Doctor XAI: an ontology-based approach to black-box sequential data classification explanations

By Cecilia Panigutti, Alan Perotti, Dino Pedreschi. 2020

166 citations recorded by the source corpus.

Several recent advancements in Machine Learning involve blackbox models: algorithms that do not provide human-understandable explanations in support of their decisions. This limitation hampers the fairness, accountability and transparency of these models; the field of eXplainable Artificial Intelligence (XAI) tries to solve this problem providing human-understandable explanations for black-box models. However, healthcare datasets (and the related learning tasks) often present peculiar features, such as sequential data, multi-label predictions, and links to structured background knowledge. In this paper, we introduce Doctor XAI, a model-agnostic explainability technique able to deal with multi-labeled, sequential, ontology-linked data. We focus on explaining Doctor AI, a multilabel classifier which takes as input the clinical history of a patient in order to predict the next visit. Furthermore, we show how exploiting the temporal dimension in the data and the domain knowledge encoded in the medical ontology improves the quality of the mined explanations.

Subfields: Artificial Intelligence, Molecular Biology, Safety, Robustness & Interpretability, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Safety, Robustness & Interpretability

In Medical & Health AI

Citations in the corpus

Investigating the emerging COVID-19 research trends in the field of business and management: A bibliometric analysis approach (2020, methodology): “AI-powered tools could be used to obviate the need for manual temperature checks and distance analysis Panigutti et al., 2020).”
Benchmarking and survey of explanation methods for black box models (2021, methodology): “…et al. (2021) TXT PH L A quint Abujabal et al. (2017) TXT PH L S anchor Ribeiro et al. (2018) ANY PH L A criage Pezeshkpour et al. (2019) TXT PH L S – Rajani et al. (2019) TXT PH L S lasts Guidotti et al. (2020b) TXT PH L S doctorxai Panigutti et al. (2020) ANY PH L S methods exist in literature.”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “Panigutti et al. (2020) extend the relational concepts over time and present Doctor XAI.”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “In [105], Doctor XAI was introduced as a model-agnostic explainer that focused on explaining the diagnosis prediction task of Doctor AI [107], which is a black-box AI model that predicts the patient’s next visit time.”