Consensus for antifungal stewardship in China (2024 edition).

Background: Invasive fungal disease (IFD) has become a serious threat to human health in China and around the world, with high mortality and morbidity. Currently, the misdiagnosis rate of IFD is extremely high, compounded with the low quality of prescription antifungals and the high incidence of adverse events associated with IFD treatment, resulting in lengthy hospitalization, low clinical response, and high disease burden, which have become serious challenges in clinical practice. Antifungal stewardship (AFS) can not only significantly increase the early diagnosis rate of IFD, reduce inappropriate utilization of antifungal drugs, improve patient prognosis, but can also improve therapeutic safety and reduce healthcare expenses. Thus, it is urgent to identify key AFS metrics suitable for China's current situation. Methods: Based on metrics recommended by international AFS consensuses, combined with the current situation of China and the clinical experience of authoritative experts in various fields, several metrics were selected, and experts in the fields of respiratory diseases, hematology, intensive care units (ICUs), dermatology, infectious diseases, microbiology laboratory and pharmacy were invited to assess AFS metrics by the Delphi method. Consensus was considered to be reached with an agreement level of ≥80% for the metric. Results: Consensus was reached for 24 metrics, including right patient metrics (n=4), right time metrics (n=3), and right use metrics (n=17). Right use metrics were further subdivided into drug choice (n=8), drug dosage (n=4), drug de-escalation (n=1), drug duration (n=2), and drug consumption (n=2) metrics. Forty-six authoritative experts assessed and reviewed the above metrics, and a consensus was reached with a final agreement level of ≥80% for 22 metrics. Conclusions: This consensus is the first to propose a set of AFS metrics suitable for China, which helps to establish AFS standards in China and is also the first AFS consensus in Asia, and may improve the standard of clinical diagnosis and treatment of IFD, and guide hospitals to implement AFS, ultimately promoting the rational use of antifungal drugs and improving patient prognosis.

Developing a Machine Learning Model to Predict 180-day Readmission for Elderly Patients with Angina.

Background: Readmission of elderly angina patients has become a serious problem, with a dearth of available prediction tools for readmission assessment. The objective of this study was to develop a machine learning (ML) model that can predict 180-day all-cause readmission for elderly angina patients. Methods: The clinical data for elderly angina patients was retrospectively collected. Five ML algorithms were used to develop prediction models. Area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), and the Brier score were applied to assess predictive performance. Analysis by Shapley additive explanations (SHAP) was performed to evaluate the contribution of each variable. Results: A total of 1502 elderly angina patients (45.74% female) were enrolled in the study. The extreme gradient boosting (XGB) model showed good predictive performance for 180-day readmission (AUROC = 0.89; AUPRC = 0.91; Brier score = 0.21). SHAP analysis revealed that the number of medications, hematocrit, and chronic obstructive pulmonary disease were important variables associated with 180-day readmission. Conclusions: An ML model can accurately identify elderly angina patients with a high risk of 180-day readmission. The model used to identify individual risk factors can also serve to remind clinicians of appropriate interventions that may help to prevent the readmission of patients.

Operation-friendly and accurate naked-eye observation assay for fast zoonotic echinococcosis and pulmonary tuberculosis monitoring in clinics.

Echinococcosis and tuberculosis are two common zoonotic diseases that can cause severe pulmonary infections. Early screening and treatment monitoring are of great significance, especially in areas with limited medical resources. Herein, we designed an operation-friendly and rapid magnetic enrichment-silver acetylene chromogenic immunoassay (Me-Sacia) to monitor the antibody. The main components included secondary antibody-modified magnetic nanoparticles (MNP-Ab2) as capture nanoparticles, specific peptide (EG95 or CFP10)-modified silver nanoparticles (AgNP-PTs) as detection nanoparticles, and alkyne-modified gold nanoflowers as chromogenic nanoparticles. Based on the magnetic separation and plasma luminescence techniques, Me-Sacia could completely replace the colorimetric assay of biological enzymes. It reduced the detection time to approximately 1 h and simplified the labor-intensive and equipment-intensive processes associated with conventional ELISA. Meanwhile, the Me-Sacia showed universality for various blood samples and intuitive observation with the naked eye. Compared to conventional ELISA, Me-Sacia lowered the detection limit by approximately 96.8 %, increased the overall speed by approximately 15 times, and improved sensitivity by approximately 7.2 %, with a 100 % specificity and a coefficient of variation (CV) of less than 15 %.

