Machine learning predictions of the adverse events of different treatments in patients with ischemic left ventricular systolic dysfunction.

This study aimed to develop several new machine learning models based on hibernating myocardium to predict the major adverse cardiac events(MACE) of ischemic left ventricular systolic dysfunction(LVSD) patients receiving either percutaneous coronary intervention(PCI) or optimal medical therapy(OMT). This study included 329 LVSD patients, who were randomly assigned to the training or validation cohort. Least absolute shrinkage and selection operator(LASSO) regression was used to identify variables associated with MACE. Subsequently, various machine learning models were established. Model performance was compared using receiver operating characteristic(ROC) curves, the Brier score(BS), and the concordance index(C-index). A total of 329 LVSD patients were retrospectively enrolled between January 2016 and December 2021. Utilizing LASSO regression analysis, five factors were selected. Based on these factors, RSF, GBM, XGBoost, Cox, and DeepSurv models were constructed. In the development and validation cohorts, the C-indices were 0.888 vs. 0.955 (RSF). The RSF model (0.991 vs. 0.982 vs. 0.980) had the highest area under the ROC curve (AUC) compared with the other models. The BS (0.077 vs. 0.095vs. 0.077) of RSF model were less than 0.25 at 12, 18, and 24 months. This study developed a novel predictive model based on RSF to predict MACE in LVSD patients who underwent either PCI or OMT.

Drug-Loaded Mesoporous Silica Nanoparticles Enhance Antitumor Immunotherapy by Regulating MDSCs.

Myeloid-derived suppressor cells (MDSCs) are recognized as major immune suppressor cells in the tumor microenvironment that may inhibit immune checkpoint blockade (ICB) therapy. Here, we developed a Stattic-loaded mesoporous silica nanoparticle (PEG-MSN-Stattic) delivery system to tumor sites to reduce the number of MDSCs in tumors. This approach is able to significantly deplete intratumoral MSDCs and thereby increase the infiltration of T lymphocytes in tumors to enhance ICB therapy. Our approach may provide a drug delivery strategy for regulating the tumor microenvironment and enhancing cancer immunotherapy efficacy.

Comparison of intravascular lithotripsy versus rotational atherectomy for the treatment of severe coronary artery calcification.

BACKGROUND: Calcified lesions are one of the most challenging cases for PCI, where optimal angiographic results and satisfying outcomes are hard to achieve. METHODS: We evaluated the baseline clinical, procedures characteristics and outcomes of patients with severe coronary artery calcification (CAC) who underwent coronary intravascular lithotripsy (IVL) and rotational atherectomy (RA). RESULTS: Respectively 152 and 238 patients who underwent IVL and RA are enrolled from January 2023 to November 2023. Regarding demographic characteristics, the gender proportion, medical history of PCI and smoke history among groups reach statistical significance. Left anterior descending and right coronary artery were the main vessels treated in both groups. The 2.5 and 3.0 mm IVL balloons and 1.5 mm burr were the most commonly used. 99.3% cases were successfully implanted drug-eluting stents after IVL balloon pre-treatment, which was higher than in the group treated with RA. During hospitalization, there were no serious adverse events in the IVL group, but there were two adverse events in the RA group. Procedural complications were higher in the RA group than the IVL group (5.5% vs. 0.7%, P = 0.027). CONCLUSIONS: IVL appears to be safe and effective for the treatment of severe CAC lesions compared to RA.

Development of a Novel Nomogram to Predict Major Adverse Cardiac Events in Patients with Chronic Total Occlusion.

