Key result
BRIDGE Bayesian model predicts lipid-lowering therapy adherence trajectories with ~0.81 AUROC, matching XGBoost.
Why the study?
Longitudinal non-adherence trajectories for lipid-lowering therapies remain poorly predicted in primary care because adherence is typically assessed using static measures. No existing models combine patient-reported barriers at treatment initiation with real-world prescribing data to forecast these trajectories.
Does the BRIDGE barrier-informed Bayesian model improve the prediction of longitudinal medication adherence trajectories compared to machine-learning baselines in primary care patients initiating lipid-lowering therapy?
Observational (n=50,881)
Does the BRIDGE barrier-informed Bayesian model improve the prediction of longitudinal medication adherence trajectories compared to machine-learning baselines in primary care patients initiating lipid-lowering therapy?
Answers are grounded in this paper and cite their sources.
The BRIDGE Bayesian model accurately predicts longitudinal lipid-lowering therapy adherence trajectories using routine primary care data (AUROC 0.808), enabling targeted, barrier-specific adherence interventions at treatment initiation.
Background Medication non-adherence is a major driver of cardiovascular morbidity, yet adherence to cardioprotective therapies (specifically lipid lowering) is often assessed using static measures that obscure important early behavioural patterns. Distinct longitudinal trajectories, such as rapid or gradual decline, remain poorly predicted in primary care. No current models combine patient-reported barriers at treatment initiation with real-world prescribing data to forecast these trajectories, limiting opportunities for timely, targeted adherence interventions. Methods We developed BRIDGE, a Bayesian model that predicts adherence trajectories based on GBTM trajectories. BRIDGE is a barrier-informed Bayesian multiclass model that uniquely integrates risk factors and patient-reported barriers as electronic medical record proxies grouped by WHO adherence domains, incorporating these into hierarchical priors to regularise trajectory prediction and enable counterfactual intervention analysis. Performance was compared with machine-learning baselines. We conducted counterfactual analyses to quantify the impact of modifying specific barriers at initiation. Results Among 50,881 LLT initiators (mean age 63 years; 90% statins), trajectories were: early discontinuation (41%), rapid decline (29%), persistent adherence (20%), and gradual decline (10%), nearly 70% exhibited early non-adherence patterns. BRIDGE achieved AUROC 0.808 (95% CI 0.805–0.811), accuracy 58.4%, and Brier score 0.531, comparable to XGBoost with superior interpretability. Incorporating hierarchical priors improved accuracy by 3.4 percentage points and enhanced calibration. Barrier profiles differed by trajectory: early discontinuers showed lesser healthcare utilisation (lowest visit frequency, 0.44/month); gradual decliners reflected medication burden (highest polypharmacy, 13%); rapid decliners indicated therapy instability (highest switching, 4%); persistent adherers displayed condition-related motivation despite higher clinical risk. Counterfactual analysis identified trajectory-specific intervention levers: timely adherence-support touchpoints and medication burden reduction for gradual decliners; continuity-of-care and early refill support for early discontinuers; and treatment stability with regimen simplification for rapid decliners. Conclusions Embedding structured, risk factors and patient-reported barriers as hierarchical priors improves prediction of longitudinal adherence trajectories while preserving transparency. BRIDGE enables barrier-targeted interventions at initiation using routine primary care data. External validation and a prospective implementation study are underway.
No takes yet. Share an insight, caveat, or question.
Koh et al. (2026) conducted an observational in Medication non-adherence in lipid-lowering therapy initiators (n=50,881). BRIDGE (barrier-informed Bayesian multiclass risk prediction model) vs. Machine-learning baselines (including XGBoost) was evaluated on Prediction of longitudinal medication adherence trajectories (early discontinuation, rapid decline, persistent adherence, gradual decline) (AUROC 0.808, 95% CI 0.805-0.811). The BRIDGE Bayesian model predicted lipid-lowering therapy adherence trajectories with an AUROC of 0.808 (95% CI 0.805-0.811) and 58.4% accuracy, comparable to XGBoost.
Synapse has enriched 10 related papers. Consider them for comparative context: