Improved cardiovascular risk prediction in patients with end-stage renal disease on hemodialysis using machine learning modeling and circulating microribonucleic acids

Diagnostic predictability of serum miR-4793-3p and miR-1180-3p expression in community-acquired pneumonia

Background: Early identification of community-acquired pneumonia (CAP) is crucial to prevent severe progression. Methods: The authors enrolled 150 hospitalized CAP patients and collected clinicopathologic features and blood indicators. Plasma miRNA profiling was conducted using microarray detection, and selected miRNAs were tested with reverse transcription quantitative PCR. Predictive models were built using least shrinkage and selection operator regression. Results: Least shrinkage and selection operator regression identified two miRNAs (miR-4793-3p and miR-1180-3p) that distinguished mild from severe CAP patients (area under the curve = 0.948). The miRNA model outperformed D-dimer, platelet and procalcitonin (max area under the curve = 0.729). Conclusion: Increased levels of miR-4793-3p and miR-1180-3p may indicate severe pneumonia development. Plasma miRNA profiling enables early prediction of severe CAP, aiding therapeutic decisions.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

A Machine Learning Model Based on microRNAs for the Diagnosis of Essential Hypertension

INTRODUCTION

Hypertension is a major and modifiable risk factor for cardiovascular diseases. Essential, primary, or idiopathic hypertension accounts for 90-95% of all cases. Identifying novel biomarkers specific to essential hypertension may help in understanding pathophysiological pathways and developing personalized treatments. We tested whether the integration of circulating microRNAs (miRNAs) and clinical risk factors via machine learning modeling may provide useful information and novel tools for essential hypertension diagnosis and management.

MATERIALS AND METHODS

In total, 174 participants were enrolled in the present observational case-control study, among which, there were 89 patients with essential hypertension and 85 controls. A discovery phase was conducted using small RNA sequencing in whole blood samples obtained from age- and sex-matched hypertension patients (n = 30) and controls (n = 30). A validation phase using RT-qPCR involved the remaining 114 participants. For machine learning, 170 participants with complete data were used to generate and evaluate the classification model.

RESULTS

Small RNA sequencing identified seven miRNAs downregulated in hypertensive patients as compared with controls in the discovery group, of which six were confirmed with RT-qPCR. In the validation group, miR-210-3p/361-3p/362-5p/378a-5p/501-5p were also downregulated in hypertensive patients. A machine learning support vector machine (SVM) model including clinical risk factors (sex, BMI, alcohol use, current smoker, and hypertension family history), miR-361-3p, and miR-501-5p was able to classify hypertension patients in a test dataset with an AUC of 0.90, a balanced accuracy of 0.87, a sensitivity of 0.83, and a specificity of 0.91. While five miRNAs exhibited substantial downregulation in hypertension patients, only miR-361-3p and miR-501-5p, alongside clinical risk factors, were consistently chosen in at least eight out of ten sub-training sets within the SVM model.

CONCLUSIONS

This study highlights the potential significance of miRNA-based biomarkers in deepening our understanding of hypertension's pathophysiology and in personalizing treatment strategies. The strong performance of the SVM model highlights its potential as a valuable asset for diagnosing and managing essential hypertension. The model remains to be extensively validated in independent patient cohorts before evaluating its added value in a clinical setting.

Circulating miR-133a-3p defines a low-risk subphenotype in patients with heart failure and central sleep apnea: a decision tree machine learning approach

BACKGROUND

Patients with heart failure with reduced ejection fraction (HFrEF) and central sleep apnea (CSA) are at a very high risk of fatal outcomes.

OBJECTIVE

To test whether the circulating miRNome provides additional information for risk stratification on top of clinical predictors in patients with HFrEF and CSA.

METHODS

The study included patients with HFrEF and CSA from the SERVE-HF trial. A three-step protocol was applied: microRNA (miRNA) screening (n = 20), technical validation (n = 60), and biological validation (n = 587). The primary outcome was either death from any cause, lifesaving cardiovascular intervention, or unplanned hospitalization for worsening of heart failure, whatever occurred first. MiRNA quantification was performed in plasma samples using miRNA sequencing and RT-qPCR.

