Artificial Intelligence / discovery / 4 MIN READ

AI and Digital Health for Rare Diseases: Promising but Thin Evidence

A scoping review of 245 studies on digital health in lysosomal storage disorders finds real momentum — and a field still running almost entirely on small, single-center observational data, zero completed RCTs, and a heavy bias toward two diseases out of dozens.

Reality 72 /100
Hype 15 /100
Impact 65 /100
Share

Explanation

Lysosomal storage disorders (LSDs) are a group of roughly 70 rare inherited metabolic diseases where the body can't break down certain cellular waste products. They're a useful proxy for rare diseases broadly: hard to diagnose, complex to manage, and chronically under-resourced. Only about 5% of all rare diseases have approved treatments.

This scoping review — covering 1,751 records from 2015–2024, with 245 included — is the first systematic map of where AI and connected care (telemedicine, remote monitoring, patient-engagement tools) actually sit in LSD care today.

The headline finding: there's genuine activity, but the evidence base is shallow. AI is mostly being used for diagnostic decision support and patient phenotyping (grouping patients by disease characteristics). Connected care tools are concentrated in telemedicine and remote monitoring. The bulk of the literature — nearly half — clusters around screening and diagnosis. Treatment optimization, rehabilitation, and end-of-life care are barely touched.

Two diseases, Gaucher and Fabry, dominate the literature. The other 68-odd LSDs are largely invisible in the digital health research record.

The methodological picture is blunt: no completed randomized controlled trials, no LSD-specific systematic reviews, and outcomes are mostly healthcare delivery metrics rather than what patients actually experience. Algorithms are rarely described transparently enough to replicate or audit.

Why does this matter now? The EU's rare disease policy agenda is accelerating, and digital health infrastructure decisions — registries, interoperability standards, AI procurement — are being made today. A field that can't yet demonstrate effectiveness risks either being ignored in those decisions or, worse, having unvalidated tools quietly embedded in clinical workflows. The review's practical output is a gap map that can anchor expert consensus and direct the next wave of multicenter, prospective studies toward the questions that actually need answering.

Reality meter

Artificial Intelligence Time horizon · mid term
Reality Score 72 / 100
Hype Risk 15 / 100
Impact 65 / 100
Source Quality 75 / 100
Community Confidence 50 / 100

Why this score?

Trust Layer Score basis
Score basis

A detailed evidence breakdown is being added. For now, the score basis is the source list below and the reality meter above.

Source receipts
  • 48 sources on file
  • Avg trust 42/100
  • Trust 40–95/100

Time horizon

Expected mid term

Community read

Community live aggregateIdle
Reality (article)72/ 100
Hype15/ 100
Impact65/ 100
Confidence50/ 100
Prediction Yes0%none yet
Prediction votes0

Glossary

Scoping review
A systematic mapping of literature across a broad topic to identify gaps, types of evidence, and research trends, without formally assessing the quality or risk of bias in individual studies.
Diagnostic odyssey
The prolonged period of clinical investigation and specialist consultations that patients with rare or complex diseases experience before receiving a correct diagnosis.
Enzyme replacement therapy (ERT)
A treatment approach for genetic disorders where a functional enzyme is supplied to patients who lack or have deficient production of that enzyme.
Substrate reduction therapy
A treatment that reduces the accumulation of harmful metabolic byproducts in cells by inhibiting the enzymes that produce them, used in certain genetic storage disorders.
Digital biomarkers
Quantifiable physiological or behavioral indicators measured through digital devices or platforms that reflect disease status or progression.
Algorithm transparency
The degree to which the internal workings, training data, and decision-making logic of an artificial intelligence model can be understood and explained to users and regulators.
EU AI Act
European Union legislation that establishes risk-based requirements for artificial intelligence systems, including strict oversight for high-risk applications like medical diagnostics.
Your signal

What's your read?

Your read shapes future topic weighting.

Quick vote
More rating options
Stars (1–5)
How real is this? Reality Ø 72
More or less of this?

Your vote feeds topic weights, community direction and future prioritisation. Open community direction

Sources

Optional Submit a prediction Optional: add your prediction on the core question if you like.

Prediction

Will a completed randomized controlled trial evaluating an AI or connected care intervention specifically in lysosomal storage disorders be published by the end of 2027?

Related transmissions