Risk Prediction in Patients With Heart Failure With Preserved Ejection Fraction Using Gene Expression Data and Machine Learning

Machine learning in heart failure diagnosis, prediction, and prognosis: review

Globally, cardiovascular diseases take the lives of over 17 million people each year, mostly through myocardial infarction, or MI, and heart failure (HF). This comprehensive literature review examines various aspects related to the diagnosis, prediction, and prognosis of HF in the context of machine learning (ML). The review covers an array of topics, including the diagnosis of HF with preserved ejection fraction (HFpEF) and the identification of high-risk patients with HF with reduced ejection fraction (HFrEF). The prediction of mortality in different HF populations using different ML approaches is explored, encompassing patients in the ICU, and HFpEF patients using biomarkers and gene expression. The review also delves into the prediction of mortality and hospitalization rates in HF patients with mid-range ejection fraction (HFmrEF) using ML methods. The findings highlight the significance of a multidimensional approach that encompasses clinical evaluation, laboratory assessments, and comprehensive research to improve our understanding and management of HF. Promising predictive models incorporating biomarkers, gene expression, and consideration of epigenetics demonstrate potential in estimating mortality and identifying high-risk HFpEF patients. This literature review serves as a valuable resource for researchers, clinicians, and healthcare professionals seeking a comprehensive and updated understanding of the role of ML diagnosis, prediction, and prognosis of HF across different subtypes and patient populations.

Prognostic Value of a Multi-mRNA Signature for 1-Year All-Cause Death in Hospitalized Patients With Heart Failure With a Preserved Ejection Fraction

BACKGROUND

Heart failure with preserved ejection fraction is a major global public health problem, while effective risk stratification tools are still lacking. We sought to construct a multi-mRNA signature to predict 1-year all-cause death.

METHODS

We selected 30 patients with heart failure with preserved ejection fraction who died during 1-year follow-up and 30 who survived in the discovery set. One hundred seventy-one and 120 patients with heart failure with preserved ejection fraction were randomly selected as a test set and a validation set, respectively. We performed mRNA microarrays in all patients.

RESULTS

We constructed a 5-mRNA signature for predicting 1-year all-cause death. The scores of the 5-mRNA signature were significantly associated with the 1-year risk of all-cause death in both the test set (hazard ratio, 2.72 [95% CI, 1.98-3.74]; P<0.001) and the validation set (hazard ratio, 3.95 [95% CI, 2.40-6.48]; P<0.001). Compared with a reference model, which included sex, ASCEND-HF (Acute Study of Clinical Effectiveness of Nesiritide in Decompensated Heart Failure) score, history of HF and NT-proBNP (N-terminal pro-B-type natriuretic peptide), the 5-mRNA signature had a better discrimination capability, with an increased area under the curve from 0.696 to 0.813 in the test set and from 0.712 to 0.848 in the validation set. A composite model integrating the 5-mRNA risk score and variables in the reference model demonstrated an excellent discrimination capability, with an area under the curve of 0.861 (95% CI, 0.784-0.939) in the test set and an area under the curve of 0.859 (95% CI, 0.755-0.963) in the validation set. The net reclassification improvement and integrated discrimination improvement indicated that the composite model significantly improved patient classification compared with the reference model in both sets (P<0.001).

CONCLUSIONS

The 5-mRNA signature is a promising predictive tool for 1-year all-cause death and shows improved prognostic power over the established risk scores and NT-proBNP in patients with heart failure with preserved ejection fraction.

Identification of diagnostic model in heart failure with myocardial fibrosis and conduction block by integrated gene co-expression network analysis

BACKGROUND

Despite the advancements in heart failure(HF) research, the early diagnosis of HF continues to be a challenging issue in clinical practice. This study aims to investigate the genes related to myocardial fibrosis and conduction block, with the goal of developing a diagnostic model for early treatment of HF in patients.

METHOD

The gene expression profiles of GSE57345, GSE16499, and GSE9128 were obtained from the Gene Expression Omnibus (GEO) database. After merging the expression profile data and adjusting for batch effects, differentially expressed genes (DEGs) associated with conduction block and myocardial fibrosis were identified. Gene Ontology (GO) resources, Kyoto Encyclopedia of Genes and Genomes (KEGG) resources, and gene set enrichment analysis (GSEA) were utilized for functional enrichment analysis. A protein-protein interaction network (PPI) was constructed using a string database. Potential key genes were selected based on the bioinformatics information mentioned above. SVM and LASSO were employed to identify hub genes and construct the module associated with HF. The mRNA levels of TAC mice and external datasets (GSE141910 and GSE59867) are utilized for validating the diagnostic model. Additionally, the study explores the relationship between the diagnostic model and immune cell infiltration.