RESULTS

Circulating miR-133a-3p levels were inversely associated with the primary study outcome. Nonetheless, miR-133a-3p did not improve a previously established clinical prognostic model in terms of discrimination or reclassification. A customized regression tree model constructed using the Classification and Regression Tree (CART) algorithm identified eight patient subphenotypes with specific risk patterns based on clinical and molecular characteristics. MiR-133a-3p entered the regression tree defining the group at the lowest risk; patients with log(NT-proBNP) ≤ 6 pg/mL (miR-133a-3p levels above 1.5 arbitrary units). The overall predictive capacity of suffering the event was highly stable over the follow-up (from 0.735 to 0.767).

CONCLUSIONS

The combination of clinical information, circulating miRNAs, and decision tree learning allows the identification of specific risk subphenotypes in patients with HFrEF and CSA.

Circulating microRNAs as Potential Biomarkers in Pancreatic Cancer-Advances and Challenges

There is an urgent unmet need for robust and reliable biomarkers for early diagnosis, prognosis, and prediction of response to specific treatments of many aggressive and deadly cancers, such as pancreatic cancer, and liquid biopsy-based miRNA profiling has the potential for this. MiRNAs are a subset of non-coding RNAs that regulate the expression of a multitude of genes post-transcriptionally and thus are potential diagnostic, prognostic, and predictive biomarkers and have also emerged as potential therapeutics. Because miRNAs are involved in the post-transcriptional regulation of their target mRNAs via repressing gene expression, defects in miRNA biogenesis pathway and miRNA expression perturb the expression of a multitude of oncogenic or tumor-suppressive genes that are involved in the pathogenesis of various cancers. As such, numerous miRNAs have been identified to be downregulated or upregulated in many cancers, functioning as either oncomes or oncosuppressor miRs. Moreover, dysregulation of miRNA biogenesis pathways can also change miRNA expression and function in cancer. Profiling of dysregulated miRNAs in pancreatic cancer has been shown to correlate with disease diagnosis, indicate optimal treatment options and predict response to a specific therapy. Specific miRNA signatures can track the stages of pancreatic cancer and hold potential as diagnostic, prognostic, and predictive markers, as well as therapeutics such as miRNA mimics and miRNA inhibitors (antagomirs). Furthermore, identified specific miRNAs and genes they regulate in pancreatic cancer along with downstream pathways can be used as potential therapeutic targets. However, a limited understanding and validation of the specific roles of miRNAs, lack of tissue specificity, methodological, technical, or analytical reproducibility, harmonization of miRNA isolation and quantification methods, the use of standard operating procedures, and the availability of automated and standardized assays to improve reproducibility between independent studies limit bench-to-bedside translation of the miRNA biomarkers for clinical applications. Here I review recent findings on miRNAs in pancreatic cancer pathogenesis and their potential as diagnostic, prognostic, and predictive markers.

Diagnosis of acute myocardial infarction using a combination of circulating circular RNA cZNF292 and clinical information based on machine learning

Circulating circular RNAs (circRNAs) are emerging as novel biomarkers for cardiovascular diseases (CVDs). Machine learning can provide optimal predictions on the diagnosis of diseases. Here we performed a proof-of-concept study to determine if combining circRNAs with an artificial intelligence approach works in diagnosing CVD. We used acute myocardial infarction (AMI) as a model setup to prove the claim. We determined the expression level of five hypoxia-induced circRNAs, including cZNF292, cAFF1, cDENND4C, cTHSD1, and cSRSF4, in the whole blood of coronary angiography positive AMI and negative non-AMI patients. Based on feature selection by using lasso with 10-fold cross validation, prediction model by logistic regression, and ROC curve analysis, we found that cZNF292 combined with clinical information (CM), including age, gender, body mass index, heart rate, and diastolic blood pressure, can predict AMI effectively. In a validation cohort, CM + cZNF292 can separate AMI and non-AMI patients, unstable angina and AMI patients, acute coronary syndromes (ACS), and non-ACS patients. RNA stability study demonstrated that cZNF292 was stable. Knockdown of cZNF292 in endothelial cells or cardiomyocytes showed anti-apoptosis effects in oxygen glucose deprivation/reoxygenation. Thus, we identify circulating cZNF292 as a potential biomarker for AMI and construct a prediction model "CM + cZNF292."

