{"id":3475,"date":"2025-09-03T11:12:59","date_gmt":"2025-09-03T09:12:59","guid":{"rendered":"https:\/\/neuraldesigner.com\/learning\/colon-cancer-liver-metastasis\/"},"modified":"2026-02-11T11:53:37","modified_gmt":"2026-02-11T10:53:37","slug":"metastasis-prediction-machine-learning","status":"publish","type":"learning","link":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/","title":{"rendered":"Metastasis prediction using machine learning"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"3475\" class=\"elementor elementor-3475\" data-elementor-post-type=\"learning\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5e27a4b3 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5e27a4b3\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-687d2dad\" data-id=\"687d2dad\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-1b2b437 elementor-widget elementor-widget-heading\" data-id=\"1b2b437\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Introduction<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-934b8ed elementor-widget elementor-widget-text-editor\" data-id=\"934b8ed\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p>Colorectal cancer frequently leads to liver metastasis, which significantly worsens patient prognosis. Therefore, early prediction of metastatic risk plays a crucial role in treatment planning.<\/p><p>We developed a neural network integrating 492 genes and clinical variables, trained on the MSK-MET cohort (&gt;25,000 patients), achieving 78% accuracy and 0.85 AUC.<\/p><p>This approach shows strong potential as a decision-support tool, and healthcare professionals can explore it using\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/product\">Neural Designer<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-df82b5c e-flex e-con-boxed e-con e-parent\" data-id=\"df82b5c\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-0403f3f e-con-full e-flex e-con e-child\" data-id=\"0403f3f\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-5c29baf elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"5c29baf\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/www.neuraldesigner.com\/downloads\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-icon\">\n\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-download\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M216 0h80c13.3 0 24 10.7 24 24v168h87.7c17.8 0 26.7 21.5 14.1 34.1L269.7 378.3c-7.5 7.5-19.8 7.5-27.3 0L90.1 226.1c-12.6-12.6-3.7-34.1 14.1-34.1H192V24c0-13.3 10.7-24 24-24zm296 376v112c0 13.3-10.7 24-24 24H24c-13.3 0-24-10.7-24-24V376c0-13.3 10.7-24 24-24h146.7l49 49c20.1 20.1 52.5 20.1 72.6 0l49-49H488c13.3 0 24 10.7 24 24zm-124 88c0-11-9-20-20-20s-20 9-20 20 9 20 20 20 20-9 20-20zm64 0c0-11-9-20-20-20s-20 9-20 20 9 20 20 20 20-9 20-20z\"><\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Download<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c046261 elementor-widget elementor-widget-heading\" data-id=\"c046261\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Contents<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2b26b68 elementor-widget elementor-widget-text-editor\" data-id=\"2b26b68\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The following index outlines the steps for performing the analysis.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-ecd5be3 e-flex e-con-boxed e-con e-parent\" data-id=\"ecd5be3\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-18880f5 e-grid e-con-full e-con e-child\" data-id=\"18880f5\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-3821a3a elementor-align-center elementor-widget elementor-widget-button\" data-id=\"3821a3a\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#model_type\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">1.Model type<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e7f62f8 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"e7f62f8\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#dataset\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">2.Dataset<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b19914d elementor-align-center elementor-widget elementor-widget-button\" data-id=\"b19914d\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#neural_network\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">3.Neural network<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-031a44a elementor-align-center elementor-widget elementor-widget-button\" data-id=\"031a44a\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#training_strategy\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">4.Training strategy<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-65f1efa elementor-align-center elementor-widget elementor-widget-button\" data-id=\"65f1efa\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#model_selection\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">5.Model selection<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-82c44dc elementor-align-center elementor-widget elementor-widget-button\" data-id=\"82c44dc\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#testing_analysis\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">6.Testing analysis<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d52a9c6 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"d52a9c6\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"#model_deployment\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">7.Model deployment<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ab6b40f elementor-widget elementor-widget-heading\" data-id=\"ab6b40f\" data-element_type=\"widget\" id=\"model_type\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">1. Model type<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d759939 elementor-widget elementor-widget-text-editor\" data-id=\"d759939\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"548\" data-end=\"737\">In this example, we develop a binary classification model to predict whether a patient will develop liver metastasis. Specifically, the model outputs 1 if metastasis occurs and 0 otherwise.