Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals
The biomedical field is characterized by an ever-increasing production of sequential data, which often come in the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the devel...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/8/1064 |
| _version_ | 1797523908987977728 |
|---|---|
| author | Michele Resta Anna Monreale Davide Bacciu |
| author_facet | Michele Resta Anna Monreale Davide Bacciu |
| author_sort | Michele Resta |
| collection | DOAJ |
| description | The biomedical field is characterized by an ever-increasing production of sequential data, which often come in the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the development of machine learning techniques for the predictive analysis of such biosignals. Unfortunately, in high-stakes decision making, such as clinical diagnosis, the opacity of machine learning models becomes a crucial aspect to be addressed in order to increase the trust and adoption of AI technology. In this paper, we propose a model agnostic explanation method, based on occlusion, that enables the learning of the input’s influence on the model predictions. We specifically target problems involving the predictive analysis of time-series data and the models that are typically used to deal with data of such nature, i.e., recurrent neural networks. Our approach is able to provide two different kinds of explanations: one suitable for technical experts, who need to verify the quality and correctness of machine learning models, and one suited to physicians, who need to understand the rationale underlying the prediction to make aware decisions. A wide experimentation on different physiological data demonstrates the effectiveness of our approach both in classification and regression tasks. |
| first_indexed | 2024-03-10T08:49:48Z |
| format | Article |
| id | doaj.art-7d5437046ab94f7889723648468c3ba9 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T08:49:48Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-7d5437046ab94f7889723648468c3ba92023-11-22T07:35:46ZengMDPI AGEntropy1099-43002021-08-01238106410.3390/e23081064Occlusion-Based Explanations in Deep Recurrent Models for Biomedical SignalsMichele Resta0Anna Monreale1Davide Bacciu2Computer Science Department, University of Pisa, 56127 Pisa, ItalyKDDLab, Computer Science Department, University of Pisa, 56127 Pisa, ItalyComputer Science Department, University of Pisa, 56127 Pisa, ItalyThe biomedical field is characterized by an ever-increasing production of sequential data, which often come in the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the development of machine learning techniques for the predictive analysis of such biosignals. Unfortunately, in high-stakes decision making, such as clinical diagnosis, the opacity of machine learning models becomes a crucial aspect to be addressed in order to increase the trust and adoption of AI technology. In this paper, we propose a model agnostic explanation method, based on occlusion, that enables the learning of the input’s influence on the model predictions. We specifically target problems involving the predictive analysis of time-series data and the models that are typically used to deal with data of such nature, i.e., recurrent neural networks. Our approach is able to provide two different kinds of explanations: one suitable for technical experts, who need to verify the quality and correctness of machine learning models, and one suited to physicians, who need to understand the rationale underlying the prediction to make aware decisions. A wide experimentation on different physiological data demonstrates the effectiveness of our approach both in classification and regression tasks.https://www.mdpi.com/1099-4300/23/8/1064interpretabilityocclusionrecurrent networksbiomedical signals |
| spellingShingle | Michele Resta Anna Monreale Davide Bacciu Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals Entropy interpretability occlusion recurrent networks biomedical signals |
| title | Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals |
| title_full | Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals |
| title_fullStr | Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals |
| title_full_unstemmed | Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals |
| title_short | Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals |
| title_sort | occlusion based explanations in deep recurrent models for biomedical signals |
| topic | interpretability occlusion recurrent networks biomedical signals |
| url | https://www.mdpi.com/1099-4300/23/8/1064 |
| work_keys_str_mv | AT micheleresta occlusionbasedexplanationsindeeprecurrentmodelsforbiomedicalsignals AT annamonreale occlusionbasedexplanationsindeeprecurrentmodelsforbiomedicalsignals AT davidebacciu occlusionbasedexplanationsindeeprecurrentmodelsforbiomedicalsignals |