What is cacti ml?
cacti ml is a project dedicated to building clinical Artificial Intelligence (AI) software and resources. Its primary objective is to improve the accessibility of information contained within medical records, such as Electronic Medical Records (EMRs), by enabling semantic filtering, searching, and extraction of clinical data.
The initiative strives to develop generalizable AI solutions applicable to diverse clinical tasks without extensive task-specific training. Furthermore, cacti ml focuses on creating reusable packages, models, and tools, like Named Entity Recognition (NER) models and clinical text tokenizers, to serve as foundational components for ongoing clinical research and development, particularly in the field of clinical Natural Language Processing (NLP).
The initiative strives to develop generalizable AI solutions applicable to diverse clinical tasks without extensive task-specific training. Furthermore, cacti ml focuses on creating reusable packages, models, and tools, like Named Entity Recognition (NER) models and clinical text tokenizers, to serve as foundational components for ongoing clinical research and development, particularly in the field of clinical Natural Language Processing (NLP).
Features
- MedQA: GPT-powered clinical reference tool for answering clinical questions with source references.
- clinisift: Multitool designed for processing clinical medical records.
- clinitokenizer: Specialized sentence tokenizer for clinical and medical text.
- bert-Clinical-NER: Named Entity Recognition model identifying clinical entities (problem, treatment, test).
- bert-Med-NER: Named Entity Recognition model extracting medication details (name, dosage, duration, frequency, reason).
- Clinical GPT-3 Exploration: Research into GPT-3's application for clinical NLP tasks on patient records.
Use Cases
- Enhancing the searchability of Electronic Medical Records (EMRs).
- Extracting specific clinical entities like problems, treatments, and tests from text.
- Analyzing medication information documented in medical notes.
- Querying clinical information using natural language questions.
- Tokenizing clinical text for subsequent NLP analysis.
- Supporting clinical research with specialized AI tools and models.
Related Queries
Helpful for people in the following professions
Featured Tools
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
