Medicine and artificial intelligence (AI) engineering represent two distinct
fields each with decades of published history. With such history comes a set of
terminology that has a specific way in which it is applied. However, when two
distinct fields with overlapping terminology start to collaborate,
miscommunication and misunderstandings can occur. This narrative review aims to
give historical context for these terms, accentuate the importance of clarity
when these terms are used in medical AI contexts, and offer solutions to
mitigate misunderstandings by readers from either field. Through an examination
of historical documents, including articles, writing guidelines, and textbooks,
this review traces the divergent evolution of terms for data sets and their
impact. Initially, the discordant interpretations of the word 'validation' in
medical and AI contexts are explored. Then the data sets used for AI evaluation
are classified, namely random splitting, cross-validation, temporal,
geographic, internal, and external sets. The accurate and standardized
description of these data sets is crucial for demonstrating the robustness and
generalizability of AI applications in medicine. This review clarifies existing
literature to provide a comprehensive understanding of these classifications
and their implications in AI evaluation. This review then identifies often
misunderstood terms and proposes pragmatic solutions to mitigate terminological
confusion. Among these solutions are the use of standardized terminology such
as 'training set,' 'validation (or tuning) set,' and 'test set,' and explicit
definition of data set splitting terminologies in each medical AI research
publication. This review aspires to enhance the precision of communication in
medical AI, thereby fostering more effective and transparent research
methodologies in this interdisciplinary field.

医学和人工智能工程代表了两个不同的领域，每个领域都有数十年的出版历史。两个有重叠术语的不同领域合作时，可能会出现沟通不畅和误解。本文通过考察历史文献，包括文章、写作指南和教材，追溯数据集术语的分歧演化及其影响。通过明确这些数据集的准确和标准化描述，可以展示人工智能应用在医学中的健壮性和普适性。本文还识别了常被误解的术语，并提出了解决方案以减少术语混淆。为了提高医学人工智能中的沟通准确性，本综述旨在促进这个交叉学科领域更有效和透明的研究方法。

人工智能医学数据集术语：历史回顾与建议

Data Set Terminology of Artificial Intelligence in Medicine: A  Historical Review and Recommendation

Misunderstandings arise not only in interpersonal communication but also
between humans and Large Language Models (LLMs). Such discrepancies can make
LLMs interpret seemingly unambiguous questions in unexpected ways, yielding
incorrect responses. While it is widely acknowledged that the quality of a
prompt, such as a question, significantly impacts the quality of the response
provided by LLMs, a systematic method for crafting questions that LLMs can
better comprehend is still underdeveloped. In this paper, we present a method
named `Rephrase and Respond' (RaR), which allows LLMs to rephrase and expand
questions posed by humans and provide responses in a single prompt. This
approach serves as a simple yet effective prompting method for improving
performance. We also introduce a two-step variant of RaR, where a rephrasing
LLM first rephrases the question and then passes the original and rephrased
questions together to a different responding LLM. This facilitates the
effective utilization of rephrased questions generated by one LLM with another.
Our experiments demonstrate that our methods significantly improve the
performance of different models across a wide range to tasks. We further
provide a comprehensive comparison between RaR and the popular Chain-of-Thought
(CoT) methods, both theoretically and empirically. We show that RaR is
complementary to CoT and can be combined with CoT to achieve even better
performance. Our work not only contributes to enhancing LLM performance
efficiently and effectively but also sheds light on a fair evaluation of LLM
capabilities. Data and codes are available at
this https URL

介绍了一种名为 “重述和回答”（RaR）的方法，通过使人类的问题被大型语言模型（LLMs）重述和展开，从而在单个提示中提供回答，以提高 LLM 的性能。还介绍了 RaR 的两步变体方法，通过将问题由一个 LLM 重述后传递给另一个 LLM，有效地利用了由一个 LLM 生成的重述问题。实验证明这些方法显著提高了不同模型在各种任务上的性能，并与 Chain-of-Thought（CoT）方法进行了综合比较，发现 RaR 与 CoT 互补，结合使用效果更好。该工作不仅对提高 LLM 性能具有高效和有效的贡献，还对公正评估 LLM 能力具有重要意义。

重述与回应：让大型语言模型为自己提出更好的问题

Rephrase and Respond: Let Large Language Models Ask Better Questions for  Themselves

Each year, crowd disasters happen in different areas of the world. How and
why do such disasters happen? Are the fatalities caused by relentless behavior
of people or a psychological state of panic that makes the crowd 'go mad'? Or
are they a tragic consequence of a breakdown of coordination? These and other
questions are addressed, based on a qualitative analysis of publicly available
videos and materials, which document the planning and organization of the Love
Parade in Duisburg, Germany, and the crowd disaster on July 24, 2010. Our
analysis reveals a number of misunderstandings that have widely spread. We also
provide a new perspective on concepts such as 'intentional pushing', 'mass
panic', 'stampede', and 'crowd crushs'. The focus of our analysis is on the
contributing causal factors and their mutual interdependencies, not on legal
issues or the judgment of personal or institutional responsibilities. Video
recordings show that, in Duisburg, people stumbled and piled up due to a
'domino effect', resulting from a phenomenon called 'crowd turbulence' or
'crowd quake'. Crowd quakes are a typical reason for crowd disasters, to be
distinguished from crowd disasters resulting from 'panic stampedes' or 'crowd
crushes'. In Duisburg, crowd turbulence was the consequence of amplifying
feedback and cascading effects, which are typical for systemic instabilities.
Accordingly, things can go terribly wrong in spite of no bad intentions from
anyone. Comparing the incident in Duisburg with others, we give recommendations
to help prevent future crowd disasters. In particular, we introduce a new scale
to assess the criticality of conditions in the crowd. This may allow
preventative measures to be taken earlier on. Furthermore, we discuss the
merits and limitations of citizen science for public investigation, considering
that today, almost every event is recorded and reflected in the World Wide Web.

对全球各地人群灾难的研究分析，重点关注了对所述事件的原因和潜在因素进行的新视角和建议措施。