[Re: https://www.hifa.org/dgroups-rss/independent-18-children-had-illnesses-s... ]
Where is the full citation of the study. It always good to read what you think but it is always better to have the full citation of the article you are talking about. [*see note below]
With kind regards
Najeeb
[*Note from HIFA moderator (NPW): Thanks for noting this. Yes, curiously the article does not contain a link to the study. I have searched the recent publication on the NEJM AI website and it seems that this is the paper referred to.
LLM-Assisted Reanalysis of Unsolved Rare Disease Genomes Increases Diagnostic Yield
Authors: Aaron Jaech, Ph.D. et al
NEJM AI. Published June 18, 2026
DOI: 10.1056/AIcs2501343
https://ai.nejm.org/doi/full/10.1056/AIcs2501343
Here is the abstract:
Background: Rare and undiagnosed genetic disorders affect millions of patients globally, and many patients endure years of inconclusive testing. Conventional genomic interpretation can be insufficiently sensitive and costly and is rarely repeated as knowledge evolves.
Methods: We conducted a retrospective multicohort reanalysis using a large language model (LLM)–assisted workflow that ingests clinician notes, Human Phenotype Ontology (HPO) terms, and a filtered variant table to propose explanation-rich candidate hypotheses for expert adjudication under American College of Medical Genetics and Genomics and Association for Molecular Pathology criteria. A diagnosis was defined a priori as a variant classified as pathogenic or likely pathogenic, confirmed in a Clinical Laboratory Improvement Amendments–certified laboratory, and returned to families. Secondary outputs included “rediscoveries” of externally established diagnoses not yet available locally and hypothesis generation signals.
Results: Across four cohorts, new local diagnoses were made in 10 of 100 rare disease neurodevelopmental cases (10.0%, [exact binomial: 95% confidence interval (CI), 4.9 to 17.6]), 4 of 61 neuromuscular cases (6.6%, [CI, 1.8 to 16.0]), 2 of 200 cases of sudden unexpected death in pediatrics (1.0% [CI, 0.1 to 3.6]), and 2 of 15 early psychosis cases (13.3% [CI, 1.7 to 40.5]) for an overall diagnostic yield of 18 of 376 (4.8%, [CI, 2.9 to 7.5]). We identified seven rediscoveries in which pathogenic or likely pathogenic findings had been established externally but were not available in the local research record at the time of review. In one case, the model’s synthesis of genotype-quality patterns and phenotype concordance triaged a putative 22q11.2 deletion that was subsequently confirmed by whole-genome sequencing. The workflow also generated testable biological hypotheses, including a candidate association between the sphingosine-1-phosphate receptor 1 gene (S1PR1) and vitiligo.
Conclusions: In retrospective reanalysis, an explanation-first LLM applied to routine HPO terms and variant tables produced clinically relevant gains in diagnostic yield, surfaced overlooked pathogenic findings, and generated biologically grounded hypotheses. These results motivate prospective multicenter evaluation with predefined end points, calibration reporting, and comparator baselines. (Funded by the U.S. National Institute of Child Health and Human Development and others.)
I think the Independent article has 'hyped' the article. We were led to believe that 18 undiagnosed cases were resolved by AI, without telling us that the overall number of cases was 376. 18/376 is not so impressive as 18/18.
Finally, it is interesting that to learn that the NEJM now publishes a specialist journal on AI. I would like to ask any HIFA member with an interest in AI to monitor NEJM AI for papers of relevance to HIFA: neil@hifa.org ]