Improving the Reliability of LLMs as Medical Assistants for the General Public (LAMP-1)
2026. szeptember 1. frissítette: 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.
A tanulmány áttekintése
Állapot
Befejezve
Körülmények
Beavatkozás / kezelés
Részletes leírás
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.
Tanulmány típusa
Beavatkozó
Beiratkozás (Tényleges)
527
Fázis
- Nem alkalmazható
Kapcsolatok és helyek
Ez a rész a vizsgálatot végzők elérhetőségeit, valamint a vizsgálat lefolytatásának helyére vonatkozó információkat tartalmazza.
Tanulmányi helyek
-
-
Beijing Municipality
-
Beijing, Beijing Municipality, Kína
- Beijing Ctiy
-
-
Részvételi kritériumok
A kutatók olyan embereket keresnek, akik megfelelnek egy bizonyos leírásnak, az úgynevezett jogosultsági kritériumoknak. Néhány példa ezekre a kritériumokra a személy általános egészségi állapota vagy a korábbi kezelések.
Jogosultsági kritériumok
Tanulmányozható életkorok
- Felnőtt
- Idősebb felnőtt
Egészséges önkénteseket fogad
Igen
Leírás
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.
Tanulási terv
Ez a rész a vizsgálati terv részleteit tartalmazza, beleértve a vizsgálat megtervezését és a vizsgálat mérését.
Hogyan készül a tanulmány?
Tervezési részletek
- Elsődleges cél: Egészségügyi szolgáltatások kutatása
- Kiosztás: Véletlenszerűsített
- Beavatkozó modell: Párhuzamos hozzárendelés
- Maszkolás: Egyetlen
Fegyverek és beavatkozások
Résztvevő csoport / kar |
Beavatkozás / kezelés |
|---|---|
|
Kísérleti: 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.
|
Participants use ChatGPT to complete a standardized simulated clinical scenarios in unrestricted natural language.
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, the investigators 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 the investigators call this approach three minutes six dimensions education (3M-6D education). |
|
Kísérleti: 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.
|
Participants use Gemini to complete a standardized simulated clinical scenarios in unrestricted natural language.
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, the investigators 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 the investigators call this approach three minutes six dimensions education (3M-6D education). |
|
Aktív összehasonlító: 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.
|
|
Aktív összehasonlító: 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.
|
|
Nincs beavatkozás: 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.
|
Mit mér a tanulmány?
Elsődleges eredményintézkedések
Eredménymérő |
Intézkedés leírása |
Időkeret |
|---|---|---|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
Disposition concordance of the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
Relevant conditions identification of the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Disposition concordance of the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 1 hour.
|
1 hour.
|
Másodlagos eredményintézkedések
Eredménymérő |
Intézkedés leírása |
Időkeret |
|---|---|---|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Relevant conditions identification of the 3M-6D education Gemini group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Disposition concordance of the 3M-6D education GPT group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Disposition concordance of the 3M-6D education Gemini group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Red-flag identification in the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
Red-flag identification in the 3M-6D education GPT group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Red-flag identification in the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Red-flag identification in the 3M-6D education Gemini group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the control group
Időkeret: 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.
|
1 hour.
|
|
NASA Task Load Index score of the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 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.
|
1 hour.
|
|
NASA Task Load Index score of the 3M-6D education Gemini group compared with the control group
Időkeret: 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.
|
1 hour.
|
|
Relevant conditions identification of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Disposition concordance of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Red-flag identification in the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
NASA Task Load Index score of the 3M-6D education GPT group compared with the 3M-6D education Gemini group
Időkeret: 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.
|
1 hour.
|
Egyéb eredményintézkedések
Eredménymérő |
Intézkedés leírása |
Időkeret |
|---|---|---|
|
Failure to identify red flags in the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
Failure to identify red flags in the 3M-6D education GPT group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Failure to identify red flags in the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Failure to identify red flags in the 3M-6D education Gemini group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education GPT group compared with the GPT group
Időkeret: 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.
|
1 hour.
|
|
Underestimation of disposition in the 3M-6D education GPT group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education Gemini group compared with the Gemini group
Időkeret: 1 hour.
|
1 hour.
|
|
|
Underestimation of disposition in the 3M-6D education Gemini group compared with the control group
Időkeret: 1 hour.
|
1 hour.
|
Együttműködők és nyomozók
Itt találhatja meg a tanulmányban érintett személyeket és szervezeteket.
Szponzor
Együttműködők
Tanulmányi rekorddátumok
Ezek a dátumok nyomon követik a ClinicalTrials.gov webhelyre benyújtott vizsgálati rekordok és összefoglaló eredmények benyújtásának folyamatát. A vizsgálati feljegyzéseket és a jelentett eredményeket a Nemzeti Orvostudományi Könyvtár (NLM) felülvizsgálja, hogy megbizonyosodjon arról, hogy megfelelnek-e az adott minőség-ellenőrzési szabványoknak, mielőtt közzéteszik őket a nyilvános weboldalon.
Tanulmány főbb dátumok
Tanulmány kezdete (Tényleges)
2026. július 3.
Elsődleges befejezés (Tényleges)
2026. augusztus 26.
A tanulmány befejezése (Tényleges)
2026. augusztus 26.
Tanulmányi regisztráció dátumai
Először benyújtva
2026. június 11.
Először nyújtották be, amely megfelel a minőségbiztosítási kritériumoknak
2026. június 11.
Első közzététel (Tényleges)
2026. június 16.
Tanulmányi rekordok frissítései
Utolsó frissítés közzétéve (Tényleges)
2026. szeptember 3.
Az utolsó frissítés elküldve, amely megfelel a minőségbiztosítási kritériumoknak
2026. szeptember 1.
Utolsó ellenőrzés
2026. szeptember 1.
Több információ
A tanulmányhoz kapcsolódó kifejezések
Kulcsszavak
Egyéb vizsgálati azonosító számok
- LAMP-1
Terv az egyéni résztvevői adatokhoz (IPD)
Tervezi megosztani az egyéni résztvevői adatokat (IPD)?
ELDÖNTETLEN
Gyógyszer- és eszközinformációk, tanulmányi dokumentumok
Egy amerikai FDA által szabályozott gyógyszerkészítményt tanulmányoz
Nem
Egy amerikai FDA által szabályozott eszközterméket tanulmányoz
Nem
Ezt az információt közvetlenül a clinicaltrials.gov webhelyről szereztük be, változtatás nélkül. Ha bármilyen kérése van vizsgálati adatainak módosítására, eltávolítására vagy frissítésére, kérjük, írjon a következő címre: register@clinicaltrials.gov. Amint a változás bevezetésre kerül a clinicaltrials.gov oldalon, ez a webhelyünkön is automatikusan frissül. .