Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911465962733568 |
|---|---|
| author | Cheng, Jingya Azhir, Alaleh Tian, Jiazi Estiri, Hossein |
| author_facet | Cheng, Jingya Azhir, Alaleh Tian, Jiazi Estiri, Hossein |
| contents | Counterfactual inference enables clinicians to ask "what if" questions about patient outcomes, but standard methods assume feature independence and simultaneous modifiability -- assumptions violated by longitudinal clinical data. We introduce the Sequential Counterfactual Framework, which respects temporal dependencies in electronic health records by distinguishing immutable features (chronic diagnoses) from controllable features (lab values) and modeling how interventions propagate through time. Applied to 2,723 COVID-19 patients (383 Long COVID heart failure cases, 2,340 matched controls), we demonstrate that 38-67% of patients with chronic conditions would require biologically impossible counterfactuals under naive methods. We identify a cardiorenal cascade (CKD -> AKI -> HF) with relative risks of 2.27 and 1.19 at each step, illustrating temporal propagation that sequential -- but not naive -- counterfactuals can capture. Our framework transforms counterfactual explanation from "what if this feature were different?" to "what if we had intervened earlier, and how would that propagate forward?" -- yielding clinically actionable insights grounded in biological plausibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21168 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma Cheng, Jingya Azhir, Alaleh Tian, Jiazi Estiri, Hossein Machine Learning Counterfactual inference enables clinicians to ask "what if" questions about patient outcomes, but standard methods assume feature independence and simultaneous modifiability -- assumptions violated by longitudinal clinical data. We introduce the Sequential Counterfactual Framework, which respects temporal dependencies in electronic health records by distinguishing immutable features (chronic diagnoses) from controllable features (lab values) and modeling how interventions propagate through time. Applied to 2,723 COVID-19 patients (383 Long COVID heart failure cases, 2,340 matched controls), we demonstrate that 38-67% of patients with chronic conditions would require biologically impossible counterfactuals under naive methods. We identify a cardiorenal cascade (CKD -> AKI -> HF) with relative risks of 2.27 and 1.19 at each step, illustrating temporal propagation that sequential -- but not naive -- counterfactuals can capture. Our framework transforms counterfactual explanation from "what if this feature were different?" to "what if we had intervened earlier, and how would that propagate forward?" -- yielding clinically actionable insights grounded in biological plausibility. |
| title | Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.21168 |