A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes
Explainable artificial intelligence (XAI) tools are used to enhance the applications of existing artificial intelligence (AI) technologies by explaining their execution processes and results. In most past research, XAI tools and techniques are typically applied to only the inference part of the AI a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442523000503 |
| _version_ | 1797796044263653376 |
|---|---|
| author | Yu-Cheng Wang Tin-Chih Toly Chen Min-Chi Chiu |
| author_facet | Yu-Cheng Wang Tin-Chih Toly Chen Min-Chi Chiu |
| author_sort | Yu-Cheng Wang |
| collection | DOAJ |
| description | Explainable artificial intelligence (XAI) tools are used to enhance the applications of existing artificial intelligence (AI) technologies by explaining their execution processes and results. In most past research, XAI tools and techniques are typically applied to only the inference part of the AI application. This study proposes a systematic approach to enhance the explainability of AI applications in healthcare. Several AI applications for type 2 diabetes diagnosis are taken as examples to illustrate the applicability of the proposed methodology. According to experimental results, the XAI tools and technologies in the proposed methodology were more diverse than those in the past research. In addition, an artificial neural network was approximated to a simpler and more intuitive classification and regression tree (CART) using local interpretable model-agnostic explanation (LIME). The extracted rules were used to recommend actions to the users to restore their health. |
| first_indexed | 2024-03-13T03:27:12Z |
| format | Article |
| id | doaj.art-4cfe0aed01e04832b690e10f6e2a26c7 |
| institution | Directory Open Access Journal |
| issn | 2772-4425 |
| language | English |
| last_indexed | 2024-03-13T03:27:12Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj.art-4cfe0aed01e04832b690e10f6e2a26c72023-06-25T04:44:19ZengElsevierHealthcare Analytics2772-44252023-11-013100183A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetesYu-Cheng Wang0Tin-Chih Toly Chen1Min-Chi Chiu2Department of Aeronautical Engineering, Chaoyang University of Technology, Taichung City, Taiwan; Corresponding author.Department of Industrial Engineering and Management, National Yang Ming Chiao Tung University, Hsinchu City, TaiwanDepartment of Industrial Engineering and Management, National Chin-Yi University of Technology, Taichung City, TaiwanExplainable artificial intelligence (XAI) tools are used to enhance the applications of existing artificial intelligence (AI) technologies by explaining their execution processes and results. In most past research, XAI tools and techniques are typically applied to only the inference part of the AI application. This study proposes a systematic approach to enhance the explainability of AI applications in healthcare. Several AI applications for type 2 diabetes diagnosis are taken as examples to illustrate the applicability of the proposed methodology. According to experimental results, the XAI tools and technologies in the proposed methodology were more diverse than those in the past research. In addition, an artificial neural network was approximated to a simpler and more intuitive classification and regression tree (CART) using local interpretable model-agnostic explanation (LIME). The extracted rules were used to recommend actions to the users to restore their health.http://www.sciencedirect.com/science/article/pii/S2772442523000503Explainable artificial intelligenceHealthcareLocal interpretable model-agnostic explanationDiabetes diagnosisArtificial intelligence |
| spellingShingle | Yu-Cheng Wang Tin-Chih Toly Chen Min-Chi Chiu A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes Healthcare Analytics Explainable artificial intelligence Healthcare Local interpretable model-agnostic explanation Diabetes diagnosis Artificial intelligence |
| title | A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| title_full | A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| title_fullStr | A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| title_full_unstemmed | A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| title_short | A systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| title_sort | systematic approach to enhance the explainability of artificial intelligence in healthcare with application to diagnosis of diabetes |
| topic | Explainable artificial intelligence Healthcare Local interpretable model-agnostic explanation Diabetes diagnosis Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S2772442523000503 |
| work_keys_str_mv | AT yuchengwang asystematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes AT tinchihtolychen asystematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes AT minchichiu asystematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes AT yuchengwang systematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes AT tinchihtolychen systematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes AT minchichiu systematicapproachtoenhancetheexplainabilityofartificialintelligenceinhealthcarewithapplicationtodiagnosisofdiabetes |