Objectives: To create a nomogram using single photon emission computed tomography (SPECT) myocardial perfusion imaging and 18F-FDG positron emissions tomography (PET) gated myocardial metabolism imaging to forecast major adverse cardiovascular events (MACE) in chronic total occlusion (CTO) patients treated with optimal medical therapy (OMT). Methods: A total of 257 patients who received OMT between January 2016 and December 2021 were included in this retrospective study. Patients were randomly divided into development (n=179) and validation (n=78) cohorts. A thorough evaluation was conducted, encompassing clinical features and imaging analysis, which involved assessing myocardial perfusion and metabolism. Independent risk factors were identified using least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression analyses. Calibration curves and decision curve analysis (DCA) were used to evaluate the clinical usefulness. Results: In the development cohort, 53 patients (29.6%) experienced MACE out of 179 patients, while in the validation cohort, MACE occurred in 23 (29.5%) patients out of 78. The PET-left ventricular end-systolic volume (P-ESV) (HR 1.01; 95% CI 1.003-1.017; p=0.003), hibernating myocardium / total perfusion defect (HM/TPD) (HR 1.053; 95% CI 1.038-1.069; p<0.001), PET-left ventricular ejection fraction (P-LVEF) (HR 0.862; 95% CI 0.788-0.943; p=0.001), and left anterior descending branch (LAD) (HR 2.303; 95% CI 1.086-4.884; p=0.03) were significantly associated with MACE and were used to develop the nomogram. The nomogram demonstrated excellent discrimination with C-indexes of 0.931 and 0.911 in the development and validation cohorts. DCA determined that the model exhibited a considerably superior net advantage in predicting MACE. Conclusion: A new nomogram integrating clinical factors and imaging features was created to predict the risk of MACE in patients with CTO.

Efficacy of revascularization in CTO patients based on hibernating myocardium therapy.

BACKGROUND: The effectiveness of percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) is still uncertain, especially for patients with ischemic left ventricular dysfunction. This study aimed to assess hibernating myocardium (HM), as determined by single-photon emission computed tomography (SPECT) and 18F-FDG positron emission tomography (PET), and to compare the benefits of PCI and optimal medical therapy (OMT). METHODS: A retrospective study collected data from 332 patients with CTO and ischemic left ventricular dysfunction. The study compared patients who underwent PCI or OMT via propensity score matching (PSM) analysis which was performed with a 1:2 matching protocol using the nearest neighbour matching algorithm. The primary endpoint of the study was the occurrence of major adverse cardiac events (MACE), defined as a composite of cardiac death, readmission for worsening heart failure (WHF), revascularization and myocardial infarction (MI). RESULTS: After PSM, there were a total of 246 individuals in the PCI and OMT groups. Following Cox regression, hibernating myocardium/total perfusion defect (HM/TPD) was identified as an independent risk factor (hazard ratio (HR): 1.03, 95% confidence interval (CI): 1.008-1.052, p = .007). The cut-off value of HM/TPD was 38%. The results of the subgroup analysis suggest that for patients with HM/TPD >38%, the OMT group had a greater risk of MACE (p = .035). A sensitivity analysis restricting patients with single-vessel CTO lesions, HM/TPD remained an independent predictor (HR 1.025, 95% CI 1.008-1.043, p = .005). CONCLUSION: HM/TPD is an independent predictor of MACE, and for patients with HM/TPD > 38%, CTO-PCI had a lower risk of MACE compared with OMT. However, further validation is still needed through large-scale studies.

scCRT: a contrastive-based dimensionality reduction model for scRNA-seq trajectory inference.

Trajectory inference is a crucial task in single-cell RNA-sequencing downstream analysis, which can reveal the dynamic processes of biological development, including cell differentiation. Dimensionality reduction is an important step in the trajectory inference process. However, most existing trajectory methods rely on cell features derived from traditional dimensionality reduction methods, such as principal component analysis and uniform manifold approximation and projection. These methods are not specifically designed for trajectory inference and fail to fully leverage prior information from upstream analysis, limiting their performance. Here, we introduce scCRT, a novel dimensionality reduction model for trajectory inference. In order to utilize prior information to learn accurate cells representation, scCRT integrates two feature learning components: a cell-level pairwise module and a cluster-level contrastive module. The cell-level module focuses on learning accurate cell representations in a reduced-dimensionality space while maintaining the cell-cell positional relationships in the original space. The cluster-level contrastive module uses prior cell state information to aggregate similar cells, preventing excessive dispersion in the low-dimensional space. Experimental findings from 54 real and 81 synthetic datasets, totaling 135 datasets, highlighted the superior performance of scCRT compared with commonly used trajectory inference methods. Additionally, an ablation study revealed that both cell-level and cluster-level modules enhance the model's ability to learn accurate cell features, facilitating cell lineage inference. The source code of scCRT is available at https://github.com/yuchen21-web/scCRT-for-scRNA-seq.

Development and validation of a predicting nomogram for in-hospital mortality of COVID-19 Omicron variant: A cohort study of 1324 cases in Beijing Anzhen Hospital.

Coronavirus disease 2019 (COVID-19) is continuously posing high global public health concerns due to its high morbidity and mortality. This study aimed to construct a convenient risk model for predicting in-hospital mortality of COVID-19 Omicron variant. A total of 1324 hospitalized patients with Omicron variant were enrolled from Beijing Anzhen Hospital. During hospitalization, the Omicron variant mortality rate was found to be 24.4%. Using the datasets of clinical demographics and laboratory tests, three machine learning algorithms, including best subset selection, stepwise selection, and least absolute shrinkage and selection operator regression analyses were employed to identify the potential predictors of in-hospital mortality. The results found that a panel of twenty-four clinical variables (including age, hyperlipemia, stroke, tumor, and several cardiovascular markers) identified by stepwise selection model exhibited significant performances in predicting the in-hospital mortality of COVID-19. The resultant nomogram showed good discrimination, highlighted by the areas under the curve values of 0.88 for 10 days, 0.81 for 20 days, and 0.82 for 30 days, respectively. Furthermore, decision curve analysis showed a significant reliability and precision for the established stepwise selection model. Collectively, this study developed an accurate and convenience risk model for predicting the in-hospital mortality of COVID-19 Omicron.

Global burden of diseases attributable to intimate partner violence: findings from the Global Burden of Disease Study 2019.

PURPOSE: Our study aims to evaluate the global burden of disease attributable to IPV from 1990 to 2019 at global, regional, national, and socio-demographic index (SDI) levels. Our research question is: What is the global burden of disease attributable to intimate partner violence (IPV) from 1990 to 2019, and how does it vary at global, regional, national, and socio-demographic index (SDI) levels? METHODS: Data parameters for the number of deaths, disability-adjusted life years (DALYs), and age-standardized rate were obtained from the Global Burden of Disease Study 2019. We calculated the percentage change and population attributable fraction with 95% uncertainty intervals. RESULTS: IPV directly accounted for 0.14% [95% UI 0.09%, 0.21%] and 0.32% [95% UI 0.17%, 0.49%] of global all-cause deaths and DALYs in 2019, respectively. The age-standardized deaths and DALYs rates of IPV increased by 12.83% and 4.00% respectively from 1990 to 2019. Women aged 35-39 and 30-34 had the highest deaths and DALYs rate respectively. The highest age-standardized rates of IPV-related deaths and DALYs were observed in Southern Sub-Saharan. Both of deaths and DALYs were high in low-socio-demographic Index (SDI) quintile in 2019. CONCLUSIONS: A higher level of deaths and DALYs attributable to IPV were reported in younger women, in the early 2000s, in Southern Sub-Saharan regions and in low SDI regions. Our study provides policymakers with up-to-date and comprehensive information.

Association Between Red Blood Cell Distribution Width and Coronary Calcification in Patients Referred for Invasive Coronary Angiography.

This study aimed to determine whether red cell distribution width (RDW) is associated with coronary calcification. A total of 4796 patients who underwent coronary computed tomography angiography and subsequent invasive coronary angiography were consecutively enrolled. Coronary artery calcium score (CACS), demographic, clinical, and laboratory data were collected from electronic medical records. RDW were expressed in two forms, as a coefficient of variation (CV) or as a standard deviation (SD). Multivariable ordinal logistic regression was used to investigate the association of RDW with CACS grades (CACS 0-99, 100-399, 400-999, and >1000). A significant association was found between elevated RDW-SD and higher CACS grades after full adjustment (adjusted OR per 1-SD increase: 1.11, 95% CI: 1.05-1.18; P < .001), while no significant association was found between RDW-CV and CACS grades. When RDW-SD was analyzed as a categorical variable, it was primarily the 4th quartile of RDW-SD that was associated with elevated CACS grades compared with the 1st quartile (adjusted OR: 1.25, 95% CI: 1.07-1.46; P = .006), while the 2nd and 3rd quartiles showed no significantly higher risk. RDW-SD is a more robust biomarker for coronary calcification compared with RDW-CV.