<\/p><p data-start=\"739\" data-end=\"987\">By framing the problem this way, we allow the neural network to identify patterns associated with metastatic progression. Consequently, clinicians can use the model\u2019s output as decision-support information during follow-up and therapeutic planning.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c3e9b1b elementor-widget elementor-widget-heading\" data-id=\"c3e9b1b\" data-element_type=\"widget\" id=\"dataset\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">2. Data set<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-36619c2 elementor-widget elementor-widget-heading\" data-id=\"36619c2\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Data source<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ae2e897 elementor-widget elementor-widget-text-editor\" data-id=\"ae2e897\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"77\" data-end=\"249\" style=\"text-align: justify;\">The\u00a0dataset (3537 instances, 510 variables) for a binary classification problem (target: distant_metastasis_liver, [yes or no]).<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-41d6e29 e-flex e-con-boxed e-con e-parent\" data-id=\"41d6e29\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-5646fa4 e-con-full e-flex e-con e-child\" data-id=\"5646fa4\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-daa3a57 elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"daa3a57\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/10\/liver_metastasis_colon_cancer.csv\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-icon\">\n\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-file-download\" viewBox=\"0 0 384 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M224 136V0H24C10.7 0 0 10.7 0 24v464c0 13.3 10.7 24 24 24h336c13.3 0 24-10.7 24-24V160H248c-13.2 0-24-10.8-24-24zm76.45 211.36l-96.42 95.7c-6.65 6.61-17.39 6.61-24.04 0l-96.42-95.7C73.42 337.29 80.54 320 94.82 320H160v-80c0-8.84 7.16-16 16-16h32c8.84 0 16 7.16 16 16v80h65.18c14.28 0 21.4 17.29 11.27 27.36zM377 105L279.1 7c-4.5-4.5-10.6-7-17-7H256v128h128v-6.1c0-6.3-2.5-12.4-7-16.9z\"><\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Download Dataset<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-fe9b3cb elementor-widget elementor-widget-heading\" data-id=\"fe9b3cb\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Variables<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-e6f2720 elementor-widget elementor-widget-text-editor\" data-id=\"e6f2720\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The following list summarizes the\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/data-set#Variables\">variables<\/a>\u00a0information:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3881adc elementor-widget elementor-widget-heading\" data-id=\"3881adc\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Patient information<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4bb505e elementor-widget elementor-widget-text-editor\" data-id=\"4bb505e\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li data-start=\"294\" data-end=\"395\" style=\"text-align: justify;\">\n<p data-start=\"296\" data-end=\"395\"><strong data-start=\"296\" data-end=\"334\">age at first metastasis diagnostic<\/strong> \u2013 Age at which the first metastasis was diagnosed (years).<\/p>\n<\/li>\n \t<li data-start=\"396\" data-end=\"482\" style=\"text-align: justify;\">\n<p data-start=\"398\" data-end=\"482\"><strong data-start=\"398\" data-end=\"427\">age_at_surgical_procedure<\/strong> \u2013 Age of the patient at the time of surgery (years).<\/p>\n<\/li>\n \t<li data-start=\"483\" data-end=\"530\" style=\"text-align: justify;\">\n<p data-start=\"485\" data-end=\"530\"><strong data-start=\"485\" data-end=\"492\">sex<\/strong> \u2013 Patient sex (e.g., male, female).<\/p>\n<\/li>\n \t<li data-start=\"531\" data-end=\"581\" style=\"text-align: justify;\">\n<p data-start=\"533\" data-end=\"581\"><strong data-start=\"533\" data-end=\"550\">race_category<\/strong> \u2013 Patient race or ethnicity.<\/p>\n<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4b801b5 elementor-widget elementor-widget-heading\" data-id=\"4b801b5\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Tumor characteristics<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-64db05a elementor-widget elementor-widget-text-editor\" data-id=\"64db05a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li data-start=\"611\" data-end=\"693\" style=\"text-align: justify;\">\n<p data-start=\"613\" data-end=\"693\"><strong data-start=\"613\" data-end=\"637\">cancer_type_detailed<\/strong> \u2013 Specific cancer type: colon, rectal, or colorectal.<\/p>\n<\/li>\n \t<li data-start=\"694\" data-end=\"740\" style=\"text-align: justify;\">\n<p data-start=\"696\" data-end=\"740\"><strong data-start=\"696\" data-end=\"714\">cancer_subtype<\/strong> \u2013 Subtype of the tumor.<\/p>\n<\/li>\n \t<li data-start=\"741\" data-end=\"800\" style=\"text-align: justify;\">\n<p data-start=\"743\" data-end=\"800\"><strong data-start=\"743\" data-end=\"765\">primary_tumor_site<\/strong> \u2013 Location of the primary tumor.<\/p>\n<\/li>\n \t<li data-start=\"801\" data-end=\"882\" style=\"text-align: justify;\">\n<p data-start=\"803\" data-end=\"882\"><strong data-start=\"803\" data-end=\"831\">tumour_mutational_burden<\/strong> \u2013 Number of mutations per megabase in the tumor.<\/p>\n<\/li>\n \t<li data-start=\"883\" data-end=\"944\" style=\"text-align: justify;\">\n<p data-start=\"885\" data-end=\"944\"><strong data-start=\"885\" data-end=\"901\">tumor_purity<\/strong> \u2013 Fraction of tumor cells in the sample.<\/p>\n<\/li>\n \t<li data-start=\"945\" data-end=\"1033\" style=\"text-align: justify;\">\n<p data-start=\"947\" data-end=\"1033\"><strong data-start=\"947\" data-end=\"974\">fraction_genome_altered<\/strong> \u2013 Proportion of the genome with copy number alterations.<\/p>\n<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-af4938a elementor-widget elementor-widget-heading\" data-id=\"af4938a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Metastasis information<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-aac0880 elementor-widget elementor-widget-text-editor\" data-id=\"aac0880\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li data-start=\"1064\" data-end=\"1127\" style=\"text-align: justify;\">\n<p data-start=\"1066\" data-end=\"1127\"><strong data-start=\"1066\" data-end=\"1086\">metastasis_count<\/strong> \u2013 Total number of metastases observed.<\/p>\n<\/li>\n \t<li data-start=\"1128\" data-end=\"1215\" style=\"text-align: justify;\">\n<p data-start=\"1130\" data-end=\"1215\"><strong data-start=\"1130\" data-end=\"1163\">metastasis primary site count<\/strong> \u2013 Number of metastases in the primary tumor site.<\/p>\n<\/li>\n \t<li data-start=\"1216\" data-end=\"1312\" style=\"text-align: justify;\">\n<p data-start=\"1218\" data-end=\"1312\"><strong data-start=\"1218\" data-end=\"1254\">microsatellite instability score<\/strong> \u2013 Score indicating level of microsatellite instability.<\/p>\n<\/li>\n \t<li data-start=\"1313\" data-end=\"1399\" style=\"text-align: justify;\">\n<p data-start=\"1315\" data-end=\"1399\"><strong data-start=\"1315\" data-end=\"1350\">microsatellite instability type<\/strong> \u2013 Type of microsatellite instability detected.<\/p>\n<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9d06510 elementor-widget elementor-widget-heading\" data-id=\"9d06510\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Genomic features<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-29caedb elementor-widget elementor-widget-text-editor\" data-id=\"29caedb\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li style=\"text-align: justify;\"><strong>gene variables<\/strong> \u2013 Presence or absence of mutations in each of 492 genes, capturing the tumor\u2019s genomic profile.<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3b13bf7 elementor-widget elementor-widget-heading\" data-id=\"3b13bf7\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Target variable<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-80c1636 elementor-widget elementor-widget-text-editor\" data-id=\"80c1636\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul data-start=\"1402\" data-end=\"1505\">\n \t<li data-start=\"1402\" data-end=\"1505\" style=\"text-align: justify;\">\n<p data-start=\"1404\" data-end=\"1505\"><span style=\"box-sizing: border-box; margin: 0px; padding: 0px;\"><strong>distant_metastasis_liver<\/strong> (yes or no) \u2013 whether liver metastasis is present or not.<\/span><\/p>\n<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-99318b6 elementor-widget elementor-widget-heading\" data-id=\"99318b6\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Variables distributions<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7909af9 elementor-widget elementor-widget-text-editor\" data-id=\"7909af9\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">We can calculate variable\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/data-set#Distributions\">distributions<\/a>; the figure shows a pie chart comparing metastatic versus non-metastatic tumors in the dataset.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8f51ac2 elementor-widget elementor-widget-image\" data-id=\"8f51ac2\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"504\" height=\"380\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-pie-chart.png\" class=\"attachment-large size-large wp-image-19738\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-pie-chart.png 504w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-pie-chart-300x226.png 300w\" sizes=\"(max-width: 504px) 100vw, 504px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7340c51 elementor-widget elementor-widget-text-editor\" data-id=\"7340c51\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">As depicted in the image, liver metastatic tumors represent 57% of the samples, while non-metastatic tumors account for 43%.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b4a7158 elementor-widget elementor-widget-heading\" data-id=\"b4a7158\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Input-target correlations<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ed69da0 elementor-widget elementor-widget-text-editor\" data-id=\"ed69da0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/data-set#InputsTargetsCorrelations\">inputs-targets correlations<\/a> indicate which factors most influence whether a tumor develops liver metastases and, therefore, are more relevant to our analysis.