Post Procedure Follow Up Team
The problem: Post-hospitalization/post-procedure readmissions cost health systems billions a year and are penalized directly under CMS's Hospital Readmissions Reduction Program.
Core trick
A voice agent places post-discharge check-in calls and scores answers against condition-specific red flags to route each patient to one of four outcomes.
Description
The problem: Post-hospitalization/post-procedure readmissions cost health systems billions a year and are penalized directly under CMS's Hospital Readmissions Reduction Program. Most of the early warning signs — worsening symptoms, medication confusion, uncontrolled pain — surface in the days right after discharge, in a phone check-in that may or may not happen, get documented inconsistently, or reach the right clinician in time.
The idea: An agent places (or receives) a structured check-in call a few days after discharge, grounded in that specific patient's actual diagnosis, comorbidities, and medications. It scores the conversation against condition-specific red flags and routes the patient to one of four outcomes: urgent care referral, same-day physician callback, labs/imaging recommended, or routine follow-up — with a drafted chart note and a rationale a clinician can quickly verify.
This is a natural extension of what Abridge already does (ambient conversation → structured clinical output), just pointed at a post-visit check-in instead of the exam room.
lakshmisubbaraj/post-discharge-triage-agent★ 01 forksPythonCreated Jul 18, 2026 · last push Jul 19, 2026
README excerpt
# Post-Discharge Triage Agent — Hackathon Mockup **The problem:** Post-hospitalization/post-procedure readmissions cost health systems billions a year and are penalized directly under CMS's Hospital Readmissions Reduction Program. Most of the early warning signs — worsening symptoms, medication confusion, uncontrolled pain — surface in the days right after discharge, in a phone check-in that may or may not happen, get documented inconsistently, or reach the right clinician in time. **The idea:** An agent places (or receives) a structured check-in call a few days after discharge, grounded in that specific patient's actual diagnosis, comorbidities, and medications. It scores the conversation against condition-specific red flags and routes the patient to one of four outcomes: **urgent care referral**, **same-day physician callback**, **labs/imaging recommended**, or **routine follow-up** — with a drafted chart note and a rationale a clinician can quickly verify. This is a natural extension of what Abridge already does (ambient conversation → structured clinical output), just pointed at a post-visit check-in instead of the exam room. ## What's in this mockup right now `index.html` is a **single self-contained file** — open it directly in any browser, no server or install needed. It's built around 5 real patients pulled from the hackathon's `synthetic-ambient-fhir-25` dataset (their actual ages, conditions, and medications come from the FHIR data), each showing a different on