Selected synthetic case / actual retained answers
The right tissue can matter more than another normal screen
Both tools favour an ISCU-type iron–sulfur assembly disorder. This pair shows agreement on the diagnosis and a useful OpenEvidence explanation of tissue-specific testing.
A selected synthetic development case, published by MontMedical. The clinical fingerprints match, but the exact prompts submitted to OpenEvidence were not independently retained. This is an editorial comparison of historical answers, not a blinded efficacy trial.
Our editorial assessment
How the retained answers rate.
OpenEvidence8.2/10
MontMedical7.6/10
OpenEvidence gives the more useful tissue-specific explanation.
Same five criteria and weights for both systems| Criterion and weight | OpenEvidence | MontMedical |
|---|
| Diagnosis and case fit 25% | 9/10 | 9/10 |
|---|
| Interpretation of tests and experiments 25% | 8/10 | 8/10 |
|---|
| Strength of the claims 20% | 6/10 | 7/10 |
|---|
| Decisions and next steps 15% | 9/10 | 6/10 |
|---|
| Clarity and teaching 15% | 9/10 | 7/10 |
|---|
Why each criterion received its mark
Diagnosis and case fit
OpenEvidence · 9/10: Correctly identifies a muscle-specific iron–sulfur assembly hypothesis.
MontMedical · 9/10: Correctly identifies ISCU as provisional and retains the important enzyme and exercise findings.
Interpretation of tests and experiments
OpenEvidence · 8/10: Clearly connects the enzyme pattern, normal fibroblasts and tissue-specific splicing.
MontMedical · 8/10: Preserves assay denominators and the deep-intronic gap, but compresses the original exome coverage.
Strength of the claims
OpenEvidence · 6/10: The broad exclusion of primary respiratory-chain disease overstates the specificity of the pattern.
MontMedical · 7/10: The provisional label helps, though “only coding regions” omits the supplied nearby-splice coverage.
Decisions and next steps
OpenEvidence · 9/10: Explicitly recommends muscle RNA and appropriately targeted intronic investigation.
MontMedical · 6/10: Explains the gap but provides a less direct muscle-specific next investigation.
Clarity and teaching
OpenEvidence · 9/10: Gives the stronger connected explanation of why the sampled tissue matters.
MontMedical · 7/10: Dense numerical restatement and tangential research make the teaching less focused.
AI-assisted editorial judgment of these historical texts, published by MontMedical. Read the rubric, anchors and limits. These are answer-quality scores, not measured diagnostic accuracy or patient benefit.
The actual retained wording
OpenEvidence vs MontMedical.
These are verbatim passages from the retained answers, not rewritten examples. Bold, link formatting and line breaks have been removed. Each labelled passage is contiguous; an excerpt may begin within a sentence. Our interpretation and scores are separate.
OpenEvidence
Retained 2026-09-12
Tissue explanation
Fibroblasts are typically spared in ISCU-related disease because the causative defect is often a muscle-specific aberrant splicing event, which would not be detected by blood mtDNA sequencing or a coding-exon exome and requires muscle-derived RNA or targeted intronic analysis to uncover.
Overstatement
this selective loss of two Fe-S-cluster-containing enzymes (aconitase, complex II) with sparing of non-Fe-S enzymes is the biochemical fingerprint of an Fe-S cluster assembly defect, not a primary respiratory chain (mtDNA) disorder.
MontMedical
Retained 2026-09-12
Leading classification
Iron–sulfur cluster assembly deficiency (ISCU) myopathy is the leading provisional diagnosis, supported by lifelong exercise intolerance, recurrent rhabdomyolysis, severe exertional lactic acidosis, intramitochondrial iron accumulation, and selective muscle deficiency of iron–sulfur enzymes (succinate dehydrogenase and mitochondrial aconitase) with normal cytochrome-c oxidase.
Coverage wording
Definitive molecular confirmation remains unresolved because standard clinical exome sequencing covers only coding regions, missing deep-intronic ISCU mutations.
The case and the decision
The case has lifelong exercise intolerance, recurrent rhabdomyolysis, severe exertional lactic acidosis, muscle iron deposits and selectively low aconitase and succinate dehydrogenase activity. Other muscle enzyme activities are preserved. Fibroblast testing is normal, and a coding-and-nearby-splice-region exome is negative.
Why the enzyme pattern is coherent
Aconitase and succinate dehydrogenase require iron–sulfur clusters. A defect in their assembly can affect both without producing the same pattern in enzymes that use other cofactors. Original ISCU work connects an intronic splicing defect to muscle enzyme abnormalities, and later work investigates the tissue specificity. [1] [2]
How the answers compare
Both answers identify the ISCU hypothesis and the unassessed deep-intronic/splicing question. OpenEvidence explains particularly clearly why cultured fibroblasts can be less informative than the affected muscle. MontMedical preserves a provisional diagnosis and the stated enzyme-assay denominators.
We do not claim a MontMedical diagnostic win. Its retained wording that the exome covers only coding regions is too compressed: the case explicitly includes nearby splice junctions. OpenEvidence also overreaches if its broad dismissal of primary respiratory-chain disease is read as excluding every alternative.
What the next experiment should distinguish
Muscle-derived RNA and appropriately targeted genomic investigation can ask whether abnormal ISCU splicing explains the tissue pattern. A negative result from a less affected compartment cannot substitute for that question.
The general lesson is to preserve the actual coverage and sample type. A precise description of a test's limits is more useful than describing a whole class of tests as either definitive or useless.
Retained answer dates: MontMedical 2026-09-12; OpenEvidence 2026-09-12. Excerpt wording was checked against the retained answers; formatting was removed. These versions were selected during development. Complete original run settings and identical submitted prompts are not documented.
This article examines the MontMedical Pro beta using retained diagnostic answers.