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ae5c6a5 elementor-widget elementor-widget-image\" data-id=\"ae5c6a5\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"686\" height=\"605\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-Pearson-correlations-chart.png\" class=\"attachment-large size-large wp-image-19868\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-Pearson-correlations-chart.png 686w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-Pearson-correlations-chart-300x265.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/distant_metastasis_liver-Pearson-correlations-chart-600x529.png 600w\" sizes=\"(max-width: 686px) 100vw, 686px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1a2cc98 elementor-widget elementor-widget-text-editor\" data-id=\"1a2cc98\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">Here, the most correlated variables with liver metastases are <strong>microsatellite_instability_type<\/strong>, <strong>race_category<\/strong>, and <strong>metastasis_primary_site_count<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d5a91b4 elementor-widget elementor-widget-heading\" data-id=\"d5a91b4\" data-element_type=\"widget\" id=\"neural_network\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">3. Neural network<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a2b6d9b elementor-widget elementor-widget-text-editor\" data-id=\"a2b6d9b\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">A neural network is an artificial intelligence model inspired by the way the human brain processes information. In practice, it organizes information into layers that work sequentially. First, the input layer receives the variables. Then, hidden layers process and transform that information. Finally, the output layer provides the probability that a tumor belongs to a given class. To generate these predictions, the network learns from historical data. Specifically, it identifies patterns that distinguish benign tumors from metastatic ones. As a result, the model can estimate the likelihood of metastasis for new patients.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9ef088f elementor-widget elementor-widget-image\" data-id=\"9ef088f\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"743\" height=\"370\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-11.png\" class=\"attachment-large size-large wp-image-19851\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-11.png 743w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-11-300x149.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-11-600x299.png 600w\" sizes=\"(max-width: 743px) 100vw, 743px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b44d37a elementor-widget elementor-widget-text-editor\" data-id=\"b44d37a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The network uses 497 input variables to output the probability of liver metastasis for each patient, with connections showing each variable\u2019s contribution to the prediction.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-cf2b79a elementor-widget elementor-widget-heading\" data-id=\"cf2b79a\" data-element_type=\"widget\" id=\"training_strategy\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">4. Training strategy<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2a91f9a elementor-widget elementor-widget-text-editor\" data-id=\"2a91f9a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p>Training a neural network involves defining a loss function to measure prediction error and selecting an optimization algorithm to adjust the model parameters. In this way, the network learns from data while maintaining its ability to generalize to new cases.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-dbcba68 elementor-widget elementor-widget-image\" data-id=\"dbcba68\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"424\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-8.png\" class=\"attachment-large size-large wp-image-19828\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-8.png 980w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-8-300x159.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-8-768x408.png 768w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-8-600x318.png 600w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-af2e9d8 elementor-widget elementor-widget-text-editor\" data-id=\"af2e9d8\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p>During training, the model achieved a training error of 0.3969 and a validation error of 0.8127. However, this gap between training and validation performance suggests potential overfitting.<\/p><div class=\"flex flex-col text-sm pb-25\"><article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-698b2975-ded8-832b-81bc-cb10bba74507-19\" data-testid=\"conversation-turn-46\" data-scroll-anchor=\"true\" data-turn=\"assistant\"><div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] @w-sm\/main:[--thread-content-margin:--spacing(6)] @w-lg\/main:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\"><div class=\"[--thread-content-max-width:40rem] @w-lg\/main:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\"><div class=\"flex max-w-full flex-col grow\"><div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"590cd6c2-35d2-44a3-86b2-00302f721110\" data-message-model-slug=\"gpt-5-2\"><div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\"><div class=\"markdown prose dark:prose-invert w-full wrap-break-word light markdown-new-styling\"><p data-start=\"612\" data-end=\"777\" data-is-last-node=\"\" data-is-only-node=\"\">Therefore, we apply input selection to remove irrelevant variables. By doing so, we aim to reduce model complexity and improve generalization on unseen data.