Data From: ChatGPT versus expert feedback on clinical reasoning questions and their effect on learning: a randomized controlled trial

Dataset Info

1) Immediate Test-    The first row of the dataset identifies the columns.-    Column A represents the participants’ iDs.-    Column B represents the participants’ assigned group [0: Control (ExpertFeedback) 1: Intervention (ChatGPTFeedback)].-    Column C represents the genders of the participants (1: Female, 2: Male).-    Column D represents the first-year repetition status of the participants. (0: No, 1: Yes)-    Column E to H represent the scores in four different uncomplicated urinary tract infection (UTI) Key-Features Questions Items separately. -    Column I represents the total scores in uncomplicated UTI Key-Features Questions Items. -    Column J to M represent the scores in four different complicated UTI Key-Features Questions Items separately. -    Column N represents the total scores in complicated UTI Key-Features Questions Items. -    Column O to R represent the scores in four different pyelonephritis Key-Features Questions Items separately. -    Column S represents the total scores in pyelonephritis Key-Features Questions Items. -    Column T represents the total scores in immediate test. 

2) Delayed Test-    The first row of the dataset identifies the columns.-    Column A represents the participants iDs.-    Column B represents the participants’ assigned group [0: Control (ExpertFeedback) 1: Intervention (ChatGPTFeedback)].-    Column C represents the genders of the participants (1: Female, 2: Male).-    Column D represents the first-year repetition status of the participants. (0: No, 1: Yes)-    Column E to H represent the scores in four different uncomplicated urinary tract infection (UTI) Key-Features Questions Items separately. -    Column I represents the total scores in uncomplicated UTI Key-Features Questions Items. -    Column J to M represent the scores in four different complicated UTI Key-Features Questions Items separately. -    Column N represents the total scores in complicated UTI Key-Features Questions Items. -    Column O to R represent the scores in four different pyelonephritis Key-Features Questions Items separately. -    Column S represents the total scores in pyelonephritis Key-Features Questions Items. -    Column T represents the total scores in delayed test. 

3) Pre-Intervention Survey on Critical Approach to AI-    The first row of the dataset identifies the columns.-    Column A represents the participants iDs.-    Column B represents the participants’ assigned group [0: Control (ExpertFeedback) 1: Intervention (ChatGPTFeedback)].-    Column C represents the genders of the participants (1: Female, 2: Male).-    Column D represents the first-year repetition status of the participants (0: No, 1: Yes).-    Column E to J represent the responses of the participants to survey questions before the intervention. Each column is evaluated on a scale from 1 to 7. As it progresses from 1 to 7, the agreement status of participants to survey questions increases. (1: No agreement at all, 7: completely agree)

4) Post-Intervention Survey on Critical Approach to AI-    The first row of the dataset identifies the columns.-    Column A represents the participants iDs.-    Column B represents the participants’ assigned group [0: Control (ExpertFeedback) 1: Intervention (ChatGPTFeedback)].-    Column C represents the genders of the participants (1: Female, 2: Male).-    Column D represents the first-year repetition status of the participants (0: No, 1: Yes).-    Column E to J represent the evaluation of the participants to survey questions after intervention. Each column is evaluated on a scale from 1 to 7. As it progresses from 1 to 7, the agreement status of participants to survey questions increases.  (1: No agreement at all, 7: completely agree)

数据集信息

1. 即时测试
- 数据集首行为列标题。
- 列A代表参与者ID（participants’ IDs）。
- 列B代表参与者所属分组：[0: 对照组（专家反馈组），1: 干预组（ChatGPT反馈组）]。
- 列C代表参与者性别：1为女性，2为男性。
- 列D代表参与者一年级留级状态：0为否，1为是。
- 列E至H分别代表4道不同的单纯性尿路感染（uncomplicated urinary tract infection, UTI）核心特征试题的得分。
- 列I代表单纯性尿路感染核心特征试题的总得分。
- 列J至M分别代表4道不同的复杂性尿路感染（complicated urinary tract infection, UTI）核心特征试题的得分。
- 列N代表复杂性尿路感染核心特征试题的总得分。
- 列O至R分别代表4道不同的肾盂肾炎（pyelonephritis）核心特征试题的得分。
- 列S代表肾盂肾炎核心特征试题的总得分。
- 列T代表即时测试的总得分。

2. 延迟测试
- 数据集首行为列标题。
- 列A代表参与者ID（participants’ IDs）。
- 列B代表参与者所属分组：[0: 对照组（专家反馈组），1: 干预组（ChatGPT反馈组）]。
- 列C代表参与者性别：1为女性，2为男性。
- 列D代表参与者一年级留级状态：0为否，1为是。
- 列E至H分别代表4道不同的单纯性尿路感染（uncomplicated urinary tract infection, UTI）核心特征试题的得分。
- 列I代表单纯性尿路感染核心特征试题的总得分。
- 列J至M分别代表4道不同的复杂性尿路感染（complicated urinary tract infection, UTI）核心特征试题的得分。
- 列N代表复杂性尿路感染核心特征试题的总得分。
- 列O至R分别代表4道不同的肾盂肾炎（pyelonephritis）核心特征试题的得分。
- 列S代表肾盂肾炎核心特征试题的总得分。
- 列T代表延迟测试的总得分。

3. 人工智能批判性思维干预前调查问卷
- 数据集首行为列标题。
- 列A代表参与者ID（participants’ IDs）。
- 列B代表参与者所属分组：[0: 对照组（专家反馈组），1: 干预组（ChatGPT反馈组）]。
- 列C代表参与者性别：1为女性，2为男性。
- 列D代表参与者一年级留级状态：0为否，1为是。
- 列E至J代表参与者在干预前对调查问卷题目的作答，所有题目采用1至7级计分。计分从1到7递增时，参与者对题目的认同程度逐步提升：1代表完全不认同，7代表完全认同。

4. 人工智能批判性思维干预后调查问卷
- 数据集首行为列标题。
- 列A代表参与者ID（participants’ IDs）。
- 列B代表参与者所属分组：[0: 对照组（专家反馈组），1: 干预组（ChatGPT反馈组）]。
- 列C代表参与者性别：1为女性，2为男性。
- 列D代表参与者一年级留级状态：0为否，1为是。
- 列E至J代表参与者在干预后对调查问卷题目的作答，所有题目采用1至7级计分。计分从1到7递增时，参与者对题目的认同程度逐步提升：1代表完全不认同，7代表完全认同。