Unique ID issued by UMIN | UMIN000058346 |
---|---|
Receipt number | R000066519 |
Scientific Title | Efficacy of a large language model (LLM) data extraction system for simplifying evidence reviews of emerging infectious diseases: A randomized crossover trial |
Date of disclosure of the study information | 2025/07/02 |
Last modified on | 2025/07/02 14:50:10 |
Efficacy of a large language model (LLM) data extraction system for simplifying evidence reviews of emerging infectious diseases: A randomized crossover trial
LLM data extraction system crossover RCT for emerging infectious disease evidence review
Efficacy of a large language model (LLM) data extraction system for simplifying evidence reviews of emerging infectious diseases: A randomized crossover trial
LLM data extraction system crossover RCT for emerging infectious disease evidence review
Japan |
Emerging Infectious Diseases (Evidence Review Efficiency Research)
Infectious disease |
Others
NO
To verify the hypothesis that using an LLM system reduces data input time to web forms and improves data extraction efficiency compared to not using the system. To evaluate whether using an LLM system improves time efficiency when extracting data from papers on emerging infectious diseases.
Efficacy
Confirmatory
Pragmatic
Not applicable
Time from authentication of subject ID after accessing the web form and starting input until completion of input
Accuracy of data extraction (experts check data extracted by participants for errors and calculate the percentage of correct answers)
Interventional
Cross-over
Randomized
Individual
Open -no one is blinded
Active
NO
NO
Institution is not considered as adjustment factor.
YES
Central registration
2
Educational,Counseling,Training
Other |
LLM System Use (Using structured data extraction system from papers with OpenAI o4-mini latest version to input into Streamlit web form)
No LLM System Use (Reading paper PDFs directly and manually inputting into Streamlit web form)
18 | years-old | <= |
Not applicable |
Male and Female
1. Researchers or healthcare professionals with experience in evidence review
2. Researchers or healthcare professionals specializing in infectious diseases
3. Individuals with basic computer skills
4. Individuals who have consented to participate in the research
1. Individuals with severe visual impairment
2. Individuals participating in an environment with unstable internet connection
5
1st name | Masahiro |
Middle name | |
Last name | Ishikane |
National Center for Global Health and Medicine, Japan Institute for Health Security
Disease Control and Prevention Center
162-8655
1-21-1 Toyama, Shinjuku-ku, Tokyo 162-8655, Japan
03-3202-7181
ishikanemasahiro@gmail.com
1st name | Masahiro |
Middle name | |
Last name | Ishikane |
National Center for Global Health and Medicine
Disease Control and Prevention Center
162-8655
1-21-1 Toyama, Shinjuku-ku, Tokyo 162-8655, Japan
03-3202-7181
ishikanemasahiro@gmail.com
Japan Institute for Health Security
Japan Society for the Promotion of Science (JSPS)
Japanese Governmental office
Japan Institute for Health Security
1-21-1 Toyama, Shinjuku-ku, Tokyo 162-8655, Japan
03-3202-7181
ishikanemasahiro@gmail.com
NO
2025 | Year | 07 | Month | 02 | Day |
https://github.com/SRWS-PSG/emerging_infection_24K13518
Unpublished
Preinitiation
2025 | Year | 06 | Month | 20 | Day |
2025 | Year | 07 | Month | 01 | Day |
2025 | Year | 12 | Month | 31 | Day |
2025 | Year | 07 | Month | 02 | Day |
2025 | Year | 07 | Month | 02 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000066519