Related Experiment Video
Updated: Jan 15, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
MedReadr: Development and Evaluation of an In-Browser, Rule-Based Natural Language Processing Algorithm to Estimate
Joshua Winograd1, Autumn Kim2, Nikit Venishetty3
1Joan and Sanford I. Weill Medical College, Weill Cornell Medicine, New York, NY, USA.
A new tool, MedReadr, uses natural language processing (NLP) to automatically assess the reliability of online health articles. This algorithm shows strong agreement with manual scoring, improving access to trustworthy medical information.
Area of Science:
- Medical Informatics
- Natural Language Processing
- Health Communication
Background:
- Online health information quality is inconsistent, posing challenges for patients and providers.
- Existing manual tools for assessing health content reliability are often inefficient or limited.
- Automated assessment of online health article reliability is needed.
Purpose of the Study:
- To develop and validate MedReadr, a novel natural language processing (NLP) algorithm for automated reliability scoring of consumer health articles.
- To assess the performance of MedReadr against established manual scoring systems.
- To identify key features that predict the reliability of online health content.
Main Methods:
- Developed MedReadr, a rule-based NLP algorithm integrated into a web browser.
- Utilized manual assessments of 35 consumer medical articles using QUEST and Sandvik scoring systems.
- Trained a multivariable linear regression model to predict manual reliability scores, validated on 20 additional articles.
Main Results:
- MedReadr demonstrated strong predictive performance with R²=0.90 (development) and R²=0.83 (validation).
- Key features influencing reliability scores included article currency, references, sentiment, and specific content phrases.
- The algorithm achieved high agreement with manual scoring systems (Cohen's κ > 0.6).
Conclusions:
- MedReadr offers an automated, transparent method for assessing online health article reliability.
- The tool shows promise for improving digital health literacy and clinician-patient communication.
- Further validation across diverse web content is recommended to expand its utility.
More Related Videos
Related Concept Videos
Reliability and Validity
Pre-Procedural Guidelines for Assessing Blood Pressure
Health Literacy
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,...
Health Information Technology and Healthcare Information System
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Improving Translational Accuracy

