The goal of this observational experimental study is to determine how system-level features of artificial intelligence clinical decision support systems (AI-CDSS)-specifically explainability and integrability-affect usage behavior among primary care physicians in China. The study focuses on licensed primary care physicians, regardless of gender, age, years of clinical experience, or prior AI exposure.
The main questions it aims to answer are:
* Do specific AI features (e.g., feature attribution, chain-of-thought explanation, seamless workflow integration, automated data input) independently influence physicians' adoption intention, diagnostic accuracy, and their perceptions of the system's usefulness and ease of use? * Do pairwise combinations of these AI features produce significant interaction effects-either synergistic or antagonistic-on these outcomes? Researchers will compare 32 distinct AI interface configurations generated from a 2⁶-¹ fractional factorial design (Resolution VI), each representing a unique combination of six binary AI features: (A) gradient-based feature importance (0 = absent, 1 = present), (B) chain-of-thought reasoning (0/1), (C) workflow integration (0 = multiple pop-up alerts, 1 = unified sidebar display), (D) automated data extraction (0 = manual entry, 1 = auto-populated from case text), (E) recommendation scope adapted to primary care settings (0 = restricted to essential options, 1 = full range of recommendations), and (F) model confidence display (0 = absent, 1 = present). This design enables unbiased estimation of all six main effects and all 15 two-way interactions.
Participants will:
Complete three standardized clinical case scenarios involving common respiratory infections via a web-based simulation platform; First provide an initial diagnosis and treatment plan without any AI input; Then review an AI-generated recommendation embedded with a randomly assigned combination of the six AI features; Revise their final diagnosis and prescription based on the AI suggestion; Rate their adoption intention, perceived usefulness, and perceived ease of use using validated 7-point Likert-scale items after each case.
Be currently employed full-time in clinical practice at a primary care facility, including community health centers, community health stations, township hospitals, or village clinics;
Hold a clinical medical license with a specialty in general practice or internal medicine, and have experience in diagnosing and managing respiratory tract infections;
Have at least one year of clinical work experience;
Be proficient in basic computer use (e.g., web browsing and online questionnaire completion), have reliable internet access, and be capable of independently completing the online experimental tasks;
Non-clinical staff (e.g., administrative personnel, pharmacists, laboratory technicians, or public health workers who do not directly provide outpatient clinical care);
Individuals unable to independently complete the online experimental procedure or who demonstrate significant difficulty understanding the task instructions.
Factorial
AI-CDSS with Stepwise Medication and Auto-extraction
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Stepwise Medication; Auto-extraction. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Feature Importance. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Feature Importance and Auto-extraction
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Feature Importance; Auto-extraction. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Feature Importance and Stepwise Medication
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Feature Importance; Stepwise Medication. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Confidence Display and Auto-extraction
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Confidence Display; Auto-extraction. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Feature Importance; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Confidence Display and Stepwise Medication
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Confidence Display; Stepwise Medication. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Feature Importance; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Confidence Display and Feature Importance
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Confidence Display; Feature Importance. Inactive features: Sidebar Display; Chain-of-Thought Reasoning; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 8)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Confidence Display; Feature Importance; Stepwise Medication; Auto-extraction. Inactive features: Sidebar Display; Chain-of-Thought Reasoning. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Chain-of-Thought Reasoning and Auto-extraction
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Auto-extraction. Inactive features: Sidebar Display; Confidence Display; Feature Importance; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Chain-of-Thought Reasoning and Stepwise Medication
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Stepwise Medication. Inactive features: Sidebar Display; Confidence Display; Feature Importance; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Chain-of-Thought Reasoning and Feature Importance
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Feature Importance. Inactive features: Sidebar Display; Confidence Display; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 12)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Feature Importance; Stepwise Medication; Auto-extraction. Inactive features: Sidebar Display; Confidence Display. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Chain-of-Thought Reasoning and Confidence Display
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Confidence Display. Inactive features: Sidebar Display; Feature Importance; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 14)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Confidence Display; Stepwise Medication; Auto-extraction. Inactive features: Sidebar Display; Feature Importance. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 15)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Confidence Display; Feature Importance; Auto-extraction. Inactive features: Sidebar Display; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 16)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Chain-of-Thought Reasoning; Confidence Display; Feature Importance; Stepwise Medication. Inactive features: Sidebar Display; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Sidebar Display and Auto-extraction
