Objective:To construct a frailty risk prediction model for elderly patients with CHD based on machine learning, to address the limitations of existing tools and provide evidence-based support for clinical practice.Methods:A retrospective study was conducted on elderly CHD patients hospitalized at the Heart Center of the First Affiliated Hospital of Henan University of Chinese Medicine from September 2023 to March 2024. Meta-analysis and expert meetings were used to identify the risk factors for frailty in elderly CHD patients. Three machine learning algorithms, Logistic Regression, Random Forest, and Support Vector Machine, were used to construct predictive models using R 4.3.1 software. The predictive performance of the models was evaluated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC).Results:A total of 490 elderly CHD patients were included, with 267 males and 223 females, and an age of (71.02 ± 7.73) years. Among them, 160 patients (32.7%) developed frailty. Of the constructed models, the Random Forest model demonstrated the best predictive performance, with an accuracy of 0.703, recall of 0.629, and F1 score of 0.741, while the AUC was 0.811 (95% CI 0.762-0.850). Conclusions:The Random Forest model exhibited good predictive performance in assessing frailty risk in elderly CHD patients, with high accuracy and reliability. Future external validation studies can further assess its applicability and stability in different populations.

Objective:To construct a frailty risk prediction model for elderly patients with CHD based on machine learning, to address the limitations of existing tools and provide evidence-based support for clinical practice.Methods:A retrospective study was conducted on elderly CHD patients hospitalized at the Heart Center of the First Affiliated Hospital of Henan University of Chinese Medicine from September 2023 to March 2024. Meta-analysis and expert meetings were used to identify the risk factors for frailty in elderly CHD patients. Three machine learning algorithms, Logistic Regression, Random Forest, and Support Vector Machine, were used to construct predictive models using R 4.3.1 software. The predictive performance of the models was evaluated using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC).Results:A total of 490 elderly CHD patients were included, with 267 males and 223 females, and an age of (71.02 ± 7.73) years. Among them, 160 patients (32.7%) developed frailty. Of the constructed models, the Random Forest model demonstrated the best predictive performance, with an accuracy of 0.703, recall of 0.629, and F1 score of 0.741, while the AUC was 0.811 (95% CI 0.762-0.850). Conclusions:The Random Forest model exhibited good predictive performance in assessing frailty risk in elderly CHD patients, with high accuracy and reliability. Future external validation studies can further assess its applicability and stability in different populations.

OBJECTIVE To establish the quality standard of Clinopodium gracile. METHODS Ten batches of C. gracile were collected to perform appearance and property identification， microscopic identification and thin layer chromatography （TLC） identification. Moisture， total ash， acid-insoluble ash and dilute ethanol extract were detected， and the content of rosmarinic acid was determined by HPLC. RESULTS The stem of C. gracile was slender， square columnar， covered by white fluff， the surface was grayish green or greenish brown； epidermal cells， non-glandular hairs， cortical cells and so on were seen in the cross section of the stem. Non-glandular hairs， ducts， wood fibers， mesophyll cells and so on could be seen in the powder. Results of TLC identification showed that there were spots of the same color in the chromatographic position corresponding to the chromatographic position of buddlejasaponin Ⅳb control. The contents of water， total ash， acid-insoluble ash， dilute ethanol extract and rosmarinic acid in 10 batches of samples were 8.69%-12.33%， 5.96%-13.33%， 0.14%-3.29%， 18.57%-32.61%， 0.35%-0.82%， respectively. The average values were 10.10%， 9.73%， 1.06%， 23.54% and 0.56%， respectively. CONCLUSIONS The established method can be used for quality control of C. gracile. It is preliminarily proposed that the ash content in the herb should not exceed 12.0%， the total ash content should not exceed 12.0%， the acid-insoluble ash content should not exceed 1.5%， the dilute ethanol extract should not be less than 18.0%， and the rosmarinic acid content should not be less than 0.45%.

OBJECTIVE To explore the material basis and mechanism of expectorant and cough relief effects of the fruits of Phellodendron chinense var. glabriusulum Schneid. METHODS The expectorant and cough relief effects of volatile oil and water decoction of the fruits of P. chinense var. glabriusulum Schneid. were studied by ammonia water cough induction and drug expectorant model mice experiments； GC-MS and UPLC-MS technologies were used to identify its volatile oils and non-volatile components of the fruits of P. chinense var. glabriusulum Schneid. The active ingredients， core targets and pathways of expectoration and cough relief were analyzed by network pharmacology. RESULTS The volatile oil （0.8， 0.2 g/kg， calculated by volatile oil） and water decoction （12， 3 g/kg， calculated by crude drug） of the fruits of P. chinense var. glabriusulum Schneid. both had obvious expectorant and cough relief effects， and showed obvious dose-dependent relationship. A total of 38 volatile oil components were identified from the medicinal herbs， and the relative percentage contents of 8 components were greater than 1%， such as α -pinene， myrcene， β -caryophyllene， germanene D， isospathulenol； a total of 69 non-volatile oil components were identified， mainly including phenolic compounds， alkaloids， and flavonoids. The active ingredients screened from the identified components included 13 compounds such as α-pinene， myrcene， chlorogenic acid， luteolin， berberine. There were a total of 55 intersection targets with diseases， and the core targets were tumor necrosis factor （TNF）， epidermal growth factor receptor （EGFR）， vascular endothelial growth factor A （VEGFA）， serine/threonine kinase proteins （AKT1） and Toll-like receptor 4 （TLR4）. The molecular docking results showed that the active ingredients and the core targets had good binding ability. GO functional analysis found that the targets were significantly enriched in biological processes such as the reaction affecting lipopolysaccharides， the positive regulation of peptidyl serine phosphorylation， and the positive regulation of the biosynthesis process of nitric oxide. KEGG pathway enrichment analysis found that the targets were significantly enriched in the signaling pathways such as cancer， non-small cell lung cancer， proteoglycans in cancer. CONCLUSIONS Fruits of P. chinense var. glabriusulum Schneid. have obvious expectorant and cough relief effects， and its material basis may be α-pinene， myrcene， chlorogenic acid， luteolin， berberine， etc.， and mainly act on TNF， EGFR， VEGFA， AKT1， TLR4 and its significantly enriched signaling pathway.

Humans ; Karyotype ; Leukemia, Myeloid, Acute