Improving the Reliability of LLMs as Medical Assistants for the General Public (LAMP-1)
11. června 2026 aktualizováno: Ji Xunming,MD,PhD, Capital Medical University
Improving the Reliability of LLMs as Medical Assistants for the General Public: a Proof of Concept Simulation Trial
This study will evaluate whether three-minute six-dimensions education(3M-6D education) can improve the reliability of large language models as medical assistants for the general public.
Participants will be randomly assigned to receive or not receive 3M-6D education and then use ChatGPT, Gemini, or non-AI information resources.
The study will assess relevant condition identification, disposition concordance, red-flag identification, and NASA-TLX score.
Přehled studie
Postavení
Zatím nenabíráme
Podmínky
Intervence / Léčba
Detailní popis
This randomized, controlled, proof-of-concept simulation trial will evaluate whether three-minute six-dimensions education (3M-6D education) can improve the reliability of large language models as medical assistants for the general public.
Eligible participants will be randomly assigned in a 1:1:1:1:1 ratio to one of five study groups: the 3M-6D education GPT group, the GPT group, the 3M-6D education Gemini group, the Gemini group, or the control group. Participants in the 3M-6D education GPT and 3M-6D education Gemini groups will receive approximately three minutes of education before using ChatGPT or Gemini.Each participant will be randomly assigned one of 10 standardized clinical scenarios and complete a simulated counseling task in unrestricted natural language within approximately 10 minutes. The study will assess relevant condition identification, disposition concordance, red-flag identification, and NASA-TLX score.
Typ studie
Intervenční
Zápis (Odhadovaný)
525
Fáze
- Nelze použít
Kontakty a umístění
Tato část poskytuje kontaktní údaje pro ty, kteří studii provádějí, a informace o tom, kde se tato studie provádí.
Studijní kontakt
- Jméno: Xunming Ji
- Telefonní číslo: 01083198962
- E-mail: jixm@ccmu.edu.cn
Studijní záloha kontaktů
- Jméno: Chuanjie Wu
- Telefonní číslo: 01083199439
- E-mail: wuchuanjie@ccmu.edu.cn
Studijní místa
-
-
Beijing Municipality
-
Beijing, Beijing Municipality, Čína, 100053
- Xuanwu Hospital, Capital Medical University
-
Kontakt:
- Chuanjie Wu
- Telefonní číslo: 010-83199439
- E-mail: wuchuanjie@ccmu.edu.cn
-
-
Kritéria účasti
Výzkumníci hledají lidi, kteří odpovídají určitému popisu, kterému se říká kritéria způsobilosti. Některé příklady těchto kritérií jsou celkový zdravotní stav osoby nebo předchozí léčba.
Kritéria způsobilosti
Věk způsobilý ke studiu
- Dospělý
- Starší dospělý
Přijímá zdravé dobrovolníky
Ano
Popis
Inclusion Criteria:
- Age 18 years or greater, male or female;
- Completed primary school or higher education;
- Able to use a smartphone or computer to complete online interaction;
- No history of acute ischemic stroke, systemic lupus erythematosus, gastric ulcer, pneumonia, acute cardiac infarction, urinary tract infection, uterine fibroids, diabetes, osteoarthritis, or migraine.
- Able to understand and comply with study procedures and to provide written informed consent.
Exclusion Criteria:
- Currently or previously employed as a healthcare worker;
- Previously received systematic medical training;
- Currently involved in concurrent research that may interfere with the results of the present trial;
- The investigator considered that the participant had other conditions that might affect compliance or preclude participation.
Studijní plán
Tato část poskytuje podrobnosti o studijním plánu, včetně toho, jak je studie navržena a co studie měří.
Jak je studie koncipována?
Detaily designu
- Primární účel: Výzkum zdravotnických služeb
- Přidělení: Randomizované
- Intervenční model: Paralelní přiřazení
- Maskování: Singl
Zbraně a zásahy
Skupina účastníků / Arm |
Intervence / Léčba |
|---|---|
|
Experimentální: 3M-6D education GPT Group
Participants will first be trained in 3M-6D education, then use ChatGPT to complete a consultation task in unrestricted natural language in approximately 10 minutes.
|
3M-6D education is designed based on Cognitive Load Theory to reduce the cognitive burden on patients during medical interactions with AI and to improve the clarity and completeness of symptom reporting. Guided by cognitive load theory and the natural process physicians use to take medical histories, we identified candidate information dimensions and developed a structured expression framework with six dimensions for public health queries through a Delphi expert consensus process. Participants were instructed to use the framework to describe their symptoms across these six dimensions; this process can typically be completed within three minutes, so we call this approach three minutes six dimensions education (3M-6D education).
Participants use ChatGPT to complete a standardized simulated clinical scenarios in unrestricted natural language.
|
|
Experimentální: 3M-6D education Gemini Group
Participants will first be trained in 3M-6D education, then use Gemini to complete a consultation task in unrestricted natural language in approximately 10 minutes.
|
3M-6D education is designed based on Cognitive Load Theory to reduce the cognitive burden on patients during medical interactions with AI and to improve the clarity and completeness of symptom reporting. Guided by cognitive load theory and the natural process physicians use to take medical histories, we identified candidate information dimensions and developed a structured expression framework with six dimensions for public health queries through a Delphi expert consensus process. Participants were instructed to use the framework to describe their symptoms across these six dimensions; this process can typically be completed within three minutes, so we call this approach three minutes six dimensions education (3M-6D education).
