Arthur Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Arthur Choi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Adnan Darwiche
Computer Science Department University of California Los Angeles USA
3 shared publications - Angela Fidler Pfammatter
Department of Nutrition and Public Health Sciences, The University of Tennessee-Knoxville, Knoxville, TN 37996, USA
2 shared publications - Bonnie Spring
Department of Preventive Medicine Northwestern University Feinberg School of Medicine Chicago Illinois USA
2 shared publications - Glenn Fernandes
Northwestern University, Computer Science, USA
2 shared publications - Jacob Michael Schauer
Division of Gastroenterology and Hepatology, Department of Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
2 shared publications - Nabil Alshurafa
Preventive Medicine and Computer Science, Northwestern University, Chicago, Illinois, USA
2 shared publications
Latest Publications
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 302-307
On Provenance in Topic Models
Topic models are statistical models that can be used to discover the latent topical structure of a text dataset. In this paper, we consider the provenance of topics found by topic models. In particular, we seek to answer questions such as "Why does this topic appear in this dataset?" and "Why does this topic appear in this document?" We propose to answer these questions by formulating them as probabilistic queries in a topic model. The ability to answer such questions helps us to better understand the topic models that we learn from data, and further providing insights on the text datasets that they represent. Moreover, they provide trust in the topic model, and trust in the topics learned from the data. To facilitate the analysis of provenance in topic models, we contribute a new open-source software system for navigating topic models, called SPOT (Seeking the Provenance Of Topics). Using our new tool, we provide some case studies where we seek the provenance of topics that were discovered from datasets of Wikipedia articles.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 302-307
Open AccessOn Provenance in Topic Models
Topic models are statistical models that can be used to discover the latent topical structure of a text dataset. In this paper, we consider the provenance of topics found by topic models. In particular, we seek to answer questions such as "Why does this topic appear in this dataset?" and "Why does this topic appear in this document?" We propose to answer these questions by formulating them as probabilistic queries in a topic model. The ability to answer such questions helps us to better understand the topic models that we learn from data, and further providing insights on the text datasets that they represent. Moreover, they provide trust in the topic model, and trust in the topics learned from the data. To facilitate the analysis of provenance in topic models, we contribute a new open-source software system for navigating topic models, called SPOT (Seeking the Provenance Of Topics). Using our new tool, we provide some case studies where we seek the provenance of topics that were discovered from datasets of Wikipedia articles.
- Open Access
- 6 September 2023
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 25, e42047
An Explainable Artificial Intelligence Software Tool for Weight Management Experts (PRIMO): Mixed Methods Study
Background: Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts. Objective: This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts’ agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts. Methods: We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants’ weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants’ agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts’ understanding and trust in the model. Results: Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ2=7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts’ understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances. Conclusions: Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts.
- 6 September 2023
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 25, e42047
Open AccessAn Explainable Artificial Intelligence Software Tool for Weight Management Experts (PRIMO): Mixed Methods Study
Background: Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts. Objective: This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts’ agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts. Methods: We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants’ weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants’ agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts’ understanding and trust in the model. Results: Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ2=7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts’ understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances. Conclusions: Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts.
- Open Access
- 19 August 2022
- Published by JMIR Publications Inc. in JMIR Preprints
An Explainable Artificial Intelligence Software Tool for Weight Management Experts (PRIMO): Mixed Methods Study (Preprint)
BACKGROUND Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts. OBJECTIVE This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts’ agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts. METHODS We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants’ weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants’ agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts’ understanding and trust in the model. RESULTS Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ2=7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts’ understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances. CONCLUSIONS Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts.
- 19 August 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAn Explainable Artificial Intelligence Software Tool for Weight Management Experts (PRIMO): Mixed Methods Study (Preprint)
BACKGROUND Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts. OBJECTIVE This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts’ agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts. METHODS We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants’ weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants’ agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts’ understanding and trust in the model. RESULTS Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ2=7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts’ understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances. CONCLUSIONS Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts.
- 17 August 2021
- Published by MIT Press
- p. 259-280
Lifted Generalized Belief Propagation: Relax, Compensate and Recover
- 17 August 2021
- Published by MIT Press
- p. 259-280
Lifted Generalized Belief Propagation: Relax, Compensate and Recover