Predicting 1 year readmission for heart failure: A comparative study of machine learning and the LACE index.

AIMS: There is a lack of tools for accurately identifying the risk of readmission for heart failure in elderly patients with arrhythmia. The aim of this study was to establish and compare the performance of the LACE [length of stay ('L'), acute (emergent) admission ('A'), Charlson comorbidity index ('C') and visits to the emergency department during the previous 6 months ('E')] index and machine learning in predicting 1 year readmission for heart failure in elderly patients with arrhythmia. METHODS: Elderly patients with arrhythmia who were hospitalized at Sichuan Provincial People's Hospital between 1 June 2018 and 31 May 2020 were enrolled. The LACE index was calculated for each patient, and the area under the receiver operating characteristic curve (AUROC) was calculated. Six machine learning algorithms, combined with three variable selection methods and clinically relevant features available at the time of hospital discharge, were used to develop machine learning models. AUROC and area under the precision-recall curve (AUPRC) were used to assess discrimination. Shapley additive explanations (SHAP) analysis was used to explain the contributions of the features. RESULTS: A total of 523 patients were enrolled, and 108 patients experienced 1 year hospital readmission for heart failure. The AUROC of the LACE index was 0.5886. The complete machine learning model had the best predictive performance, with an AUROC of 0.7571 and an AUPRC of 0.4096. The most important predictors for 1 year readmission were educational level, total triiodothyronine (TT3), aspartate aminotransferase/alanine aminotransferase (AST/ALT), number of medications (NOM) and triglyceride (TG) level. CONCLUSIONS: Compared with the LACE index, the machine learning model can accurately identify the risk of 1 year readmission for heart failure in elderly patients with arrhythmia.

Risk prediction model based on machine learning for predicting miscarriage among pregnant patients with immune abnormalities.

Introduction: It is known that patients with immune-abnormal co-pregnancies are at a higher risk of adverse pregnancy outcomes. Traditional pregnancy risk management systems have poor prediction abilities for adverse pregnancy outcomes in such patients, with many limitations in clinical application. In this study, we will use machine learning to screen high-risk factors for miscarriage and develop a miscarriage risk prediction model for patients with immune-abnormal pregnancies. This model aims to provide an adjunctive tool for the clinical identification of patients at high risk of miscarriage and to allow for active intervention to reduce adverse pregnancy outcomes. Methods: Patients with immune-abnormal pregnancies attending Sichuan Provincial People's Hospital were collected through electronic medical records (EMR). The data were divided into a training set and a test set in an 8:2 ratio. Comparisons were made to evaluate the performance of traditional pregnancy risk assessment tools for clinical applications. This analysis involved assessing the cost-benefit of clinical treatment, evaluating the model's performance, and determining its economic value. Data sampling methods, feature screening, and machine learning algorithms were utilized to develop predictive models. These models were internally validated using 10-fold cross-validation for the training set and externally validated using bootstrapping for the test set. Model performance was assessed by the area under the characteristic curve (AUC). Based on the best parameters, a predictive model for miscarriage risk was developed, and the SHapley additive expansion (SHAP) method was used to assess the best model feature contribution. Results: A total of 565 patients were included in this study on machine learning-based models for predicting the risk of miscarriage in patients with immune-abnormal pregnancies. Twenty-eight risk warning models were developed, and the predictive model constructed using XGBoost demonstrated the best performance with an AUC of 0.9209. The SHAP analysis of the best model highlighted the total number of medications, as well as the use of aspirin and low molecular weight heparin, as significant influencing factors. The implementation of the pregnancy risk scoring rules resulted in accuracy, precision, and F1 scores of 0.3009, 0.1663, and 0.2852, respectively. The economic evaluation showed a saving of ¥7,485,865.7 due to the model. Conclusion: The predictive model developed in this study performed well in estimating the risk of miscarriage in patients with immune-abnormal pregnancies. The findings of the model interpretation identified the total number of medications and the use of other medications during pregnancy as key factors in the early warning model for miscarriage risk. This provides an important basis for early risk assessment and intervention in immune-abnormal pregnancies. The predictive model developed in this study demonstrated better risk prediction performance than the Pregnancy Risk Management System (PRMS) and also demonstrated economic value. Therefore, miscarriage risk prediction in patients with immune-abnormal pregnancies may be the most cost-effective management method.

