AI Dialogues in Cartilage Repair: ChatGPT, DeepSeek, and Google Search Comparison

A 2026 study by Sen Yang Xiao compares ChatGPT, DeepSeek, and Google Search on cartilage repair questions. The analysis covers two domains—cartilage tissue engineering (2023) and cartilage repair surgery (2024)—using a dual-axis framework for classification, blinded quality scoring, and readability assessment. The dataset is a 23.3 KB document summarizing the methodology and results of this three-way platform evaluation.

Use Cases

• Benchmarking AI model accuracy and safety in medical domains based on the described Accuracy-Safety-Hallucination (ASH) framework.
• Analyzing question classification patterns in medical FAQs based on the modified Rothwell taxonomy mentioned.
• Comparing the readability of AI-generated versus search engine answers using the Flesch-Kincaid formula results described.
• Informing stakeholder-specific tool selection for clinical or educational tasks based on the functional role analysis in the conclusion.

Strengths

• Uses a dual-axis framework integrating classification, blinded quality scoring, and readability analysis.
• Includes matched three-way comparison of three platforms (Google, ChatGPT, DeepSeek) on identical questions.
• Quality was independently evaluated by three blinded raters using the ASH framework.
• Results include specific median accuracy scores and statistical significance (p-values) for each platform.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 23.3 KB, indicating limited scope, likely a summary document rather than raw data.

Provenance

Source

Sen Yang Xiao via figshare.

Collection Method

Google Search was queried for top FAQs, which were then submitted to ChatGPT and DeepSeek APIs for matched comparison.

Time Range

Analysis based on questions from cartilage tissue engineering (2023) and cartilage repair surgery (2024) domains.

Freshness

Last updated 2026-05-29 05:53:28; freshness should be verified.