Original authors: Bertrand PATUREL - Kaixian HUANG - Ramy MERABET - Nawel ARAB - Pierre-André MIKEM

As part of the Data Camp course, within the Data Science Masters at Institut Polytechnique de Paris in collaboration with University of Paris-Saclay, students were required to build a data challenge addressing some social/science/business problem using data obtained from external sources. This is our challenge on the Thyroid desease detection.

It is estimated that over 200,000 million people worldwide suffer from a thyroid disease, such as enlarged thyroid gland (goiter), thyroid nodules with or without cancer, hyperthyroidism or hypothyroidism. The influence of the thyroid gland on the body is major. The role of this butterfly-shaped organ located at the base of the neck (under the Adam's apple) is to regulate the metabolism of the cells in our body. It therefore determines the speed of the "motor" of our cells and organs and is involved in the proper functioning of our organs: the heart, muscles, brain, but also the digestive tract, bone health, regulation of our temperature and energy ... When the thyroid gets excited about producing hormones, the body does the same in its energy combustion, running several vital functions at full speed. This is called hyperthyroidism. When the gland is idling and not producing enough hormones, it is called hypothyroidism.

The task asked here in this challenge is to predict whether a patient suffer from hyper or hypothyroidism or none of them.

The starting kit notebook provides more details on this challenge and exploratory analysis on the data used.

To get started on this challenge follow the instructions here.

The submissions need to be located in the submissions folder. For instance for my_submission, it should be located in submissions/my_submission.

To run a specific submission, you can use the ramp-test command line:

ramp-test --submission my_submission

You can get more information regarding this command line:

ramp-test --help