Insights into vaccines for elderly individuals: from the impacts of immunosenescence to delivery strategies.

Immunosenescence increases the risk and severity of diseases in elderly individuals and leads to impaired vaccine-induced immunity. With aging of the global population and the emerging risk of epidemics, developing adjuvants and vaccines for elderly individuals to improve their immune protection is pivotal for healthy aging worldwide. Deepening our understanding of the role of immunosenescence in vaccine efficacy could accelerate research focused on optimizing vaccine delivery for elderly individuals. In this review, we analyzed the characteristics of immunosenescence at the cellular and molecular levels. Strategies to improve vaccination potency in elderly individuals are summarized, including increasing the antigen dose, preparing multivalent antigen vaccines, adding appropriate adjuvants, inhibiting chronic inflammation, and inhibiting immunosenescence. We hope that this review can provide a review of new findings with regards to the impacts of immunosenescence on vaccine-mediated protection and inspire the development of individualized vaccines for elderly individuals.

A systematic review and meta-analysis on sodium tanshinone IIA sulfonate injection for the adjunctive therapy of pulmonary heart disease.

AIMS: Sodium tanshinone IIA sulfonate (STS) injection has been widely used as adjunctive therapy for pulmonary heart disease (PHD) in China. Nevertheless, the efficacy of STS injection has not been systematically evaluated so far. Hence, the efficacy of STS injection as adjunctive therapy for PHD was explored in this study. METHODS: Randomized controlled trials (RCTs) were screened from China Science and Technology Journal Database, China National Knowledge Infrastructure, Wanfang Database, PubMed, Sino-Med, Google Scholar, Medline, Chinese Biomedical Literature Database, Cochrane Library, Embase and Chinese Science Citation Database until 20 January 2024. Literature searching, data collection and quality assessment were independently performed by two investigators. The extracted data was analyzed with RevMan 5.4 and STATA 14.0. Basing on the methodological quality, dosage of STS injection, control group measures and intervention time, sensitivity analysis and subgroup analysis were performed. RESULTS: 19 RCTs with 1739 patients were included in this study. Results showed that as adjunctive therapy, STS injection combined with Western medicine showed better therapeutic efficacy than Western medicine alone for PHD by increasing the clinical effective rate (RR = 1.22; 95% CI, 1.17 to 1.27; p < 0.001), partial pressure of oxygen (MD = 10.16; 95% CI, 5.07 to 15.24; p < 0.001), left ventricular ejection fraction (MD = 8.66; 95% CI, 6.14 to 11.18; p < 0.001) and stroke volume (MD = 13.10; 95% CI, 11.83 to 14.38; p < 0.001), meanwhile decreasing the low shear blood viscosity (MD = -1.16; 95% CI, -1.57 to -0.74; p < 0.001), high shear blood viscosity (MD = -0.64; 95% CI, -0.86 to -0.42; p < 0.001), plasma viscosity (MD = -0.23; 95% CI, -0.30 to -0.17; p < 0.001), hematokrit (MD = -8.52; 95% CI, -11.06 to -5.98; p < 0.001), fibrinogen (MD = -0.62; 95% CI, -0.87 to -0.37; p < 0.001) and partial pressure of carbon dioxide (MD = -8.56; 95% CI, -12.09 to -5.02; p < 0.001). CONCLUSION: STS injection as adjunctive therapy seemed to be more effective than Western medicine alone for PHD. However, due to low quality of the included RCTs, more well-designed RCTs were necessary to verify the efficacy of STS injection.