<\/p><\/div><\/div><\/div><\/div><\/div><\/div><\/article><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-608e641 elementor-widget elementor-widget-heading\" data-id=\"608e641\" data-element_type=\"widget\" id=\"model_selection\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">5. Model selection<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-31d138d elementor-widget elementor-widget-text-editor\" data-id=\"31d138d\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"235\" data-end=\"483\" style=\"text-align: justify;\">Due to the high number of input neurons and relatively low evaluation metrics, a neuron selection process was performed.<\/p>\n<p data-start=\"485\" data-end=\"811\" style=\"text-align: justify;\">The selection method trains several network architectures with varying numbers of neurons and identifies the configuration that achieves the lowest selection error.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-33c382c elementor-widget elementor-widget-image\" data-id=\"33c382c\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"424\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/selection-errors-plot-1.png\" class=\"attachment-large size-large wp-image-19829\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/selection-errors-plot-1.png 980w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/selection-errors-plot-1-300x159.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/selection-errors-plot-1-768x408.png 768w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/selection-errors-plot-1-600x318.png 600w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-a80be4d elementor-widget elementor-widget-text-editor\" data-id=\"a80be4d\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">After performing input selection, the model was reduced to 34 inputs (by removing less relevant features), which lowered the difference between the training and selection errors, and simplified the network architecture.<\/p>\n\n<p style=\"text-align: justify;\">As shown in the chart, both training error and selection error decrease as the number of inputs is optimized, resulting in a more efficient network with improved performance.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ba196d4 elementor-widget elementor-widget-image\" data-id=\"ba196d4\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"424\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-9.png\" class=\"attachment-large size-large wp-image-19833\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-9.png 980w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-9-300x159.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-9-768x408.png 768w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Quasi-Newton-method-errors-history-9-600x318.png 600w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f847f0d elementor-widget elementor-widget-text-editor\" data-id=\"f847f0d\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The new model was trained for accuracy and stability, with steadily decreasing training and selection errors (1.036 and 0.997 WSE), demonstrating effective learning and strong generalization to new patients.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-efb11bf elementor-widget elementor-widget-heading\" data-id=\"efb11bf\" data-element_type=\"widget\" id=\"testing_analysis\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">6. Testing analysis<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-46abe22 elementor-widget elementor-widget-text-editor\" data-id=\"46abe22\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis\">testing analysis<\/a>\u00a0aims to validate the performance of the generalization properties of the trained neural network.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4800761 elementor-widget elementor-widget-heading\" data-id=\"4800761\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">ROC curve<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4e1d3f6 elementor-widget elementor-widget-text-editor\" data-id=\"4e1d3f6\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis#RocCurve\">ROC curve<\/a> is a standard tool for evaluating classification models, showing how well the model distinguishes between two classes by comparing predicted outcomes with actual results, such as the presence or absence of liver metastasis.<\/p>\n\n<p style=\"text-align: justify;\">A random classifier scores 0.5, while a perfect classifier scores 1.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6392a19 elementor-widget elementor-widget-image\" data-id=\"6392a19\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"540\" height=\"540\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7.png\" class=\"attachment-large size-large wp-image-19834\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7.png 540w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7-300x300.