TemporAI is a Machine Learning-centric time-series library tailored for medicine, focusing on time-series prediction, time-to-event analysis, and counterfactual inference for individualised treatment effects.
How is it unique?
TemporAI offers a comprehensive suite of ML models and preprocessing utilities, catering to various medical use cases involving time-series data. It supports data in time series, static, and event modalities, and is the first to provide a unified interface for prediction, causal inference, and time-to-event analysis, as well as common preprocessing utilities. It bridges the gap between ML research, healthcare professionals, medical/pharmacological industries, and data science communities.
How is it useful?
TemporAI can, for example:
1. Enhance drug discovery and development by leveraging time-series data for predicting patient responses to treatments and identifying optimal treatment durations.
2. Improve clinical trial designs by analysing time-to-event data for patient survival predictions and risk estimation.
3. Enable personalised medicine by estimating individualised treatment effects using observational data with longitudinal components.
4. Facilitate collaboration between data scientists, researchers, and healthcare professionals with an open-source, community-driven platform.
TemporAI’ s versatile models, such as ODE classifier/regressor, Seq2Seq classifier/regressor, Dynamic Deephit, and Counterfactual Recurrent Network (CRN), among others, can be applied to a wide range of medical applications. This empowers the community to unlock the full potential of medical data and to accelerate innovation in the medical ML space.
