Back

Contrastive Transformer-Driven Discovery of Temporal Hemodynamic Subphenotypes in Cardiac Surgery Patients

Desman, J. M.; Sabounchi, M.; Oh, W.; Kumar, G.; Shaikh, A.; Gupta, R.; Gidwani, U.; Manasia, A.; Varghese, R.; Oropello, J.; Smith, G.; Kia, A.; Timsina, P.; Kaplan, B.; Shetreat-Klein, A.; Glicksberg, B.; Legrand, M.; Khanna, A. K.; Kellum, J. A.; Kovatch, P.; Kohli-Seth, R.; Charney, A. W.; Reich, D.; Nadkarni, G. N.; Sakhuja, A.

2026-03-30 intensive care and critical care medicine
10.64898/2026.03.27.26349519 medRxiv
Show abstract

Cardiac surgery patients experience rapidly evolving hemodynamics in early post-operative period requiring intensive support. Identifying hemodynamic subphenotypes from these data can inform personalized management. Using 24-hour high-resolution physiologic and treatment data from 6,630 MIMIC-IV and 1,963 SICdb patients, we trained a transformer encoder with a reconstruction-contrastive objective to derive patient-level embeddings capturing multivariate temporal dynamics within first 24h of ICU stay and compared them against those generated by dynamic time warping (DTW). Spectral clustering uncovered three reproducible hemodynamic subphenotypes. Compared with subphenotype 1, subphenotype 3 received more IV fluids, vasopressors, inotropes, and exhibited higher in-hospital mortality (OR 5.85, 95 % CI 2.43-14.13), longer ICU stay (7.12 days, 95% CI: 5.52-8.73) and hospitalization (8.86 days, 95% CI: 6.57-11.16). DTW derived subphenotypes had weaker prognostic separation. Thus, contrastive-transformer framework identified more clinically meaningful temporal hemodynamic subphenotypes that may optimize post-operative risk stratification and inform personalized management.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.