Pathogenic bacteria and treatment resistance in older cardiovascular disease patients with lung infection and risk prediction model

This study analyzes the distribution of pathogenic bacteria and their antimicrobial susceptibilities in elderly patients with cardiovascular diseases to identify risk factors for pulmonary infections. A risk prediction model is established, aiming to serve as a clinical tool for early prevention and management of pulmonary infections in this vulnerable population. A total of 600 patients were categorized into infected and uninfected groups. Independent risk factors such as older age, diabetes history, hypoproteinemia, invasive procedures, high cardiac function grade, and a hospital stay of ≥10 days were identified through logistic regression. A predictive model was constructed, with a Hosmer-Lemeshow goodness of fit (P = 0.236) and an area under the receiver operating characteristic curve of 0.795, demonstrating good discriminative ability. The model had 63.40% sensitivity and 82.80% specificity, with a cut-off value of 0.13. Our findings indicate that the risk score model is valid for identifying high-risk groups for pulmonary infection among elderly cardiovascular patients. The study contributes to the early prevention and control of pulmonary infections, potentially reducing infection rates in this vulnerable population.

Prediction of Parkinson's Disease Using Machine Learning Methods

The detection of Parkinson's disease (PD) in its early stages is of great importance for its treatment and management, but consensus is lacking on what information is necessary and what models should be used to best predict PD risk. In our study, we first grouped PD-associated factors based on their cost and accessibility, and then gradually incorporated them into risk predictions, which were built using eight commonly used machine learning models to allow for comprehensive assessment. Finally, the Shapley Additive Explanations (SHAP) method was used to investigate the contributions of each factor. We found that models built with demographic variables, hospital admission examinations, clinical assessment, and polygenic risk score achieved the best prediction performance, and the inclusion of invasive biomarkers could not further enhance its accuracy. Among the eight machine learning models considered, penalized logistic regression and XGBoost were the most accurate algorithms for assessing PD risk, with penalized logistic regression achieving an area under the curve of 0.94 and a Brier score of 0.08. Olfactory function and polygenic risk scores were the most important predictors for PD risk. Our research has offered a practical framework for PD risk assessment, where necessary information and efficient machine learning tools were highlighted.

An Integrative Pancreatic Cancer Risk Prediction Model in the UK Biobank

Pancreatic cancer (PaCa) is a lethal cancer with an increasing incidence, highlighting the need for early prevention strategies. There is a lack of a comprehensive PaCa predictive model derived from large prospective cohorts. Therefore, we have developed an integrated PaCa risk prediction model for PaCa using data from the UK Biobank, incorporating lifestyle-related, genetic-related, and medical history-related variables for application in healthcare settings. We used a machine learning-based random forest approach and a traditional multivariable logistic regression method to develop a PaCa predictive model for different purposes. Additionally, we employed dynamic nomograms to visualize the probability of PaCa risk in the prediction model. The top five influential features in the random forest model were age, PRS, pancreatitis, DM, and smoking. The significant risk variables in the logistic regression model included male gender (OR = 1.17), age (OR = 1.10), non-O blood type (OR = 1.29), higher polygenic score (PRS) (Q5 vs. Q1, OR = 2.03), smoking (OR = 1.82), alcohol consumption (OR = 1.27), pancreatitis (OR = 3.99), diabetes (DM) (OR = 2.57), and gallbladder-related disease (OR = 2.07). The area under the receiver operating curve (AUC) of the logistic regression model is 0.78. Internal validation and calibration performed well in both models. Our integrative PaCa risk prediction model with the PRS effectively stratifies individuals at future risk of PaCa, aiding targeted prevention efforts and supporting community-based cancer prevention initiatives.

Minimal improvement in coronary artery disease risk prediction in Chinese population using polygenic risk scores: evidence from the China Kadoorie Biobank

BACKGROUND

Several studies have reported that polygenic risk scores (PRSs) can enhance risk prediction of coronary artery disease (CAD) in European populations. However, research on this topic is far from sufficient in non-European countries, including China. We aimed to evaluate the potential of PRS for predicting CAD for primary prevention in the Chinese population.

METHODS

Participants with genome-wide genotypic data from the China Kadoorie Biobank were divided into training ( n = 28,490) and testing sets ( n = 72,150). Ten previously developed PRSs were evaluated, and new ones were developed using clumping and thresholding or LDpred method. The PRS showing the strongest association with CAD in the training set was selected to further evaluate its effects on improving the traditional CAD risk-prediction model in the testing set. Genetic risk was computed by summing the product of the weights and allele dosages across genome-wide single-nucleotide polymorphisms. Prediction of the 10-year first CAD events was assessed using hazard ratios (HRs) and measures of model discrimination, calibration, and net reclassification improvement (NRI). Hard CAD (nonfatal I21-I23 and fatal I20-I25) and soft CAD (all fatal or nonfatal I20-I25) were analyzed separately.

