TokeNER
Your gateway to seamless text annotation for training powerful Language Models. Born out of need for a robust and user-friendly text annotation platform, and recognizing the challenges faced by data scientists and AI researchers, our team set out to create a solution that simplifies the annotation workflow, integrates seamlessly with existing ML pipelines, and scales with growing data needs.
With TokeNER you can annotate text files directly or upload CSV files for bulk annotation tasks, streamlining your workflow. Utilize a suite of advanced tagging tools to create custom tags to suit your specific use cases, and train your models with precision. Implement robust quality control measures with overlapping tags are supported, allowing for more complex and accurate annotations. Export your annotations in JSON format for easy integration with popular NLP libraries and frameworks, enhancing your development process
De-ID
PixelGuard is an advanced software solution designed to de-identify medical images while preserving clinical relevance. It ensures patient confidentiality by removing identifiable data embedded within pixel-level data and metadata. Its AI-enabled technology supports multiple languages for removing pixel data.
PixelGuard employs metadata scrubbing algorithms, with options for swapping/shifting contents. Harnessing Optical Character Recognition (OCR) and Natural Language Processing (NLP), PixelGuard detects
and redacts burned-in text in a variety of languages. Its user-configurable de-identification rules comply with HIPAA, GDPR, or local regulations/needs.
PixelGuard offers powerful and unique value in realms of Clinical Research, Education and Training, AI Model development, and Telemedicine
PSMpy
Matching techniques for epidemiological observational studies as carried out in Python. Propensity score matching is a statistical matching technique used with observational data that attempts to ascertain the validity of concluding there is a potential causal link between a treatment or intervention and an outcome(s) of interest. It does so by accounting for a set of covariates between a binary treatment state (as would occur in a randomized control trial, either received the intervention or not), and control for potential confounding (covariates) in outcome measures between the treatment and control groups such as death, or length of stay etc. It is using this technique on observational data that we gain an insight into the effects or lack thereof of an interventional state.
GeneralizIT
GeneralizIT is a Python-based library designed for conducting Generalizability Theory (GT) analyses. The library supports multiple research designs and provides tools to calculate ANOVA tables, generalizability coefficients (G coefficients), and decision (D) studies.
It is particularly useful for researchers and practitioners who work with multi-faceted designs and want to quantify the reliability and generalizability of their measurements.
