Dr. GPT Will See You Now, but Should It? Exploring the Benefits and Harms of Large Language Models in Medical Diagnosis using Crowdsourced Clinical Cases
The proliferation of Large Language Models (LLMs) in high-stakes applications such as medical (self-)diagnosis and preliminary triage raises significant ethical and practical concerns about the effectiveness, appropriateness, and possible harmfulness of the use of these technologies for health-related concerns and queries. Some prior work has considered the effectiveness of LLMs in answering expert-written health queries/prompts, questions from medical examination banks, or queries based on pre-existing clinical cases. Unfortunately, these existing studies completely ignore an in-the-wild evaluation of the effectiveness of LLMs in answering everyday health concerns and queries typically asked by general users, which corresponds to the more prevalent use case for LLMs. To address this research gap, this paper presents the findings from a university-level competition that leveraged a novel, crowdsourced approach for evaluating the effectiveness of LLMs in answering everyday health queries. Over the course of a week, a total of 34 participants prompted four publicly accessible LLMs with 212 real (or imagined) health concerns, and the LLM generated responses were evaluated by a team of nine board-certified physicians. At a high level, our findings indicate that on average, 76% of the 212 LLM responses were deemed to be accurate by physicians. Further, with the help of medical professionals, we investigated whether RAG versions of these LLMs (powered with a comprehensive medical knowledge base) can improve the quality of responses generated by LLMs. Finally, we also derive qualitative insights to explain our quantitative findings by conducting interviews with seven medical professionals who were shown all the prompts in our competition. This paper aims to provide a more grounded understanding of how LLMs perform in real-world everyday health communication.
Code (0)
등록된 구현이 없습니다.
Tasks
Medical DiagnosisRAGMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
What Is the Point of Equality in Machine Learning Fairness? Beyond Equality of Opportunity
Fairness in machine learning (ML) has become a rapidly growing area of research. But why, in the first place, is unfairness in ML morally wrong? And why should we care about improving fairness? Most fair-ML research impl…
FairnessPhilosophyEstimation Bias in Multi-Armed Bandit Algorithms for Search Advertising
In search advertising, the search engine needs to select the most profitable advertisements to display, which can be formulated as an instance of online learning with partial feedback, also known as the stochastic multi-…
Selection biasShould Politicians be Informed? Targeted Benefits and Heterogeneous Voters
We compare two scenarios in a model where politicians offer local public goods to heterogeneous voters: one where politicians have access to data on voters and thus can target specific ones, and another where politicians…
Agency in the Age of AI
There is significant concern about the impact of generative AI on society. Modern AI tools are capable of generating ever more realistic text, images, and videos, and functional code, from minimal prompts. Accompanying t…
Senescence, change, and competition: when the desire to pick one model harms our understanding
The question of why we age is a fundamental one. It is about who we are, and it also might have critical practical aspects as we try to find ways to age slower. Or to not age at all. Different reasons point at distinct s…