RESULTS

In the testing set, 1214 hard and 7201 soft CAD cases were documented during a mean follow-up of 11.2 years. The HR per standard deviation of the optimal PRS was 1.26 (95% CI:1.19-1.33) for hard CAD. Based on a traditional CAD risk prediction model containing only non-laboratory-based information, the addition of PRS for hard CAD increased Harrell's C index by 0.001 (-0.001 to 0.003) in women and 0.003 (0.001 to 0.005) in men. Among the different high-risk thresholds ranging from 1% to 10%, the highest categorical NRI was 3.2% (95% CI: 0.4-6.0%) at a high-risk threshold of 10.0% in women. The association of the PRS with soft CAD was much weaker than with hard CAD, leading to minimal or no improvement in the soft CAD model.

CONCLUSIONS

In this Chinese population sample, the current PRSs minimally changed risk discrimination and offered little improvement in risk stratification for soft CAD. Therefore, this may not be suitable for promoting genetic screening in the general Chinese population to improve CAD risk prediction.

Significance of RNA N6-methyladenosine regulators in the diagnosis and subtype classification of coronary heart disease using the Gene Expression Omnibus database

Background

Many investigations have revealed that alterations in m6A modification levels may be linked to coronary heart disease (CHD). However, the specific link between m6A alteration and CHD warrants further investigation.

Methods

Gene expression profiles from the Gene Expression Omnibus (GEO) databases. We began by constructing a Random Forest model followed by a Nomogram model, both aimed at enhancing our predictive capabilities on specific m6A markers. We then shifted our focus to identify distinct molecular subtypes based on the key m6A regulators and to discern differentially expressed genes between the unique m6A clusters. Following this molecular exploration, we embarked on an in-depth analysis of the biological characteristics associated with each m6A cluster, revealing profound differences between them. Finally, we delved into the identification and correlation analysis of immune cell infiltration across these clusters, emphasizing the potential interplay between m6A modification and the immune system.

Results

In this research, 37 important m6Aregulators were identified by comparing non-CHD and CHD patients from the GSE20680, GSE20681, and GSE71226 datasets. To predict the risk of CHD, seven candidate m6A regulators (CBLL1, HNRNPC, YTHDC2, YTHDF1, YTHDF2, YTHDF3, ZC3H13) were screened using the logistic regression model. Based on the seven possible m6A regulators, a nomogram model was constructed. An examination of decision curves revealed that CHD patients could benefit from the nomogram model. On the basis of the selected relevant m6A regulators, patients with CHD were separated into two m6A clusters (cluster1 and cluster2) using the consensus clustering approach. The Single Sample Gene Set Enrichment Analysis (ssGSEA) and CIBERSORT methods were used to estimate the immunological characteristics of two separate m6A Gene Clusters; the results indicated a close association between seven candidate genes and immune cell composition. The drug sensitivity of seven candidate regulators was predicted, and these seven regulators appeared in numerous diseases as pharmacological targets while displaying strong drug sensitivity.

Conclusion

m6A regulators play crucial roles in the development of CHD. Our research of m6A clusters may facilitate the development of novel molecular therapies and inform future immunotherapeutic methods for CHD.

A five necroptosis-related lncRNA signature predicts the prognosis of bladder cancer and identifies hot or cold tumors

Bladder cancer (BC) is a leading cause of male cancer-related deaths globally. Immunotherapy is showing promise as a treatment option for BC. Numerous studies suggested that necroptosis and long noncoding RNAs (lncRNAs) were critical players in the development of cancers and interacting with cancer immunity. However, the prognostic value of necroptosis-related lncRNAs and their impact on immunotherapeutic response in patients with BC have yet to be well examined. Thus, this study aims to find new biomarkers for predicting prognosis and determining immune subtypes of BC to select appropriate patients from a heterogeneous population. The clinicopathology and transcriptome information from The Cancer Genome Atlas (TCGA) was downloaded, and coexpression analysis was performed to identify necroptosis-related lncRNAs. Then LASSO regression was employed to construct a prediction signature. The signature performance was evaluated by Kaplan-Meier (K-M) method, Time-dependent receiver operating characteristics (ROC). The functional enrichment, immune infiltration, immune checkpoint activation, and the half-maximal inhibitory concentration (IC50) of common drugs in risk groups were compared. The consensus clustering analysis based on lncRNAs associated with necroptosis was made to get 2 clusters to identify hot and cold tumors further. Lastly, the immune response between cold and hot tumors was discussed. In this study, a model containing 5 necroptosis-related lncRNAs was constructed. The risk score distribution of these lncRNAs was compared between low- and high-risk groups in the training, testing, and entire sets. K-M analysis showed that the low-risk patients had significantly better prognosis. The area under the ROC curve (AUC) for the 1-, 3-, and 5-year ROC curves in the entire sets were 0.690, 0.709, and 0.722, respectively. High-risk patients were enriched in lncRNAs related to tumor immunity and had better immune cell infiltration and immune checkpoint activation. Hot tumors and cold tumors were effectively distinguished by clusters 1 and cluster 2, respectively. We developed a necroptosis-related signature based on 5 prognostic lncRNAs, expected to become a new tool for evaluating the prognosis of patients with BC and classifying hot or cold tumors, thus facilitating the development of precision therapy for BC.

