Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making

Zytek, Alexandra; Liu, Dongyu; Vaithianathan, Rhema; Veeramachaneni, Kalyan

doi:10.1109/tvcg.2021.3114864

Cited by 27 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of AI and mental health outlined data sources as electronic health records, mood rating scales, brain imaging data, monitoring systems and social media platforms to predict, organize, or subgroup a range of mental ill-health and suicidality [81]. Machine learning automates processes, analyzes big data, and assists mental health care practitioners with making decisions on an individual's mental ill-health or suicide risk, but there has yet to be any accurate prediction of specific risks across populations [40,82].…”

Section: Artificial Intelligencementioning

confidence: 99%

“…Usability challenges for machine learning include the sufficient skills and time required to develop and run models, users lacking trust in the models, and the struggle rooted in human-machine learning disagreement [82]. Human-centered AI (HAI) was suggested to counter HCI deficiencies-it is a user-centered HCI approach consisting of human factors design, ethically aligned design, and technology that covers human intelligence [94].…”

Section: Artificial Intelligencementioning

confidence: 99%

“…Human-centered AI (HAI) was suggested to counter HCI deficiencies-it is a user-centered HCI approach consisting of human factors design, ethically aligned design, and technology that covers human intelligence [94]. Human factors design can benefit from cost-benefit analyses to provide information on expectations and to clarify the prediction target [82]. In addition, it is important to build trust, decrease disagreement, improve responsibility, explain a model's logic, quantify specific contributions to the prediction, assess the performance metrics, and illustrate historical predictions from previous studies [82].…”

Section: Artificial Intelligencementioning

confidence: 99%

“…Human factors design can benefit from cost-benefit analyses to provide information on expectations and to clarify the prediction target [82]. In addition, it is important to build trust, decrease disagreement, improve responsibility, explain a model's logic, quantify specific contributions to the prediction, assess the performance metrics, and illustrate historical predictions from previous studies [82].…”

Section: Artificial Intelligencementioning

confidence: 99%

See 3 more Smart Citations

Human-Computer Interaction in Digital Mental Health

Balcombe

Leo

2022

Informatics

View full text Add to dashboard Cite

Human-computer interaction (HCI) has contributed to the design and development of some efficient, user-friendly, cost-effective, and adaptable digital mental health solutions. But HCI has not been well-combined into technological developments resulting in quality and safety concerns. Digital platforms and artificial intelligence (AI) have a good potential to improve prediction, identification, coordination, and treatment by mental health care and suicide prevention services. AI is driving web-based and smartphone apps; mostly it is used for self-help and guided cognitive behavioral therapy (CBT) for anxiety and depression. Interactive AI may help real-time screening and treatment in outdated, strained or lacking mental healthcare systems. The barriers for using AI in mental healthcare include accessibility, efficacy, reliability, usability, safety, security, ethics, suitable education and training, and socio-cultural adaptability. Apps, real-time machine learning algorithms, immersive technologies, and digital phenotyping are notable prospects. Generally, there is a need for faster and better human factors in combination with machine interaction and automation, higher levels of effectiveness evaluation and the application of blended, hybrid or stepped care in an adjunct approach. HCI modeling may assist in the design and development of usable applications, and to effectively recognize, acknowledge, and address the inequities of mental health care and suicide prevention and assist in the digital therapeutic alliance.

show abstract

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

See 2 more Smart Citations

Human-Computer Interaction in Digital Mental Health

Balcombe

Leo

2022

Informatics

View full text Add to dashboard Cite

show abstract

“…Much work has been done on developing models and algorithms to improve the interpretability and explainability of ML for tabular data. 1 However, our experiences introducing ML solutions to a wide variety of real-world domains [1] [5] [21] [35] [40] has shown that models are only as interpretable as their features. ML explanations are presented using the language of the model features; whether through presenting feature importances, meaningful example inputs, decision boundary visualizations, or other methods.…”

Section: Introductionmentioning

confidence: 99%

The Need for Interpretable Features: Motivation and Taxonomy

Zytek¹,

Arnaldo²,

Liu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features. Even simple, highly interpretable model types such as regression models can be difficult or impossible to understand if they use uninterpretable features. Different users, especially those using ML models for decision-making in their domains, may require different levels and types of feature interpretability. Furthermore, based on our experiences, we claim that the term "interpretable feature" is not specific nor detailed enough to capture the full extent to which features impact the usefulness of ML explanations. In this paper, we motivate and discuss three key lessons: 1) more attention should be given to what we refer to as the interpretable feature space, or the state of features that are useful to domain experts taking real-world actions, 2) a formal taxonomy is needed of the feature properties that may be required by these domain experts (we propose a partial taxonomy in this paper), and 3) transforms that take data from the model-ready state to an interpretable form are just as essential as traditional ML transforms that prepare features for the model.

show abstract