@OWMorgan
Account based inGermany
About this account
- Account based in
- Germany
- Connected via
- Switzerland App Store
Account-level information from X, not a live location or the device used for a specific post.
Director Pandemic and Epidemic Intelligence Systems @WHO #WHOPandmicHub #globalhealth #surveillance #riskassessment #healthemergencies #outbreaks
Berlin, Germany
Joined January 2018
- Tweets1.8K
- Following214
- Followers3.6K
- Likes1.3K
This week's AI + public health journal digest is out.
9 papers: pharmacovigilance, dengue diagnostics, gender bias in clinical AI, maternal drug-evidence gaps, viral evolution and more.
Full digest: aipublichealth.substack.com/…
#APHIDigest
31,917 patient surveys. 31 physicians. One question: do ambient AI scribes change how patients rate their care?
The answer: no measurable difference, up or down.
Sometimes the useful finding is that nothing broke. Reassuring before these tools scale further.
If an AI study landed on your ethics committee tomorrow, could it review the algorithm?
In Tanzania, researchers asked 10 committees. The governance was solid. The AI-specific capacity was not: judging algorithms, vetting big datasets, monitoring after approval.
"Just pilot it, train staff, embed it, move on." That is how we roll out most health innovations.
A new analysis argues AI breaks that model. It can be opaque, and it drifts as data and vendors change. Adoption is not the finish line. It is the start of oversight.
In 2024, more than 60% of US local health departments reported no dedicated informatics staff.
You cannot fix a data pipeline no one on staff can change. The workforce is a layer of AI readiness, not an afterthought.
aipublichealth.substack.com/…
~250,000 adverse safety events hit US healthcare every year. More than 95% go undetected.
A new tool in PLOS Digital Health goes after that gap, without handing the final call to a black box. 🧵
Tested on 300 paediatric cardiac arrest charts for adrenaline dosing errors:
97.9% accuracy on overdoses
91.6% on dangerous delays
under 1 minute per chart
It beat LLM-only baselines, and most misses came from data extraction, not the logic.
The catch: one drug, one setting, and a hand-built rule set for each new use case.
But pairing model-based extraction with rule-based decisions is a workable answer to trust in clinical AI.
Full digest: aipublichealth.substack.com/…
#APHIDigest
1/ Most public health agencies are not ready for AI. Readiness isn't a model you buy. It's four layers of infrastructure, built in order. A short thread.
5/ Layer 4, partnerships. Where does capability sit when the contract ends? A vendor can leave, and the gap it filled comes straight back.
6/ The layers compound. Each dataset, standard, and skilled hire makes the next one worth more. Skip them, and every project starts from scratch.
Full article: aipublichealth.substack.com/…
#APHIArticle
This week's AI and public health journal digest is out.
6 papers on where AI is actually landing in health: a safety-event detector, an ambient scribe, and a hard look at whether AI is 'just another innovation'.
Full digest: aipublichealth.substack.com/…
#APHIDigest
A perfect sepsis alert does nothing in a clinic with no antibiotics, no fluids, and no power.
A prediction with nowhere to act is worthless. AI readiness is about the whole system, not the model.
Buying a capable AI model does not make a health agency ready to use it.
A model is only as good as what feeds it. Late data, no shared identifier, no one on staff to reshape the system: the tool inherits every gap beneath it.
More than half of sub-Saharan health facilities have no reliable electricity.
About a third of the continent uses the internet, against three-quarters globally.
These are not problems a better AI model can solve.
aipublichealth.substack.com/…
