Prognostic Modeling in Heart Failure: Time for a Reboot

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

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.

Clinical Predictors of Mortality in Prehospital Distress Calls by Emergency Medical Service Subscribers

(1) Introduction: Most studies rely on in-hospital data to predict cardiovascular risk and do not include prehospital information that is substantially important for early decision making. The aim of the study was to define clinical parameters in the prehospital setting, which may affect clinical outcomes. (2) Methods: In this population-based study, we performed a retrospective analysis of emergency calls that were made by patients to the largest private emergency medical services (EMS) in Israel, SHL Telemedicine Ltd., who were treated on-site by the EMS team. Demographics, clinical characteristics, and clinical outcomes were analyzed. Mortality was evaluated at three time points: 1, 3, and 12 months’ follow-up. The first EMS prehospital measurements of the systolic blood pressure (SBP) were recorded and analyzed. Logistic regression analyses were performed. (3) Results: A total of 64,320 emergency calls were included with a follow-up of 12 months post index EMS call. Fifty-five percent of patients were men and the mean age was 70.2 ± 13.1 years. During follow-up of 12 months, 7.6% of patients died. Age above 80 years (OR 3.34; 95% CI 3.03–3.69, p < 0.005), first EMS SBP ≤ 130 mm Hg (OR 2.61; 95% CI 2.36–2.88, p < 0.005), dyspnea at presentation (OR 2.55; 95% CI 2.29–2.83, p < 0001), and chest pain with ischemic ECG changes (OR 1.95; 95% CI 1.71–2.23, p < 0.001) were the highest predictors of 1 month mortality and remained so for mortality at 3 and 12 months. In contrast, history of hypertension and first EMS prehospital SBP ≥ 160 mm Hg were significantly associated with decreased mortality at 1, 3 and 12 months. (4) Conclusions: We identified risk predictors for all-cause mortality in a large cohort of patients during prehospital EMS calls. Age over 80 years, first EMS-documented prehospital SBP < 130 mm Hg, and dyspnea at presentation were the most profound risk predictors for short- and long-term mortality. The current study demonstrates that in prehospital EMS call settings, several parameters can be used to improve prioritization and management of high-risk patients.

Evaluating risk prediction models for adults with heart failure: A systematic literature review

Background

The ability to predict risk allows healthcare providers to propose which patients might benefit most from certain therapies, and is relevant to payers’ demands to justify clinical and economic value. To understand the robustness of risk prediction models for heart failure (HF), we conducted a systematic literature review to (1) identify HF risk-prediction models, (2) assess statistical approach and extent of validation, (3) identify common variables, and (4) assess risk of bias (ROB).

Methods

Literature databases were searched from March 2013 to May 2018 to identify risk prediction models conducted in an out-of-hospital setting in adults with HF. Distinct risk prediction variables were ranked according to outcomes assessed and incorporation into the studies. ROB was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST).

Results

Of 4720 non-duplicated citations, 40 risk-prediction publications were deemed relevant. Within the 40 publications, 58 models assessed 55 (co)primary outcomes, including all-cause mortality (n = 17), cardiovascular death (n = 9), HF hospitalizations (n = 15), and composite endpoints (n = 14). Few publications reported detail on handling missing data (n = 11; 28%). The discriminatory ability for predicting all-cause mortality, cardiovascular death, and composite endpoints was generally better than for HF hospitalization. 105 distinct predictor variables were identified. Predictors included in >5 publications were: N-terminal prohormone brain-natriuretic peptide, creatinine, blood urea nitrogen, systolic blood pressure, sodium, NYHA class, left ventricular ejection fraction, heart rate, and characteristics including male sex, diabetes, age, and BMI. Only 11/58 (19%) models had overall low ROB, based on our application of PROBAST. In total, 26/58 (45%) models discussed internal validation, and 14/58 (24%) external validation.

Conclusions

The majority of the 58 identified risk-prediction models for HF present particular concerns according to ROB assessment, mainly due to lack of validation and calibration. The potential utility of novel approaches such as machine learning tools is yet to be determined.

Registration number

The SLR was registered in Prospero (ID: CRD42018100709).