ChatGPT for Univariate Statistics: Validation of AI-Assisted Data Analysis in Healthcare Research
Salvato in:
| Pubblicato in: | Journal of Medical Internet Research vol. 27 (2025), p. e63550 |
|---|---|
| Autore principale: | |
| Altri autori: | , , |
| Pubblicazione: |
Gunther Eysenbach MD MPH, Associate Professor
|
| Soggetti: | |
| Accesso online: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3222367933 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1438-8871 | ||
| 024 | 7 | |a 10.2196/63550 |2 doi | |
| 035 | |a 3222367933 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 100 | 1 | |a Ruta, Michael R | |
| 245 | 1 | |a ChatGPT for Univariate Statistics: Validation of AI-Assisted Data Analysis in Healthcare Research | |
| 260 | |b Gunther Eysenbach MD MPH, Associate Professor |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Background:ChatGPT, a conversational artificial intelligence developed by OpenAI, has rapidly become an invaluable tool for researchers. With the recent integration of Python code interpretation into the ChatGPT environment, there has been a significant increase in the potential utility of ChatGPT as a research tool, particularly in terms of data analysis applications.Objective:This study aimed to assess ChatGPT as a data analysis tool and provide researchers with a framework for applying ChatGPT to data management tasks, descriptive statistics, and inferential statistics.Methods:A subset of the National Inpatient Sample was extracted. Data analysis trials were divided into data processing, categorization, and tabulation, as well as descriptive and inferential statistics. For data processing, categorization, and tabulation assessments, ChatGPT was prompted to reclassify variables, subset variables, and present data, respectively. Descriptive statistics assessments included mean, SD, median, and IQR calculations. Inferential statistics assessments were conducted at varying levels of prompt specificity (“Basic,” “Intermediate,” and “Advanced”). Specific tests included chi-square, Pearson correlation, independent 2-sample t test, 1-way ANOVA, Fisher exact, Spearman correlation, Mann-Whitney U test, and Kruskal-Wallis H test. Outcomes from consecutive prompt-based trials were assessed against expected statistical values calculated in Python (Python Software Foundation), SAS (SAS Institute), and RStudio (Posit PBC).Results:ChatGPT accurately performed data processing, categorization, and tabulation across all trials. For descriptive statistics, it provided accurate means, SDs, medians, and IQRs across all trials. Inferential statistics accuracy against expected statistical values varied with prompt specificity: 32.5% accuracy for “Basic” prompts, 81.3% for “Intermediate” prompts, and 92.5% for “Advanced” prompts.Conclusions:ChatGPT shows promise as a tool for exploratory data analysis, particularly for researchers with some statistical knowledge and limited programming expertise. However, its application requires careful prompt construction and human oversight to ensure accuracy. As a supplementary tool, ChatGPT can enhance data analysis efficiency and broaden research accessibility. | |
| 653 | |a Artificial intelligence | ||
| 653 | |a Analysis | ||
| 653 | |a Health care | ||
| 653 | |a Nonparametric statistics | ||
| 653 | |a Datasets | ||
| 653 | |a Length of stay | ||
| 653 | |a Classification | ||
| 653 | |a Bioinformatics | ||
| 653 | |a Multimedia | ||
| 653 | |a Data processing | ||
| 653 | |a Variables | ||
| 653 | |a Data analysis | ||
| 653 | |a Statistical inference | ||
| 653 | |a Medical research | ||
| 653 | |a Python | ||
| 653 | |a Tests | ||
| 653 | |a Expected values | ||
| 653 | |a Chatbots | ||
| 653 | |a Statistical methods | ||
| 653 | |a Inpatient care | ||
| 653 | |a Access | ||
| 653 | |a Accuracy | ||
| 653 | |a Statistical analysis | ||
| 653 | |a Health services | ||
| 653 | |a Conversation | ||
| 653 | |a Statistics | ||
| 653 | |a Research methodology | ||
| 653 | |a Human-computer interaction | ||
| 653 | |a Variance analysis | ||
| 653 | |a Programming languages | ||
| 653 | |a Research | ||
| 653 | |a Evaluation | ||
| 653 | |a Researchers | ||
| 700 | 1 | |a Gaidici, Tony | |
| 700 | 1 | |a Chase, Irwin | |
| 700 | 1 | |a Lifshitz, Jonathan | |
| 773 | 0 | |t Journal of Medical Internet Research |g vol. 27 (2025), p. e63550 | |
| 786 | 0 | |d ProQuest |t Library Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3222367933/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3222367933/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3222367933/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |