Automatic matching of surgeries to predict surgeons' next actions

This is the companion web page for our paper titled Automatic matching of surgeries to predict surgeons' next actions

This work is an extention of our paper "Optimal sub-sequence matching for the automatic prediction of surgical tasks" published a the AIME 2015 conference.

This paper has been submitted for publication to a special issue of Artificial Intelligence in Medicine .

If you have any comments/questions regarding the research work or software, please feel free to contact us.


The software

The software is developed in Java.

The package is licensed under a GPLv3 (license in the Jar files) : Download source-code-aiim-2017.zip

The package contains examples illustrating how to use the library in the class Prediciton.java

Prediction Demo

This demo visually illustrates how the prediction system works.

Sequences of symbols (each symbol is considered as an individual state) can be entered in the first textbox, one sequence per line.

The first line is the partial sequence, the following are the full available sequences.

Then push the "Run Prediction" button to see the results of the application of the algorithm.



Last update : May 2015