MENTOR: a Bayesian Model for prediction of mental retardation in newborns.
MENTOR gives newborn probability ranges for later cognitive level so families can choose next tests with open eyes.
01Research in Context
What this study did
Dall et al. (1997) built a computer tool called MENTOR.
It takes newborn facts and gives a probability range for later intellectual disability.
Doctors can use the numbers to decide if more tests are needed.
What they found
The paper shows the math behind the tool, not trial results.
It tells how to turn small clues into risk odds for families.
How this fits with other research
Corbo et al. (2024) asked moms who got newborn FXS screens.
Most still liked early news even when first feelings were hard.
MENTOR gives the same kind of early odds, so pre-test talks must plan for worry.
Préfontaine et al. (2019) found parents over-hope genetic tests will give clear cures.
MENTOR’s probability talk can calm this hope by showing ranges, not promises.
Wong et al. (2009) proved one teen test predicts later issues in 22q11DS.
MENTOR tries to do the same job but starts from day one.
Why it matters
You can borrow MENTOR’s style when you speak with families after early screens.
Share chance bands, not yes-or-no labels.
Add plain words like “one in four” or “three in ten” so parents leave with real numbers, not fog.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Add a simple probability line to your intake sheet, like “chance of ID: low/medium/high” to match MENTOR’s spirit.
02At a glance
03Original abstract
Mental retardation (MR) is a diagnosis that is made with extreme caution because of the many uncertainties in its etiology and prognosis. In fact, most physicians will delay the diagnosis for months or years so that substantial evidence is available to rule the diagnosis in or out. MENTOR is a Bayesian Model for the prediction of MR in newborns that provides probabilities for the full range of cognitive outcomes, ranging from MR to superior intelligence. Using the model to confirm clinical judgment could help physicians decide when to proceed with diagnostic tests. The physician and family could discuss the probabilities for MR, borderline, normal, and superior intelligence, given the child's status in infancy and base their decision about additional testing, in part, on this information.
Research in developmental disabilities, 1997 · doi:10.1016/s0891-4222(97)00012-7