Noncoding RNome as Enabling Biomarkers for Precision Health

Noncoding RNAs (ncRNAs), in the form of structural, catalytic or regulatory RNAs, have emerged to be critical effectors of many biological processes. With the advent of new technologies, we have begun to appreciate how intracellular and circulatory ncRNAs elegantly choreograph the regulation of gene expression and protein function(s) in the cell. Armed with this knowledge, the clinical utility of ncRNAs as biomarkers has been recently tested in a wide range of human diseases. In this review, we examine how critical factors govern the success of interrogating ncRNA biomarker expression in liquid biopsies and tissues to enhance our current clinical management of human diseases, particularly in the context of cancer. We also discuss strategies to overcome key challenges that preclude ncRNAs from becoming standard-of-care clinical biomarkers, including sample pre-analytics standardization, data cross-validation with closer attention to discordant findings, as well as correlation with clinical outcomes. Although harnessing multi-modal information from disease-associated noncoding RNome (ncRNome) in biofluids or in tissues using artificial intelligence or machine learning is at the nascent stage, it will undoubtedly fuel the community adoption of precision population health.

Bronchial Aspirate-Based Profiling Identifies MicroRNA Signatures Associated With COVID-19 and Fatal Disease in Critically Ill Patients

Background

The pathophysiology of COVID-19-related critical illness is not completely understood. Here, we analyzed the microRNA (miRNA) profile of bronchial aspirate (BAS) samples from COVID-19 and non-COVID-19 patients admitted to the ICU to identify prognostic biomarkers of fatal outcomes and to define molecular pathways involved in the disease and adverse events.

Methods

Two patient populations were included (n = 89): (i) a study population composed of critically ill COVID-19 and non-COVID-19 patients; (ii) a prospective study cohort composed of COVID-19 survivors and non-survivors among patients assisted by invasive mechanical ventilation (IMV). BAS samples were obtained by bronchoaspiration during the ICU stay. The miRNA profile was analyzed using RT-qPCR. Detailed biomarker and bioinformatics analyses were performed.

Results

The deregulation in five miRNA ratios (miR-122-5p/miR-199a-5p, miR-125a-5p/miR-133a-3p, miR-155-5p/miR-486-5p, miR-214-3p/miR-222-3p, and miR-221-3p/miR-27a-3p) was observed when COVID-19 and non-COVID-19 patients were compared. In addition, five miRNA ratios segregated between ICU survivors and nonsurvivors (miR-1-3p/miR-124-3p, miR-125b-5p/miR-34a-5p, miR-126-3p/miR-16-5p, miR-199a-5p/miR-9-5p, and miR-221-3p/miR-491-5p). Through multivariable analysis, we constructed a miRNA ratio-based prediction model for ICU mortality that optimized the best combination of miRNA ratios (miR-125b-5p/miR-34a-5p, miR-199a-5p/miR-9-5p, and miR-221-3p/miR-491-5p). The model (AUC 0.85) and the miR-199a-5p/miR-9-5p ratio (AUC 0.80) showed an optimal discrimination value and outperformed the best clinical predictor for ICU mortality (days from first symptoms to IMV initiation, AUC 0.73). The survival analysis confirmed the usefulness of the miRNA ratio model and the individual ratio to identify patients at high risk of fatal outcomes following IMV initiation. Functional enrichment analyses identified pathological mechanisms implicated in fibrosis, coagulation, viral infections, immune responses and inflammation.

Conclusions

COVID-19 induces a specific miRNA signature in BAS from critically ill patients. In addition, specific miRNA ratios in BAS samples hold individual and collective potential to improve risk-based patient stratification following IMV initiation in COVID-19-related critical illness. The biological role of the host miRNA profiles may allow a better understanding of the different pathological axes of the disease.

Circulating microRNA profiles predict the severity of COVID-19 in hospitalized patients

We aimed to examine the circulating microRNA (miRNA) profile of hospitalized COVID-19 patients and evaluate its potential as a source of biomarkers for the management of the disease. This was an observational and multicenter study that included 84 patients with a positive nasopharyngeal swab Polymerase chain reaction (PCR) test for SARS-CoV-2 recruited during the first pandemic wave in Spain (March-June 2020). Patients were stratified according to disease severity: hospitalized patients admitted to the clinical wards without requiring critical care and patients admitted to the intensive care unit (ICU). An additional study was completed including ICU nonsurvivors and survivors. Plasma miRNA profiling was performed using reverse transcription polymerase quantitative chain reaction (RT-qPCR). Predictive models were constructed using least absolute shrinkage and selection operator (LASSO) regression. Ten circulating miRNAs were dysregulated in ICU patients compared to ward patients. LASSO analysis identified a signature of three miRNAs (miR-148a-3p, miR-451a and miR-486-5p) that distinguishes between ICU and ward patients [AUC (95% CI) = 0.89 (0.81-0.97)]. Among critically ill patients, six miRNAs were downregulated between nonsurvivors and survivors. A signature based on two miRNAs (miR-192-5p and miR-323a-3p) differentiated ICU nonsurvivors from survivors [AUC (95% CI) = 0.80 (0.64-0.96)]. The discriminatory potential of the signature was higher than that observed for laboratory parameters such as leukocyte counts, C-reactive protein (CRP) or D-dimer [maximum AUC (95% CI) for these variables = 0.73 (0.55-0.92)]. miRNA levels were correlated with the duration of ICU stay. Specific circulating miRNA profiles are associated with the severity of COVID-19. Plasma miRNA signatures emerge as a novel tool to assist in the early prediction of vital status deterioration among ICU patients.

