unthinkable
Case study · Mount Sinai, New York · hospital system

Heart-attack patients arrive at Mount Sinai with the cardiac team already waiting for them.

For a heart-attack (STEMI) patient, the cath lab should be ready when the ambulance arrives, so treatment starts within the 90-minute door-to-balloon goal instead of waiting on phone calls.

New York, United StatesCare coordination & remote monitoring

What changed

47%shorter door-to-balloon time (as reported)
1,000+STEMI patients monitored (as reported)
120 to 91 minmean door-to-device time for transfer patients, before the app and in the July 2021 to July 2022 pilot (as reported by Mount Sinai)
71% to 100%of transfers meeting the 120-minute goal, before the app and during the pilot (as reported by Mount Sinai)
What stood in the way

What stood in the way.

What stood in the way
  • Guidelines call for a door-to-balloon time of 90 minutes or less.
  • Paramedics and doctors passed information by phone, and paramedics had to keep updating the cardiology team, which delayed treatment.
  • Transfers and patient status were tracked by phone, so no one saw the same picture at the same time.
What changed
  • 47%shorter door-to-balloon time (as reported)
  • 1,000+STEMI patients monitored (as reported)
  • 120 to 91 minmean door-to-device time for transfer patients, before the app and in the July 2021 to July 2022 pilot (as reported by Mount Sinai)
  • 71% to 100%of transfers meeting the 120-minute goal, before the app and during the pilot (as reported by Mount Sinai)
What we built

What we built.

  • Android and iOS apps that send a photo of the ECG with the patient's details to the whole STEMI team the moment a STEMI is identified.
  • Real-time messaging and group chat, so the team prepares while the ambulance is on the way.
  • Live GPS tracking of the ambulance for everyone on the case.
  • Roles for each part of the pathway: the doctor who raises the alarm, the cardiac specialist who accepts, the transfer centre that assigns the ambulance, and the ambulance crew.
  • An admin panel linked to the hospital's EMS for users, alarm monitoring, pre-procedure metrics and patient dashboards, with performance tracked against standard benchmarks.
  • Clinical and administrative data exchanged to the HL7 standard.
  • Built with a low-code approach in 1.5 months against an estimated 3.5 months.
  • Android
  • iOS
  • HL7
  • GPS tracking
  • Low-code development
What it shows

What this work shows about us.

We know where minutes are lost in an emergency

The app follows the STEMI pathway itself, from the doctor who raises the alarm to the transfer centre, the ambulance and the cath lab, so each hand-off happens at once instead of by phone.

Real time, for everyone at once

ECG, chat and the ambulance's position reach the whole team together, which is what lets the cath lab be ready on arrival.

Fast to build, measured afterwards

Built in 1.5 months, then measured by the hospital's own pathway metrics against the national goal.

Want to build a similar real-time care coordination app? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.

Start your plan ↗
If we built it today

If we built it today, with AI.

This work came before today's AI. If Mount Sinai asked us now, this is what we would add, step by step.

Emergency

An agent would gather the ECG, history and arrival time into one summary for the cardiologist on call and tell the cath lab team when to be ready. The cardiologist still decides whether to accept every case.

Tests and results

An agent would compare each case with the 90-minute goal and show the team where the minutes went, for the monthly review. The team decides what to change.

Ask Unthinkable

Want this for your business?

Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.

Send us a note instead

Required

Thanks. A senior AI engineer will reply to you.
u
Ask UnthinkableClarity first, then the right team
Your conversation

An AI agent. This prototype uses prepared answers and sends nothing.