Development and validation of risk prediction and neural network models for dilated cardiomyopathy based on WGCNA

Background

Dilated cardiomyopathy (DCM) is a progressive heart condition characterized by ventricular dilatation and impaired myocardial contractility with a high mortality rate. The molecular characterization of DCM has not been determined yet. Therefore, it is crucial to discover potential biomarkers and therapeutic options for DCM.

Methods

The hub genes for the DCM were screened using Weighted Gene Co-expression Network Analysis (WGCNA) and three different algorithms in Cytoscape. These genes were then validated in a mouse model of doxorubicin (DOX)-induced DCM. Based on the validated hub genes, a prediction model and a neural network model were constructed and validated in a separate dataset. Finally, we assessed the diagnostic efficiency of hub genes and their relationship with immune cells.

Results

A total of eight hub genes were identified. Using RT-qPCR, we validated that the expression levels of five key genes (ASPN, MFAP4, PODN, HTRA1, and FAP) were considerably higher in DCM mice compared to normal mice, and this was consistent with the microarray results. Additionally, the risk prediction and neural network models constructed from these genes showed good accuracy and sensitivity in both the combined and validation datasets. These genes also demonstrated better diagnostic power, with AUC greater than 0.7 in both the combined and validation datasets. Immune cell infiltration analysis revealed differences in the abundance of most immune cells between DCM and normal samples.

Conclusion

The current findings indicate an underlying association between DCM and these key genes, which could serve as potential biomarkers for diagnosing and treating DCM.

Validation of a pre-endoscopy risk score for predicting the presence of gastric intestinal metaplasia in a U.S. population

BACKGROUND AND AIMS

Surveillance of gastric intestinal metaplasia (GIM) may lead to early gastric cancer detection. Our purpose was to externally validate a predictive model for endoscopic GIM previously developed in a veteran population in a second U.S.

POPULATION

METHODS

We previously developed a pre-endoscopy risk model for detection of GIM using 423 GIM cases and 1796 control subjects from the Houston Veterans Affairs Hospital. The model included sex, age, race/ethnicity, smoking, and Helicobacter pylori infection with an area under the receiver-operating characteristic curve (AUROC) of .73 for GIM and .82 for extensive GIM. We validated this model in a second cohort of patients from 6 Catholic Health Initiative (CHI)-St Luke's hospitals (Houston, Tex, USA) from January to December 2017. Cases were defined as having GIM on any gastric biopsy sample and extensive GIM as involving both the antrum and corpus. We further optimized the model by pooling both cohorts and assessing discrimination using AUROC.

RESULTS

The risk model was validated in 215 GIM cases (55 with extensive GIM) and 2469 control subjects. Cases were older than control subjects (59.8 vs 54.7 years) with more nonwhites (59.1% vs 42.0%) and H pylori infections (23.7% vs 10.9%). The model applied to the CHI-St Luke's cohort had an AUROC of .62 (95% confidence interval [CI], .57-.66) for predicting GIM and of .71 (95% CI, .63-.79) for predicting extensive GIM. When the Veterans Affairs and CHI-St Luke's cohorts were pooled, discrimination of both models improved (GIM vs extensive GIM AUROC: .74 vs .82).

CONCLUSIONS

A pre-endoscopy risk prediction model was validated and updated using a second U.S. cohort with robust discrimination for endoscopic GIM. This model should be evaluated in other U.S. populations to risk-stratify patients for endoscopic GIM screening.

A nomogram for predicting breast cancer based on hematologic and ultrasound parameters

BACKGROUND

The aim of this study was to investigate the ultrasound and hematological indicators, subsequently utilizing them to predict breast cancer and construct predictive models and columnar plots.

METHODS

The clinical data of 200 patients with breast tumors receiving ultrasound and blood tests at Henan Provincial People's Hospital from January 2020 to January 2023 were collected. Patients were divided into training and validation sets at a 6:4 ratio using R language. Variables were screened using logistic regression, and a nomogram predicting breast cancer probability was constructed based on the training set. The predictive performance of the nomogram was evaluated in the validation set through receiver operating characteristic, calibration and decision curves. Model robustness was validated by bootstrap resampling.

