Key result
Multimodal AI combining CXRs and EHRs predicts clinical deterioration in HF with ~0.84 AUC.
Why the study?
Predicting clinical deterioration—including in-hospital mortality, transition to hospice care, and readmission—is essential for guiding early interventions and advanced care planning in hospitalized HF patients. This study developed a multimodal transformer decoder model analyzing sequential CXRs and EHRs to predict these composite adverse outcomes early across varying lead-time windows.
Does a multimodal transformer decoder model analyzing sequential chest X-rays and electronic health records accurately predict composite clinical deterioration (in-hospital mortality, transition to hospice care, and readmission) across varying lead-time windows in hospitalized heart failure patients?
Observational (n=14,498)
Does a multimodal transformer decoder model analyzing sequential chest X-rays and electronic health records accurately predict composite clinical deterioration (in-hospital mortality, transition to hospice care, and readmission) across varying lead-time windows in hospitalized heart failure patients?
A multimodal transformer decoder integrating sequential chest X-rays and electronic health records can effectively predict composite clinical deterioration in hospitalized heart failure patients up to and beyond 72 hours before the event.
Background Predicting clinical deterioration including in-hospital mortality, transition to hospice care, and readmission is essential for guiding early interventions and advanced care planning in hospitalized heart failure (HF) patients. Purpose This study developed a multimodal transformer decoder model that analyzes sequential chest X-rays (CXRs) and electronic health records (EHRs). This model acts as a comprehensive safety net, predicting these composite adverse outcomes early across varying lead-time windows. Methods The model was trained using a dataset of 13,821 admissions comprising sequential CXRs (≥2 AP/PA projections) and paired EHRs. To evaluate the model's capacity as an early safety net, a test cohort of 677 heart failure admissions was utilized. To assess early warning capabilities, the analysis stratified the test data into four lead-time windows prior to the event (death or discharge): < 24h (n=164), 24–48h (n=108), 48–72h (n=88), and > 72h (n=317). Results Within the test cohort (mean age 71.2 ± 14.4 years; 54.8% male), the multimodal transformer decoder model demonstrated significant predictive utility in the < 24h window, achieving an area under the curve (AUC) of 0.838 (95% CI, 0.745–0.930), a sensitivity of 60.0%, and a specificity of 91.8% (p < 0.0001). The model maintained robust discriminative ability at 24–48h (AUC 0.808, 95% CI, 0.687–0.929) and > 72h (AUC 0.708, 95% CI, 0.617–0.798) prior to the event (both p < 0.0001). Although discriminative performance dipped at 48–72h (AUC 0.624, 95% CI, 0.450–0.798), specificity remained consistently high across all intervals (85.3%–93.2%). This suggests that the model maintains promising predictive potential even beyond the 72-hour threshold prior to clinical deterioration. Conclusion By integrating sequential CXRs and EHRs, the multimodal transformer decoder effectively anticipates clinical deterioration in heart failure patients even beyond 72 hours prior to the event.data Table 1Performance chart 1
No takes yet. Share an insight, caveat, or question.
Minjun et al. (2026) conducted an observational in Hospitalized heart failure (n=14,498). Multimodal transformer decoder model analyzing sequential CXRs and EHRs was evaluated on Composite clinical deterioration (in-hospital mortality, transition to hospice care, and readmission) (AUC 0.838, 95% CI 0.745-0.930, p=<0.0001). A multimodal transformer decoder analyzing sequential CXRs and EHRs predicted clinical deterioration in HF patients with an AUC of 0.838 (<24h) and 0.708 (>72h; both p<0.0001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: