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).
Competing Interests: GLDT was an employee of Amgen at the time of the study. HW, and GG. are employees of Amgen. H.W. also holds corporate stock in Teva Pharmaceutical Industries Ltd. KLB is an employee of Envision Pharma Group, who were contracted by Amgen in relation to the SLR and manuscript development. This does not alter our adherence to PLOS ONE policies on sharing data and materials. Author contributions: All authors fulfill International Committee of Medical Journal Editors (ICMJE) authorship criteria. GLDT and GG planned and designed this study. GLDT, HW and KLB conducted the review, screened the studies, and/or extracted the information. All authors were involved in aspects of data analysis and interpretation. All authors were involved in drafting the manuscript and approved its final version for submission and take responsibility for the whole content.

Erratum in: PLoS One. 2020 Jul 2;15(7):e0235970. (PMID: 32614921)