Could LLM psychiatrists be better than meat ones?

[Not medical advice, obviously]

I had a call with my psychiatrist – the first one in about a year; I hadn’t really felt the need to see him until then – and we spoke for a scant ten minutes. I gave a one-minute description of how I was feeling, and he fiddled with the dose of a mood stabiliser I take and that was it.

He didn’t attempt to really dig deeper into how I was feeling, give me a standard questionnaire like the PHQ-9 or MADRS which would have given a numerical idea of how I was doing over time. The session cost £150, which makes his hourly rate £900. And he charged me £15 for a private prescription which he forgot to issue.

Needless to say I didn’t really feel like he was taking me seriously.

(On the plus side, I’ve had medical professionals who were so disorganised they never even bothered to invoice me. How nice of them to give me a discount.)

I wondered if an LLM couldn’t do a better job than this guy.

So I went and downloaded a copy of the Maudsley¹1. The Maudsley Prescribing Guidelines in Psychiatry (a):

The Maudsley Prescribing Guidelines in Psychiatry is the essential evidence-based handbook on the safe and effective prescribing of psychotropic agents. Covering both common and complex prescribing situations encountered in day-to-day clinical practice, this comprehensive resource provides expert guidance on drug choice, minimum and maximum doses, adverse effects, switching medications, prescribing for special patient groups, and more. Each clear and concise chapter includes an up-to-date reference list providing easy access to the evidence on which the guidance is based.

Here is it dismantling some common myths (Opus 4.5):

User: how long does it take antidepressants to start working in depression?

The Maudsley is clear on this, and it’s actually good news: the idea that antidepressants take 2–4 weeks to work is a myth.

All antidepressants show a response pattern where the rate of improvement is highest during weeks 1–2 and lowest during weeks 4–6. Statistical separation from placebo is seen at 2–4 weeks in single trials (which is where the “lag effect” idea comes from), but after only 1–2 weeks in meta-analyses. When large numbers of patients are treated and detailed rating scales are used, an antidepressant effect is statistically evident at 1 week.

In clinical practice using simpler observations, an antidepressant effect in an individual is usually seen by 2 weeks.

The practical implication: in those who will ultimately respond, virtually all will have begun to show at least minor improvement by 4 weeks. Those showing no discernible improvement at this point will very probably never respond to that drug at that dose. …

Of course, with internet access it you can get state-of-the-art evidence, which is likely more up-to-date than what your psych knows.

User: what’s the evidence for pushing escitalopram to doses higher than 20mg? search online as well.

The Maudsley says there’s minimal evidence for SSRI dose escalation in general, but specifically notes that escitalopram (along with venlafaxine and tricyclics) may be an exception.

The Furukawa 2019 meta-analysis found SSRIs plateau around 20–40mg fluoxetine equivalents (~10–20mg escitalopram). But a Bayesian reanalysis suggested escitalopram specifically can be escalated higher than other SSRIs—up to ~30mg for ages 30–65.

A Korean RCT (2019) found 30mg vs 20mg in non-remitters showed improved depressive symptoms on MADRS, but not increased response/remission rates—a modest continuous effect, not a categorical one.

An open-label pilot escalating to 50mg found median remission dose was 30mg, with 38% of remitters needing 50mg. Tolerability declined above 40mg.

Why escitalopram might be different: It has a unique allosteric mechanism—binding to an allosteric site decreases its own dissociation rate from SERT, potentially potentiating effect at higher doses. Other SSRIs don’t do this.

Safety: QTc increases ~10.7ms at 30mg—modest and generally not clinically concerning.

Bottom line: 30mg is reasonable and better-supported than high doses of other SSRIs, though the evidence isn’t definitive.

Certainly it seems like, if not a replacement for a traditional psychiatrist, an LLM + a copy of the Maudsley is very good foil for classical care.