Mortality risk in dilated cardiomyopathy: the accuracy of heart failure prognostic models and dilated cardiomyopathy‐tailored prognostic model

Dziewięcka, Ewa; Gliniak, Matylda; Winiarczyk, Mateusz; Karapetyan, Arman; Wiśniowska‐Śmiałek, Sylwia; Karabinowska, Aleksandra; Dziewięcki, Marcin; Podolec, Piotr; Rubiś, Paweł

doi:10.1002/ehf2.12809

Cited by 22 publications

(25 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several clinical prediction models have been constructed for heart failure in the general cardiology population in order to facilitate prognostic assessments. The Seattle Heart Failure Model (SHFM) [ 71 ], MAGGIC risk score [ 72 ], and the Barcelona bio-HF calculator [ 73 ] are three models with comparable risk prediction performance [ 74 ]. The performance of these models in DCM may, however, be suboptimal because their derivation also included patients with ischemic aetiology who are known to have a higher mortality risk than DCM patients (3-year mortality between 24–40%) [ 37 , 74 ].…”

Section: Prognosis Of Dcmmentioning

confidence: 99%

“…The Seattle Heart Failure Model (SHFM) [ 71 ], MAGGIC risk score [ 72 ], and the Barcelona bio-HF calculator [ 73 ] are three models with comparable risk prediction performance [ 74 ]. The performance of these models in DCM may, however, be suboptimal because their derivation also included patients with ischemic aetiology who are known to have a higher mortality risk than DCM patients (3-year mortality between 24–40%) [ 37 , 74 ]. Indeed, a recent comparison of these prediction models in an external DCM cohort produced an area under the curve (AUC) of ≥0.6, with the more sophisticated risk models (BCN Bio-HF and SHFM) yielding the highest accuracies [ 71 , 73 , 74 ].…”

Section: Prognosis Of Dcmmentioning

confidence: 99%

“…The performance of these models in DCM may, however, be suboptimal because their derivation also included patients with ischemic aetiology who are known to have a higher mortality risk than DCM patients (3-year mortality between 24–40%) [ 37 , 74 ]. Indeed, a recent comparison of these prediction models in an external DCM cohort produced an area under the curve (AUC) of ≥0.6, with the more sophisticated risk models (BCN Bio-HF and SHFM) yielding the highest accuracies [ 71 , 73 , 74 ]. Interestingly, the risk models typically overestimated mortality risk in DCM patients.…”

Section: Prognosis Of Dcmmentioning

confidence: 99%

“…Interestingly, the risk models typically overestimated mortality risk in DCM patients. This may be caused by a difference in age (DCM patients tend to be younger (±15 years) than other heart failure aetiologies), which is one of the strongest variables affecting mortality [ 37 , 74 ]. Moreover, there is a distinct subgroup of DCM patients who experience LV function recovery and have a subsequent mild clinical course during follow-up [ 75 ].…”

Section: Prognosis Of Dcmmentioning

confidence: 99%

“…These patients typically have higher LV contractile reserve and are more often women, whereas the presence of LGE on CMR in patients with DCM often represents an ominous marker [ 76 , 77 ]. Larger prospective studies are warranted for two purposes: (1) to discriminate patients who may recover and better understand their pathophysiologic substrates which may impact new treatment strategies, and (2) to develop a risk stratification tool dedicated for DCM patients that also incorporates variables reflecting LV recovery [ 74 , 77 , 78 ].…”

Section: Prognosis Of Dcmmentioning

confidence: 99%

See 4 more Smart Citations

Diagnosis and Risk Prediction of Dilated Cardiomyopathy in the Era of Big Data and Genomics

Sammani

Baas

Asselbergs

et al. 2021

JCM

View full text Add to dashboard Cite

Dilated cardiomyopathy (DCM) is a leading cause of heart failure and life-threatening ventricular arrhythmias (LTVA). Work-up and risk stratification of DCM is clinically challenging, as there is great heterogeneity in phenotype and genotype. Throughout the last decade, improved genetic testing of patients has identified genotype–phenotype associations and enhanced evaluation of at-risk relatives leading to better patient prognosis. The field is now ripe to explore opportunities to improve personalised risk assessments. Multivariable risk models presented as “risk calculators” can incorporate a multitude of clinical variables and predict outcome (such as heart failure hospitalisations or LTVA). In addition, genetic risk scores derived from genome/exome-wide association studies can estimate an individual’s lifetime genetic risk of developing DCM. The use of clinically granular investigations, such as late gadolinium enhancement on cardiac magnetic resonance imaging, is warranted in order to increase predictive performance. To this end, constructing big data infrastructures improves accessibility of data by using electronic health records, existing research databases, and disease registries. By applying methods such as machine and deep learning, we can model complex interactions, identify new phenotype clusters, and perform prognostic modelling. This review aims to provide an overview of the evolution of DCM definitions as well as its clinical work-up and considerations in the era of genomics. In addition, we present exciting examples in the field of big data infrastructures, personalised prognostic assessment, and artificial intelligence.

show abstract

Section: Prognosis Of Dcmmentioning

confidence: 99%

Section: Prognosis Of Dcmmentioning

confidence: 99%

Section: Prognosis Of Dcmmentioning

confidence: 99%

Section: Prognosis Of Dcmmentioning

confidence: 99%

Section: Prognosis Of Dcmmentioning

confidence: 99%

See 3 more Smart Citations

Diagnosis and Risk Prediction of Dilated Cardiomyopathy in the Era of Big Data and Genomics

Sammani

Baas

Asselbergs

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

Outcomes after transvenous defibrillator implantation in cardiac sarcoidosis: A systematic review

Taha

Assaf

Champsi

et al. 2022

Journal of Arrhythmia

View full text Add to dashboard Cite

Introduction Sarcoidosis is a systemic inflammatory disorder associated with ventricular arrhythmias (VAs) and sudden death in the context of cardiac involvement. Guidelines advocate implantable cardioverter‐defibrillator (ICD) implantation in specific subcohorts, but there is a paucity of data on outcomes. Methods and Results A systematic review was performed to assess outcomes in patients with definite or probable cardiac sarcoidosis (CS) treated with ICD. Observational studies were identified from multiple databases from inception to 21st May 2021. Outcomes of interest included appropriate and inappropriate ICD therapies in addition to all‐cause mortality. Study quality was assessed individually using the Newcastle Ottawa Scale (NOS). Eight studies were identified comprising 530 patients, with follow‐up period of 24–66 months (weighted average 40 months). Mean age was 53.9 years with ejection fraction of 41.3%. Overall incidence of appropriate therapy was 38.1% during follow‐up. Left ventricular systolic dysfunction (LVSD) with ejection fraction <40% was a predictor of appropriate therapy in the majority of studies, as were sustained VAs during electrophysiological testing (EP) in one study. There was no interaction with device indication (i.e. primary or secondary). Where documented, inappropriate therapy was primarily driven by atrial arrhythmias. All‐cause mortality was 6.0% over a median follow‐up period of 42 months. Only three studies achieved good quality in the comparability domain of NOS. Conclusions Appropriate ICD therapy in patients with CS is commonly associated with LVSD, which can act as a surrogate for scar burden. The utility of EP testing in this setting remains unclear.

show abstract

What can machines learn about heart failure? A systematic literature review

Jasinska-Piadlo

Bond

Biglarbeigi

et al. 2021

Int J Data Sci Anal

View full text Add to dashboard Cite

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

show abstract

Mortality risk in dilated cardiomyopathy: the accuracy of heart failure prognostic models and dilated cardiomyopathy‐tailored prognostic model

Cited by 22 publications

References 37 publications

Diagnosis and Risk Prediction of Dilated Cardiomyopathy in the Era of Big Data and Genomics

Diagnosis and Risk Prediction of Dilated Cardiomyopathy in the Era of Big Data and Genomics

Outcomes after transvenous defibrillator implantation in cardiac sarcoidosis: A systematic review

What can machines learn about heart failure? A systematic literature review

Contact Info

Product

Resources

About