RESULTS

A total of 395 genes exhibiting differential expression were identified. Functional enrichment analysis revealed that these specific genes primarily participate in biological processes and pathways associated with the constituents of the extracellular matrix (ECM), immune system processes, and inflammatory responses. We identified a diagnostic model consisting of 16 hub genes, and its predictive performance was validated using external data sets and a transverse aortic coarctation (TAC) mouse model. In addition, we observed significant differences in mRNA expression of 7 genes in the TAC mouse model. Interestingly, our study also unveiled a correlation between these model genes and immune cell infiltration.

CONCLUSIONS

We identified sixteen key genes associated with myocardial fibrosis and conduction block, as well as diagnostic models for heart failure. Our findings have significant implications for the intensive management of individuals with potential genetic variants associated with heart failure, especially in the context of advancing cell-targeted therapy for myocardial fibrosis.

Application of machine learning approaches in predicting clinical outcomes in older adults - a systematic review and meta-analysis

BACKGROUND

Machine learning-based prediction models have the potential to have a considerable positive impact on geriatric care.

DESIGN

Systematic review and meta-analyses.

PARTICIPANTS

Older adults (≥ 65 years) in any setting.

INTERVENTION

Machine learning models for predicting clinical outcomes in older adults were evaluated. A random-effects meta-analysis was conducted in two grouped cohorts, where the predictive models were compared based on their performance in predicting mortality i) under and including 6 months ii) over 6 months.

OUTCOME MEASURES

Studies were grouped into two groups by the clinical outcome, and the models were compared based on the area under the receiver operating characteristic curve metric.

RESULTS

Thirty-seven studies that satisfied the systematic review criteria were appraised, and eight studies predicting a mortality outcome were included in the meta-analyses. We could only pool studies by mortality as there were inconsistent definitions and sparse data to pool studies for other clinical outcomes. The area under the receiver operating characteristic curve from the meta-analysis yielded a summary estimate of 0.80 (95% CI: 0.76 - 0.84) for mortality within 6 months and 0.81 (95% CI: 0.76 - 0.86) for mortality over 6 months, signifying good discriminatory power.

CONCLUSION

The meta-analysis indicates that machine learning models display good discriminatory power in predicting mortality. However, more large-scale validation studies are necessary. As electronic healthcare databases grow larger and more comprehensive, the available computational power increases and machine learning models become more sophisticated; there should be an effort to integrate these models into a larger research setting to predict various clinical outcomes.

Artificial Intelligence-Based Prediction of Lower Extremity Deep Vein Thrombosis Risk After Knee/Hip Arthroplasty

Deep vein thrombosis (DVT) is a common postoperative complication of knee/hip arthroplasty. There is a continued need for artificial intelligence-based methods of predicting lower extremity DVT risk after knee/hip arthroplasty. In this study, we performed a retrospective study to analyse the data from patients who underwent primary knee/hip arthroplasty between January 2017 and December 2021 with postoperative bilateral lower extremity venous ultrasonography. Patients' features were extracted from electronic health records (EHRs) and assigned to the training (80%) and test (20%) datasets using six models: eXtreme gradient boosting, random forest, support vector machines, logistic regression, ensemble, and backpropagation neural network. The Caprini score was calculated according to the Caprini score measurement scale, and the corresponding optimal cut-off Caprini score was calculated according to the largest Youden index. In total, 6897 cases of knee/hip arthroplasty were included (average age, 65.5 ± 8.9 years; 1702 men), among which 1161 (16.8%) were positive and 5736 (83.2%) were negative for deep vein thrombosis. Among the six models, the ensemble model had the highest area under the curve [0.9206 (0.8956, 0.9364)], with a sensitivity, specificity, positive predictive value, negative predictive value, and F1 score of 0.8027, 0.9059, 0.6100, 0.9573 and 0.7003, respectively. The corresponding optimal cut-off Caprini score was 10, with an area under the curve, sensitivity, specificity, positive predictive value, and negative predictive values of 0.5703, 0.8915, 0.2491, 0.1937, 0.9191, and 0.3183, respectively. In conclusion, machine learning models based on EHRs can help predict the risk of deep vein thrombosis after knee/hip arthroplasty.

