Ada-WHIPS: Explaining AdaBoost Classification with Applications in the Health Sciences
Background
Computer Aided Diagnostics (CAD) can support medical practitioners to make critical decisions about their patients' disease conditions. Practitioners require access to the chain of reasoning behind CAD to build trust in the CAD advice and to supplement their own expertise. Yet, CAD systems might be based on black box machine learning (ML) models and high dimensional data sources (electronic health records, MRI scans, cardiotocograms, etc). These foundations make interpretation and explanation of the CAD advice very challenging. This challenge is recognised throughout the machine learning research community. eXplainable Artificial Intelligence (XAI) is emerging as one of the most important research areas of recent years because it addresses the interpretability and trust concerns of critical decision makers, including those in clinical and medical practice. Methods
In this work, we focus on AdaBoost, a black box ML model that has been widely adopted in the CAD literature. We address the challenge -- to explain AdaBoost classification -- with a novel algorithm that extracts simple, logical rules from AdaBoost models. Our algorithm, Adaptive-Weighted High Importance Path Snippets (Ada-WHIPS), makes use of AdaBoost's adaptive classifier weights. Using a novel formulation, Ada-WHIPS uniquely redistributes the weights among individual decision nodes of the internal decision trees (DT) of the AdaBoost model. Then, a simple heuristic search of the weighted nodes finds a single rule that dominated the model's decision. We compare the explanations generated by our novel approach with the state of the art in an experimental study. We evaluate the derived explanations with simple statistical tests of well-known quality measures, precision and coverage, and a novel measure stability that is better suited to the XAI setting .
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Due to technical limitations, full-text HTML conversion of this manuscript could not be completed. However, the manuscript can be downloaded and accessed as a PDF.
On 21 Jul, 2020
Posted 24 Sep, 2020
On 14 Jul, 2020
On 17 Jun, 2020
On 16 Jun, 2020
On 16 Jun, 2020
On 04 Jun, 2020
Received 22 May, 2020
Received 22 May, 2020
On 18 May, 2020
On 17 May, 2020
On 21 Apr, 2020
Received 24 Mar, 2020
Received 24 Mar, 2020
On 28 Feb, 2020
On 26 Feb, 2020
Invitations sent on 11 Feb, 2020
On 10 Feb, 2020
On 09 Feb, 2020
On 06 Feb, 2020
Received 18 Jan, 2020
On 18 Jan, 2020
Received 10 Jan, 2020
On 09 Jan, 2020
On 06 Jan, 2020
On 31 Dec, 2019
Invitations sent on 31 Dec, 2019
On 18 Dec, 2019
On 17 Dec, 2019
On 16 Dec, 2019
On 13 Dec, 2019
Ada-WHIPS: Explaining AdaBoost Classification with Applications in the Health Sciences
On 21 Jul, 2020
Posted 24 Sep, 2020
On 14 Jul, 2020
On 17 Jun, 2020
On 16 Jun, 2020
On 16 Jun, 2020
On 04 Jun, 2020
Received 22 May, 2020
Received 22 May, 2020
On 18 May, 2020
On 17 May, 2020
On 21 Apr, 2020
Received 24 Mar, 2020
Received 24 Mar, 2020
On 28 Feb, 2020
On 26 Feb, 2020
Invitations sent on 11 Feb, 2020
On 10 Feb, 2020
On 09 Feb, 2020
On 06 Feb, 2020
Received 18 Jan, 2020
On 18 Jan, 2020
Received 10 Jan, 2020
On 09 Jan, 2020
On 06 Jan, 2020
On 31 Dec, 2019
Invitations sent on 31 Dec, 2019
On 18 Dec, 2019
On 17 Dec, 2019
On 16 Dec, 2019
On 13 Dec, 2019
Background
Computer Aided Diagnostics (CAD) can support medical practitioners to make critical decisions about their patients' disease conditions. Practitioners require access to the chain of reasoning behind CAD to build trust in the CAD advice and to supplement their own expertise. Yet, CAD systems might be based on black box machine learning (ML) models and high dimensional data sources (electronic health records, MRI scans, cardiotocograms, etc). These foundations make interpretation and explanation of the CAD advice very challenging. This challenge is recognised throughout the machine learning research community. eXplainable Artificial Intelligence (XAI) is emerging as one of the most important research areas of recent years because it addresses the interpretability and trust concerns of critical decision makers, including those in clinical and medical practice. Methods
In this work, we focus on AdaBoost, a black box ML model that has been widely adopted in the CAD literature. We address the challenge -- to explain AdaBoost classification -- with a novel algorithm that extracts simple, logical rules from AdaBoost models. Our algorithm, Adaptive-Weighted High Importance Path Snippets (Ada-WHIPS), makes use of AdaBoost's adaptive classifier weights. Using a novel formulation, Ada-WHIPS uniquely redistributes the weights among individual decision nodes of the internal decision trees (DT) of the AdaBoost model. Then, a simple heuristic search of the weighted nodes finds a single rule that dominated the model's decision. We compare the explanations generated by our novel approach with the state of the art in an experimental study. We evaluate the derived explanations with simple statistical tests of well-known quality measures, precision and coverage, and a novel measure stability that is better suited to the XAI setting .
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Due to technical limitations, full-text HTML conversion of this manuscript could not be completed. However, the manuscript can be downloaded and accessed as a PDF.