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7-150x150.png 150w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7-100x100.png 100w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-7-120x120.png 120w\" sizes=\"(max-width: 540px) 100vw, 540px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-5f03375 elementor-widget elementor-widget-text-editor\" data-id=\"5f03375\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The\u00a0<strong>AUC<\/strong>\u00a0obtained is\u00a0<strong>0.85<\/strong>, showing that the model performs exceptionally well at distinguishing between patients with metastasis and those without it.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t<div class=\"elementor-element elementor-element-cc6001e e-grid e-con-boxed e-con e-parent\" data-id=\"cc6001e\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-9f9d270 elementor-widget elementor-widget-heading\" data-id=\"9f9d270\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Confusion matrix<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-53160a3 elementor-widget elementor-widget-text-editor\" data-id=\"53160a3\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">The <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis#ConfusionMatrix\">confusion matrix<\/a> shows the model\u2019s performance by comparing predicted and actual outcomes. It includes:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d17f32b elementor-widget elementor-widget-text-editor\" data-id=\"d17f32b\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-08a2cec elementor-widget elementor-widget-text-editor\" data-id=\"08a2cec\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n<ul>\n \t<li data-start=\"190\" data-end=\"255\" style=\"text-align: justify;\">\n<p data-start=\"192\" data-end=\"255\"><strong data-start=\"192\" data-end=\"210\">True positives<\/strong>\u00a0\u2013 patients correctly predicted as deceased<\/p>\n<\/li>\n \t<li data-start=\"256\" data-end=\"324\" style=\"text-align: justify;\">\n<p data-start=\"258\" data-end=\"324\"><strong data-start=\"258\" data-end=\"277\">False positives<\/strong>\u00a0\u2013 patients incorrectly predicted as deceased<\/p>\n<\/li>\n \t<li data-start=\"325\" data-end=\"394\" style=\"text-align: justify;\">\n<p data-start=\"327\" data-end=\"394\"><strong data-start=\"327\" data-end=\"346\">False negatives<\/strong>\u00a0\u2013 patients incorrectly predicted as surviving<\/p>\n<\/li>\n \t<li data-start=\"395\" data-end=\"459\" data-is-last-node=\"\" style=\"text-align: justify;\">\n<p data-start=\"397\" data-end=\"459\" data-is-last-node=\"\"><strong data-start=\"397\" data-end=\"415\">True negatives<\/strong>\u00a0\u2013 patients correctly predicted as surviving<\/p>\n<\/li>\n<\/ul>\n<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f5ef3a6 elementor-widget elementor-widget-text-editor\" data-id=\"f5ef3a6\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">For a decision threshold of 0.5, the confusion matrix was:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-01221c3 e-con-full e-flex e-con e-child\" data-id=\"01221c3\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7cd04b0 elementor-widget elementor-widget-text-editor\" data-id=\"7cd04b0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<table class=\"mi-tabla\" style=\"margin: auto; display: table; border-collapse: collapse;\"><tbody><tr><th>\u00a0<\/th><th>Predicted positive<\/th><th>Predicted negative<\/th><\/tr><tr><th style=\"text-align: left;\">Real positive<\/th><td style=\"text-align: right;\">329<\/td><td style=\"text-align: right;\">73<\/td><\/tr><tr><th style=\"text-align: left;\">Real negative<\/th><td style=\"text-align: right;\">82<\/td><td style=\"text-align: right;\">223<\/td><\/tr><\/tbody><\/table>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-099d079 elementor-widget elementor-widget-heading\" data-id=\"099d079\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Binary classification<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4ee5116 elementor-widget elementor-widget-text-editor\" data-id=\"4ee5116\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-28f8181 elementor-widget elementor-widget-text-editor\" data-id=\"28f8181\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\n<p style=\"text-align: justify;\">Using a classification threshold of 0.3, the performance of this\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis#BinaryClassificationTests\">binary classification<\/a> model is summarized with standard measures.<\/p>\n\n<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b51290c elementor-widget elementor-widget-text-editor\" data-id=\"b51290c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-7936267 elementor-widget elementor-widget-text-editor\" data-id=\"7936267\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n<ul>\n \t<li data-start=\"222\" data-end=\"291\" style=\"text-align: justify;\">\n<p data-start=\"224\" data-end=\"291\"><strong data-start=\"224\" data-end=\"237\">Accuracy:<\/strong> 78.1% of patient outcomes were correctly predicted.<\/p>\n<\/li>\n \t<li data-start=\"292\" data-end=\"345\" style=\"text-align: justify;\">\n<p data-start=\"294\" data-end=\"345\"><strong data-start=\"294\" data-end=\"309\">Error rate:<\/strong> 21.9% of cases were misclassified.<\/p>\n<\/li>\n \t<li data-start=\"346\" data-end=\"419\" style=\"text-align: justify;\">\n<p data-start=\"348\" data-end=\"419\"><strong data-start=\"348\" data-end=\"364\">Sensitivity:<\/strong> 81.8% of deceased patients were correctly identified.