Expert-Validated ChatGPT Support for Arterial Blood Gas Interpretation (ABG-AI RCT)
Expert-Validated Generative AI Support for Arterial Blood Gas Interpretation in Early-Career Non-Specialist Physicians: A Randomized Controlled Study
This randomized controlled study evaluated whether expert-validated ChatGPT support improved arterial blood gas (ABG) interpretation performance among early-career non-specialist physicians. Participants completed a baseline assessment consisting of 11 standardized clinical scenarios covering five domains of ABG interpretation. Eligible participants who entered the reassessment phase were randomly assigned to either an AI-supported group or a control group.
One week after baseline assessment, participants completed a posttest using the same clinical scenarios. The AI-supported group received expert-validated ChatGPT responses before answering each case, whereas the control group completed the assessment without AI support.
The primary outcome was posttest total ABG interpretation accuracy across 55 scored items, compared between groups after adjustment for baseline accuracy. Secondary outcomes included changes in total accuracy, domain-specific accuracy, case-level performance, and item-level accuracy.
Studieoversigt
Status
Betingelser
Intervention / Behandling
Undersøgelsestype
Tilmelding (Faktiske)
Fase
- Ikke anvendelig
Kontakter og lokationer
Studiesteder
-
-
Gaziantep
-
Gaziantep, Gaziantep, Tyrkiet (Türkiye)
- Gaziantep City Hospital
-
-
Deltagelseskriterier
Berettigelseskriterier
Aldre berettiget til at studere
- Barn
- Voksen
- Ældre voksen
Tager imod sunde frivillige
Køn, der er berettiget til at studere
Beskrivelse
Inclusion Criteria:
- Fewer than five years of postgraduate clinical experience
- Actively involved in patient care
- Had not completed specialty training
Exclusion Criteria:
- Residents
- Specialists
- Physicians not actively assessing patients
- Incomplete, duplicate, or unmatchable pretest-posttest records
Studieplan
Hvordan er undersøgelsen tilrettelagt?
Design detaljer
- Primært formål: Andet
- Tildeling: Randomiseret
- Interventionel model: Parallel tildeling
- Maskning: Ingen (Åben etiket)
Våben og indgreb
Deltagergruppe / Arm |
Intervention / Behandling |
|---|---|
|
Ingen indgriben: Control group
Participants completed the 11 ABG cases without receiving any AI response, explanation, or recommendation |
|
|
Eksperimentel: AI-Supported Group
Before each of the 11 ABG cases, participants viewed the expert-validated ChatGPT response before providing their own answers. |
Before each of the 11 arterial blood gas (ABG) cases, participants viewed a standardized ChatGPT response that had been independently validated against the expert reference key by three physician experts. The response addressed five scored domains and included a brief rationale. Participants then provided their own answers to each case. |
Hvad måler undersøgelsen?
Primære resultatmål
Resultatmål |
Foranstaltningsbeskrivelse |
Tidsramme |
|---|---|---|
|
Posttest Total ABG Interpretation Accuracy
Tidsramme: One week after baseline assessment
|
Total accuracy across 55 scored items, comprising five scored domains for each of 11 ABG cases. Each item was scored as correct (1) or incorrect (0), and total accuracy was calculated as the number of correct responses divided by 55 × 100. The primary analysis compared posttest total accuracy between the AI-supported and control groups, adjusted for baseline total accuracy. |
One week after baseline assessment
|
Sekundære resultatmål
Resultatmål |
Foranstaltningsbeskrivelse |
Tidsramme |
|---|---|---|
|
Change in Total ABG Interpretation Accuracy From Pretest to Posttest
Tidsramme: From baseline to one week after baseline assessment
|
Change in total ABG interpretation accuracy from baseline (pretest) to the one-week posttest was assessed within each study group. Total accuracy was calculated across 55 scored items as the number of correct responses divided by 55 × 100. |
From baseline to one week after baseline assessment
|
|
Between-Group Difference in Change in Total ABG Interpretation Accuracy
Tidsramme: From baseline to one week after baseline assessment
|
The change in total ABG interpretation accuracy from baseline to posttest was compared between the AI-supported and control groups. Change scores were calculated as posttest accuracy minus baseline accuracy. |
From baseline to one week after baseline assessment
|
|
Change From Baseline in Primary Acid-Base Disorder Identification Accuracy on an 11-Item Assessment
Tidsramme: Baseline and one week after baseline assessment
|
Accuracy in identifying the primary acid-base disorder was calculated as the number of correct responses across 11 arterial blood gas cases divided by 11 and multiplied by 100. Each response was scored as correct (1) or incorrect (0). The outcome was the change in accuracy from baseline to posttest, calculated as posttest accuracy minus baseline accuracy and expressed in percentage points. Possible change scores ranged from -100 to +100 percentage points, with positive values indicating improved accuracy. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Acute Asthma Exacerbation Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the acute asthma exacerbation case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Item-Level ABG Interpretation Accuracy
Tidsramme: One week after baseline assessment
|
Item-level performance was evaluated across the 55 scored items, comprising five scored domains for each of the 11 ABG cases. The probability of a correct response for individual items was compared between the AI-supported and control groups. |
One week after baseline assessment
|
|
Change From Baseline in Acid-Base Compensation Assessment Accuracy on an 11-Item Assessment
Tidsramme: Baseline and one week after baseline assessment
|
