients with sarcopenia.We collected medical records from Korean postmenopausal women based on Korea National Health and Nutrition Examination Surveys. A training data set compiled from simple survey data was used to construct models based on popular ML algorithms (e.g., support vector machine, random forest [RF], and logistic regression).A total of 4020 patients ≥65 years of age were enrolled in this study. The study population consisted of 1698 (42.2%) male and 2322 (57.8%) female patients. The 10 most important risk factors in men were body mass index (BMI), red blood cell (RBC) count, blood urea nitrogen (BUN), vitamin D, ferritin, fiber intake (g/d), primary diastolic blood pressure, white blood cell (WBC) count, fat intake (g/d), age, glutamic-pyruvic transaminase, niacin intake (mg/d), protein intake (g/d), fasting blood sugar, and water intake (g/d). The 10 most important risk factors in women were BMI, water intake (g/d), WBC, RBC count, iron intake (mg/d), BUN, high-density lipoprotein, protein intake (g/d), fiber consumption (g/d), vitamin C intake (mg/d), parathyroid hormone, niacin intake (mg/d), carotene intake (μg/d), potassium intake (mg/d), calcium intake (mg/d), sodium intake (mg/d), retinol intake (μg/d), and age. A receiver operating characteristic (ROC) curve analysis found that the area under the ROC curve for each ML model was not significantly different within a gender.The most cost-effective method in clinical practice is to make feature selection using RF models and expert knowledge and to make disease prediction using verification by several ML models. However, the developed prediction model should be validated using additional studies.
Background The purpose of this study was to report the RNA sequencing profile according to the presence or absence of sarcopenia in elderly patients with osteoporotic hip fracture. Therefore, an important genetic factor candidate for sarcopenia causing hip fracture in elderly with osteoporosis has been identified. Methods The patient group involved subjects over 65 years who had undergone hip fracture surgery. Among 323 hip fracture (HF) patients identified from May 2017 to December 2019, 162 HF patients (90 non-sarcopenia and 72 sarcopenia groups), excluding subjects with high energy trauma and non-osteoporosis, were finally included in the analysis. For RNA sequencing, each patient with hand grip strength (HGS) values in the top 10% were enrolled in the control group and with the bottom 10% in the patient group. After excluding patients with poor tissue quality, 6 patients and 5 patients were selected for sarcopenia and non-sarcopenia groups, respectively. For qPCR validation, each patient with HGS values in the top 20% and bottom 20% was enrolled in the control and patient groups, respectively. After excluding patients with poor tissue quality, 12 patients and 12 patients were enrolled in the sarcopenia and non-sarcopenia groups, respectively. Sarcopenia was defined according to the Asia Working Group for Sarcopenia (AWGS) criteria for low muscle strength (hand grip strength below 18 kg in women and 28 kg in men) and low muscle mass (SMI below 5.4 kg/m 2 in women and 7.0 kg/m 2 in men). The libraries were prepared for 100 bp paired-end sequencing using TruSeq Stranded mRNA Sample Preparation Kit (Illumina, CA, USA). The gene expression counts were supplied to Deseq2 to extract possible gene sets as differentially expressed genes (DEG) that discriminate between sarcopenia and non-sarcopenia groups that were carefully assigned by clinical observation. For the classification of the candidate genes from DEG analysis, we used the public databases; gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG). Quantitative real-time PCR was performed for validation. Results Samples collected were subjected to RNAseq using the Illumina platform. A total of 11 samples from both sarcopenia and non-sarcopenia groups were sequenced. Fifteen genes (RUNX 1, NGFR, CH3L1, BCL3, PLA2G2A, MYBPH, TEP1, SEMA6B, CSPG4, ACSL5, SLC25A3, NDUFB5, CYC1, ACAT1, and TCAP) were identified as differentially expressed genes (DEG) in both the groups. In the qPCR results, the expression levels of SLC25A3 and TCAP gene in the OS group were significantly lower than in the non-OS groups whereas an increase in RUNX1 mRNA level was observed in the OS samples ( p < 0.05). Conclusions In summary, this study detected gene expression difference according to the p...
Background Femoral head osteonecrosis (FHON) is a worldwide challenging clinical topic. Steroid use is one of the main etiologies of FHON. There are several genetic variants associated with FHON. Therefore, the purpose of this umbrella review was to provide a comprehensive summary of a meta-analysis and systematic review of genetic variations associated with nonsteroidal and steroid-induced FHON. Methods The eligible studies were selected from the PubMed and MEDLINE databases for the collection of diverse systematic meta-analyses and reviews. The genetic main effect score was assigned using the Human Genome Epidemiology Network’s Venice criteria to assess the cumulative evidence on the effects of a single nucleotide polymorphism (SNP) on FHON. Results Eight articles reported the meta-analysis of candidate SNP-based studies covering eight genes and 13 genetic variants. In the nonsteroid-induced FHON genetic variants including rs2012390 and rs11225394 in MMP8, rs1800629 and rs361525 in tumor necrosis factor (TNF)-α, VNTR in intron 4, rs1799983 and rs2070744 in endothelial nitric oxide synthase (eNOS), rs2010963 in vascular endothelial growth factor (VEGF), and rs6025 in factor V showed significance in each reference. The steroid-induced FHON genetic variants including rs693 and rs1042031 in apolipoprotein (Apo)B, rs1045642 in ABCB1, and rs1799889 in PAI-1 showed significance in each reference. Conclusion Based on the systematic review conducted in this study, we organized the genomes associated with FHON and looked at each contribution. Our results could give an integrative approach for understanding the mechanism of FHON etiology. It is expected that these results could contribute to the strategy of prediagnosis, evaluating the individual risk of nonsteroid-induced and steroid-induced FHON. Level of Evidence: Level I.
Stomatal observation and automatic stomatal detection are useful analyses of stomata for taxonomic, biological, physiological, and eco-physiological studies. We present a new clearing method for improved microscopic imaging of stomata in soybean followed by automated stomatal detection by deep learning. We tested eight clearing agent formulations based upon different ethanol and sodium hypochlorite (NaOCl) concentrations in order to improve the transparency in leaves. An optimal formulation—a 1:1 (v/v) mixture of 95% ethanol and NaOCl (6–14%)—produced better quality images of soybean stomata. Additionally, we evaluated fixatives and dehydrating agents and selected absolute ethanol for both fixation and dehydration. This is a good substitute for formaldehyde, which is more toxic to handle. Using imaging data from this clearing method, we developed an automatic stomatal detector using deep learning and improved a deep-learning algorithm that automatically analyzes stomata through an object detection model using YOLO. The YOLO deep-learning model successfully recognized stomata with high mAP (~0.99). A web-based interface is provided to apply the model of stomatal detection for any soybean data that makes use of the new clearing protocol.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.