<\/p>\n<\/li>\n \t<li data-start=\"420\" data-end=\"493\" style=\"text-align: justify;\">\n<p data-start=\"422\" data-end=\"493\"><strong data-start=\"422\" data-end=\"438\">Specificity:<\/strong> 73.1% of surviving patients were correctly identified.<\/p>\n<\/li>\n<\/ul>\n<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-32c0e10 elementor-widget elementor-widget-text-editor\" data-id=\"32c0e10\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\">These measures indicate that the model is highly effective at predicting patient survival outcomes.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ae43eb0 elementor-widget elementor-widget-heading\" data-id=\"ae43eb0\" data-element_type=\"widget\" id=\"model_deployment\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">7. Model deployment<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-dc72452 elementor-widget elementor-widget-text-editor\" data-id=\"dc72452\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p style=\"text-align: justify;\" data-start=\"51\" data-end=\"171\">Once validated, the neural network can be saved for deployment, allowing clinicians to use patients\u2019 clinical data to predict breast cancer mortality.<\/p><p style=\"text-align: justify;\" data-start=\"51\" data-end=\"171\"><a href=\"https:\/\/www.neuraldesigner.com\/downloads\">Neural Designer<\/a>\u00a0automatically exports the trained model, enabling seamless integration as a diagnostic support tool.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-335b9bb e-con-full e-flex e-con e-child\" data-id=\"335b9bb\" data-element_type=\"container\">\n\t\t<div class=\"elementor-element elementor-element-5e3ecad e-con-full e-flex e-con e-child\" data-id=\"5e3ecad\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-eff1c16 elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"eff1c16\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-button elementor-button-link elementor-size-sm\" href=\"https:\/\/www.neuraldesigner.com\/downloads\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-icon\">\n\t\t\t\t<svg aria-hidden=\"true\" class=\"e-font-icon-svg e-fas-download\" viewBox=\"0 0 512 512\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\"><path d=\"M216 0h80c13.3 0 24 10.7 24 24v168h87.7c17.8 0 26.7 21.5 14.1 34.1L269.7 378.3c-7.5 7.5-19.8 7.5-27.3 0L90.1 226.1c-12.6-12.6-3.7-34.1 14.1-34.1H192V24c0-13.3 10.7-24 24-24zm296 376v112c0 13.3-10.7 24-24 24H24c-13.3 0-24-10.7-24-24V376c0-13.3 10.7-24 24-24h146.7l49 49c20.1 20.1 52.5 20.1 72.6 0l49-49H488c13.3 0 24 10.7 24 24zm-124 88c0-11-9-20-20-20s-20 9-20 20 9 20 20 20 20-9 20-20zm64 0c0-11-9-20-20-20s-20 9-20 20 9 20 20 20 20-9 20-20z\"><\/path><\/svg>\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t<span class=\"elementor-button-text\">Download<\/span>\n\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-25b9723 elementor-widget elementor-widget-heading\" data-id=\"25b9723\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Conclusions<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-fe328fe elementor-widget elementor-widget-text-editor\" data-id=\"fe328fe\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"150\" data-end=\"537\" style=\"text-align: justify;\">The machine learning model predicts liver metastasis in colon cancer patients with 78% accuracy and 0.85 AUC.<\/p>\n<p data-start=\"150\" data-end=\"537\" style=\"text-align: justify;\">Key factors\u2014metastasis count, primary site involvement, and mutations in KIT, RB1, and PIK3R1\u2014align with known clinical markers.<\/p>\n<p data-start=\"150\" data-end=\"537\" style=\"text-align: justify;\">Its strong generalization makes it a valuable tool to support risk assessment, clinical decision-making, and treatment planning.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6e69b55 elementor-widget elementor-widget-heading\" data-id=\"6e69b55\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">References<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2ba0f55 elementor-widget elementor-widget-text-editor\" data-id=\"2ba0f55\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul>\n \t<li style=\"text-align: justify;\">The data for this problem has been taken from the <a href=\"https:\/\/www.cbioportal.org\/\">cBioportal Repository MSK-MET (Memorial Sloan Kettering &#8211; Metastatic Events and Tropisms) dataset<\/a>.<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9445824 elementor-widget elementor-widget-heading\" data-id=\"9445824\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Related posts<\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"author":19,"featured_media":1984,"template":"","categories":[29],"tags":[38],"class_list":["post-3475","learning","type-learning","status-publish","has-post-thumbnail","hentry","category-examples","tag-healthcare"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Metastasis prediction using machine learning<\/title>\n<meta name=\"description\" content=\"Build a machine learning model to assess colorectal cancer patients&#039; risk of liver metastasis using clinical and mutational data.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Colon cancer liver metastasis machine learning example\" \/>\n<meta property=\"og:description\" content=\"This example aims to assess the probability to suffer liver metastasis in colorectal patients from mutational data.