ShippedHealthcare AIRemote Monitoring
// product

VitalLoop

An AI remote patient monitoring platform that triages home vitals into a prioritized care queue, drafts patient outreach, and tracks billable RPM minutes.

Client:Chronic-care management group (NDA)
Duration9 weeks
ScopeMVP product design and front-end build of the Care Queue triage board and single-patient detail experience, backed by a deterioration-risk scoring model and an outreach-drafting engine.
Team1 product designer, 2 senior front-end engineers, and a fractional clinical PM

// The Care Queue board — 486 patients monitored, 1,204 readings ingested today, a worst-first queue by risk tier, and 8,940 billable RPM minutes.

486Patients monitored
1,204Readings today
23Open alerts
8,940Billable RPM minutes
01

Overview

VitalLoop gives a chronic-care team an always-on view of patients they only used to see at appointments. Patients take blood pressure, glucose, weight, SpO₂ and heart-rate readings at home on connected devices; VitalLoop ingests every reading, triages abnormal trends into a worst-first care queue, and explains each risk score with the weighted drivers behind it. BuildspaceLabs designed and built the MVP front end — a population Care Queue for triage and a per-patient detail view with 30-day vitals sparklines, a weighted AI risk assessment and a drafted outreach message — turning a stream of device data into a workflow a nurse can act on in minutes, while every qualifying RPM minute is logged toward billing.

02

Highlights

  • Catches early decompensation from home readings before it becomes an admission
  • Ranks the whole panel into one worst-first care queue for the nurse
  • Every alert is explainable — a weighted breakdown, not a black-box score
  • Drafts patient outreach and tracks every billable RPM minute in one place
03

Gallery

04

Outcomes

  • Delivered a production-quality MVP of the Care Queue and patient detail view in a 9-week engagement
  • Consolidated reading ingestion, triage, outreach and RPM billing into a single care-team workflow
  • Gave nurses a worst-first queue with explainable risk drivers instead of an undifferentiated inbox
  • Established a reusable clinical design system (risk pills, vitals sparklines, care-action cards) for the product's next surfaces
05

Tech Stack

Chosen per constraint, not per habit — the stack shifts with the problem.

AI & ML
Python · risk model
Frontend & Mobile
Next.jsReactTypeScript
Data & Infrastructure
PostgreSQL
Backend & APIs
FastAPIHL7 FHIR
06

Features

  • Care Queue board with live readings, open alerts, and billable RPM-minute KPIs
  • AI triage that scores every trend and ranks patients into Critical, Elevated and Stable tiers
  • Per-patient detail with 30-day blood pressure, glucose and weight sparklines
  • Explainable deterioration-risk score attributed to weighted drivers (weight, BP, adherence, missed readings)
  • AI-drafted patient outreach — a message or call script the nurse approves before it sends
  • RPM billing tracker logging every qualifying minute toward the 20-minute threshold per patient
// live landing page

See VitalLoop as its own site.

Beyond the build, we designed and shipped VitalLoop a standalone landing page — its own look, copy and motion. Here's a live preview; scroll inside it, or open it full-screen.

// more from the lab

A team that ships across the board.

36products in production
8industries served
68+technologies in play

// next

Building something in this space?

A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.