Shenfu injection: a review of pharmacological effects on cardiovascular diseases.

Shenfu injection (SFI), composed of ginseng and aconite, is a Chinese patent developed from the classic traditional prescription Shenfu Decoction created more than 700 years ago. SFI has been widely used in China for over 30 years for treating cardiovascular diseases. The main components in it include ginsenosides and aconitum alkaloids. In recent years, the role of SFI in the treatment of cardiovascular diseases has attracted much attention. The pharmacological effects and therapeutic applications of SFI in cardiovascular diseases are summarized here, highlighting pharmacological features and potential mechanisms developments, confirming that SFI can play a role in multiple ways and is a promising drug for treating cardiovascular diseases.

Dual properties of pharmacological activities and preparation excipient: Bletilla striata polysaccharides.

Bletilla striata has been used for thousands of years and shows the functions of stopping bleeding, reducing swelling, and promoting healing in traditional applications. For Bletilla striata, Bletilla striata polysaccharides (BSP) is the main active ingredient, exhibiting biological functions of anti-inflammatory, anti-oxidant, anti-fibrotic, immune modulation, anti-glycation, and so on. In addition, BSP has exhibited the characteristics of excipient such as bio-adhesion, bio-degradability, and bio-safety and has been prepared into a series of preparations such as nanoparticles, microspheres, microneedles, hydrogels, etc. BSP, as both a drug and an excipient, has already aroused more and more attention. In this review, publications in recent years related to the extraction and identification, biological activities, and excipient application of BSP are reviewed. Specifically, we focused on the advances in the application of BSP as a formulation excipient. We hold opinion that BSP not only needed more researches in the mechanisms, but also the development into hydrogels, nano-formulations, tissue engineering, and so on. And we believe that this paper provides a beneficial reference for further BSP innovation and in-depth research and promotes the use of these natural products in pharmaceutical applications.

S670, an amide derivative of 3-O-acetyl-11-keto-ß-boswellic acid, induces ferroptosis in human glioblastoma cells by generating ROS and inhibiting STX17-mediated fusion of autophagosome and lysosome.

Glioblastoma (GBM) is the most common malignant tumor in the brain with temozolomide (TMZ) as the only approved chemotherapy agent. GBM is characterized by susceptibility to radiation and chemotherapy resistance and recurrence as well as low immunological response. There is an urgent need for new therapy to improve the outcome of GBM patients. We previously reported that 3-O-acetyl-11-keto-ß-boswellic acid (AKBA) inhibited the growth of GBM. In this study we characterized the anti-GBM effect of S670, a synthesized amide derivative of AKBA, and investigated the underlying mechanisms. We showed that S670 dose-dependently inhibited the proliferation of human GBM cell lines U87 and U251 with IC50 values of around 6 µM. Furthermore, we found that S670 (6 µM) markedly stimulated mitochondrial ROS generation and induced ferroptosis in the GBM cells. Moreover, S670 treatment induced ROS-mediated Nrf2 activation and TFEB nuclear translocation, promoting protective autophagosome and lysosome biogenesis in the GBM cells. On the other hand, S670 treatment significantly inhibited the expression of SXT17, thus impairing autophagosome-lysosome fusion and blocking autophagy flux, which exacerbated ROS accumulation and enhanced ferroptosis in the GBM cells. Administration of S670 (50 mg·kg-1·d-1, i.g.) for 12 days in a U87 mouse xenograft model significantly inhibited tumor growth with reduced Ki67 expression and increased LC3 and LAMP2 expression in the tumor tissues. Taken together, S670 induces ferroptosis by generating ROS and inhibiting STX17-mediated fusion of autophagosome and lysosome in GBM cells. S670 could serve as a drug candidate for the treatment of GBM.

