Understanding COVID-19 infection among people with intellectual and developmental disabilities using machine learning.

BACKGROUND: People with intellectual and developmental disabilities (IDD) were disproportionately affected by the COVID-19 pandemic. Predicting COVID-19 infection has been difficult. OBJECTIVE: We sought to address two research questions in this study: 1) to assess the overall utility of a machine learning model to predict COVID-19 diagnosis for people with IDD, and 2) to determine the primary predictors of COVID-19 diagnosis in a random sample of Home and Community Based Services users in one state. METHODS: We merged three major IDD-specific datasets (National Core Indicators, Supports Intensity Scale, Medicaid HCBS expenditures) from one state to create one combined dataset for analyses that included more than 700 variables. We then built a random forest machine learning algorithm to predict COVID-19 diagnosis and to explore the top predictors of such a diagnosis, when present. RESULTS: Our algorithm predicted COVID-19 diagnosis in a random sample of HCBS users with IDD with 62.5% accuracy. The top predictors of having a documented case of COVID-19 among our sample were higher age, having high overall, medical, or behavioral support needs, living in a lower-income neighborhood, total Medicaid expenditure, and higher body mass index. CONCLUSIONS: Results largely followed trends in the general population, and were largely suggestive that increased contact with other people may have exposed a person with IDD to greater COVID-19 risk.

Co-Occurring Mental Illness and Behavioral Support Needs in Adults with Intellectual and Developmental Disabilities.

People with intellectual and developmental disabilities (IDD) have higher incidences of mental health conditions and behavioral support needs than people without IDD but may not receive needed care from community providers. We examined rates of co-occurring conditions in a representative sample of adults with IDD who use state funded services in Virginia. Using data from two datasets, we identified four categories of mental health and behavioral conditions. We used these categories to examine differences in individual- and system-level factors in people with and without co-occurring conditions. We found high rates of co-occurring conditions in our sample. We found important disability factors and system-level characteristics that were associated with having a diagnosed mental health condition or behavioral support needs. Differing patterns of diagnosis and treatment for co-occurring conditions suggests more work needs to be done to support people with IDD and co-occurring mental health conditions living in the community.

The Role of Information and Knowledge in COVID-19 Vaccination Among People With Intellectual and Developmental Disabilities and Their Families.

People with intellectual and developmental disabilities (IDD) may be at an increased risk of severe illness and death from COVID-19. This article examines the role of information and knowledge in COVID-19 vaccine uptake for people with IDD and their families. We developed a survey about COVID-19 vaccine uptake, confidence, and knowledge for people with IDD and their families. COVID-19 vaccine uptake was associated with higher self-reported knowledge about the vaccine, learning about the vaccine from one's doctor, and social media use. Qualitative results reflected the importance of trusted relationships with medical providers in vaccination.

An Examination of Support Needs, Supports, and Outcomes for People With Intellectual and Developmental Disabilities.

Researchers used a merged dataset to examine if more resources were expended on those with greater support needs and if support needs impacted personal outcomes when controlling for relevant personal and contextual factors. Results indicated that the amount of support a person receives had a direct relationship to their needs. However, we also found that people with the greatest needs had weaker personal outcomes suggesting that distribution of resources based on need may not result in equivalent outcomes. The authors suggest strategies at an individual and systems level to address the outcomes gap for people with the greatest support needs.

Comparing employment, employment services, and employment goals in propensity-matched samples of people with intellectual and developmental disabilities with and without autism.

Background: People with intellectual and developmental disabilities (IDD) tend to have poor employment outcomes relative to the general population, as do people with autism. Research is unclear, however, about how people with IDD with and without autism compare on a variety of employment-related indicators, including desire to work, having work as a goal in their service plans, and being employed. Objectives: To understand how people with IDD with and without autism compare on important employment related outcomes, based on a matched random sample. Methods: Using merged administrative datasets, we used propensity score matching to construct statistically proximate samples of Medicaid waiver users in a single state with IDD both with and without autism, and then tested differences between the two groups on important employment-related indicators. Results: People with IDD and autism were less likely than people with IDD alone to have a goal for employment in their individualized service plans and to hold employment in group community settings. There was no statistical difference between the two groups in terms of desire to have a job or employment in individual community settings. Conclusions: Results reinforce the importance of planning for employment if holding employment is a person's aim, regardless of the presence of autism.