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Auto-extraction. Inactive features: Chain-of-Thought Reasoning; Confidence Display; Feature Importance; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Sidebar Display and Stepwise Medication
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Stepwise Medication. Inactive features: Chain-of-Thought Reasoning; Confidence Display; Feature Importance; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Sidebar Display and Feature Importance
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Feature Importance. Inactive features: Chain-of-Thought Reasoning; Confidence Display; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 20)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Feature Importance; Stepwise Medication; Auto-extraction. Inactive features: Chain-of-Thought Reasoning; Confidence Display. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Sidebar Display and Confidence Display
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Confidence Display. Inactive features: Chain-of-Thought Reasoning; Feature Importance; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 22)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Confidence Display; Stepwise Medication; Auto-extraction. Inactive features: Chain-of-Thought Reasoning; Feature Importance. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 23)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Confidence Display; Feature Importance; Auto-extraction. Inactive features: Chain-of-Thought Reasoning; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 24)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Confidence Display; Feature Importance; Stepwise Medication. Inactive features: Chain-of-Thought Reasoning; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with Sidebar Display and Chain-of-Thought Reasoning
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning. Inactive features: Confidence Display; Feature Importance; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 26)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Stepwise Medication; Auto-extraction. Inactive features: Confidence Display; Feature Importance. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 27)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Feature Importance; Auto-extraction. Inactive features: Confidence Display; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 28)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Feature Importance; Stepwise Medication. Inactive features: Confidence Display; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 29)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Auto-extraction. Inactive features: Feature Importance; Stepwise Medication. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 30)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Stepwise Medication. Inactive features: Feature Importance; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
AI-CDSS with 4 Features (Config 31)
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Feature Importance. Inactive features: Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
Full-Featured AI-CDSS
BehavioralAn artificial intelligence-based Clinical Decision Support System for respiratory tract infections. Active features: Sidebar Display; Chain-of-Thought Reasoning; Confidence Display; Feature Importance; Stepwise Medication; Auto-extraction. The system provides diagnosis suggestions and antibiotic recommendations for primary care physicians.
32
Treatment groupsSee each treatment group below.
Correction Event Rate
Proportion of cases where the physician's initial decision was incorrect, but was corrected to the right decision after viewing AI recommendations. Calculated as: (Number of cases where initial decision was wrong AND final decision was correct) / (Total number of cases where initial decision was wrong). This measures the positive corrective influence of AI-CDSS on physician decision-making. Continuous variable ranging from 0 to 1.
Misleading Event Rate
Proportion of cases where the physician's initial decision was correct, but was changed to an incorrect decision after viewing AI recommendations. Calculated as: (Number of cases where initial decision was correct AND final decision was wrong) / (Total number of cases where initial decision was correct). This measures the potential negative influence of AI-CDSS on physician decision-making. Continuous variable ranging from 0 to 1.
Diagnostic Accuracy (Top-1)
Proportion of cases where the physician's final primary diagnosis (first-ranked diagnosis) matches the correct diagnosis (gold standard). Measured separately for initial diagnosis (before AI) and final diagnosis (after AI) to assess AI impact on diagnostic accuracy. Continuous variable ranging from 0 to 1.
Diagnostic Accuracy (Top-3)
Proportion of cases where the correct diagnosis (gold standard) appears within the physician's top 3 differential diagnoses. Measured separately for initial diagnosis (before AI) and final diagnosis (after AI). This captures whether the correct diagnosis was considered even if not ranked first. Continuous variable ranging from 0 to 1.
Decision Certainty
Physician's self-reported confidence level in their final clinical decision after viewing AI recommendations. Measured using a 5-point Likert scale: 1 = Very Uncertain, 2 = Uncertain, 3 = Neutral, 4 = Certain, 5 = Very Certain. This reflects the cognitive impact of AI-CDSS on decision confidence.
Intention to Adopt AI-CDSS
Measured using a 3-item scale adapted from the Technology Acceptance Model (TAM). Items assess: (1) willingness to apply AI-CDSS in daily clinical practice when available, (2) intention to use AI-CDSS based on actual patient care needs, and (3) willingness to frequently use AI-CDSS when conditions permit. Each item is rated on a 5-point Likert scale (1=Strongly Disagree to 5=Strongly Agree). Total score ranges from 3 to 15.
Perceived Usefulness of AI-CDSS
Measured using a 6-item Perceived Usefulness scale adapted from TAM (Davis, 1989). Items assess perceived improvements in: (1) task completion speed, (2) job performance, (3) productivity, (4) work effectiveness, (5) ease of work, and (6) overall usefulness. Each item is rated on a 7-point Likert scale (1=Strongly Disagree to 7=Strongly Agree). Total score ranges from 6 to 42.
Perceived Ease of Use of AI-CDSS
Measured using a 6-item Perceived Ease of Use scale adapted from TAM (Davis, 1989). Items assess: (1) ease of learning, (2) ease of getting desired functions, (3) clarity of interaction, (4) flexibility of interaction, (5) ease of becoming proficient, and (6) overall ease of use. Each item is rated on a 7-point Likert scale (1=Strongly Disagree to 7=Strongly Agree). Total score ranges from 6 to 42.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
