Chronic obstructive pulmonary disease (COPD) remains a leading cause of global morbidity and mortality, with acute exacerbations driving disease progression and healthcare utilization. Artificial intelligence (AI) offers new opportunities to predict exacerbation risk by integrating multimodal data such as electronic health records (EHRs), spirometry, and wearable sensor inputs. This systematic review, conducted in accordance with PRISMA 2020 guidelines and registered in PROSPERO (CRD420251165476), evaluated AI-based models developed for COPD exacerbation prediction using combined data modalities. Comprehensive searches of PubMed, Embase, and Google Scholar identified 859 records, of which five studies published between 2021 and 2025 met inclusion criteria. Study designs ranged from prospective monitoring cohorts to EHR-based and hybrid datasets. Models applied diverse approaches including random forests, gradient boosting, convolutional neural networks, and ensemble learning frameworks. Reported discriminative performance was moderate to high, with area under the curve (AUC) values between 0.73 and 0.92 and accuracies up to 0.92. Most of these performance metrics were derived from internal validation, with limited external testing, which restricts assumptions about generalizability. Sensitivity reached 0.94 in wearable-driven models, while only one study reported formal calibration assessment. Despite encouraging performance, methodological heterogeneity, limited external validation, and incomplete reporting of preprocessing and explainability methods restrict clinical translation. Current evidence supports the potential of multimodal AI to enhance early detection of COPD exacerbations, but future research must prioritize transparent reporting, external validation, and integration into real-world care pathways.
Kapatais et al. (Thu,) studied this question.