Machine learning-based coronary artery calcium score predicted from clinical variables as a prognostic indicator in patients referred for invasive coronary angiography.

OBJECTIVES: Utilising readily available clinical variables, we aimed to develop and validate a novel machine learning (ML) model to predict severe coronary calcification, and further assessed its prognostic significance. METHODS: This retrospective study enrolled patients who underwent coronary CT angiography and subsequent invasive coronary angiography. Multiple ML algorithms were used to train the models for predicting severe coronary calcification (cardiac CT-measured coronary artery calcium [CT-CAC] score ≥ 400). The ML-based CAC (ML-CAC) score derived from the ML predictive probability was stratified into quartiles for prognostic analysis. The primary endpoint was a composite of all-cause death, nonfatal myocardial infarction, or nonfatal stroke. RESULTS: Overall, 5785 patients were divided into training (80%) and test sets (20%). For clinical practicability, we selected the nine-feature support vector machine model with good and satisfactory performance regarding both discrimination and calibration based on five repetitions of the 10-fold cross-validation in the training set (mean AUC = 0.715, Brier score = 0.202), and based on the test in the test set (AUC = 0.753, Brier score = 0.191). In the test set cohort (n = 1137), the primary endpoint was observed in 50 (4.4%) patients during a median 2.8 years' follow-up. The ML-CAC system was significantly associated with an increased risk of the primary endpoint (adjusted hazard ratio for trend 2.26, 95% CI 1.35-3.79, p = 0.002). There was no significant difference in the prognostic value between the ML-CAC and CT-CAC systems (C-index, 0.67 vs. 0.69; p = 0.618). CONCLUSION: ML-CAC score predicted from clinical variables can serve as a novel prognostic indicator in patients referred for invasive coronary angiography. CLINICAL RELEVANCE STATEMENT: In patients referred for invasive coronary angiography who have not undergone preoperative CT-measured coronary artery calcium scoring, machine learning-based coronary artery calcium score assessment can serve as an alternative for predicting the prognosis. KEY POINTS: • The coronary artery calcium (CAC) score, a solid prognostic indicator, can be predicted using non-CT methods. • We developed a machine learning (ML)-CAC model utilising nine clinical variables to predict severe coronary calcification. • The ML-CAC system offers significant prognostic value in patients referred for invasive coronary angiography.

Ultra-processed food consumption and metabolic disease risk: an umbrella review of systematic reviews with meta-analyses of observational studies.

Background and aims: There is an ongoing debate on whether to advocate reducing ultra-processed food (UPF) in dietary guidelines to control metabolic disease (such as obesity and type 2 diabetes mellitus [T2DM]). We aimed to summarize the evidence from systematic reviews with meta-analyses between UPF consumption and metabolic diseases risk, assess the credibility, and verify the robustness of these associations. Methods: We systematically searched PubMed, Web of Science, Embase, and Cochrane Library databases from their inception to July 15, 2023, to identify relevant systematic reviews with meta-analyses. We used the random-effects model to evaluate the summary effect size, along with 95% confidence interval and prediction interval. We also assessed heterogeneity, evidence of small-study effects and excess significance bias, and categorized the credibility of each association based on quantitative umbrella review criteria. Additionally, we conducted subgroup and sensitivity analyses to assess the robustness of associations based on continents, study design, dietary assessment methods, definition methods of UPF, population, and units of UPF consumption. Results: Overall, 6 systematic reviews with 13 meta-analyses were included. Three (23.08%) meta-analyses were classified as highly suggestive evidence for meeting the criteria that associations were significant at p < 10-6, had more than 1,000 cases, and presented the largest study with significance at p < 0.05. Among them, the highest UPF consumption quantile was associated with an increased risk of obesity (OR = 1.55, 95% CI: 1.36-1.77) when compared with the lowest UPF consumption quantile. The highest UPF consumption quantile was associated with an increased risk of T2DM (RR = 1.40, 95% CI: 1.23-1.59) when compared with the lowest UPF consumption quantile, and a 10% increase in UPF consumption (% g/d) was associated with an increased risk of T2DM (RR = 1.12, 95% CI: 1.10-1.13). Meanwhile, the robustness of these associations was verified by a series of subgroup and sensitivity analyses. Conclusion: UPF consumption may be a risk factor for several metabolic diseases. However, well-designed studies are still needed to verify our findings in the future.

