临床医生更喜欢哪些解释? 对XAI可理解性和可操作性的比较评估,用于预测住院治疗的需要
Laura Bergomi1, Giovanna Nicora2, Marta Anna Orlowska2
1Department of Electrical, Computer and Biomedical Engineering, Via Ferrata 5, Pavia, 27100, Italy. laura.bergomi01@universitadipavia.it.
临床医生更喜欢像SHAP这样的可解释AI (XAI) 方法,用于COVID-19住院预测,发现它们是可以理解和可操作的. 然而,专业知识影响了人工智能工具的感知,突出显示了对量身定制的临床决策支持系统的需求.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 临床决策支持 临床决策支持
背景情况:
- 在临床环境中对临床医生对可解释AI (XAI) 的态度的理解有限.
- 专注于XAI用于使用表格数据的机器学习模型,特别是用于COVID-19住院预测.
- 探索临床医生对XAI方法的可理解性和可操作性的看法.
研究的目的:
- 评估临床医生对不同XAI方法的态度.
- 在临床环境中评估XAI解释的可理解性和可操作性.
- 为临床决策支持系统 (DSS) 确定首选的XAI方法.
主要方法:
- 基于问卷的实验,对10名临床医生进行了实验.
- 评估了10个现实世界的案例,其中包括来自贝叶斯网络,SHAP和AraucanaXAI的预测和解释.
- 使用利克特尺度来评分认知陈述和预测协议;与两名临床医生进行大声思考采访.
主要成果:
- 一般来说,临床医生对人工智能的态度是积极的,但高合规性表明自动化偏差风险.
- 解释的可理解性和可操作性是正相关的.
- 由于简单性,SHAP被确定为首选方法;根据专业和专业知识的不同,人们的看法会有所不同.
结论:
- 在临床DSS中,SHAP和AraucanaXAI显示了增强XAI的前景.
- 临床医生的专业知识,专业和环境对于选择和开发有效的XAI至关重要.
- 该研究为设计未来XAI驱动的临床决策支持工具提供了见解.
更多相关视频
04:05Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
相关概念视频
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...
Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
The X̄ Chart
The x̄ chart, often known as the individual control chart, is a crucial tool in statistical process control. It is designed to monitor process behavior and performance over time and is widely used in various industries to ensure that processes are operating at their optimum capacity and within specified limits.
A x̄ chart is constructed by plotting individual measurements of a quality...
Comparing the Survival Analysis of Two or More Groups
Receiver Operating Characteristic Plot
The Availability Heuristic