Prognostic value of circulating microRNAs compared to high-sensitivity troponin T in patients presenting with suspected acute coronary syndrome to the emergency department

BACKGROUND

To evaluate the prognostic value of eleven microRNAs (miRNAs) compared to high-sensitivity Troponin T (hs-cTnT) in patients presenting with suspected acute coronary syndrome (ACS) to the emergency department (ED).

METHODS

1,042 patients presenting between August 2014 and April 2017 were included. Expression levels of eleven microRNAs (miR-21-5p, miR-22-3p, miR-29a-3p, miR-92a-3p, miR-122-5p, miR-126-3p, miR-132-3p, miR-133a-3p, miR-134-5p, miR-191-3p, and miR-423-5p) were determined using RT-qPCR. All-cause mortality (ACM) and a composite of ACM, acute myocardial infarction (AMI) and stroke were defined as endpoints.

RESULTS

During a median follow-up of 399 (P25-P75: 381-525) days 58 patients (5.6%) died. The composite endpoint occurred in 86 patients (8.3%). Different expression levels of miR-21-5p (median, P25-P75: 5.28 [5.14-5.51] vs. 5.16 [4.97-5.35], p = 0.0033) and miR-122-5p (median, P25-P75: 5.17 [4.81-5.49] vs. 5.35 [5.01-5.69], p = 0.0184) were observed in patients who died compared to survivors. ROC-optimized cutoff of miR-21-5p (HR, P25-P75: 3.3 [1.2-9.4], p = 0.0239), but not miR-122-5p (HR, P25-P75: 0.4 [0.2-0.8], p = 0.0116), was predictive for all-cause mortality, even after adjustment in a multivariate model. Nevertheless, addition of miR-21-5p and miR-122-5p decreased prognostic accuracy of hs-cTnT for all-cause mortality (△AUC: 0.112, p = 0.0159). Hs-cTnT admission values had a high prognostic value for ACM (AUC [95%CI] = 0.794 [0.751-0.837]) and the composite of ACM, AMI and stroke (AUC [95%CI] = 0.745 [0.695-0.794]).

CONCLUSIONS

Despite a different expression depending on outcomes miR-21-5p and miR-122-5p do not add prognostic information to hs-cTnT in patients presenting with suspected ACS to the ED.

Development and Validation of a Prediction Model for Elevated Arterial Stiffness in Chinese Patients With Diabetes Using Machine Learning

Background

Arterial stiffness assessed by pulse wave velocity is a major risk factor for cardiovascular diseases. The incidence of cardiovascular events remains high in diabetics. However, a clinical prediction model for elevated arterial stiffness using machine learning to identify subjects consequently at higher risk remains to be developed.

Methods

Least absolute shrinkage and selection operator and support vector machine-recursive feature elimination were used for feature selection. Four machine learning algorithms were used to construct a prediction model, and their performance was compared based on the area under the receiver operating characteristic curve metric in a discovery dataset (n = 760). The model with the best performance was selected and validated in an independent dataset (n = 912) from the Dryad Digital Repository (https://doi.org/10.5061/dryad.m484p). To apply our model to clinical practice, we built a free and user-friendly web online tool.

Results

The predictive model includes the predictors: age, systolic blood pressure, diastolic blood pressure, and body mass index. In the discovery cohort, the gradient boosting-based model outperformed other methods in the elevated arterial stiffness prediction. In the validation cohort, the gradient boosting model showed a good discrimination capacity. A cutoff value of 0.46 for the elevated arterial stiffness risk score in the gradient boosting model resulted in a good specificity (0.813 in the discovery data and 0.761 in the validation data) and sensitivity (0.875 and 0.738, respectively) trade-off points.

