top of page


We've created ground-breaking analytical tools to add to your data science toolkit.

Our publicly-available analytical tools provide data scientists everywhere with ready-made models that can be modified to suit their needs.  Looking for more clinical data science learning? Check our WebinarsArticles & Publications and Recommended Resources pages.

Forecasting Time Series Data/Intervention Assessment

One of the most common analyses conducted by any decision support unit at a hospital is a time series analysis, as it can help with understanding seasonal variances in hospital volumes, planning for volume surges, and with evaluating targeted interventions. This time series forecasting and intervention analysis software allows hospital analysts to conduct a rigorous and reproducible time series analysis. Specifically, the software allows users to visually explore their time series, build, cross-validate, and forecast dozens of time series models. View our video guide for instructions on how to use the tool

Most patient information is stored only in the form of transcribed, dictated notes. CHARTextract is a rule-based information extraction tool with the ability to quickly and easily refine rules on-the-fly. By combining physician knowledge and keyword-based pattern matching, we can extract patient attributes (e.g., diagnosis, country of birth, procedures, etc.) from free-form text notes. With this tool, hospital leadership, clinicians and clinical researchers everywhere can automatically extract patient information from text notes and perform large-scale analyses of patient data. You can download the tool and rulesets here, and read up on the documentation here

Recurrent Neural Network (RNN) Algorithm

Recurrent Neural Networks (RNNs) were recently shown to be able to effectively model rich longitudinal data. In particular, RNNs are effective for modeling electronic health records (EHR) to predict patient events - however, they are difficult to train.  LKS-CHART is developing a software package to reduce the amount of time needed to apply RNNs to EHR. The goal is for data scientists to use the ready-made implementation and customize it to suit their needs so they can rapidly apply RNNs to their EHR data.

Please reload

bottom of page