Promising Practices in the Frontiers of Quality Outcome Measurement for Intellectual and Developmental Disability Services.

Medicaid Home and Community-Based Services (HCBS) for people with intellectual and developmental disabilities (IDD) are vital for supporting people with IDD to live well in their communities, but there are not set standards for monitoring quality outcomes related to HCBS. In this paper, we propose promising practices for improving the quality of HCBS outcome measurement, based both in the literature and our own experience conducting an extensive U.S. state-level study. Specifically, we discuss: (1) using merged administrative datasets, (2) developing high-quality psychometrics that attend to ecological issues in measurement, (3) using advanced statistical analyses, and (4) creating immersive, user-friendly translational dissemination products. We conclude by suggesting what we see as important new frontiers for researchers to consider in order to enhance the quality of HCBS outcome measurement for people with IDD in the future.

Measuring Four Personal Opportunities for Adults With Intellectual and Developmental Disabilities.

This study tests an empirically derived model for measuring personal opportunities for people with intellectual and developmental disabilities (IDD) using National Core Indicators In-Person Survey (NCI-IPS) state and national datasets. The four personal opportunities measured, (a) privacy rights, (b) everyday choice, (c) community participation, and (d) expanded friendships, were informed by existing conceptualizations of service as well as NCI-IPS measures. Analyses confirmed the fit of a four-factor model and demonstrated that factors were significantly and positively correlated. To demonstrate the relationships between personal opportunities and personal and environmental characteristics, we estimated a structural equation model that regressed personal opportunities on age, gender, place of residence, and level of intellectual disability. Implications for using personal opportunities for evaluating service quality of IDD systems are discussed.

Using Machine Learning to Predict Patterns of Employment and Day Program Participation.

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.

Testing a Wellness Indicators Measure for People with Intellectual and Developmental Disabilitiesa.

Background and Purpose: People with intellectual and developmental disabilities (IDD) often have health and wellness issues that are not as good as people without disabilities. States are required to monitor health and wellness for people with IDD who use many disability services. However, there are few ways to monitor wellness between states or at different points in time. In this study, we share a new model that states may use to monitor wellness of people with IDD. Methods: We used data from a survey called the National Core Indicators (NCI) to develop this model. First, we developed the model using our state's data. Then, after we found a model that worked well, we tested that model using the National Core Indicators from the entire U.S. Results: Our final model worked well in both our state NCI data and the national NCI data. This is important because policies at both levels can affect the services that people with disabilities can use. Our model had three parts: heart health, mental health, and behavioral wellness. These are described more in the paper. We also used statistics to test some factors that might predict outcomes related to heart health, mental health, and behavioral wellness. Age, sex, where someone lives, and level of intellectual disability were all good predictors of all three categories of wellness that we studied. Implications: The model of wellness that we developed worked well but should be tested using data from other individual states. It is very important to know about health and wellness right now since the services people with disabilities can use are changing in many states. We think our model can help planners and advocates understand how services affect wellness in a way that is easy to compare from state to state and at different points in time.

Rapid detection of enterotoxigenic clostridium perfringens by real-time fluorescence resonance energy transfer PCR.

Clostridium perfringens is one of the etiologic agents of gas gangrene that can occur when a wound is contaminated with soil. Type A C. perfringens can cause foodborne and nonfoodborne gastrointestinal illnesses due to an enterotoxin (CPE) produced by some strains during sporulation. We developed a quantitative real-time PCR assay based on fluorescence resonance energy transfer hybridization chemistry that targets the C. perfringens-specific phospholipase C (plc) gene and the enterotoxigenic gene (cpe) with the LightCycler and the Ruggedized Advanced Pathogen Identification Device (R.A.P.I.D.). The assay can detect as few as 20 copies of target sequences per PCR. The total assay time, from extraction to PCR analysis, is 90 min. This assay is rapid, sensitive, and specific and will allow direct detection of C. perfringens in water, food, and stool samples. It should prove helpful in investigating foodborne illnesses due to C. perfringens and can be used as a tool to ensure the safety of food and water supplies.