Conclusion

The gradient boosting-based prediction system presents a good classification in elevated arterial stiffness prediction. The web online tool makes our gradient boosting-based model easily accessible for further clinical studies and utilization.

Development and Validation of a Prediction Model for Elevated Arterial Stiffness in Chinese Patients With Diabetes Using Machine Learning

Background

Arterial stiffness assessed by pulse wave velocity is a major risk factor for cardiovascular diseases. The incidence of cardiovascular events remains high in diabetics. However, a clinical prediction model for elevated arterial stiffness using machine learning to identify subjects consequently at higher risk remains to be developed.

Methods

Least absolute shrinkage and selection operator and support vector machine-recursive feature elimination were used for feature selection. Four machine learning algorithms were used to construct a prediction model, and their performance was compared based on the area under the receiver operating characteristic curve metric in a discovery dataset (n = 760). The model with the best performance was selected and validated in an independent dataset (n = 912) from the Dryad Digital Repository (https://doi.org/10.5061/dryad.m484p). To apply our model to clinical practice, we built a free and user-friendly web online tool.

Results

The predictive model includes the predictors: age, systolic blood pressure, diastolic blood pressure, and body mass index. In the discovery cohort, the gradient boosting-based model outperformed other methods in the elevated arterial stiffness prediction. In the validation cohort, the gradient boosting model showed a good discrimination capacity. A cutoff value of 0.46 for the elevated arterial stiffness risk score in the gradient boosting model resulted in a good specificity (0.813 in the discovery data and 0.761 in the validation data) and sensitivity (0.875 and 0.738, respectively) trade-off points.

Conclusion

The gradient boosting-based prediction system presents a good classification in elevated arterial stiffness prediction. The web online tool makes our gradient boosting-based model easily accessible for further clinical studies and utilization.

Computational Models Used to Predict Cardiovascular Complications in Chronic Kidney Disease Patients: A Systematic Review

Background and objectives: cardiovascular complications (CVC) are the leading cause of death in patients with chronic kidney disease (CKD). Standard cardiovascular disease risk prediction models used in the general population are not validated in patients with CKD. We aim to systematically review the up-to-date literature on reported outcomes of computational methods such as artificial intelligence (AI) or regression-based models to predict CVC in CKD patients. Materials and methods: the electronic databases of MEDLINE/PubMed, EMBASE, and ScienceDirect were systematically searched. The risk of bias and reporting quality for each study were assessed against transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) and the prediction model risk of bias assessment tool (PROBAST). Results: sixteen papers were included in the present systematic review: 15 non-randomized studies and 1 ongoing clinical trial. Twelve studies were found to perform AI or regression-based predictions of CVC in CKD, either through single or composite endpoints. Four studies have come up with computational solutions for other CV-related predictions in the CKD population. Conclusions: the identified studies represent palpable trends in areas of clinical promise with an encouraging present-day performance. However, there is a clear need for more extensive application of rigorous methodologies. Following the future prospective, randomized clinical trials, and thorough external validations, computational solutions will fill the gap in cardiovascular predictive tools for chronic kidney disease.

Peripheral blood microRNAs and the COVID-19 patient: methodological considerations, technical challenges and practice points

The COVID-19 emergency pandemic resulting from infection with SARS-CoV-2 represents a major threat to public health worldwide. There is an urgent clinical demand for easily accessible tools to address weaknesses and gaps in the management of COVID-19 patients. In this context, transcriptomic profiling of liquid biopsies, especially microRNAs (miRNAs), has recently emerged as a robust source of potential clinical indicators for medical decision-making. Nevertheless, the analysis of the circulating miRNA signature and its translation to clinical practice requires strict control of a wide array of methodological details. In this review, we indicate the main methodological aspects that should be addressed when evaluating the circulating miRNA profiles in COVID-19 patients, from preanalytical and analytical variables to the experimental design, impact of confounding, analysis of the data and interpretation of the findings, among others. Additionally, we provide practice points to ensure the rigour and reproducibility of miRNA-based biomarker investigations of this condition.Abbreviations: ACE: angiotensin-converting enzyme; ARDS: acute respiratory distress syndrome; COVID-19: coronavirus disease 2019; ERDN: early Detection Research Network; LMWH: low molecular weight heparin; miRNA: microRNA; ncRNA: noncoding RNA; SARS-CoV-2: severe acute respiratory syndrome coronavirus-2; SOP: standard operating procedure.