RESULTS

Regression analysis revealed that maximum blood flow velocity within the breast mass ≥ 16.395 m/s, perfusion index ≥ 1.505, cancer antigen 15-3 ≥ 39.620 U/m, cancer antigen 125 ≥ 42.30 U/ml, carcinoembryonic antigen ≥ 6.520 ng/ml, Adler blood flow classification II & III, breast calcification present, and diameter of the lump > 2 cm were independent risk factors for breast cancer. Based on these ultrasonic parameters and blood indicators, the developed nomogram demonstrated excellent discrimination in both the training set (AUC = 0.917) and validation set (AUC = 0.844). The calibration plot showed high consistency between the nomogram-predicted and the actual results. Decision curve analysis indicated higher net benefit of this model.

CONCLUSIONS

The nomogram developed in this study demonstrated solid predictive abilities for breast malignancy, indicating potential clinical value pending further research.

Impact of Social Support on Cardiovascular Risk Prediction Models: A Systematic Review

Cardiovascular diseases (CVD) stand as the primary causes of both mortality and morbidity on a global scale. Social factors such as low social support can increase the risk of developing heart diseases and have shown poor prognosis in cardiac patients. Resources such as PubMed and Google Scholar were searched using a boolean algorithm for articles published between 2003 and 2023. Eligible articles showed an association between social support and cardiovascular risks. A systematic review was conducted using the guidance published in the Cochrane Prognosis Method Group and the PRISMA checklist, for reviews of selected articles. A total of five studies were included in our final analysis. Overall, we found that participants with low social support developed cardiovascular events, and providing a good support system can decrease the risk of readmission in patients with a history of CVD. We also found that integrating social determinants in the cardiovascular risk prediction model showed improvement in accessing the risk. Population with good social support showed low mortality and decreased rate of readmission. There are various prediction models, but the social determinants are not primarily included while calculating the algorithms. Although it has been proven in multiple studies that including the social determinants of health (SDOH) improves the accuracy of cardiovascular risk prediction models. Hence, the inclusion of SDOH should be highly encouraged.

Can spirometry improve the performance of cardiovascular risk model in high-risk Eastern European countries?

Aims

Impaired lung function has been strongly associated with cardiovascular disease (CVD) events. We aimed to assess the additive prognostic value of spirometry indices to the risk estimation of CVD events in Eastern European populations in this study.

Methods

We randomly selected 14,061 individuals with a mean age of 59 ± 7.3 years without a previous history of cardiovascular and pulmonary diseases from population registers in the Czechia, Poland, and Lithuania. Predictive values of standardised Z-scores of forced expiratory volume measured in 1 s (FEV1), forced vital capacity (FVC), and FEV1 divided by height cubed (FEV1/ht3) were tested. Cox proportional hazards models were used to estimate hazard ratios (HRs) of CVD events of various spirometry indices over the Framingham Risk Score (FRS) model. The model performance was evaluated using Harrell's C-statistics, likelihood ratio tests, and Bayesian information criterion.

Results

All spirometry indices had a strong linear relation with the incidence of CVD events (HR ranged from 1.10 to 1.12 between indices). The model stratified by FEV1/ht3 tertiles had a stronger link with CVD events than FEV1 and FVC. The risk of CVD event for the lowest vs. highest FEV1/ht3 tertile among people with low FRS was higher (HR: 2.35; 95% confidence interval: 1.96-2.81) than among those with high FRS. The addition of spirometry indices showed a small but statistically significant improvement of the FRS model.

Conclusions

The addition of spirometry indices might improve the prediction of incident CVD events particularly in the low-risk group. FEV1/ht3 is a more sensitive predictor compared to other spirometry indices.

Establishment and validation of a prognostic nomogram for long-term low vision after diabetic vitrectomy

Purpose

We aimed to evaluate the risk factors and develop a prognostic nomogram of long-term low vision after diabetic vitrectomy.

Methods

This retrospective study included 186 patients (250 eyes) that underwent primary vitrectomy for proliferative diabetic retinopathy with a minimum follow-up period of one year. Patients were assigned to the training cohort (200 eyes) or validation cohort (50 eyes) at a 4:1 ratio randomly. Based on a cutoff value of 0.3 in best-corrected visual acuity (BCVA) measurement, the training cohort was separated into groups with or without low vision. Univariate and multivariate logistic regression analyses were performed on preoperative systemic and ocular characteristics to develop a risk prediction model and nomogram. The calibration curve and the area under the receiver operating characteristic curves (AUC) were used to evaluate the calibration and discrimination of the model. The nomogram was internally validated using the bootstrapping method, and it was further verified in an external cohort.

Results

Four independent risk factors were selected by stepwise forward regression, including tractional retinal detachment (β=1.443, OR=4.235, P<0.001), symptom duration ≥6 months (β=0.954, OR=2.595, P=0.004), preoperative BCVA measurement (β=0.540, OR=1.716, P=0.033), and hypertension (β=0.645, OR=1.905, P=0.044). AUC values of 0.764 (95% CI: 0.699-0.829) in the training cohort and 0.755 (95% CI: 0.619-0.891) in the validation cohort indicated the good predictive ability of the model.

