A Guide to AI in epidemiology: ChatGPT and the STROBE checklist for observational studies

观察研究 加强流行病学观察研究报告 检查表 相关性(法律) 计算机科学 连贯性(哲学赌博策略) 心理学 医学教育 应用心理学 医学 认知心理学 统计 病理 数学 政治学 法学
作者
Davide Golinelli,Francesco Sanmarchi,Andrea Giovanni Nuzzolese,F Toscano,Andrea Bucci,Nicola Nante
出处
期刊:European journal of public health [Oxford University Press]
卷期号:33 (Supplement_2) 被引量:1
标识
DOI:10.1093/eurpub/ckad160.1213
摘要

Abstract Background Chat-Generative Pre-training Transformer (ChatGPT) is a recently developed Artificial Intelligence (AI) model capable of generating high-quality scientific text and answering complex tasks. This study aims at investigating how AI-based transformers can support public health researchers in designing and conducting epidemiological studies. To accomplish this, we used ChatGPT to reformulate the STrengthening the Reporting of OBservational studies in Epidemiology (STROBE) recommendations for observational studies into a list of questions to be answered by the transformer itself. We then qualitatively evaluated the coherence and relevance of the transformer's outputs. Methods We first chose a study to be used as a basis for the simulation. We then used ChatGPT to transform each STROBE checklist's item into specific prompts. Each answer was evaluated by independent researchers in terms of coherence and relevance. Results The mean scores assigned to each prompt were heterogeneous. On average, for the coherence domain, the overall mean score was 3.6 out of 5.0, and for relevance it was 3.3 out of 5.0. The lowest scores were assigned to items belonging to the Methods section of the checklist. Conclusions ChatGPT can be considered as a valuable support for researchers in conducting an epidemiological study, following internationally recognized guidelines. It is crucial for the users to have knowledge on the subject and a critical mindset when evaluating its outputs. The potential benefits of AI in scientific research are undeniable, but it is crucial to address the risks, and the ethical and legal consequences associated with its use. Key messages • Our analysis showed the ability of AI-based transformers to generate answers and human-like text, which could potentially be used to conduct epidemiological studies or write research articles. • We advocate the necessity for taking a proactive stance towards this evolving context, in order to ensure a careful governance of this inevitable process.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
advance完成签到,获得积分10
刚刚
1秒前
zhangxian0426完成签到,获得积分10
3秒前
3秒前
冰水混合物完成签到,获得积分10
3秒前
4秒前
Rachael发布了新的文献求助10
5秒前
好久不见发布了新的文献求助10
5秒前
科研通AI2S应助冰水混合物采纳,获得10
7秒前
7秒前
Panjiao完成签到 ,获得积分10
7秒前
8秒前
zhiger完成签到,获得积分10
9秒前
M777完成签到,获得积分10
10秒前
特斯小子发布了新的文献求助30
10秒前
孤独梦曼发布了新的文献求助10
10秒前
天天快乐应助小台采纳,获得10
12秒前
许不让完成签到,获得积分10
15秒前
16秒前
失眠的怀柔完成签到 ,获得积分10
16秒前
peterlu完成签到,获得积分20
19秒前
姜汁发布了新的文献求助10
19秒前
科研通AI2S应助haizz采纳,获得10
22秒前
bkagyin应助岑岑岑采纳,获得10
23秒前
昏睡的语山完成签到 ,获得积分20
24秒前
李富贵儿发布了新的文献求助10
24秒前
不要引力完成签到 ,获得积分10
24秒前
852应助阿迪采纳,获得10
25秒前
英俊的铭应助美好斓采纳,获得10
25秒前
今后应助阿迪采纳,获得10
25秒前
香蕉觅云应助阿迪采纳,获得10
25秒前
小蘑菇应助阿迪采纳,获得10
26秒前
科目三应助阿迪采纳,获得10
26秒前
完美世界应助阿迪采纳,获得10
26秒前
思源应助阿迪采纳,获得10
26秒前
26秒前
不配.应助小木子采纳,获得10
26秒前
27秒前
栗悟饭与龟波功完成签到,获得积分10
28秒前
高分求助中
Sustainability in Tides Chemistry 2000
Bayesian Models of Cognition:Reverse Engineering the Mind 800
Essentials of thematic analysis 700
A Dissection Guide & Atlas to the Rabbit 600
Very-high-order BVD Schemes Using β-variable THINC Method 568
Внешняя политика КНР: о сущности внешнеполитического курса современного китайского руководства 500
Revolution und Konterrevolution in China [by A. Losowsky] 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3124564
求助须知:如何正确求助?哪些是违规求助? 2774883
关于积分的说明 7724421
捐赠科研通 2430307
什么是DOI,文献DOI怎么找? 1291057
科研通“疑难数据库(出版商)”最低求助积分说明 622052
版权声明 600297