Abstract: 

Advances in sensing, computation, and machine learning are creating an opportunity to fundamentally rethink how patient state is assessed in acute care environments. Despite decades of technological progress, many critical aspects of patient health—such as functional status, cognition, sleep quality, and environmental stressors—are still evaluated intermittently, subjectively, or not at all. These gaps limit the ability to deliver timely, personalized, and proactive care, particularly in high-acuity settings like the ICU.

In this seminar, we discuss how pervasive sensing combined with interpretable artificial intelligence can enable continuous, fine-grained characterization of patient physiology, behavior, and environment. By fusing multimodal sensor data with clinical and physiological streams, we move beyond episodic measurements toward dynamic representations of patient state that evolve in real time. We highlight recent progress in translating these approaches into clinically meaningful indices, along with the technical, ethical, and workflow challenges that arise when deploying intelligent systems at the bedside.

More broadly, this work points toward a future in which hospitals function as adaptive, data-driven environments—supporting clinicians with richer situational awareness while preserving interpretability and trust. We conclude by outlining open research questions and design principles for building AI-enabled health technologies that meaningfully augment, rather than replace, clinical expertise.

Biography:

Students registered for the seminar are expected to attend in person.

Teams ID and Passcode:

Meeting ID: 211 123 896 292 8

Passcode: Uh9qs2pf

MARK YOUR CALENDARS