Conclusion

The prognostic nomogram established in this study is useful for predicting long-term low vision after diabetic vitrectomy.

Development of a Cardiovascular Disease Risk Prediction Model: A Preliminary Retrospective Cohort Study of a Patient Sample in Saudi Arabia

Saudi Arabia has an alarmingly high incidence of cardiovascular disease (CVD) and its associated risk factors. To effectively assess CVD risk, it is essential to develop tailored models for diverse regions and ethnicities using local population variables. No CVD risk prediction model has been locally developed. This study aims to develop the first 10-year CVD risk prediction model for Saudi adults aged 18 to 75 years. The electronic health records of Saudi male and female patients aged 18 to 75 years, who were seen in primary care settings between 2002 and 2019, were reviewed retrospectively via the Integrated Clinical Information System (ICIS) database (from January 2002 to February 2019). The Cox regression model was used to identify the risk factors and develop the CVD risk prediction model. Overall, 451 patients were included in this study, with a mean follow-up of 12.05 years. Thirty-five (7.7%) patients developed a CVD event. The following risk factors were included: fasting blood sugar (FBS) and high-density lipoprotein cholesterol (HDL-c), heart failure, antihyperlipidemic therapy, antithrombotic therapy, and antihypertension therapy. The Bayesian information criterion (BIC) score was 314.4. This is the first prediction model developed in Saudi Arabia and the second in any Arab country after the Omani study. We assume that our CVD predication model will have the potential to be used widely after the validation study.

Risk Prediction Model of Early-Onset Preeclampsia Based on Risk Factors and Routine Laboratory Indicators

Background: Globally, 10-15% of maternal deaths are statistically attributable to preeclampsia. Compared with late-onset PE, the severity of early-onset PE remains more harmful with higher morbidity and mortality. Objective: To establish an early-onset preeclampsia prediction model by clinical characteristics, risk factors and routine laboratory indicators were investigated from pregnant women at 6 to 10 gestational weeks. Methods: The clinical characteristics, risk factors, and 38 routine laboratory indicators (6-10 weeks of gestation) including blood lipids, liver and kidney function, coagulation, blood count, and other indicators of 91 early-onset preeclampsia patients and 709 normal controls without early-onset preeclampsia from January 2010 to May 2021 in Peking University Third Hospital (PUTH) were retrospectively analyzed. A logistic regression, decision tree model, and support vector machine (SVM) model were applied for establishing prediction models, respectively. ROC curves were drawn; area under curve (AUCROC), sensitivity, and specificity were calculated and compared. Results: There were statistically significant differences in the rates of diabetes, antiphospholipid syndrome (APS), kidney disease, obstructive sleep apnea (OSAHS), primipara, history of preeclampsia, and assisted reproductive technology (ART) (p < 0.05). Among the 38 routine laboratory indicators, there were no significant differences in the levels of PLT/LYM, NEU/LYM, TT, D-Dimer, FDP, TBA, ALP, TP, ALB, GLB, UREA, Cr, P, Cystatin C, HDL-C, Apo-A1, and Lp(a) between the two groups (p > 0.05). The levels of the rest indicators were all statistically different between the two groups (p < 0.05). If only 12 risk factors of PE were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.78, 0.74, and 0.66, respectively, while 12 risk factors of PE and 38 routine laboratory indicators were analyzed with the logistic regression, decision tree model, and support vector machine (SVM), and the AUCROC were 0.86, 0.77, and 0.93, respectively. Conclusions: The efficacy of clinical risk factors alone in predicting early-onset preeclampsia is not high while the efficacy increased significantly when PE risk factors combined with routine laboratory indicators. The SVM model was better than logistic regression model and decision tree model in early prediction of early-onset preeclampsia incidence.

Comparing Explainable Machine Learning Approaches With Traditional Statistical Methods for Evaluating Stroke Risk Models: Retrospective Cohort Study

BACKGROUND

Stroke has multiple modifiable and nonmodifiable risk factors and represents a leading cause of death globally. Understanding the complex interplay of stroke risk factors is thus not only a scientific necessity but a critical step toward improving global health outcomes.

OBJECTIVE

We aim to assess the performance of explainable machine learning models in predicting stroke risk factors using real-world cohort data by comparing explainable machine learning models with conventional statistical methods.

METHODS

This retrospective cohort included high-risk patients from Ramathibodi Hospital in Thailand between January 2010 and December 2020. We compared the performance and explainability of logistic regression (LR), Cox proportional hazard, Bayesian network (BN), tree-augmented Naïve Bayes (TAN), extreme gradient boosting (XGBoost), and explainable boosting machine (EBM) models. We used multiple imputation by chained equations for missing data and discretized continuous variables as needed. Models were evaluated using C-statistics and F1-scores.

