- Rating
- 3
- Confidence
- 2(−1)
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper introduces PULMOWORLD, which incorporates synchronous multimodal longitudinal data to estimate a patient's state, simulate future states, and ideally perform evidence-constrained planning. PULMOWORLD builds a Gaussian belief of a patient's state using past observations and evolves it with new observation corrections. Validated on a private MASS dataset and the public MIMIC dataset, PULMOWORLD's simulated states retain clinical and prognostic information. For evidence-constrained planning, the paper introduces Cap-MBRL, which restricts policy optimization to actions passing predictive-evidence and identification-evidence checks, and replaces a frozen fallback policy only when a candidate satisfies a risk budget and predicted-cost margin. On the synthetic dataset MASS-Syn with known mechanism environments, Cap-MBRL lowers selection regret relative to direct fallback execution.
Critical strengths
- Handling asynchronous and incomplete multimodal Data: PULMOWORLD decoupled elapsed-time state propagation from observation corrections and xplicitly modeling missing modalities with masks, allowing flexible integration of irregular, asynchronous longitudinal clinical measurements (such as imaging and BALF).
- Multi-faceted evaluation across core world-model capabilities. PULMOWORLD separately examines state modeling through history reconstruction, future simulation through recursive clinical and modality-representation forecasting and prognostic utility, and planning in known-mechanism environments.
Critical weaknesses
- The empirical evidence for nontrivial planning performance is restricted to the synthetic MASS-Syn environments. On the real cohorts, planning remains fail-closed because the identification gate is not passed. The clinical relevance and generalizability of the reported planning results therefore remain unclear.
- The construction of MASS-Syn and its relationship to the real MASS cohort and pneumonia physiology are not sufficiently specified or validated.
Questions for authors
- Why is each latent state represented by a diagonal Gaussian? Is there any theoretical or empirical justification? Can the authors compare it with deterministic, non-Gaussian, or point-process alternatives?
- How does removing CT, CXR, or BALF affect the latent state, future predictions, and action selection? Can the authors report clinical-only, clinical-plus-imaging, and full-modality results, as well as an ablation removing cross-compartment messages?
- How were Qwen3-VL-30B-A3B and Hulu-Med-32B adapted for longitudinal numerical forecasting? Please clarify the input/output format, prompting or fine-tuning procedure, and why their errors are unusually large. For these models, H4 error is lower than H1; how should this pattern be interpreted?
- Please report hardware, memory, training time, preprocessing cost, and inference overhead. Also, please explain the rationale for using the selected pretrained encoders and freezing them. Why were stronger CXR-specific pretrained encoders or task-specific fine-tuning not considered?
- (minor) Figure 2 would be clearer without the patterned backgrounds, with larger labels, consistent variable notation, and unified modality representations across Figures 1, 2, and 8.