Toward Human-AI Interfaces to Support Explainability and Causability in Medical AI

被引：70
作者：
Holzinger, Andreas [1 ]
Mueller, Heimo [2 ,3 ,4 ]
机构：
[1] Med Univ Graz, Inst Med Informat & Stat, Human Ctr Artificial Intelligence AI Lab, A-8010 Graz, Austria
[2] Med Univ Graz, Informat Sci & Machine Learning Lab Diagnost, A-8010 Graz, Austria
[3] Med Univ Graz, Res Inst Pathol Diagnost, A-8010 Graz, Austria
[4] Med Univ Graz, Res Ctr Mol Biomed, A-8010 Graz, Austria
来源：
COMPUTER | 2021年 / 54卷 / 10期
基金：
欧盟地平线“2020”; 奥地利科学基金会;
关键词：
Artificial intelligence;
D O I：
10.1109/MC.2021.3092610
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Our concept of causability is a measure of whether and to what extent humans can understand a given machine explanation. We motivate causability with a clinical case from cancer research. We argue for using causability in medical artificial intelligence (AI) to develop and evaluate future human-AI interfaces.
引用
收藏
页码：78 / 86
页数：9
相关论文
共 20 条
[1]  
Bach S, 2016, IEEE IMAGE PROC, P2271, DOI 10.1109/ICIP.2016.7532763
[2]   Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI [J].
Barredo Arrieta, Alejandro ;
Diaz-Rodriguez, Natalia ;
Del Ser, Javier ;
Bennetot, Adrien ;
Tabik, Siham ;
Barbado, Alberto ;
Garcia, Salvador ;
Gil-Lopez, Sergio ;
Molina, Daniel ;
Benjamins, Richard ;
Chatila, Raja ;
Herrera, Francisco .
INFORMATION FUSION, 2020, 58 :82-115
[3]   Bridging the "last mile" gap between AI implementation and operation: "data awareness" that matters [J].
Cabitza, Federico ;
Campagner, Andrea ;
Balsano, Clara .
ANNALS OF TRANSLATIONAL MEDICINE, 2020, 8 (07)
[4]   Dermatologist-level classification of skin cancer with deep neural networks [J].
Esteva, Andre ;
Kuprel, Brett ;
Novoa, Roberto A. ;
Ko, Justin ;
Swetter, Susan M. ;
Blau, Helen M. ;
Thrun, Sebastian .
NATURE, 2017, 542 (7639) :115-+
[5]   Intelligent feature engineering and ontological mapping of brain tumour histomorphologies by deep learning [J].
Faust, Kevin ;
Bala, Sudarshan ;
van Ommeren, Randy ;
Portante, Alessia ;
Al Qawahmed, Raniah ;
Djuric, Ugljesa ;
Diamandis, Phedias .
NATURE MACHINE INTELLIGENCE, 2019, 1 (07) :316-321
[6]  
Hamon R., 2020, Robustness and explainability of Artificial Intelligence, DOI [DOI 10.2760/57493, 10.2760/57493]
[7]   Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI [J].
Holzinger, Andreas ;
Malle, Bernd ;
Saranti, Anna ;
Pfeifer, Bastian .
INFORMATION FUSION, 2021, 71 :28-37
[8]   Measuring the Quality of Explanations: The System Causability Scale (SCS) Comparing Human and Machine Explanations [J].
Holzinger, Andreas ;
Carrington, Andre ;
Mueller, Heimo .
KUNSTLICHE INTELLIGENZ, 2020, 34 (02) :193-198
[9]   Causability and explainability of artificial intelligence in medicine [J].
Holzinger, Andreas ;
Langs, Georg ;
Denk, Helmut ;
Zatloukal, Kurt ;
Mueller, Heimo .
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2019, 9 (04)
[10]   Interactive machine learning for health informatics: when do we need the human-in-the-loop? [J].
Holzinger A. .
Brain Informatics, 2016, 3 (02) :119-131
12