RESULTS

Out of 275,247 high-risk patients, 9659 (3.5%) experienced a stroke. XGBoost demonstrated the highest performance with a C-statistic of 0.89 and an F1-score of 0.80 followed by EBM and TAN with C-statistics of 0.87 and 0.83, respectively; LR and BN had similar C-statistics of 0.80. Significant factors associated with stroke included atrial fibrillation (AF), hypertension (HT), antiplatelets, HDL, and age. AF, HT, and antihypertensive medication were common significant factors across most models, with AF being the strongest factor in LR, XGBoost, BN, and TAN models.

CONCLUSIONS

Our study developed stroke prediction models to identify crucial predictive factors such as AF, HT, or systolic blood pressure or antihypertensive medication, anticoagulant medication, HDL, age, and statin use in high-risk patients. The explainable XGBoost was the best model in predicting stroke risk, followed by EBM.

Risk prediction model construction for post myocardial infarction heart failure by blood immune B cells

Background

Myocardial infarction (MI) is a common cardiac condition with a high incidence of morbidity and mortality. Despite extensive medical treatment for MI, the development and outcomes of post-MI heart failure (HF) continue to be major factors contributing to poor post-MI prognosis. Currently, there are few predictors of post-MI heart failure.

Methods

In this study, we re-examined single-cell RNA sequencing and bulk RNA sequencing datasets derived from the peripheral blood samples of patients with myocardial infarction, including patients who developed heart failure and those who did not develop heart failure after myocardial infarction. Using marker genes of the relevant cell subtypes, a signature was generated and validated using relevant bulk datasets and human blood samples.

Results

We identified a subtype of immune-activated B cells that distinguished post-MI HF patients from non-HF patients. Polymerase chain reaction was used to confirm these findings in independent cohorts. By combining the specific marker genes of B cell subtypes, we developed a prediction model of 13 markers that can predict the risk of HF in patients after myocardial infarction, providing new ideas and tools for clinical diagnosis and treatment.

Conclusion

Sub-cluster B cells may play a significant role in post-MI HF. We found that the STING1, HSPB1, CCL5, ACTN1, and ITGB2 genes in patients with post-MI HF showed the same trend of increase as those without post-MI HF.

New paradigm in the treatment of myositis-associated interstitial lung disease

INTRODUCTION

Interstitial lung disease (ILD) is the leading cause of mortality in idiopathic inflammatory myopathies or myositis. Clinical characteristics, including the course of ILD, rate of progression, radiological and pathohistological morphologies, extent and distribution of inflammation and fibrosis, responses to treatment, recurrence rate, and prognosis, are highly variable among myositis patients. A standard practice for ILD management in myositis patients has not yet been established.

AREAS COVERED

Recent studies have demonstrated the stratification of patients with myositis-associated ILD into more homogeneous groups based on the disease behavior and myositis-specific autoantibody (MSA) profile, leading to better prognoses and prevention of the burden of organ damage. This review introduces a new paradigm in the management of myositis-associated ILD based on research findings from relevant literature selected by a search of PubMed as of January 2023, as well as expert opinions.

EXPERT OPINION

Managing strategies for myositis-associated ILD are being established to stratify patients based on the severity of ILD and the prediction of prognosis based on the disease behavior and MSA profile. The development of a precision medicine treatment approach will provide benefits to all relevant communities.

Added value of patient- and drug-related factors to stratify drug-drug interaction alerts for risk of QT prolongation: Development and validation of a risk prediction model

AIMS

Many clinical decision support systems trigger warning alerts for drug-drug interactions potentially leading to QT prolongation and torsades de pointes (QT-DDIs). Unfortunately, there is overalerting and underalerting because stratification is only based on a fixed QT-DDI severity level. We aimed to improve QT-DDI alerting by developing and validating a risk prediction model considering patient- and drug-related factors.

METHODS

We fitted 31 predictor candidates to a stepwise linear regression for 1000 bootstrap samples and selected the predictors present in 95% of the 1000 models. A final linear regression model with those variables was fitted on the original development sample (350 QT-DDIs). This model was validated on an external dataset (143 QT-DDIs). Both true QTc and predicted QTc were stratified into three risk levels (low, moderate and high). Stratification of QT-DDIs could be appropriate (predicted risk = true risk), acceptable (one risk level difference) or inappropriate (two risk levels difference).

RESULTS

The final model included 11 predictors with the three most important being use of antiarrhythmics, age and baseline QTc. Comparing current practice to the prediction model, appropriate stratification increased significantly from 37% to 54% appropriate QT-DDIs (increase of 17.5% on average [95% CI +5.4% to +29.6%], p_adj  = 0.006) and inappropriate stratification decreased significantly from 13% to 1% inappropriate QT-DDIs (decrease of 11.2% on average [95% CI -17.7% to -4.7%], p_adj  ≤ 0.001).

CONCLUSION

The prediction model including patient- and drug-related factors outperformed QT alerting based on QT-DDI severity alone and therefore is a promising strategy to improve DDI alerting.

