Search

In this article, we demonstrate the potential of machine learning approaches as inductive analytic tools for expanding our current evidence base for policy making and practice that affects people with intellectual and developmental disabilities (IDD). Using data from the National Core Indicators In-Person Survey (NCI-IPS), a nationally validated annual survey of more than 20,000 nationally representative people with IDD, we fit a series of classification tree and random forest models to predict individuals' employment status and day activity participation as a function of their responses to all other items on the 2017-2018 NCI-IPS. The most accurate model, a random forest classifier, predicted employment outcomes of adults with IDD with an accuracy of 89 percent on the testing sample, and 80 percent on the holdout sample. The most important variable in this prediction was whether or not community employment was a goal in this person's service plan. These results suggest the potential machine learning tools to examine other valued outcomes used in evidence-based policy making to support people with IDD.

Researchers and advocates have long called for improved research methods that better include people with intellectual and developmental disabilities (IDD), but challenges to doing so persist. Proxy responses are frequently used to circumvent some of these challenges, but may not fully capture the perspectives of people with IDD. The COVID-19 pandemic highlighted the possibility of consequences due to a lack of research about health outcomes for people with IDD, with documented disproportionate impact but little understanding about specific experiences for people with IDD. Using exploratory graph analysis (EGA) we explored the use of proxy responses on the COVID-19 Supplement of the National Core Indicators In-Person Survey. Findings suggest significant differences in response patterns between people who answered independently, via proxy, and with a mix of response types beyond what would be expected due to demographic differences in participants. [ABSTRACT FROM AUTHOR]

Having a sense of social inclusion and belonging, typically characterized by our personal relationships and community participation, is the central essence of life for most people, yet it remains elusive for many people with intellectual and developmental disabilities (IDD). This article summarizes the work of a diverse group of researchers and advocates to propose 6 big-picture, equity-based goals to drive future research in the field: (1) understanding the role of intersectionality, (2) understanding intimate relationships, (3) promoting formation of communities of care to support social inclusion, (4) understanding life course trajectories of social inclusion, (5) understanding social inclusion in virtual spaces, and (6) understanding how to promote social inclusion in the entire research process. [ABSTRACT FROM AUTHOR]

BackgroundMethodsFindingsConclusionsAdults with intellectual and developmental disabilities (IDD) often have behavioral support needs that must be met in order to live in community settings. Pharmacotherapies are often used to meet such needs. We explored factors that predict medication for behavioral support among adults with IDD.We integrated three major U.S.- based IDD-specific datasets over multiple years, creating a large dataset. We used machine learning to build and test an algorithm to predict factors associated with the use of pharmacotherapies to address behavioral support needs for adults with IDD.Our algorithm correctly predicted the use of pharmacotherapies with about 79% accuracy. Top predictors of medication use to address behavioral support needs included disruptive behavior, use of medication to treat a mental health condition, and presence of an autism diagnosis.Use of behavior plans should be given more attention in conjunction with medication use, especially in relation to managing disruptive behavior. [ABSTRACT FROM AUTHOR]