Chitosan coatings with different degrees of deacetylation regulate the postharvest quality of sweet cherry through internal metabolism.

In this study, chitosan coatings with different degrees of deacetylation (DD, 88.1 % and 95.2 %) were electrostatically sprayed on sweet cherries to evaluate their impacts on postharvest characteristics and internal metabolism. The results showed that chitosan coating could effectively delay the change of weight, color, firmness, and maintain the content of total phenols, flavonoids and titratable acids, and inhibit the activities of ß-galactosidase and polyphenol oxidase during cold storage. The storage qualities and physiological activities of sweet cherry were significantly correlated with the contents of sorbitol, 4-hydroxycinnamic acid, hydrogenated hydroxycinnamic acid, tyrosine, proline, glutamine, phenylalanine, and other metabolites. Chitosan coating may modulate fruit quality by inhibiting the energy metabolism, accelerating the accumulation of carbohydrates, and promoting the metabolism of phenylalanine and flavonoid. Especially, chitosan coating with 88.1 % DD had better wettability on sweet cherry's peel and displayed more obvious preservation effect through stronger metabolic regulation ability.

Comparative study on genomic and epigenomic profiles of retinoblastoma or tuberous sclerosis complex via nanopore sequencing and a joint screening framework.

Recurrence and extraocular metastasis in advanced intraocular retinoblastoma (RB) are still major obstacles for successful treatment of Chinese children. Tuberous sclerosis complex (TSC) is a very rare, multisystemic genetic disorder characterized by hamartomatous growth. In this study, we aimed to compare genomic and epigenomic profiles with human RB or TSC using recently developed nanopore sequencing, and to identify disease-associated variations or genes. Peripheral blood samples were collected from either RB or RB/TSC patients plus their normal siblings, followed by nanopore sequencing and identification of disease-specific structural variations (SVs) and differentially methylated regions (DMRs) by a systematic biology strategy named as multiomics-based joint screening framework. In total, 316 RB- and 1295 TSC-unique SVs were identified, as well as 1072 RB- and 1114 TSC-associated DMRs, respectively. We eventually identified 6 key genes for RB for further functional validation. Knockdown of CDK19 with specific siRNAs significantly inhibited Y79 cellular proliferation and increased sensitivity to carboplatin, whereas downregulation of AHNAK2 promoted the cell growth as well as drug resistance. Those two genes might serve as potential diagnostic markers or therapeutic targets of RB. The systematic biology strategy combined with functional validation might be an effective approach for rare pediatric malignances with limited samples and challenging collection process.

Study on tumour cell-derived hybrid exosomes as dasatinib nanocarriers for pancreatic cancer therapy.

Pancreatic ductal adenocarcinoma (PDAC) is one of the leading causes of cancer-related death. Therefore, we intend to explore novel strategies against PDAC. The exosomes-based biomimetic nanoparticle is an appealing candidate served as a drug carrier in cancer treatment, due to its inherit abilities. In the present study, we designed dasatinib-loaded hybrid exosomes by fusing human pancreatic cancer cells derived exosomes with dasatinib-loaded liposomes, followed by characterization for particle size (119.9 ± 6.10 nm) and zeta potential (-11.45 ± 2.24 mV). Major protein analysis from western blot techniques reveal the presence of exosome marker proteins CD9 and CD81. PEGylated hybrid exosomes showed pH-sensitive drug release in acidic condition, benefiting drug delivery to acidic cancer environment. Dasatinib-loaded hybrid exosomes exhibited significantly higher uptake rates and cytotoxicity to parent PDAC cells by two-sample t-test or by one-way ANOVA analysis of variance, as compared to free drug or liposomal formulations. The results from our computational analysis demonstrated that the drug-likeness, ADMET, and protein-ligand binding affinity of dasatinib are verified successfully. Cancer derived hybrid exosomes may serve as a potential therapeutic candidate for pancreatic cancer treatment.