Validation of a risk prediction model for early chronic kidney disease in patients with type 2 diabetes: Data from the German/Austrian Diabetes Prospective Follow-up registry

AIM

To validate a recently proposed risk prediction model for chronic kidney disease (CKD) in type 2 diabetes (T2D).

MATERIALS AND METHODS

Subjects from the German/Austrian Diabetes Prospective Follow-up (DPV) registry with T2D, normoalbuminuria, an estimated glomerular filtration rate of 60 ml/min/1.73m² or higher and aged 39-75 years were included. Prognostic factors included age, body mass index (BMI), smoking status and HbA1c. Subjects were categorized into low, moderate, high and very high-risk groups. Outcome was CKD occurrence.

RESULTS

Subjects (n = 10 922) had a mean age of 61 years, diabetes duration of 6 years, BMI of 31.7 kg/m² , HbA1c of 6.9% (52 mmol/mol); 9.1% had diabetic retinopathy and 16.3% were smokers. After the follow-up (~59 months), 37.4% subjects developed CKD. The area under the curve (AUC; unadjusted base model) was 0.58 (95% CI 0.57-0.59). After adjustment for diabetes and follow-up duration, the AUC was 0.69 (95% CI 0.68-0.70), indicating improved discrimination. After follow-up, 15.0%, 20.1%, 27.7% and 40.2% patients in the low, moderate, high and very high-risk groups, respectively, had developed CKD. Increasing risk score correlated with increasing cumulative risk of incident CKD over a median of 4.5 years of follow-up (P < .0001).

CONCLUSIONS

The predictive model achieved moderate discrimination but good calibration in a German/Austrian T2D population, suggesting that the model may be relevant for determining CKD risk.

A Clinical Prediction Rule for Thrombosis in Critically Ill COVID-19 Patients: Step 1 Results of the Thromcco Study

The incidence of thrombosis in COVID-19 patients is exceptionally high among intensive care unit (ICU)-admitted individuals. We aimed to develop a clinical prediction rule for thrombosis in hospitalized COVID-19 patients. Data were taken from the Thromcco study (TS) database, which contains information on consecutive adults (aged ≥ 18) admitted to eight Spanish ICUs between March 2020 and October 2021. Diverse logistic regression model analysis, including demographic data, pre-existing conditions, and blood tests collected during the first 24 h of hospitalization, was performed to build a model that predicted thrombosis. Once obtained, the numeric and categorical variables considered were converted to factor variables giving them a score. Out of 2055 patients included in the TS database, 299 subjects with a median age of 62.4 years (IQR 51.5-70) (79% men) were considered in the final model (SE = 83%, SP = 62%, accuracy = 77%). Seven variables with assigned scores were delineated as age 25-40 and ≥70 = 12, age 41-70 = 13, male = 1, D-dimer ≥ 500 ng/mL = 13, leukocytes ≥ 10 × 10³/µL = 1, interleukin-6 ≥ 10 pg/mL = 1, and C-reactive protein (CRP) ≥ 50 mg/L = 1. Score values ≥28 had a sensitivity of 88% and specificity of 29% for thrombosis. This score could be helpful in recognizing patients at higher risk for thrombosis, but further research is needed.

Construction and validation of a risk prediction model for aromatase inhibitor-associated bone loss

Purpose

To establish a high-risk prediction model for aromatase inhibitor-associated bone loss (AIBL) in patients with hormone receptor-positive breast cancer.

Methods

The study included breast cancer patients who received aromatase inhibitor (AI) treatment. Univariate analysis was performed to identify risk factors associated with AIBL. The dataset was randomly divided into a training set (70%) and a test set (30%). The identified risk factors were used to construct a prediction model using the eXtreme gradient boosting (XGBoost) machine learning method. Logistic regression and least absolute shrinkage and selection operator (LASSO) regression methods were used for comparison. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the model in the test dataset.

Results

A total of 113 subjects were included in the study. Duration of breast cancer, duration of aromatase inhibitor therapy, hip fracture index, major osteoporotic fracture index, prolactin (PRL), and osteocalcin (OC) were found to be independent risk factors for AIBL (p < 0.05). The XGBoost model had a higher AUC compared to the logistic model and LASSO model (0.761 vs. 0.716, 0.691).

Conclusion

The XGBoost model outperformed the logistic and LASSO models in predicting the occurrence of AIBL in patients with hormone receptor-positive breast cancer receiving aromatase inhibitors.

Predicting risk of peripartum blood transfusion during vaginal and cesarean delivery: A risk prediction model

OBJECTIVE

The objective of this study is to develop a model that will help predict the risk of blood transfusion using information available prior to delivery.

