Multimodal clinical records contain structured measurements and clinical notes recorded over time, offering rich temporal information about the evolution of patient health. Yet these observations are sparse, and whether they are recorded depends on the patient’s latent condition. Observation patterns also differ across modalities, as structured measurements and clinical notes arise under distinct recording processes. While prior work has developed methods that accommodate missingness in clinical time series, how to extract and use the information carried by the observation process itself remains underexplored. We therefore propose a patient representation learning framework for multimodal clinical time series that explicitly leverages informative missingness. The framework combines (1) a multimodal encoder that captures signals from structured and textual data together with their observation patterns, (2) a Bayesian filtering module that updates a latent patient state over time from observed multimodal signals, and (3) downstream modules for offline treatment policy learning and patient outcome prediction based on the learned patient state. We evaluate the framework on ICU sepsis cohorts from MIMIC-III, MIMIC-IV, and eICU. It improves both offline treatment policy learning and adverse outcome prediction, achieving FQE 0.679 versus 0.528 for clinician behavior and AUROC 0.886 for post-72-hour mortality prediction on MIMIC-III.

Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring preferences). This *identity-blindness* yields incorrect responses, unnecessary refusals, or generic "equal-treatment" defaults. We study this via difference-awareness classification: given a question involving demographic groups, the task is not to answer directly, but to classify whether a correct answer requires recognizing group differences (**YES**) or whether groups should be treated identically (**NO**). Crucially, fine-tuning for accuracy triggers *harm drift*: model-generated explanations become increasingly harmful as decision accuracy improves, whether by elaborating harmful content, introducing problematic assumptions, or failing to flag harms the baseline identified. To mitigate this, we introduce **DART** (**D**istill–**A**udit–**R**epair **T**raining), which distills label-conditioned reasoning from a teacher, audits outputs for harm drift cases relative to baseline, and repairs problematic cases via severity-weighted fine-tuning. On eight benchmarks, DART improves Llama-3-8B-Instruct accuracy from 39.0% to 68.8%, with largest gains on equal-treatment prompts (11.3% → 72.6%), while reducing harm drift cases by 72.6%. It also transfers to 280 open-ended real-world queries across medical, legal, policy, and educational domains, improving difference-appropriate responses from 39.8% to 77.5% while reducing refusals from 34.3% to 3.0%. Our results demonstrate that accuracy and safety need not conflict when explicit detection and repair mechanisms are in place.

Clinical notes contain rich patient information, such as diagnoses or medications, making them valuable for patient representation learning. Recent advances in large language models have further improved the ability to extract meaningful representations from clinical texts. However, clinical notes are often missing. For example, in our analysis of the MIMIC-IV dataset, 24.5% of patients have no available discharge summaries. In such cases, representations can be learned from other modalities such as structured data, chest X-rays, or radiology reports. Yet the availability of these modalities is influenced by clinical decision-making and varies across patients, resulting in modality missing-not-at-random (MMNAR) patterns. We propose a causal representation learning framework that leverages observed data and informative missingness in multimodal clinical records. It consists of: (1) an MMNAR-aware modality fusion component that integrates structured data, imaging, and text while conditioning on missingness patterns to capture patient health and clinician-driven assignment; (2) a modality reconstruction component with contrastive learning to ensure semantic sufficiency in representation learning; and (3) a multitask outcome prediction model with a rectifier that corrects for residual bias from specific modality observation patterns. Comprehensive evaluations across MIMIC-IV and eICU show consistent gains over the strongest baselines, achieving up to 13.8% improvement for hospital readmission and 13.1% for ICU admission (AUC, relative to best baseline).