PTOTSLPCohortJournal of intellectual disability research : JIDR2024

Phenotyping Down syndrome: discovery and predictive modelling with electronic medical records.

T Q Nguyen, C I Kerley, A P Key and 5 others

PMID 38303157

WHAT IT FOUND

Electronic records show people with Down syndrome have high rates of speech disorders, coordination issues and hypothyroidism.

A model accurately predicted heart surgery needs based on pre-existing heart and breathing conditions, though diagnostic codes can be inaccurate.

Key findings

01Speech and language disorder, lack of coordination, and abnormal posture were significantly more prevalent in individuals with Down syndrome compared to controls.

02Congestive heart failure and respiratory conditions like pulmonary congestion were top predictors of the need for heart surgery in individuals with Down syndrome and congenital heart disease.

03Several conditions, including chronic kidney disease and acid-base balance disorders, were found to be prevalent in Down syndrome but less frequently studied in existing literature.

STILL TO COME

How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat it means for SLPs

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The study relies on billing codes (ICD-9/10), which can be inaccurate or incomplete. The sample represents patients from a single regional medical centre, which may not reflect broader populations. The study does not account for socioeconomic factors or access to care, which can influence health outcomes. The 'Novelty Finding Index' used to identify under-studied conditions has limitations and needs further validation.

Declared interests

The authors declare no conflicts of interest. The study was supported by NIH grants.

The easy way to misread this

Do not interpret the predictive model as a clinical tool ready for use. It was trained on historical data from one hospital using imperfect billing codes, so it cannot reliably predict surgery needs for individual patients in other settings.

Read it on PubMed →