STUDY DESIGN

The study is a secondary analysis of the Consortium on Safe Labor registry. Women who had a delivery from 2002 to 2008 were included. Pre-delivery variables that had significant associations with transfusion were included in a multivariable logistic regression model predicting transfusion. The prediction model was internally validated using randomly selected samples from the same population of women.

RESULTS

Of 156,572 deliveries, 5,463 deliveries (3.5%) required transfusion. Women who had deliveries requiring transfusion were more likely to have a number of comorbidities such as preeclampsia (6.3% versus 4.1%, OR 1.21, 95% CI 1.08-1.36), placenta previa (1.8% versus 0.4%, OR 4.11, 95% CI 3.25-5.21) and anemia (10.6% versus 5.4%, OR 1.30, 95% CI 1.21-1.41). Transfusion was least likely to occur in university teaching hospitals compared to community hospitals. The c statistic was 0.71 (95% CI 0.70-0.72) in the derivation sample. The most salient predictors of transfusion included type of hospital, placenta previa, multiple gestations, diabetes mellitus, anemia, asthma, previous births, preeclampsia, type of insurance, age, gestational age, and vertex presentation. The model was well-calibrated and showed strong internal validation.

CONCLUSION

The model identified independent risk factors that can help predict the risk of transfusion prior to delivery. If externally validated in another dataset, this model can assist health care professionals counsel patients and prepare facilities/resources to reduce maternal morbidity.

Risk Prediction Models and Novel Prognostic Factors for Heart Failure with Preserved Ejection Fraction: A Systematic and Comprehensive Review

BACKGROUND

Patients with heart failure with preserved ejection fraction (HFpEF) have large individual differences, unclear risk stratification, and imperfect treatment plans. Risk prediction models are helpful for the dynamic assessment of patients' prognostic risk and early intensive therapy of high-risk patients. The purpose of this study is to systematically summarize the existing risk prediction models and novel prognostic factors for HFpEF, to provide a reference for the construction of convenient and efficient HFpEF risk prediction models.

METHODS

Studies on risk prediction models and prognostic factors for HFpEF were systematically searched in relevant databases including PubMed and Embase. The retrieval time was from inception to February 1, 2023. The Quality in Prognosis Studies (QUIPS) tool was used to assess the risk of bias in included studies. The predictive value of risk prediction models for end outcomes was evaluated by sensitivity, specificity, the area under the curve, C-statistic, C-index, etc. In the literature screening process, potential novel prognostic factors with high value were explored.

RESULTS

A total of 21 eligible HFpEF risk prediction models and 22 relevant studies were included. Except for 2 studies with a high risk of bias and 2 studies with a moderate risk of bias, other studies that proposed risk prediction models had a low risk of bias overall. Potential novel prognostic factors for HFpEF were classified and described in terms of demographic characteristics (age, sex, and race), lifestyle (physical activity, body mass index, weight change, and smoking history), laboratory tests (biomarkers), physical inspection (blood pressure, electrocardiogram, imaging examination), and comorbidities.

CONCLUSION

It is of great significance to explore the potential novel prognostic factors of HFpEF and build a more convenient and efficient risk prediction model for improving the overall prognosis of patients. This review can provide a substantial reference for further research.

Construction and validation of risk prediction model for gestational diabetes based on a nomogram

OBJECTIVE

To construct a model to predict the risk of gestational diabetes mellitus (GDM) based on a nomogram and verify it.

METHODS

Data from 182 patients with GDM treated in Xi'an International Medical Center Hospital from January 2018 to May 2021 were retrospectively analyzed. A total of 491 normal parturients who underwent physical examination in Xi'an International Medical Center Hospital during the same period were selected as controls. With a ratio of 7:3, patients with GDM were divided into a training group (n=128) and a verification (n=54) group, and 491 normal parturients were divided into a training control group (n=344) and a verification control group (n=147). Clinical data were collected, and risk factors for GDM were analyzed by logistic regression. R language was used to construct a prognostic prediction nomogram model for GDM, and a receiver operating characteristic curve was employed to evaluate the accuracy of this nomogram model in predicting the prognosis of GDM.

RESULTS

Univariate analysis revealed that age, body mass index (BMI), family history of diabetes, hemoglobin, triglycerides, serum ferritin, and fasting blood glucose in the first trimester were different between the training group and the training control group (P<0.05). Multivariate analysis revealed that age, BMI, hemoglobin, triglycerides, serum ferritin, and fasting blood glucose in the first trimester were independent risk factors for GDM (P<0.05). Based on a logistic regression equation, the risk formula was -5.971 + 1.054 * age + 1.133 * BMI + 1.763 * hemoglobin + 1.260 * triglycerides + 3.041 * serum ferritin + 1.756 * fasting blood glucose in the first trimester. The area under the curve for predicting the risk of GDM in the training group was 0.920, and that of the validation group was 0.753.

CONCLUSION

Age, BMI, hemoglobin, serum ferritin, and fasting blood glucose in the first trimester are risk factors for GDM.