Unveiling Human Proteome Signatures of Heart Failure with Preserved Ejection Fraction

Heart failure with preserved ejection fraction (HFpEF) is a highly prevalent but still poorly understood clinical entity. Its current pathophysiological understanding supports a critical role of comorbidities and their chronic effect on cardiac function and structure. Importantly, despite the replication of some HFpEF phenotypic features, to this day, experimental models have failed to bring new effective therapies to the clinical setting. Thus, the direct investigation of HFpEF human myocardial samples may unveil key, and possibly human-specific, pathophysiological mechanisms. This study employed quantitative proteomic analysis by advanced mass spectrometry (SWATH-MS) to investigate signaling pathways and pathophysiological mechanisms in HFpEF. Protein-expression profiles were analyzed in human left ventricular myocardial samples of HFpEF patients and compared with a mixed control group. Functional analysis revealed several proteins that correlate with HFpEF, including those associated with mitochondrial dysfunction, oxidative stress, and inflammation. Despite the known disease heterogeneity, proteomic profiles could indicate a reduced mitochondrial oxidative phosphorylation and fatty-acid oxidation capacity in HFpEF patients with diabetes. The proteomic characterization described in this work provides new insights. Furthermore, it fosters further questions related to HFpEF cellular pathophysiology, paving the way for additional studies focused on developing novel therapies and diagnosis strategies for HFpEF patients.

Integration of Multimodal Data from Disparate Sources for Identifying Disease Subtypes

Simple Summary

The diagnostic and treatment strategies of cancer remain generally suboptimal resulting in over-diagnosis or under-treatment. Though many attempts on optimizing treatment decisions by early prediction of disease progression have been undertaken, these efforts yielded only modest success so far due to the heterogeneity of cancer with multifactorial etiology. Here, we propose a deep-learning based data integration model capable of predicting disease progression by integrating collective information available through multiple studies with different cohorts and heterogeneous data types. The results have shown that the proposed data integration pipeline is able to identify disease progression with higher accuracy and robustness compared to using a single cohort, by offering a more complete picture of the specific disease on patients with brain, blood, and pancreatic cancers.

Abstract

Studies over the past decade have generated a wealth of molecular data that can be leveraged to better understand cancer risk, progression, and outcomes. However, understanding the progression risk and differentiating long- and short-term survivors cannot be achieved by analyzing data from a single modality due to the heterogeneity of disease. Using a scientifically developed and tested deep-learning approach that leverages aggregate information collected from multiple repositories with multiple modalities (e.g., mRNA, DNA Methylation, miRNA) could lead to a more accurate and robust prediction of disease progression. Here, we propose an autoencoder based multimodal data fusion system, in which a fusion encoder flexibly integrates collective information available through multiple studies with partially coupled data. Our results on a fully controlled simulation-based study have shown that inferring the missing data through the proposed data fusion pipeline allows a predictor that is superior to other baseline predictors with missing modalities. Results have further shown that short- and long-term survivors of glioblastoma multiforme, acute myeloid leukemia, and pancreatic adenocarcinoma can be successfully differentiated with an AUC of 0.94, 0.75, and 0.96, respectively.

Could a Multi-Marker and Machine Learning Approach Help Stratify Patients with Heart Failure?

Half of the patients with heart failure (HF) have preserved ejection fraction (HFpEF). To date, there are no specific markers to distinguish this subgroup. The main objective of this work was to stratify HF patients using current biochemical markers coupled with clinical data. The cohort study included HFpEF (n = 24) and heart failure with reduced ejection fraction (HFrEF) (n = 34) patients as usually considered in clinical practice based on cardiac imaging (EF ≥ 50% for HFpEF; EF < 50% for HFrEF). Routine blood tests consisted of measuring biomarkers of renal and heart functions, inflammation, and iron metabolism. A multi-test approach and analysis of peripheral blood samples aimed to establish a computerized Machine Learning strategy to provide a blood signature to distinguish HFpEF and HFrEF. Based on logistic regression, demographic characteristics and clinical biomarkers showed no statistical significance to differentiate the HFpEF and HFrEF patient subgroups. Hence a multivariate factorial discriminant analysis, performed blindly using the data set, allowed us to stratify the two HF groups. Consequently, a Machine Learning (ML) strategy was developed using the same variables in a genetic algorithm approach. ML provided very encouraging explorative results when considering the small size of the samples applied. The accuracy and the sensitivity were high for both validation and test groups (69% and 100%, 64% and 75%, respectively). Sensitivity was 100% for the validation and 75% for the test group, whereas specificity was 44% and 55% for the validation and test groups because of the small number of samples. Lastly, the precision was acceptable, with 58% in the validation and 60% in the test group. Combining biochemical and clinical markers is an excellent entry to develop a computer classification tool to diagnose HFpEF. This translational approach is a springboard for improving new personalized treatment methods and identifying “high-yield” populations for clinical trials.