Related Experiment Video
Updated: Sep 10, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Accuracy and Safety of ChatGPT-3.5 in Assessing Over-the-Counter Medication Use During Pregnancy: A Descriptive
Bernadette Cornelison1, David R Axon1, Bryan Abbott1
1R. Ken Coit College of Pharmacy, University of Arizona, 1295 N. Martin Ave., Tucson, AZ 85721, USA.
Artificial intelligence (AI) chatbots like ChatGPT-3.5 show high accuracy and completeness for pregnant patients seeking over-the-counter (OTC) medication advice. However, critical safety errors were found, making AI an unsafe standalone resource for this information.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Reproductive Health
Background:
- Pregnant individuals increasingly use AI for health information, including over-the-counter (OTC) medication guidance.
- Medication safety during pregnancy is critical, yet data availability is often limited.
- AI chatbots may offer accessible information but require rigorous safety validation.
Purpose of the Study:
- To evaluate the accuracy, completeness, and safety of ChatGPT-3.5 in providing information on OTC medications for pregnant patients.
- To compare AI-generated responses against a trusted medical resource, UpToDate®.
Main Methods:
- A prospective, descriptive study assessed 87 pharmacist-recommended OTC drugs.
- ChatGPT-3.5 responses were compared to UpToDate® information using a 5-point Likert scale by independent reviewers.
- Consensus ratings were established after group discussions, with a third investigator providing final scores.
Main Results:
- ChatGPT-3.5 received high median scores for correctness (5/5) and safety (5/5).
- Completeness received a median score of 4/5.
- Despite high scores, 9% of evaluations (n=8) contained safety errors, including omissions with potential for serious complications.
Conclusions:
- While ChatGPT-3.5 demonstrates strong performance in accuracy and completeness for OTC drug information in pregnancy, safety concerns persist.
- The identified safety errors, particularly omissions, render the chatbot an unsafe standalone resource for pregnant patients.
- Further development and validation are necessary before AI chatbots can be reliably used for medication advice during pregnancy.
More Related Videos
05:33Author Spotlight: Alleviating Nausea and Vomiting in Pregnancy with Safe and Effective Auricular Acupuncture
Published on: August 4, 2023
13:35A Convenient Method for Extraction and Analysis with High-Pressure Liquid Chromatography of Catecholamine Neurotransmitters and Their Metabolites
Published on: March 1, 2018
Related Concept Videos
Teratogenicity
Drug Dosage Regimen: Overview
Typically, the starting dose and dosing interval are guided by the manufacturer's recommendations based on clinical trials conducted during and after drug...
Pharmacovigilance
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Factors Affecting Drug Response: Overview
Drug Administration and Therapy Phases: Overview
The pharmaceutical phase focuses on leveraging the physicochemical properties of the drug to design and manufacture an effective product. Variants include orally administered tablets or capsules, topical creams or ointments, and parenteral-delivery solutions or emulsions.
The pharmacokinetic phase...