The paper introduces Patient, Place, Prior (P³), an audit framework that evaluates whether a longitudinal medical imaging forecast benefits from a patient’s own imaging history (Patient), from patient‑matched spatial support (Place), and from predictive value beyond a population‑average model (Prior). It applies this framework to Cancer JEPA, a one‑step model that predicts future breast dynamic contrast‑enhanced MRI scans during neoadjuvant therapy, incorporating a lesion‑constrained neural correction trained with an occlusion‑based latent objective. Validation shows lower forecast error when the neural correction uses the patient’s own history and matched lesion maps, though the 95% interval comparing patient‑specific to population‑average corrections includes zero, illustrating that P³ distinguishes input usage from true patient‑specific predictive advantage.
arXiv:2608. 13518v1 Announce Type: new Abstract: Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint.
Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time.
The paper introduces Observation‑Anchored Selective Assimilation (OASA) for forecasting tumor‑state proxies in post‑treatment glioma patients using serial MRI observations. OASA anchors the patient‑specific state with an intermediate observation and selectively updates it via a tiered rule and voxel‑wise soft gate, outperforming baseline methods in Dice score at certain thresholds. The approach is validated on 120 patient triplets and the code is publicly released.
arXiv:2512.08029v4 Announce Type: replace Abstract: Clinical decision-making in oncology requires forecasting how disease evolves under treatment, yet most AI systems remain static predictors that ca...
FRESH (Fusion of Recent Evidence and Subject Histories) is a method that integrates population‑level summary results—such as published clinical trials, registry summaries, prior natural‑history studies, and peer‑reviewed indirect comparisons—into predictive models trained on patient‑level data. It recalibrates a generative model trained on patient data so that its predictions match specified aggregate statistics for a target population, achieving this with minimal perturbation in an information‑geometric sense. The recalibrated model can be used directly or to update the original generative model, enabling applications like contextualizing single‑arm trials, simulating clinical‑trial designs, and conducting comparative‑effectiveness analyses of on‑market therapies.
arXiv:2610.26923v1 Announce Type: cross Abstract: Treatment planning is intrinsically counterfactual: clinicians must compare how a patient's tumor and survival would evolve under competing regimens,...
A causal multi-modal AI model was developed to predict personalized chemosensitivity in breast cancer patients using routine pathology and clinical data. Trained on 9,141 patients from nine countries and validated on 1,994 patients from three countries, the model produced treatment-specific recurrence probabilities with near-perfect calibration and strong prognostic discrimination over 5- and 10-year horizons. It outperformed existing recurrence-score tests and could reduce chemotherapy prescriptions by 30% while maintaining recurrence-free rates, with predictive performance also transferring to non-breast cancers.
The paper introduces a compact patient world model that forecasts digital health campaign outcomes by maintaining a latent state per patient and learning exposure‑conditioned dynamics. Evaluated on a large US campaign dataset, the model predicts new‑to‑brand prescription volume with low relative error (2.9% at week‑4 cutoff) compared to much higher errors from baseline classifiers. The study also shows that dense next‑exposure supervision is crucial for accurate forecasts when conversions are rare and highlights limitations in interpreting exposure‑conditioned rollouts causally.
arXiv:2607. 04912v1 Announce Type: cross Abstract: In patients with breast cancer, pathological complete response (pCR) has been established as a clinically meaningful surrogate marker for long-term outcomes.
arXiv:2610.33054v1 Announce Type: new Abstract: Simulating an individual's disease course requires connecting patient history to future events, clinical timing and disease morphology. Longitudinal pr...
The paper introduces SEM‑HD, a framework that leverages longitudinal mammography history as privileged information during training to improve risk prediction while requiring only a single current exam at inference. By having a student model predict latent representations of past visits and using teacher supervision from actual longitudinal data, SEM‑HD preserves temporal modeling benefits without needing prior exams at deployment. Experiments on three cohorts and two backbone architectures show consistent gains in long‑horizon AUC and pAUC, especially in low false‑positive‑rate regions, and recover much of the performance gap to full‑history models.
arXiv:2512. 08029v3 Announce Type: replace Abstract: Clinical decision-making in oncology requires predicting dynamic disease evolution, a task current static AI predictors cannot perform.