A machine learning approach for identifying predictors of success in a Medicaid-funded, community-based behavioral health program using the Child and Adolescent Needs and Strengths (CANS)

Troy, Jesse D.; Torrie, Ryan M.; Warner, Daniel N.

doi:10.1016/j.childyouth.2021.106010

Cited by 10 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another study showed that in a publicly funded system of care, a community-based program could be utilized from tools such as the Child and Adolescent Needs and Strengths (CANS) to identify clients likely to benefit from established mental health services. The study proposed using ML methods to learn from data collected through the application of Transformational Collaborative Outcomes Management (TCOM) within a human services system, which can be replicated in various contexts [ 44 ].…”

Section: Resultsmentioning

confidence: 99%

The application of artificial intelligence in health financing: a scoping review

Ramezani,

Takian,

Bakhtiari

et al. 2023

Cost Eff Resour Alloc

View full text Add to dashboard Cite

Introduction Artificial Intelligence (AI) represents a significant advancement in technology, and it is crucial for policymakers to incorporate AI thinking into policies and to fully explore, analyze and utilize massive data and conduct AI-related policies. AI has the potential to optimize healthcare financing systems. This study provides an overview of the AI application domains in healthcare financing. Method We conducted a scoping review in six steps: formulating research questions, identifying relevant studies by conducting a comprehensive literature search using appropriate keywords, screening titles and abstracts for relevance, reviewing full texts of relevant articles, charting extracted data, and compiling and summarizing findings. Specifically, the research question sought to identify the applications of artificial intelligence in health financing supported by the published literature and explore potential future applications. PubMed, Scopus, and Web of Science databases were searched between 2000 and 2023. Results We discovered that AI has a significant impact on various aspects of health financing, such as governance, revenue raising, pooling, and strategic purchasing. We provide evidence-based recommendations for establishing and improving the health financing system based on AI. Conclusions To ensure that vulnerable groups face minimum challenges and benefit from improved health financing, we urge national and international institutions worldwide to use and adopt AI tools and applications.

show abstract

Section: Resultsmentioning

confidence: 99%

The application of artificial intelligence in health financing: a scoping review

Ramezani,

Takian,

Bakhtiari

et al. 2023

Cost Eff Resour Alloc

View full text Add to dashboard Cite

show abstract

“…Because local interpretation techniques have recently become more popular in psychological and social science research (see e.g., Troy et al, 2021;Vowels et al, 2021Vowels et al, , 2022Wen et al, 2021;Yu et al, 2021;S. Zhou et al, 2021, for applications), psychological researchers are likely to get in contact with these techniques as readers of scientic articles or when conducting their own research.…”

Section: Introductionmentioning

confidence: 99%

Local interpretation techniques for machine learning methods: Theoretical background, pitfalls and interpretation of LIME and Shapley values

Henninger,

Strobl

2023

Preprint

View full text Add to dashboard Cite

Machine learning methods have become popular in psychological research. To predict the outcome variable, machine learning methods use complex functions to describe non-linear and higher order interaction effects. However, researchers from psychology are used to parametric models, such as linear or logistic regression, where parameters can be clearly interpreted, while machine learning methods often lack such interpretable parameters. To gain insights into how the machine learning method has made its predictions, different interpretation techniques have been proposed. They support researchers in understanding, for example, which variables have been important for the machine learning predictions. In this article, we focus on two local interpretation techniques that are widely used in machine learning: Local Interpretable Model-Agnostic Explanations (LIME) and Shapley values. LIME aims at explaining machine learning predictions in the close neighborhood of selected persons. Shapley values can be understood as a measure of predictor relevance or contribution of predictor variables for specific persons. Using two illustrative, simulated examples, we explain the idea behind LIME and Shapley, demonstrate their characteristics, and discuss challenges that might arise in their application and interpretation. For LIME, we demonstrate how the choice of the size of the neighborhood may impact conclusions. For Shapley values, we show how they can be interpreted jointly for all persons in the sample, and discuss similarities with global interpretation techniques. The aim of this article is to support researchers to safely use these interpretation techniques themselves, but also to critically evaluate interpretations when they encounter the interpretation techniques in research articles.

show abstract

“…However, over the last several years there has been a move towards using empirical data to better analyze systems, and produce algorithms that are more empirically grounded. For instance, Troy et al, used machine learning methods to analyze existing CANS data and create decision support that would recommend people to a level of care based on possessing a profile empirically shown to do better in one level of care versus another (Troy, 2021). Likewise, Cordell et al (Cordell, 2016) analyzed CANS data to help inform level of need at initial assessments, and Shimshock et al (Shimshock, 2022) analyzed CANS data in treatment foster care to help better tailor treatment plans in the service.…”

Section: Introductionmentioning

confidence: 99%

A linear optimization approach to decision support with CANS data

Offner,

Warner,

et al. 2023

Preprint

View full text Add to dashboard Cite

This research is meant to make a contribution to the field of Communimetric (CMX) algorithms (Lyons, 2004, 2009). This is the science underscoring the behavioral health and child welfare assessment tools such as the Child and Adolescent Needs and Strengths (CANS) assessment, the Adult Needs and Strengths Assessment (ANSA), and the Family Advocacy and Support Tool (FAST), amongst others (https://praedfoundation.org/). These tools are used throughout the US child serving and adult mental health system not only to assure a standardized assessment process, but also to provide real-time Decision Support (DS) to assessors about client treatment planning and disposition. We propose a novel method for developing CMX DS utilizing linear optimization (commonly known also as linear programming (LP) or (mixed) integer linear programming (ILP or MILP)). Using administrative data from Pennsylvania’s Child Medicaid Behavioral Health system, a MILP model is developed to differentiate profiles that benefit from one of two programs in the Pennsylvania child system of care. The programs picked are both for children at risk of out of home placement, but their clinical models are different. There is often debate in the field as to which program is most appropriate for a given family, and thus the MILP model is meant to help facilitate this decision making. We propose both a method for developing a MILP model in Medicaid behavioral health, as well as a method for testing and validating the model. We then propose a method for identifying the impact on care that utilization of the model could have in facilitating improved care matching in a system. We close with a discussion of how this information could also be used for system planning, and program development issues.

show abstract

A machine learning approach for identifying predictors of success in a Medicaid-funded, community-based behavioral health program using the Child and Adolescent Needs and Strengths (CANS)

Cited by 10 publications

References 15 publications

The application of artificial intelligence in health financing: a scoping review

The application of artificial intelligence in health financing: a scoping review

Local interpretation techniques for machine learning methods: Theoretical background, pitfalls and interpretation of LIME and Shapley values

A linear optimization approach to decision support with CANS data

Contact Info

Product

Resources

About