Participants use Gemini to complete a standardized simulated clinical scenarios in unrestricted natural language.
|
|
Aktivní komparátor: GPT Group
Participants will use ChatGPT to complete a consultation task in unrestricted natural language in approximately 10 minutes.
|
Participants use ChatGPT to complete a standardized simulated clinical scenarios in unrestricted natural language.
|
|
Aktivní komparátor: Gemini Group
Participants will use Gemini to complete a consultation task in unrestricted natural language in approximately 10 minutes.
|
Participants use Gemini to complete a standardized simulated clinical scenarios in unrestricted natural language.
|
|
Žádný zásah: Control group
Participants will use non-AI tools such as internet searches and medical websites to complete a consultation task in unrestricted natural language in approximately 10 minutes.
|
Co je měření studie?
Primární výstupní opatření
Měření výsledku |
Popis opatření |
Časové okno |
|---|---|---|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
Relevant conditions identification is defined as the proportion of participants whose final response includes the expert-defined final diagnosis or a relevant differential diagnosis.
|
Usually within 1 hour.
|
|
Disposition concordance of the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
Disposition concordance is defined as the proportion of participants whose final care recommendation matches the expert-defined level.
The five levels are self-care, routine outpatient care, urgent outpatient care, emergency department visit, and emergency medical services.
|
Usually within 1 hour.
|
|
Relevant conditions identification of the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Disposition concordance of the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
Sekundární výstupní opatření
Měření výsledku |
Popis opatření |
Časové okno |
|---|---|---|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Relevant conditions identification of the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Disposition concordance of the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Disposition concordance of the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Red-flag identification in the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
Red-flag identification is defined as the proportion of participants whose final response includes the key warning signs that experts defined for the assigned scenario.
|
Usually within 1 hour.
|
|
Red-flag identification in the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Red-flag identification in the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Red-flag identification in the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
NASA-TLX score is a self-reported task-load score measured after the simulated consultation with a physician.
It includes six domains: mental demand, physical demand, temporal demand, effort, frustration, and performance.
Each domain is scored from 0 to 100.
The total score is the mean of the six domains.
Higher scores indicate greater perceived task load.
|
Usually within 1 hour.
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Disposition concordance of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Red-flag identification in the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
Další výstupní opatření
Měření výsledku |
Popis opatření |
Časové okno |
|---|---|---|
|
Failure to identify red flags in the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
Failure to identify red flags is defined as the proportion of participants whose final response does not include the expert-defined red-flag symptoms or warning signs for the assigned standardized simulated clinical scenario.
|
Usually within 1 hour.
|
|
Failure to identify red flags in the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Failure to identify red flags in the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Failure to identify red flags in the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education GPT group compared with the GPT group
Časové okno: Usually within 1 hour.
|
Underestimation of disposition is defined as the proportion of participants whose final care recommendation is lower than the expert-defined disposition level for the assigned standardized simulated clinical scenario.
|
Usually within 1 hour.
|
|
Underestimation of disposition in the 3M-6D education GPT group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education Gemini group compared with the Gemini group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education Gemini group compared with the control group
Časové okno: Usually within 1 hour.
|
Usually within 1 hour.
|
Spolupracovníci a vyšetřovatelé
Zde najdete lidi a organizace zapojené do této studie.
Sponzor
Spolupracovníci
Termíny studijních záznamů
Tato data sledují průběh záznamů studie a předkládání souhrnných výsledků na ClinicalTrials.gov. Záznamy ze studií a hlášené výsledky jsou před zveřejněním na veřejné webové stránce přezkoumány Národní lékařskou knihovnou (NLM), aby se ujistily, že splňují specifické standardy kontroly kvality.
Hlavní termíny studia
Začátek studia (Odhadovaný)
20. června 2026
Primární dokončení (Odhadovaný)
20. července 2026
Dokončení studie (Odhadovaný)
20. července 2026
Termíny zápisu do studia
První předloženo
11. června 2026
První předloženo, které splnilo kritéria kontroly kvality
11. června 2026
První zveřejněno (Aktuální)
16. června 2026
Aktualizace studijních záznamů
Poslední zveřejněná aktualizace (Aktuální)
16. června 2026
Odeslaná poslední aktualizace, která splnila kritéria kontroly kvality
11. června 2026
Naposledy ověřeno
1. června 2026
Více informací
Termíny související s touto studií
Klíčová slova
Další identifikační čísla studie
- LAMP-1
Plán pro data jednotlivých účastníků (IPD)
Plánujete sdílet data jednotlivých účastníků (IPD)?
NEROZHODNÝ
Informace o lécích a zařízeních, studijní dokumenty
Studuje lékový produkt regulovaný americkým FDA
Ne
Studuje produkt zařízení regulovaný americkým úřadem FDA
Ne
Tyto informace byly beze změn načteny přímo z webu clinicaltrials.gov. Máte-li jakékoli požadavky na změnu, odstranění nebo aktualizaci podrobností studie, kontaktujte prosím register@clinicaltrials.gov. Jakmile bude změna implementována na clinicaltrials.gov, bude automaticky aktualizována i na našem webu .