Evaluation of the modified asthma predictive index in high-risk preschool children.

BACKGROUND: Prediction of subsequent school-age asthma during the preschool years has proven challenging. OBJECTIVE: To confirm in a post hoc analysis the predictive ability of the modified Asthma Predictive Index (mAPI) ina high-risk cohort and a theoretical unselected population. We also tested a potential mAPI modification with a 2-wheezing episode requirement (m2API) in the same populations. METHODS: Subjects (n [ 289) with a family history of allergy and/or asthma were used to predict asthma at age 6, 8, and 11 years with the use of characteristics collected during the first 3 years of life. The mAPI and the m2API were tested for predictive value. RESULTS: For the mAPI and m2API, school-age asthma prediction improved from 1 to 3 years of age. The mAPI had high predictive value after a positive test (positive likelihood ratio ranging from 4.9 to 55) for asthma development at years 6,8, and 11. Lowering the number of wheezing episodes to 2(m2API) lowered the predictive value after a positive test(positive likelihood ratio ranging from 1.91 to 13.1) without meaningfully improving the predictive value of a negative test.Posttest probabilities for a positive mAPI reached 72% and 90%in unselected and high-risk populations, respectively. CONCLUSIONS: In a high-risk cohort, a positive mAPI greatly increased future asthma probability (eg, 30% pretest probability to 90% posttest probability) and is a preferred predictive test to them 2API. With its more favorable positive posttest probability,the mAPI can aid clinical decision making in assessing future asthma risk for preschool-age children.

Machine learning amplifies the effect of parental family history of Alzheimer's disease on list learning strategy.

Identification of preclinical Alzheimer's disease (AD) is an essential first step in developing interventions to prevent or delay disease onset. In this study, we examine the hypothesis that deeper analyses of traditional cognitive tests may be useful in identifying subtle but potentially important learning and memory differences in asymptomatic populations that differ in risk for developing Alzheimer's disease. Subjects included 879 asymptomatic higher-risk persons (middle-aged children of parents with AD) and 355 asymptotic lower-risk persons (middle-aged children of parents without AD). All were administered the Rey Auditory Verbal Learning Test at baseline. Using machine learning approaches, we constructed a new measure that exploited finer differences in memory strategy than previous work focused on serial position and subjective organization. The new measure, based on stochastic gradient descent, provides a greater degree of statistical separation (p = 1.44 × 10-5) than previously observed for asymptomatic family history and non-family history groups, while controlling for apolipoprotein epsilon 4, age, gender, and education level. The results of our machine learning approach support analyzing memory strategy in detail to probe potential disease onset. Such distinct differences may be exploited in asymptomatic middle-aged persons as a potential risk factor for AD.