Machine learning-based analysis of risk factors for chronic total occlusion in an Asian population.

OBJECTIVES: Chronic total occlusion (CTO) is a form of coronary artery disease (CAD) requiring percutaneous coronary intervention. There has been minimal research regarding CTO-specific risk factors and predictive models. We developed machine learning predictive models based on clinical characteristics to identify patients with CTO before coronary angiography. METHODS: Data from 1473 patients with CAD, including 317 patients with and 1156 patients without CTO, were retrospectively analyzed. Partial least squares discriminant analysis (PLS-DA), random forest (RF), and support vector machine (SVM) models were used to identify CTO-specific risk factors and predict CTO development. Receiver operating characteristic (ROC) curve analysis was performed for model validation. RESULTS: For CTO prediction, the PLS-DA model included 10 variables; the ROC value was 0.706. The RF model included 42 variables; the ROC value was 0.702. The SVM model included 20 variables; the ROC value was 0.696. DeLong's test showed no difference among the three models. Four variables were present in all models: sex, neutrophil percentage, creatinine, and brain natriuretic peptide (BNP). CONCLUSIONS: Validation of machine learning prediction models for CTO revealed that the PLS-DA model had the best prediction performance. Sex, neutrophil percentage, creatinine, and BNP may be important risk factors for CTO development.

Development and validation of a predicted nomogram for mortality of COVID-19: a multicenter retrospective cohort study of 4,711 cases in multiethnic.

Background: Coronavirus disease 2019 (COVID-19) is an infectious disease spreading rapidly worldwide. As it quickly spreads and can cause severe disease, early detection and treatment may reduce mortality. Therefore, the study aims to construct a risk model and a nomogram for predicting the mortality of COVID-19. Methods: The original data of this study were from the article "Neurologic Syndromes Predict Higher In-Hospital Mortality in COVID-19." The database contained 4,711 multiethnic patients. In this secondary analysis, a statistical difference test was conducted for clinical demographics, clinical characteristics, and laboratory indexes. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression analysis were applied to determine the independent predictors for the mortality of COVID-19. A nomogram was conducted and validated according to the independent predictors. The area under the curve (AUC), the calibration curve, and the decision curve analysis (DCA) were carried out to evaluate the nomogram. Results: The mortality of COVID-19 is 24.4%. LASSO and multivariate logistic regression analysis suggested that risk factors for age, PCT, glucose, D-dimer, CRP, troponin, BUN, LOS, MAP, AST, temperature, O2Sats, platelets, Asian, and stroke were independent predictors of CTO. Using these independent predictors, a nomogram was constructed with good discrimination (0.860 in the C index) and internal validation (0.8479 in the C index), respectively. The calibration curves and the DCA showed a high degree of reliability and precision for this clinical prediction model. Conclusion: An early warning model based on accessible variates from routine clinical tests to predict the mortality of COVID-19 were conducted. This nomogram can be conveniently used to facilitate identifying patients who might develop severe disease at an early stage of COVID-19. Further studies are warranted to validate the prognostic ability of the nomogram.

Association of serum thyroid hormone and coronary artery calcification in patients who underwent invasive coronary angiography: an observational study.

BACKGROUND: Thyroid hormones (TH) are known to have a range of effects on the cardiovascular system. However, there is still controversy regarding the relationship between thyroid function and coronary artery calcification (CAC). The purpose of this paper is to investigate the relationship between TH and CAC, especially severe CAC, in patients who underwent invasive coronary angiography (ICA). This may provide further insights into the potential role of TH in the development and progression of cardiovascular disease. METHOD: This observational study included 4221 patients who underwent ICA after completing CTA in a single center. We collected demographic, clinical, and laboratory data from electronic medical records and measured CAC scores via non-contrast cardiac CT. RESULT: The study found that there is a negative correlation between the CAC score and FT3 level, even after adjusting for potential confounding factors, but there was no correlation between the CAC score and FT4 or TSH. When categorized into quartiles, the highest quartile of FT3 was associated with a decrease (ß = -104.37, 95%CI: -172.54, -36.21) in calcification score compared to the lowest quartile. This correlation was more significant in the subgroup of individuals with diabetes or hypertension. CONCLUSION: The study found a negative correlation between FT3 and CAC in patients who underwent ICA. The correlation was consistent with other studies and may suggest that low levels of FT3 are associated with severe CAC. The study may provide new evidence for future research on CAC and potential therapeutic approaches.

