The Pro-AF machine learning-based protein risk score discriminated 5-year incident atrial fibrillation risk with an AUROC of 0.763, outperforming both clinical and polygenic risk scores.
Cohort (n=46,629)
Yes
Does a machine learning-based plasma protein risk score improve prediction of 5-year incident atrial fibrillation compared to clinical and genomic models in the UK Biobank cohort?
A machine learning-based proteomic risk score significantly improves the prediction of 5-year incident atrial fibrillation compared to established clinical and genetic risk models.
Effect estimate: AUROC 0.763 (95% CI 0.734-0.784)
Absolute Event Rate: 0.763% vs 0.702%
BACKGROUND: Clinical factors discriminate incident atrial fibrillation (AF) risk with moderate accuracy, with only modest improvement after incorporation of polygenic risk scores. Whether emerging large-scale proteomic profiling can augment AF risk estimation is unknown. METHODS: In the UK Biobank cohort, we derived and validated a machine learning model to predict incident AF risk using serum proteins (Pro-AF). We compared Pro-AF to a validated clinical risk score (Cohorts for Heart and Aging Research in Genomic Epidemiology-Atrial Fibrillation, CHARGE-AF) and an AF polygenic risk score. Models were evaluated in a multiply resampled test set from nested cross-validation (internal test set), and a sample of UK Biobank participants separate from model development (hold-out test set). Metrics included discrimination of 5-year incident AF using time-dependent area under the receiver operating characteristic curve and net reclassification. RESULTS: Trained in 32 631 UK Biobank participants, Pro-AF predicts incident AF using 121 protein levels (out of 2911 protein analytes). When assessed in the internal test set comprising 30 632 individuals (mean age 57±8 years, 54% women, 2045 AF events) and hold-out test set comprising 13 998 individuals (mean age 57±8 years, 54% women, 870 AF events), discrimination of 5-year incident AF was highest using Pro-AF (area under the receiver operating characteristic curve internal: 0.761 95% CI, 0.745-0.780, hold-out: 0.763 0.734-0.784), followed by CHARGE-AF (0.719 0.700-0.737; 0.702 0.668-0.730) and the polygenic risk score (0.686 0.668-0.702; 0.682 0.660-0.710). AF risk estimates were well-calibrated, and the addition of Pro-AF led to substantial continuous net reclassification improvement over CHARGE-AF (eg, internal test set 0.410 0.330-0.492). A simplified Pro-AF including only the 5 most influential proteins (NT-proBNP N-terminal pro-brain natriuretic peptide, EDA2R ectodysplasin A2 receptor, NPPB B-type natriuretic peptide, BCAN brevican core protein, and GDF15 growth/differentiation factor 15), retained favorable discriminative value (area under the receiver operating characteristic curve internal: 0.750 0.733-0.768; hold-out: 0.759 0.732-0.790). CONCLUSIONS: A machine learning-based protein score discriminates 5-year incident AF risk favorably compared with clinical and genetic risk factors. Large-scale proteomic analysis may assist in the prioritization of individuals at risk for AF for screening and related preventive interventions.
Kim et al. (Tue,) conducted a cohort in Incident Atrial Fibrillation (n=46,629). Pro-AF (Machine Learning-Based Plasma Protein Risk Score) vs. CHARGE-AF clinical risk score and AF polygenic risk score (PRS) was evaluated on Discrimination of 5-year incident AF (AUROC) (AUROC 0.763, 95% CI 0.734-0.784). The Pro-AF machine learning-based protein risk score discriminated 5-year incident atrial fibrillation risk with an AUROC of 0.763, outperforming both clinical and polygenic risk scores.