Smart nanoparticles for cancer therapy.

Smart nanoparticles, which can respond to biological cues or be guided by them, are emerging as a promising drug delivery platform for precise cancer treatment. The field of oncology, nanotechnology, and biomedicine has witnessed rapid progress, leading to innovative developments in smart nanoparticles for safer and more effective cancer therapy. In this review, we will highlight recent advancements in smart nanoparticles, including polymeric nanoparticles, dendrimers, micelles, liposomes, protein nanoparticles, cell membrane nanoparticles, mesoporous silica nanoparticles, gold nanoparticles, iron oxide nanoparticles, quantum dots, carbon nanotubes, black phosphorus, MOF nanoparticles, and others. We will focus on their classification, structures, synthesis, and intelligent features. These smart nanoparticles possess the ability to respond to various external and internal stimuli, such as enzymes, pH, temperature, optics, and magnetism, making them intelligent systems. Additionally, this review will explore the latest studies on tumor targeting by functionalizing the surfaces of smart nanoparticles with tumor-specific ligands like antibodies, peptides, transferrin, and folic acid. We will also summarize different types of drug delivery options, including small molecules, peptides, proteins, nucleic acids, and even living cells, for their potential use in cancer therapy. While the potential of smart nanoparticles is promising, we will also acknowledge the challenges and clinical prospects associated with their use. Finally, we will propose a blueprint that involves the use of artificial intelligence-powered nanoparticles in cancer treatment applications. By harnessing the potential of smart nanoparticles, this review aims to usher in a new era of precise and personalized cancer therapy, providing patients with individualized treatment options.

Metabolic dysfunction-associated steatotic liver disease: ferroptosis related mechanisms and potential drugs.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is considered a "multisystem" disease that simultaneously suffers from metabolic diseases and hepatic steatosis. Some may develop into liver fibrosis, cirrhosis, and even hepatocellular carcinoma. Given the close connection between metabolic diseases and fatty liver, it is urgent to identify drugs that can control metabolic diseases and fatty liver as a whole and delay disease progression. Ferroptosis, characterized by iron overload and lipid peroxidation resulting from abnormal iron metabolism, is a programmed cell death mechanism. It is an important pathogenic mechanism in metabolic diseases or fatty liver, and may become a key direction for improving MASLD. In this article, we have summarized the physiological and pathological mechanisms of iron metabolism and ferroptosis, as well as the connections established between metabolic diseases and fatty liver through ferroptosis. We have also summarized MASLD therapeutic drugs and potential active substances targeting ferroptosis, in order to provide readers with new insights. At the same time, in future clinical trials involving subjects with MASLD (especially with the intervention of the therapeutic drugs), the detection of serum iron metabolism levels and ferroptosis markers in patients should be increased to further explore the efficacy of potential drugs on ferroptosis.

Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning.

Introduction: Intradialytic hypotension (IDH) is prevalent and associated with high hospitalization and mortality rates. The purpose of this study was to explore the risk factors for IDH and use artificial intelligence to establish an early alert system before hemodialysis sessions to identify patients at high risk of IDH. Materials and Methods: We obtained data on 314,534 hemodialysis sessions conducted at Sichuan Provincial People's Hospital from the renal disease treatment information system. IDH was defined as a systolic blood pressure drop ≥20 mm Hg, a mean arterial pressure drop ≥10 mm Hg during dialysis, or the occurrence of clinical hypotensive events requiring nursing intervention. After pre-processing, the data were randomly divided into training (80%) and testing (20%) sets. Four interpolation methods, three feature selection methods, and 18 machine learning algorithms were used to construct predictive models. The area under the receiver operating characteristic curve (AUC) was the main indicator for evaluating the performance of the models, while Shapley Additive ExPlanation was used to explain the contribution of each variable to the best predictive model. Results: A total of 3,906 patients and 314,534 dialysis sessions were included, of which 142,237 cases showed IDH (incidence rate, 45.2%). Nineteen parameters were identified through artificial intelligence feature screening. They included age, pre-dialysis weight, dry weight, pre-dialysis blood pressure, heart rate, prescribed ultrafiltration, blood cell counts (neutrophil, lymphocyte, monocyte, eosinophil, lymphocyte, and platelet counts), hematocrit, serum calcium, creatinine, urea, glucose, and uric acid. Random forest, gradient boosting, and logistic regression were the three best models, and the AUCs were 0.812 (95% confidence interval [CI], 0.811-0.813), 0.748 (95% CI, 0.747-0.749), and 0.743 (95% CI, 0.742-0.744), respectively. Conclusion: Our dialysis software-based artificial intelligence alert system can be used to predict IDH occurrence, enabling the initiation of relevant interventions.