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design.

As a promising distributed learning paradigm, federated learning (FL) faces the challenge of communication-computation bottlenecks in practical deployments. In this work, we mainly focus on the pruning, quantization, and coding of FL. By adopting a layer-wise operation, we propose an explicit and universal scheme: FedLP-Q (federated learning with layer-wise pruning-quantization). Pruning strategies for homogeneity/heterogeneity scenarios, the stochastic quantization rule, and the corresponding coding scheme were developed. Both theoretical and experimental evaluations suggest that FedLP-Q improves the system efficiency of communication and computation with controllable performance degradation. The key novelty of FedLP-Q is that it serves as a joint pruning-quantization FL framework with layer-wise processing and can easily be applied in practical FL systems.

CL-Impute: A contrastive learning-based imputation for dropout single-cell RNA-seq data.

BACKGROUND: Single-cell RNA-sequencing (scRNA-seq) technology has revolutionized the study of cell heterogeneity and biological interpretation at the single-cell level. However, the dropout events commonly present in scRNA-seq data can markedly reduce the reliability of downstream analysis. Existing imputation methods often overlook the discrepancy between the established cell relationship from dropout noisy data and reality, which limits their performances due to the learned untrustworthy cell representations. METHOD: Here, we propose a novel approach called the CL-Impute (Contrastive Learning-based Impute) model for estimating missing genes without relying on preconstructed cell relationships. CL-Impute utilizes contrastive learning and a self-attention network to address this challenge. Specifically, the proposed CL-Impute model leverages contrastive learning to learn cell representations from the self-perspective of dropout events, whereas the self-attention network captures cell relationships from the global-perspective. RESULTS: Experimental results on four benchmark datasets, including quantitative assessment, cell clustering, gene identification, and trajectory inference, demonstrate the superior performance of CL-Impute compared with that of existing state-of-the-art imputation methods. Furthermore, our experiment reveals that combining contrastive learning and masking cell augmentation enables the model to learn actual latent features from noisy data with a high rate of dropout events, enhancing the reliability of imputed values. CONCLUSIONS: CL-Impute is a novel contrastive learning-based method to impute scRNA-seq data in the context of high dropout rate. The source code of CL-Impute is available at https://github.com/yuchen21-web/Imputation-for-scRNA-seq.

A LASSO-derived developing and validating risk model for chronic total occlusion in Asian population before coronary angiography.

Background: Despite several previous studies that have explored the predictors of high morbidity in coronary artery disease (CAD) and developed nomograms for CAD patients prior to coronary angiography (CAG), there is a lack of models available to predict chronic total occlusion (CTO). The aim of this study is to develop a risk model and a nomogram for predicting the probability of CTO prior to CAG. Methods: The study included 1,105 patients with CAG-diagnosed CTO in the derivation cohort and 368 patients in the validation cohort. Clinical demographics, echocardiography results, and laboratory indexes were analyzed using statistical difference tests. Independent risk factors affecting the CTO indication were selected using least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression analysis. A nomogram was built and validated based on these independent indicators. The performance of the nomogram was evaluated using area under the curve (AUC), calibration curve, and decision curve analysis (DCA). Results: LASSO and multivariate logistic regression analysis revealed that 6 variables, including sex (male), lymphocyte percentage (LYM%), ejection fraction (EF), myoglobin (Mb), non-high-density lipoprotein cholesterol (non-HDL), and N-terminal pro-B-type natriuretic peptide (NT-proBNP), were independent predictors of CTO. The nomogram constructed based on these variables showed good discrimination (C index of 0.744) and external validation (C index of 0.729). The calibration curves and DCA demonstrated high reliability and precision for this clinical prediction model. Conclusions: The nomogram based on sex (male), LYM%, EF, Mb, non-HDL, and NT-proBNP could be used to predict CTO in CAD patients, enhancing the ability to predict their prognosis in clinical practice. Further research is needed to validate the efficacy of the nomogram in other populations.