Causal Machine Learning for Surgical Interventions
Big Data Mining and Analytics · 2026-08 · 9 (4) · 1110-1125
DOI: 10.26599/bdma.2025.9020093 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data Mining and Analytics, 2026-08. Verfasst von Junior Ben Tamo und 8 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: Georgia Institute of Technology.
Abstract (Originalsprache)
Surgical decision-making is complex and requires understanding causal relationships between patient characteristics, interventions, and outcomes. In high-stakes settings like spinal fusion or scoliosis correction, accurate estimation of individualized treatment effects (ITEs) remains limited due to the reliance on traditional statistical methods that struggle with complex, heterogeneous data. In this study, we develop a multi-task meta-learning framework, X-MultiTask, for ITE estimation that models each surgical decision (e.g., anterior vs. posterior approach, surgery vs. no surgery) as a distinct task while learning shared representations across tasks. To strengthen causal validity, we incorporate the inverse probability weighting (IPW) into the training objective. We evaluate our approach on two datasets: (1) a public spinal fusion dataset (1,017 patients) to assess the effect of anterior vs. posterior approaches on complication severity; and (2) a private AIS dataset (368 patients) to analyze the impact of posterior spinal fusion (PSF) vs. non-surgical management on patient-reported outcomes (PROs). Our model achieves the highest average AUC (0.84) in the anterior group and maintains competitive performance in the posterior group (0.77). It outperforms baselines in treatment effect estimation with the lowest overall $\epsilon_{\text{NN-PEHE}}$ (0.2778) and $\epsilon_{\text{ATE}}$ (0.0763). Similarly, when predicting PROs in AIS, X-MultiTask consistently shows superior performance across all domains, with $\epsilon_{\text{NN-PEHE}}$ = 0.2551 and $\epsilon_{\text{ATE}}$ = 0.0902. By providing robust, patient-specific causal estimates, X-MultiTask offers a powerful tool to advance personalized surgical care and improve patient outcomes. The code is available at https://github.com/Wizaaard/X-MultiTask.
Förderung
- Georgia Institute of Technology
Zitieren
APA
Tamo, J. B., Chouhan, N. S., Nnamdi, M. C., Yuan, Y., Chivilkar, S. S., Shi, W., Hwang, S. W., Brenn, B. R., & Wang, M. D. (2026). Causal Machine Learning for Surgical Interventions. Big Data Mining and Analytics, 9(4), 1110-1125. https://doi.org/10.26599/bdma.2025.9020093
Vancouver
Tamo JB, Chouhan NS, Nnamdi MC, Yuan Y, Chivilkar SS, Shi W, et al. Causal Machine Learning for Surgical Interventions. Big Data Mining and Analytics. 2026;9(4):1110-1125. doi:10.26599/bdma.2025.9020093
BibTeX
@article{Tamo2026,
author = {Tamo, Junior Ben and Chouhan, Nishant S. and Nnamdi, Micky C. and Yuan, Yining and Chivilkar, Shreya S. and Shi, Wenqi and Hwang, Steven W. and Brenn, Bruce Randall and Wang, May D.},
title = {Causal Machine Learning for Surgical Interventions},
journal = {Big Data Mining and Analytics},
year = {2026},
volume = {9},
number = {4},
pages = {1110--1125},
doi = {10.26599/bdma.2025.9020093}
}
EUVIMED