Extending the Nested Model for User-Centric XAI: A Design Study on GNN-based Drug Repurposing

Wang, Qianwen; Huang, Kexin; Chandak, Payal; Žitnik, Marinka; Gehlenborg, Nils

doi:10.1109/tvcg.2022.3209435

Cited by 35 publications

(15 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, by accessing rich molecular and clinical knowledge, a GMAI model can solve tasks with limited data by drawing on knowledge of related problems, as exemplified by initial works on AI-based drug repurposing 22 .…”

Section: Medical Domain Knowledgementioning

confidence: 99%

Foundation models for generalist medical artificial intelligence

Moor

Banerjee

Abad

et al. 2023

Nature

544

125

View full text Add to dashboard Cite

The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI) models is likely to usher in newfound capabilities in medicine. We propose a new paradigm for medical AI, which we refer to as generalist medical AI (GMAI). GMAI models will be capable of carrying out a diverse set of tasks using very little or no task-specific labelled data. Built through self-supervision on large, diverse datasets, GMAI will flexibly interpret different combinations of medical modalities, including data from imaging, electronic health records, laboratory results, genomics, graphs or medical text. Models will in turn produce expressive outputs such as free-text explanations, spoken recommendations or image annotations that demonstrate advanced medical reasoning abilities. Here we identify a set of high-impact potential applications for GMAI and lay out specific technical capabilities and training datasets necessary to enable them. We expect that GMAI-enabled applications will challenge current strategies for regulating and validating AI devices for medicine and will shift practices associated with the collection of large medical datasets.

show abstract

Section: Medical Domain Knowledgementioning

confidence: 99%

Foundation models for generalist medical artificial intelligence

Moor

Banerjee

Abad

et al. 2023

Nature

544

125

View full text Add to dashboard Cite

show abstract

“…In developing human-AI TXGNN Explorer, we took a user-centric approach by comparing three visual explanations for displaying GNN explanations, i.e., neighbor nodes around the query disease, subgraphs, and paths (Figure 3a, Supplementary Figure 4). Our studies showed that path explanations improve user performance and satisfaction compared to neighbor and subgraph explanations 30 .…”

Section: Resultsmentioning

confidence: 74%

“…, neighbor nodes around the query disease, subgraphs, and paths (Figure 3a, Supplementary Figure 4). Our studies showed that path explanations improve user performance and satisfaction compared to neighbor and subgraph explanations 30 .…”

Section: Resultsmentioning

confidence: 74%

“…We designed and developed TXGNN Explorer following a user-centric design study process 30 , which compared three visual presentations of GNN explanations from users' perspectives and motivated the implementation of path-based explanations based on user feedback. We evaluated the usability of TXGNN Explorer by comparing it with a non-explanation baseline that shows drug predictions and corresponding confidence scores.…”

Section: Usability Study Of Txgnn With Medical Expertsmentioning

confidence: 99%

See 1 more Smart Citation

A foundation model for clinician-centered drug repurposing

Huang

Chandak

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Of the several thousand diseases that affect humans, only about 500 have treatments approved by the U.S. Food and Drug Administration. Even for those with approved treatments, discovering new drugs can offer alternative options that cause fewer side effects and replace drugs that are ineffective for certain patient groups. However, identifying new therapeutic opportunities for diseases with limited treatment options remains a challenge, as existing algorithms often perform poorly. Here, we leverage recent advances in geometric deep learning and human-centered AI to introduce TxGNN, a model for identifying therapeutic opportunities for diseases with limited treatment options and minimal molecular understanding. TxGNN is a graph neural network pre-trained on a comprehensive knowledge graph of 17,080 clinically-recognized diseases and 7,957 therapeutic candidates. The model can process various therapeutic tasks, such as indication and contraindication prediction, in a unified formulation. Once trained, we show that TxGNN can perform zero-shot inference on new diseases without additional parameters or fine-tuning on ground truth labels. Evaluation of TxGNN shows significant improvements over existing methods, with up to 49.2% higher accuracy in indication tasks and 35.1% higher accuracy in contraindication tasks. TxGNN can also predict therapeutic use for new drugs developed since June 2021. To facilitate interpretation and analysis of the model's predictions by clinicians, we develop a human-AI explorer for TxGNN and evaluate its usability with medical experts. Finally, we demonstrate that TxGNN's novel predictions are consistent with off-label prescription decisions made by clinicians in a large healthcare system. These label-efficient and clinician-centered learning systems pave the way for improvements for many therapeutic tasks.

show abstract

“…Other work has focused on actionable explanations for pre‐built models for clinicians, such as normal tissue complication models [ZHT * 13], binary classifiers [CMQ20], case‐based reasoning [MMB * 18, MXC * 19], and black box models [CLD * 21]. For explainable AI, DrugExplorer [WHC * 22] proposed a model for user‐centered XAI alongside a system for exploring graph‐neural‐networks for drug repurposing. However, none of these approaches tackle iterative probing and model development, or capturing spatial information in their data, as we do.…”

Section: Related Workmentioning

confidence: 99%

DASS Good: Explainable Data Mining of Spatial Cohort Data

Wentzel

Floricel

Canahuate

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Developing applicable clinical machine learning models is a difficult task when the data includes spatial information, for example, radiation dose distributions across adjacent organs at risk. We describe the co‐design of a modeling system, DASS, to support the hybrid human‐machine development and validation of predictive models for estimating long‐term toxicities related to radiotherapy doses in head and neck cancer patients. Developed in collaboration with domain experts in oncology and data mining, DASS incorporates human‐in‐the‐loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrate DASS with the development of two practical clinical stratification models and report feedback from domain experts. Finally, we describe the design lessons learned from this collaborative experience.

show abstract

Extending the Nested Model for User-Centric XAI: A Design Study on GNN-based Drug Repurposing

Cited by 35 publications

References 71 publications

Foundation models for generalist medical artificial intelligence

Foundation models for generalist medical artificial intelligence

A foundation model for clinician-centered drug repurposing

DASS Good: Explainable Data Mining of Spatial Cohort Data

Contact Info

Product

Resources

About