Accuracy in assessing acid-base compensation was calculated as the number of correct responses across 11 arterial blood gas cases divided by 11 and multiplied by 100. Each response was scored as correct (1) or incorrect (0). The outcome was the change in accuracy from baseline to posttest, calculated as posttest accuracy minus baseline accuracy and expressed in percentage points. Possible change scores ranged from -100 to +100 percentage points, with positive values indicating improved accuracy. |
Baseline and one week after baseline assessment
|
|
Change From Baseline in Electrolyte and Anion Gap Assessment Accuracy on an 11-Item Assessment
Tidsramme: Baseline and one week after baseline assessment
|
Accuracy in assessing electrolyte and anion gap findings was calculated as the number of correct responses across 11 arterial blood gas cases divided by 11 and multiplied by 100. Each response was scored as correct (1) or incorrect (0). The outcome was the change in accuracy from baseline to posttest, calculated as posttest accuracy minus baseline accuracy and expressed in percentage points. Possible change scores ranged from -100 to +100 percentage points, with positive values indicating improved accuracy. |
Baseline and one week after baseline assessment
|
|
Change From Baseline in Clinical Diagnosis Identification Accuracy on an 11-Item Assessment
Tidsramme: Baseline and one week after baseline assessment
|
Accuracy in identifying the most likely clinical diagnosis was calculated as the number of correct responses across 11 arterial blood gas cases divided by 11 and multiplied by 100. Each response was scored as correct (1) or incorrect (0). The outcome was the change in accuracy from baseline to posttest, calculated as posttest accuracy minus baseline accuracy and expressed in percentage points. Possible change scores ranged from -100 to +100 percentage points, with positive values indicating improved accuracy. |
Baseline and one week after baseline assessment
|
|
Change From Baseline in Clinical Management Decision Accuracy on an 11-Item Assessment
Tidsramme: Baseline and one week after baseline assessment
|
Accuracy in selecting appropriate clinical management was calculated as the number of correct responses across 11 arterial blood gas cases divided by 11 and multiplied by 100. Each response was scored as correct (1) or incorrect (0). The outcome was the change in accuracy from baseline to posttest, calculated as posttest accuracy minus baseline accuracy and expressed in percentage points. Possible change scores ranged from -100 to +100 percentage points, with positive values indicating improved accuracy. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Acute COPD Exacerbation Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the acute COPD exacerbation case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Methanol Intoxication Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the methanol intoxication case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Diabetic Ketoacidosis Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the diabetic ketoacidosis case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Carbon Monoxide Intoxication Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the carbon monoxide intoxication case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Acute Kidney Injury on Chronic Kidney Disease With Hyperkalemia Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the acute kidney injury on chronic kidney disease with hyperkalemia case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Pulmonary Embolism Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the pulmonary embolism case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Panic Attack With Hyperventilation Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the panic attack with hyperventilation case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Diuretic-Associated Metabolic Alkalosis Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the diuretic-associated metabolic alkalosis case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Hypoglycemia Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the hypoglycemia case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
|
Number of Participants by Change Category in Upper Gastrointestinal Bleeding With Hypovolemic Shock Case Interpretation Score
Tidsramme: Baseline and one week after baseline assessment
|
For the upper gastrointestinal bleeding with hypovolemic shock case, each participant received one point for each correct response across five predefined assessment domains, yielding a case-specific score ranging from 0 to 5. The posttest score was compared with the baseline score for the same case. Participants were classified into three mutually exclusive categories: improvement (posttest score greater than baseline score), no change (posttest score equal to baseline score), or deterioration (posttest score lower than baseline score). The number of participants in each category was recorded separately for the AI-supported and control groups. |
Baseline and one week after baseline assessment
|
Samarbejdspartnere og efterforskere
Sponsor
Efterforskere
- Ledende efterforsker: Coşkun, MD, Gaziantep City Hospital
Datoer for undersøgelser
Studer store datoer
Studiestart (Faktiske)
Primær færdiggørelse (Faktiske)
Studieafslutning (Faktiske)
Datoer for studieregistrering
Først indsendt
Først indsendt, der opfyldte QC-kriterier
Først opslået (Faktiske)
Opdateringer af undersøgelsesjournaler
Sidste opdatering sendt (Faktiske)
Sidste opdatering indsendt, der opfyldte kvalitetskontrolkriterier
Sidst verificeret
Mere information
Begreber relateret til denne undersøgelse
Nøgleord
Andre undersøgelses-id-numre
- 0449
Lægemiddel- og udstyrsoplysninger, undersøgelsesdokumenter
Studerer et amerikansk FDA-reguleret lægemiddelprodukt
Studerer et amerikansk FDA-reguleret enhedsprodukt
Disse oplysninger blev hentet direkte fra webstedet clinicaltrials.gov uden ændringer. Hvis du har nogen anmodninger om at ændre, fjerne eller opdatere dine undersøgelsesoplysninger, bedes du kontakte register@clinicaltrials.gov. Så snart en ændring er implementeret på clinicaltrials.gov, vil denne også blive opdateret automatisk på vores hjemmeside .