{"id":3378,"date":"2026-06-05T19:58:36","date_gmt":"2026-06-05T17:58:36","guid":{"rendered":"https:\/\/neuraldesigner.com\/blog\/colon-cancer-liver-metastasis\/"},"modified":"2026-07-01T15:43:41","modified_gmt":"2026-07-01T13:43:41","slug":"metastasis-risk-colon-cancer","status":"publish","type":"blog","link":"https:\/\/www.neuraldesigner.com\/blog\/metastasis-risk-colon-cancer\/","title":{"rendered":"Metastasis risk assessment using machine learning"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
Advancements in the field of medicine have paved the way for innovative approaches to cancer care, and one such groundbreaking avenue is the use of machine learning for metastasis risk assessment in colon cancer patients.<\/section>

<\/span><\/section>
This example assesses the risk of a patient with colorectal cancer of developing liver metastasis. <\/span>We use mutational data from 492 genes and phenotypic variables using machine learning.<\/span><\/section>\n
<\/section>\n
<\/section>\n

<\/section>
This data is obtained from MSK-MET (Memorial Sloan Kettering – Metastatic Events and Tropisms),
an integrated pan-cancer cohort of tumor genomic and clinical outcome data from 25,000 patients available at Cbioportal<\/a>.<\/section>\n
\n

Contents<\/h3>\n
    \n
  1. Application type<\/a>.<\/li>\n
  2. Data set<\/a>.<\/li>\n
  3. Neural network<\/a>.<\/li>\n
  4. Training strategy<\/a>.<\/li>\n
  5. Model selection<\/a>.<\/li>\n
  6. Testing analysis<\/a>.<\/li>\n
  7. Model deployment<\/a>.<\/li>\n<\/ol>\n


    <\/p>

    This example is solved with Neural Designer<\/a>. You can follow it step by step using the free trial<\/a>.<\/p>\n<\/section>\n

    \n

    1. Application type<\/h2>\n

    The predicted variable can have two values, “yes” if the patient has liver metastasis and “no” otherwise.
    Therefore, this is a binary     classification<\/a> project.<\/p>\n

    The goal is to model the probability of metastasis in the liver based on mutational and phenotypic data using artificial intelligence and machine learning.<\/p>\n<\/section>\n

    \n

    2. Data set<\/h2>\n

    The liver_metastasis_colon_cancer.csv<\/a> file contains the data for this example. Target variables can only have two values in a classification model: 0 (false, no) or 1 (true, yes). The number of instances (rows) in the data set is 3537, and the number of variables (columns) is 510.<\/p>\n

    The number of input variables<\/a>, or attributes for each sample, is 509. The target variable<\/a> is 1, distant_metastasis_liver (Yes or No), whether or not the patient has liver metastasis. The following list summarizes the variable’s<\/a> information:<\/p>\n