Adverse drug events in Chinese elder inpatients: a retrospective review for evaluating the efficiency of the Global Trigger Tool.

Background: Elderly patients frequently experience a high incidence of adverse drug events (ADEs) due to the coexistence of multiple diseases, the combination of various medications, poor medication compliance, and other factors. Global Trigger Tool (GTT) is a new method for identifying ADEs, introducing the concept of a trigger, that is, clues including abnormal laboratory values, reversal drugs, and clinical symptoms that may suggest ADEs, and specifically locating information related to ADEs in the medical record to identify ADEs. The aim of this study was to establish a GTT-based trigger tool for adverse medication events in elderly patients and to investigate the risk variables associated with such events. Methods: The triggers were identified by reviewing the frequency of ADEs in elderly patients in Sichuan, China, retrieving relevant literature, and consulting experts. A retrospective analysis was carried out to identify adverse medication occurrences among 480 elderly inpatients in Sichuan People's Hospital. Results: A total of 56 ADEs were detected in 51 patients (10.62%), 13.04 per 1,000 patient days, and 11.67 per 100 admissions. The overall positive predictive value (PPV) of the triggers was 23.84, and 94.64% of ADEs caused temporary injury. Gastrointestinal system injury (27.87%) and metabolic and nutritional disorders (24.53%) were the primary organ-systems affected by ADEs. The majority of ADEs were caused by drugs used to treat cardiovascular diseases. 71.43% of ADE occurred within 2 days of administration and the risk factor analysis of ADE revealed that the number of medicines had a significant correlation. Conclusion: This study demonstrated GTT's value as a tool for ADEs detection in elderly inpatients in China. It enhances the level of medication management and comprehensively reflects the situation of ADE of the elderly.

Advances in research on potential inhibitors of multiple myeloma.

Multiple myeloma (MM) is a common hematological malignancy. Although recent clinical applications of immunomodulatory drugs, proteasome inhibitors and CD38-targeting antibodies have significantly improved the outcome of MM patient with increased survival, the incidence of drug resistance and severe treatment-related complications is gradually on the rise. This review article summarizes the characteristics and clinical investigations of several MM drugs in clinical trials, including their structures, mechanisms of action, structure-activity relationships, and clinical study progress. Furthermore, the application potentials of the drugs that have not yet entered clinical trials are also reviewed. The review also outlines the future directions of MM drug development.

Predicting three-month fasting blood glucose and glycated hemoglobin changes in patients with type 2 diabetes mellitus based on multiple machine learning algorithms.

Fasting blood glucose (FBG) and glycosylated hemoglobin (HbA1c) are key indicators reflecting blood glucose control in type 2 diabetes mellitus (T2DM) patients. The purpose of this study is to establish a predictive model for blood glucose changes in T2DM patients after 3 months of treatment, achieving personalized treatment.A retrospective study was conducted on type 2 diabetes mellitus real-world medical data from 4 cities in Sichuan Province, China from January 2015 to December 2020. After data preprocessing, data inputting, data sampling, and feature screening, 16 kinds of machine learning methods were used to construct prediction models, and 5 prediction models with the best prediction performance were screened respectively. A total of 100,000 cases were included to establish the FBG model, and 2,169 cases were established to establish the HbA1c model. The best prediction model both of FBG and HbA1c finally obtained are realized by ensemble learning and modified random forest inputting, the AUC values are 0.819 and 0.970, respectively. The most important indicators of the FBG and HbA1c prediction model were FBG and HbA1c. Medication compliance, follow-up outcome, dietary habits, BMI, and waist circumference also had a greater impact on FBG levels. The prediction accuracy of the models of the two blood glucose control indicators is high and has certain clinical applicability.HbA1c and FBG are mutually important predictors, and there is a close relationship between them.

