A Human–AI interaction paradigm and its application to rhinocytology

IF 6.1 2区医学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence in Medicine Pub Date : 2024-07-22 DOI:10.1016/j.artmed.2024.102933

Giuseppe Desolda , Giovanni Dimauro , Andrea Esposito , Rosa Lanzilotti , Maristella Matera , Massimo Zancanaro

{"title":"A Human–AI interaction paradigm and its application to rhinocytology","authors":"Giuseppe Desolda , Giovanni Dimauro , Andrea Esposito , Rosa Lanzilotti , Maristella Matera , Massimo Zancanaro","doi":"10.1016/j.artmed.2024.102933","DOIUrl":null,"url":null,"abstract":"<div><p>This article explores Human-Centered Artificial Intelligence (HCAI) in medical cytology, with a focus on enhancing the interaction with AI. It presents a Human–AI interaction paradigm that emphasizes explainability and user control of AI systems. It is an iterative negotiation process based on three interaction strategies aimed to (i) elaborate the system outcomes through iterative steps (<em>Iterative Exploration</em>), (ii) explain the AI system’s behavior or decisions (<em>Clarification</em>), and (iii) allow non-expert users to trigger simple retraining of the AI model (<em>Reconfiguration</em>). This interaction paradigm is exploited in the redesign of an existing AI-based tool for microscopic analysis of the nasal mucosa. The resulting tool is tested with rhinocytologists. The article discusses the analysis of the results of the conducted evaluation and outlines lessons learned that are relevant for AI in medicine.</p></div>","PeriodicalId":55458,"journal":{"name":"Artificial Intelligence in Medicine","volume":"155 ","pages":"Article 102933"},"PeriodicalIF":6.1000,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0933365724001751/pdfft?md5=b223655b36875d5261335f6e3519aed6&pid=1-s2.0-S0933365724001751-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Medicine","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0933365724001751","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

This article explores Human-Centered Artificial Intelligence (HCAI) in medical cytology, with a focus on enhancing the interaction with AI. It presents a Human–AI interaction paradigm that emphasizes explainability and user control of AI systems. It is an iterative negotiation process based on three interaction strategies aimed to (i) elaborate the system outcomes through iterative steps (Iterative Exploration), (ii) explain the AI system’s behavior or decisions (Clarification), and (iii) allow non-expert users to trigger simple retraining of the AI model (Reconfiguration). This interaction paradigm is exploited in the redesign of an existing AI-based tool for microscopic analysis of the nasal mucosa. The resulting tool is tested with rhinocytologists. The article discusses the analysis of the results of the conducted evaluation and outlines lessons learned that are relevant for AI in medicine.

Abstract Image

查看原文本刊更多论文

人机交互范例及其在鼻细胞学中的应用

本文探讨了医学细胞学中以人为中心的人工智能（HCAI），重点是加强与人工智能的交互。它提出了一种人机交互范式，强调人工智能系统的可解释性和用户控制。这是一个基于三种交互策略的迭代协商过程，旨在：(i) 通过迭代步骤阐述系统结果（迭代探索）；(ii) 解释人工智能系统的行为或决策（澄清）；(iii) 允许非专业用户触发对人工智能模型的简单再训练（重新配置）。在重新设计现有的基于人工智能的鼻粘膜显微分析工具时，就利用了这种交互范式。鼻腔细胞学专家对该工具进行了测试。文章讨论了对评估结果的分析，并概述了与医学人工智能相关的经验教训。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Artificial Intelligence in Medicine 工程技术-工程：生物医学

CiteScore

15.00

自引率

2.70%

发文量

143

审稿时长

6.3 months

期刊介绍： Artificial Intelligence in Medicine publishes original articles from a wide variety of interdisciplinary perspectives concerning the theory and practice of artificial intelligence (AI) in medicine, medically-oriented human biology, and health care. Artificial intelligence in medicine may be characterized as the scientific discipline pertaining to research studies, projects, and applications that aim at supporting decision-based medical tasks through knowledge- and/or data-intensive computer-based solutions that ultimately support and improve the performance of a human care provider.