# Inside the PAINITE pathway: four arms, one journey

> PAINITE (Perioperative Assessment & Intelligent Navigation, Integration & Triage Efficiency) is a pathway proposed at Royal North Shore Hospital. It adds four arms to the existing pre-op pathway, a voicebot, a snifferbot, a rule-based perioperative harness and day-prior calls, and is staged to start with an ophthalmology voicebot pilot and process evaluation.

*Source: https://getpathways.ai/articles/inside-the-painite-pathway*

PAINITE stands for Perioperative Assessment & Intelligent Navigation,
Integration & Triage Efficiency. It shares its name with one of the rarest
gemstones on earth, which suits a program aimed at finding the patients a
pathway usually loses.

It grew out of an audit of 1,532 patients who didn't complete their digital
pre-operative health questionnaire at Royal North Shore Hospital in 2025. That
audit found most of the failure sat in the workflow: invitations sent too late,
sent to patients who were admitted, transferred or deceased, and a web form that
older, visually impaired and CALD patients struggled to use.

## The pathway, stage by stage

PAINITE keeps the existing perioperative pathway and adds a tool where each
stage stalls.

| Stage | Where it breaks today | PAINITE arm | What the arm does |
| --- | --- | --- | --- |
| 1. Request for admission | 30% of timed non-completers invited ≤2 days out, on the day or after | Pathway trigger | Starts the process at the decision to operate |
| 2. Questionnaire completion | 64% of non-completers over 65; 14.5% non-English preferred language | Voicebot conversation | Gathers the health history by conversation, targeted and iterated |
| 3. Correspondence chasing | Staff time on uploads, troubleshooting and follow-up | Snifferbot | Extracts key information from incoming requests and automatically asks for what's missing |
| 4. Pre-admission clinic | Not measured in the audit | Perioperative harness | Triages with rule-based logic to the right reviewer, such as a frailty coordinator, anaesthetic nurse or anaesthetist; prioritises complex cases |
| 5. Day-prior phone call | Not measured in the audit | Simultaneous voicebot calls | Calls every patient at once with fasting and medication instructions; flags anyone with an issue to staff |
| 6. Surgery | — | — | The patient arrives assessed, prepared and on the right list |

## Three design choices worth noticing

**Language AI where language is the work.** Conversation with patients and
reading referral letters are language tasks. That is where conversational AI and
document extraction add the most.

**Rules where a decision is made.** The harness triages with rule-based logic.
Each routing decision can be traced to the criteria that triggered it, which
matters for clinical governance and for staff trust.

**People where judgement is needed.** The day-prior calls don't resolve a
fasting breach or a missed medication stop. They flag it to staff, who decide
what happens next. Automation handles the volume; clinicians handle the
exceptions.

## A deliberately staged rollout

PAINITE doesn't switch on all at once. The plan starts with a voicebot pilot for
ophthalmology patients, followed by a process evaluation for quality assurance.
Only then do the voicebot, snifferbot and perioperative harness extend to the
other surgical specialties.

Ophthalmology is the right first test. It was the largest group of
non-completers, its patients are the oldest on average, and visual impairment
makes a screen-based form hardest to use. If a voice channel can lift completion
there, the case for the rest of the pathway gets much stronger.

Like any AI project in a NSW public hospital, PAINITE sits within the NSW AI
Assurance Framework, which assesses risk, privacy and governance before
deployment.

## What the pilot should show

- Completion rates in ophthalmology against the 2025 baseline
- How patients rate the voice experience, by age and language
- Agreement between voice-captured histories and clinician review
- Staff time spent on chasing and day-prior calls
- Day-of-surgery issues such as fasting breaches and missed medication stops

*Source: Zhang D, Marks A, Doane M, et al. Barriers to current perioperative
digital platforms – how can innovation solve these issues? Poster, ASA CSC.*