Every patient assessed before they reach the theatre door.

Pathways screens every patient at the moment of booking rather than at the pre-admission clinic, so the findings that cause cancellations — unwithheld SGLT2 inhibitors, poor glycaemic control, undiagnosed sleep apnoea, missing discharge support — surface weeks ahead, while the list can still be optimised, rescheduled or backfilled.

The lever is timing rather than thoroughness. In almost every cancelled case the determining fact existed weeks earlier; it simply had not reached the anaesthetist while there was still time to act on it.

That also means the screening has to cover every booked patient, not the ones who look complex on paper. The patients who cancel lists are by definition the ones whose risk was not visible in advance.

Socrates Pre-Op is the Pathways voice agent that takes a structured anaesthetic history from a patient by phone. It is delivered as a secure, time-limited SMS link — no app, no login, no paper questionnaire — and covers 12 clinical domains conversationally, producing structured, severity-tagged findings that feed the risk engine directly.

It is a purpose-built anaesthetic variant rather than a generic intake bot. The distinction matters in practice: a general-purpose intake tool collects answers to the questions it was given, whereas an anaesthetic interview needs to follow up on a positive family history of anaesthetic problems, probe functional capacity when a patient says they are “fine”, and recognise when a described medication is worth photographing.

Completion is tracked, and a finished interview automatically triggers a fresh risk analysis.

How this compares with the two methods it usually replaces — paper questionnaires and telephone pre-assessment — including where each of those still wins.

The Socrates Pre-Op interview covers 12 domains — surgical context, presenting symptoms, prior anaesthetics, systems review, functional capacity and frailty, airway assessment, medications and allergies, social and risk factors, implanted devices, pre-op investigations, a red-flag screen, and safety and shared decisions.

Every domain produces structured, severity-tagged findings rather than free text, which is what allows the risk engine to screen on them directly instead of re-parsing a narrative.

Pathways screens each case with deterministic, versioned rules referenced to perioperative guidelines. Every flag carries a severity tier, the clinical rationale, the triggering evidence, the guideline reference and a recommended action, plus the rule version that produced it. The same inputs always produce the same flags, months later.

Screening covers the domains that drive perioperative outcomes: unstable cardiac symptoms, marked hypertension, diabetes control and SGLT2 management, obstructive sleep apnoea, frailty, malnutrition, functional capacity, smoking and discharge support.

Pathways also states what it does not know. Missing investigations and unconfirmed timings are listed explicitly on every profile, and extraction confidence is shown rather than hidden — a profile that is 86% confident about a patient-reported HbA1c says so.

They proceed. Every completed profile carries a triage recommendation — anaesthetist review, pre-admission clinic, telephone review, or no further assessment — so clinic slots go to moderate-risk patients and anaesthetist time goes to red flags. Low-risk patients are not routed into a clinic appointment they do not need.

This is the throughput argument, and it runs in both directions. A pre-admission clinic booked out three weeks ahead with mostly healthy ASA 1 patients is not short of capacity so much as misallocating it. Screening every patient at booking makes the queue orderable by risk rather than by whoever called first.

Most of a Socrates Pre-Op interview is conversational rather than form-filling, and patients complete it from home in their own time rather than in a clinic slot. It can be paused and resumed, and photographing medications happens during the conversation rather than as separate homework. Duration varies with how complex the patient's history is.

The comparison that matters is not against a stopwatch but against what it replaces: a paper questionnaire that arrives in the post and comes back incomplete, or a phone call at a time that suits the service rather than the patient.

Complexity drives length, which is the correct behaviour — a patient with a long medication list and several prior anaesthetics has more to cover than a healthy patient presenting for a day case, and a structured interview should spend the time where the information is.

It says so, on the profile. Extraction confidence is shown rather than hidden, anything uncertain is flagged for human review, and missing investigations and unconfirmed timings are listed explicitly. A profile that has not been told about an outstanding echocardiogram is not presented as a clean profile — the gap is part of the output.

This is deliberate, and it is the property that separates a screening tool from a reassurance tool. A system that presents uncertain extractions with the same visual weight as verified ones is making a clinical judgement it has no standing to make.

So a patient-reported HbA1c appears with its confidence attached and “gap: recent HbA1c” recorded alongside it, rather than being silently promoted to a result. The clinician can then decide whether the gap matters for this patient and this procedure — which is the decision that was always theirs.