Vision Intelligence Network

Organizing machine learning in eye disease

Machine-learning methods allow clinicians and researchers to recognize critical pathology of visual disorders using complex data types from RNA microarrays to OCT images. However, the large number of individual models and curated datasets has made systematic comparison and implementation of such methods challenging. The goal of the Vision Intelligence Network is to provide an organized database of published machine-learning tools for ophthalmology, improving accessibility, explainability, and generalizability in the field.

Methodology

The Vision Intelligence Network applies natural language processing to survey scientific literature for recent published reports of machine learning methods in ophthalmology. The reports are processed to extract relevant hard-coded metadata and keywords. Additionally, each entry undergoes analysis with a pretrained large language model (LLM) for unstructured summary information.

For each entry, the following attributes are cataloged:

• Condition: The primary pathology that the model investigates.
• Model name: Provided by the publication, otherwise defaults to author name.
  
• Description: Brief description of model, generally the title of the reporting publication.
• Task: Brief description of the task to which the model applies.*
• Task type: The primary learning operation (segmentation, forecasting, or detection/diagnosis), if available.
• Model type: Primary type of algorithm implemented, if available.
• Input data type: Description of the type of data used for training.*
• Training set size: Number of examples in the training set.*
• Inferred sensitivity: Sensitivity of the model in the primary evaluation task, if available.*
• Inferred specificity: Specificity of the model in the primary evaluation task, if available.*
• Original report: Link to the associated article.
• Code availability: Whether corresponding code is publicly available.
  
• Code link: Link to the associated code, if available.
• Publication date: For corresponding paper, if available.

* These data elements are identified from unstructured text by querying with a general-purpose LLM (Google Gemini Pro). They may be inaccurate, and users are recommended to consult the corresponding manuscript for details of model evaluation.

Contact

team@visintelnet.org

Disclaimer

This database, including its curation and organization, is experimental. It is intended entirely as a research tool to facilitate the implementation of academic methods. Any information displayed herein may be inaccurate or outdated. For information regarding any method described in this database, please refer to the respective citation.