If clinical AI can't work in the emergency department, it doesn't work.
Most clinical AI is built and tested in calm settings: scheduled visits, known patients, time to review. The front door of medicine is none of those things. It's where a patient arrives unannounced, the history is incomplete, and the clinician has minutes to decide what happens next. That's why it's the most honest test any clinical AI can face.
On Thursday, November 12, we're putting that test on the table in a live panel, AI at the Front Door: The Future of Emergency and Urgent Care, presented in collaboration with the American College of Emergency Physicians (ACEP).
Why the front door is different
Emergency and urgent care clinicians work under conditions that strip away every shortcut. Patients are undifferentiated. Volume is relentless. Prior records are often scattered across systems, or simply not there. And every encounter still has to be documented, coded and handed off correctly.
The burden is well documented. Physicians spend close to two hours on EHR and desk work for every hour of direct patient care (Sinsky et al., Annals of Internal Medicine, 2016). And roughly half of the clinical questions raised at the point of care are never pursued, usually because there isn't time (Del Fiol et al., JAMA Internal Medicine, 2014).
In acute care, both problems compound. The note competes with the next patient. The question that goes unanswered is the one that mattered most. Any AI that claims to help has to help here, at speed, without adding a single extra step.
What the panel will discuss
This isn't a product session. It's a conversation between clinicians and leaders who run emergency and urgent care, about what AI is actually changing and what it still has to earn.
- Triage and the first minutes. How AI can support the assessment and routing of undifferentiated patients, and where clinical judgment must stay firmly in charge.
- Documentation and coding at volume. What it takes for AI to produce a complete, accurate, coded record in high-throughput, high-acuity settings.
- The whole patient at the moment of decision. Bringing prior records, the live encounter and current evidence together when the clinician needs them, not after the shift.
- Safety and oversight. What responsible deployment looks like in acute care, and how clinicians stay accountable for every decision.
- Scaling across systems. How health systems and urgent care networks evaluate AI, and what separates a pilot from a lasting deployment.
Meet the panel
The panel brings together academic emergency medicine, a national urgent care network and the national body shaping how emergency physicians adopt AI.
- Sowmya Sanapala, MD, MBA, MS, Weill Cornell Medicine
- Sarika Aggarwal, MD, MHCM, Chief Medical Officer, FastPace Health
- Philip Jarrett, UT Southwestern, ACEP AI Commission
- Jhonatan Bringas Dimitriades, MD, CEO and Co-Founder, Keikku
Moderated by Owais Durrani, DO, Chief Medical Officer USA, Keikku.
Why we're hosting this conversation
We believe the value of clinical AI isn't in any single task. It's in knowing the whole patient: decades of records, the consultation happening right now, and every result that arrives after, brought together into one clinical picture at the moment care happens.
The front door is where that matters most and where it's hardest to deliver. That's why Keikku wanted to hear directly from the clinicians and leaders who work there, and to have that conversation in the open.
Join us
AI at the Front Door: The Future of Emergency and Urgent Care
Live panel webinar, presented in collaboration with ACEP
Thursday, November 12, 1:00 PM EST
This session is for emergency physicians, urgent care clinicians, CMOs, CMIOs, and health system and operations leaders shaping how AI enters acute care.
Register on our LinkedIn event page, and bring your hardest questions for the live Q&A.