Advanced subunit vaccine delivery technologies: From vaccine cascade obstacles to design strategies.

Designing and manufacturing safe and effective vaccines is a crucial challenge for human health worldwide. Research on adjuvant-based subunit vaccines is increasingly being explored to meet clinical needs. Nevertheless, the adaptive immune responses of subunit vaccines are still unfavorable, which may partially be attributed to the immune cascade obstacles and unsatisfactory vaccine design. An extended understanding of the crosstalk between vaccine delivery strategies and immunological mechanisms could provide scientific insight to optimize antigen delivery and improve vaccination efficacy. In this review, we summarized the advanced subunit vaccine delivery technologies from the perspective of vaccine cascade obstacles after administration. The engineered subunit vaccines with lymph node and specific cell targeting ability, antigen cross-presentation, T cell activation properties, and tailorable antigen release patterns may achieve effective immune protection with high precision, efficiency, and stability. We hope this review can provide rational design principles and inspire the exploitation of future subunit vaccines.

Predicting 7-day unplanned readmission in elderly patients with coronary heart disease using machine learning.

Background: Short-term unplanned readmission is always neglected, especially for elderly patients with coronary heart disease (CHD). However, tools to predict unplanned readmission are lacking. This study aimed to establish the most effective predictive model for the unplanned 7-day readmission in elderly CHD patients using machine learning (ML) algorithms. Methods: The detailed clinical data of elderly CHD patients were collected retrospectively. Five ML algorithms, including extreme gradient boosting (XGB), random forest, multilayer perceptron, categorical boosting, and logistic regression, were used to establish predictive models. We used the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, the F1 value, the Brier score, the area under the precision-recall curve (AUPRC), and the calibration curve to evaluate the performance of ML models. The SHapley Additive exPlanations (SHAP) value was used to interpret the best model. Results: The final study included 834 elderly CHD patients, whose average age was 73.5 ± 8.4 years, among whom 426 (51.08%) were men and 139 had 7-day unplanned readmissions. The XGB model had the best performance, exhibiting the highest AUC (0.9729), accuracy (0.9173), F1 value (0.9134), and AUPRC (0.9766). The Brier score of the XGB model was 0.08. The calibration curve of the XGB model showed good performance. The SHAP method showed that fracture, hypertension, length of stay, aspirin, and D-dimer were the most important indicators for the risk of 7-day unplanned readmissions. The top 10 variables were used to build a compact XGB, which also showed good predictive performance. Conclusions: In this study, five ML algorithms were used to predict 7-day unplanned readmissions in elderly patients with CHD. The XGB model had the best predictive performance and potential clinical application perspective.

Sialylation: An alternative to designing long-acting and targeted drug delivery system.

Long-acting and specific targeting are two important properties of excellent drug delivery systems. Currently, the long-acting strategies based on polyethylene glycol (PEG) are controversial, and PEGylation is incapable of simultaneously possessing targeting ability. Thus, it is crucial to identify and develop approaches to produce long-acting and targeted drug delivery systems. Sialic acid (SA) is an endogenous, negatively charged, nine-carbon monosaccharide. SA not only mediates immune escape in the body but also binds to numerous disease related targets. This suggests a potential strategy, namely "sialylation," for preparing long-acting and targeted drug delivery systems. This review focuses on the application status of SA-based long-acting and targeted agents as a reference for subsequent research.