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"Neural Designer\" \/>\n<meta property=\"article:modified_time\" content=\"2026-02-11T10:53:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"628\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Colon cancer liver metastasis machine learning example\" \/>\n<meta name=\"twitter:description\" content=\"This example aims to assess the probability to suffer liver metastasis in colorectal patients from mutational data.\" \/>\n<meta name=\"twitter:site\" content=\"@NeuralDesigner\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/\",\"name\":\"Metastasis prediction using machine learning\",\"isPartOf\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp\",\"datePublished\":\"2025-09-03T09:12:59+00:00\",\"dateModified\":\"2026-02-11T10:53:37+00:00\",\"description\":\"Build a machine learning model to assess colorectal cancer patients' risk of liver metastasis using clinical and mutational data.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp\",\"width\":1200,\"height\":628},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.neuraldesigner.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Learning\",\"item\":\"https:\/\/www.neuraldesigner.com\/learning\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Metastasis prediction using machine learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\",\"url\":\"https:\/\/www.neuraldesigner.com\/\",\"name\":\"Neural Designer\",\"description\":\"Explanable AI Platform\",\"publisher\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.neuraldesigner.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#organization\",\"name\":\"Neural Designer\",\"url\":\"https:\/\/www.neuraldesigner.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png\",\"width\":1024,\"height\":223,\"caption\":\"Neural Designer\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/NeuralDesigner\",\"https:\/\/es.linkedin.com\/showcase\/neuraldesigner\/\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Metastasis prediction using machine learning","description":"Build a machine learning model to assess colorectal cancer patients' risk of liver metastasis using clinical and mutational data.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/","og_locale":"en_US","og_type":"article","og_title":"Colon cancer liver metastasis machine learning example","og_description":"This example aims to assess the probability to suffer liver metastasis in colorectal patients from mutational data.","og_url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/","og_site_name":"Neural Designer","article_modified_time":"2026-02-11T10:53:37+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp","type":"image\/webp"}],"twitter_card":"summary_large_image","twitter_title":"Colon cancer liver metastasis machine learning example","twitter_description":"This example aims to assess the probability to suffer liver metastasis in colorectal patients from mutational data.","twitter_site":"@NeuralDesigner","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/","url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/","name":"Metastasis prediction using machine learning","isPartOf":{"@id":"https:\/\/www.neuraldesigner.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage"},"thumbnailUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp","datePublished":"2025-09-03T09:12:59+00:00","dateModified":"2026-02-11T10:53:37+00:00","description":"Build a machine learning model to assess colorectal cancer patients' risk of liver metastasis using clinical and mutational data.","breadcrumb":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#primaryimage","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/liver_met_mutation2.webp","width":1200,"height":628},{"@type":"BreadcrumbList","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/metastasis-prediction-machine-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.neuraldesigner.com\/"},{"@type":"ListItem","position":2,"name":"Learning","item":"https:\/\/www.neuraldesigner.com\/learning\/"},{"@type":"ListItem","position":3,"name":"Metastasis prediction using machine learning"}]},{"@type":"WebSite","@id":"https:\/\/www.neuraldesigner.com\/#website","url":"https:\/\/www.neuraldesigner.com\/","name":"Neural Designer","description":"Explanable AI Platform","publisher":{"@id":"https:\/\/www.neuraldesigner.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.neuraldesigner.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.neuraldesigner.com\/#organization","name":"Neural Designer","url":"https:\/\/www.neuraldesigner.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png","width":1024,"height":223,"caption":"Neural Designer"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/NeuralDesigner","https:\/\/es.linkedin.com\/showcase\/neuraldesigner\/"]}]}},"_links":{"self":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3475","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning"}],"about":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/types\/learning"}],"author":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/users\/19"}],"version-history":[{"count":8,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3475\/revisions"}],"predecessor-version":[{"id":21887,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3475\/revisions\/21887"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media\/1984"}],"wp:attachment":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media?parent=3475"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/categories?post=3475"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/tags?post=3475"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}