We have created a machine learning model to evaluate the risk of relapse in lung cancer patients.
This model uses mutational data from lung cancer patients, as described in Evaluate the probability of relapse in patients with lung cancer. The expression values are the log2 values of the expression plus 1.
Patient’s data:
Risk of recurrence | ||||||||
---|---|---|---|---|---|---|---|---|
aaaa | Low | aaaa | Medium | aaaa | High |
The color division is made using discrete statistics for the probability of recurrence for each month. Low risk is comprised of values below the first quartile, medium risk of the values between the first quartile and the median, and high risk of values above the median. The median is represented in the figure by the grey line.
The gray line is the percentage of patients with recurrence for a given month. A patient with a line below it would have a lower risk than the population for each month.
Expression values are Affymetrix HG-U133A arrays normalized with RMA (Robust Multiarray Averaging) method.
Please note that it is impossible to predict the future with certainty, and a physician must always interpret these predictions to make a diagnosis.