{"id":3504,"date":"2025-09-02T11:12:58","date_gmt":"2025-09-02T09:12:58","guid":{"rendered":"https:\/\/neuraldesigner.com\/learning\/leukemia-microarray\/"},"modified":"2026-02-11T12:01:08","modified_gmt":"2026-02-11T11:01:08","slug":"leukemia-microarray","status":"publish","type":"learning","link":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/","title":{"rendered":"Machine learning leukemia diagnosis from microarray data"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"3504\" class=\"elementor elementor-3504\" data-elementor-post-type=\"learning\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-1d0f7a7f elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"1d0f7a7f\" 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-28f50669\" data-id=\"28f50669\" 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-a2de5b6 elementor-widget elementor-widget-heading\" data-id=\"a2de5b6\" 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-1c36200 elementor-widget elementor-widget-text-editor\" data-id=\"1c36200\" 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=\"115\" data-end=\"309\">Accurate differentiation between acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) is critical, since treatment approaches and outcomes vary significantly.<\/p><p style=\"text-align: justify;\" data-start=\"311\" data-end=\"652\">Although gene expression data can support this diagnosis, classification is challenging because of the large number of genes and subtle expression differences.<\/p><p style=\"text-align: justify;\" data-start=\"311\" data-end=\"652\">In this study, we trained a neural network using gene expression profiles from 7,129 genes across 72 patients, applying feature selection to identify the most informative markers.<\/p><p style=\"text-align: justify;\" data-start=\"654\" data-end=\"871\">This machine learning approach demonstrates strong potential to assist physicians in leukemia diagnosis and treatment planning.<\/p><p style=\"text-align: justify;\" data-start=\"654\" data-end=\"871\">Healthcare professionals can test the methodology with Neural Designer.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-1c75dc4 e-flex e-con-boxed e-con e-parent\" data-id=\"1c75dc4\" 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-93880ec elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"93880ec\" 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\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3134b09 elementor-widget elementor-widget-heading\" data-id=\"3134b09\" 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-fec118a elementor-widget elementor-widget-text-editor\" data-id=\"fec118a\" 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-4cb602e e-grid e-con-boxed e-con e-parent\" data-id=\"4cb602e\" 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-0058494 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"0058494\" 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-8a8acfc elementor-align-center elementor-widget elementor-widget-button\" data-id=\"8a8acfc\" 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-3435123 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"3435123\" 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-7fe1d79 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"7fe1d79\" 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-1c001e1 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"1c001e1\" 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-19ffec3 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"19ffec3\" 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-2ac3729 elementor-align-center elementor-widget elementor-widget-button\" data-id=\"2ac3729\" 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\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-17c9c90 elementor-widget elementor-widget-heading\" data-id=\"17c9c90\" 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-f9be74b elementor-widget elementor-widget-text-editor\" data-id=\"f9be74b\" 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;\">\n<p data-start=\"151\" data-end=\"262\"><strong data-start=\"151\" data-end=\"168\">Problem type:<\/strong> Binary <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/neural-networks-applications#Classification\">classification<\/a> (acute lymphoblastic leukemia [ALL] vs. acute myeloid leukemia [AML])<\/p>\n<\/li>\n \t<li style=\"text-align: justify;\">\n<p data-start=\"151\" data-end=\"262\"><strong data-start=\"264\" data-end=\"273\">Goal:<\/strong> Model the probability of a patient having AML based on gene expression data obtained from microarray analysis to support clinical decision-making<\/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-d2b6ca7 elementor-widget elementor-widget-heading\" data-id=\"d2b6ca7\" 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-85cce9e elementor-widget elementor-widget-heading\" data-id=\"85cce9e\" 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-010a453 elementor-widget elementor-widget-text-editor\" data-id=\"010a453\" 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 leukemiamicroarray.csv dataset includes 7129 genes and 72 patients, with ALL and AML case distributions.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-c670bc7 e-flex e-con-boxed e-con e-parent\" data-id=\"c670bc7\" 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-cfa7e8d elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"cfa7e8d\" 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\/2025\/09\/leukemiamicroarray.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\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c3bfc13 elementor-widget elementor-widget-heading\" data-id=\"c3bfc13\" 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-23beefa elementor-widget elementor-widget-text-editor\" data-id=\"23beefa\" 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 variables&#8217; information:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c796490 elementor-widget elementor-widget-heading\" data-id=\"c796490\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h4 class=\"elementor-heading-title elementor-size-default\">Genetic expression<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b549653 elementor-widget elementor-widget-text-editor\" data-id=\"b549653\" 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 1 \u2013 Gene 7129 (0\u20131):<\/strong> Normalized gene expression levels obtained from microarray analysis, where values near 0 indicate low expression and values near 1 indicate high expression.<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7934b98 elementor-widget elementor-widget-text-editor\" data-id=\"7934b98\" 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;\">Some genes show higher correlation with leukemia type:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b4888a4 elementor-widget elementor-widget-text-editor\" data-id=\"b4888a4\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul data-start=\"741\" data-end=\"968\">\n \t<li data-start=\"741\" data-end=\"807\" style=\"text-align: justify;\">\n<p data-start=\"743\" data-end=\"807\"><strong data-start=\"743\" data-end=\"756\">Gene 4847<\/strong> \u2013 Perfectly correlated with the target variable.<\/p>\n<\/li>\n \t<li data-start=\"808\" data-end=\"874\" style=\"text-align: justify;\">\n<p data-start=\"810\" data-end=\"874\"><strong data-start=\"810\" data-end=\"823\">Gene 2288<\/strong> \u2013 Perfectly correlated with the target variable.<\/p>\n<\/li>\n \t<li data-start=\"875\" data-end=\"968\" style=\"text-align: justify;\">\n<p data-start=\"877\" data-end=\"968\">Other genes \u2013 Varying degrees of correlation, potentially contributing to classification.<\/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-377066b elementor-widget elementor-widget-heading\" data-id=\"377066b\" 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-c40cf12 elementor-widget elementor-widget-text-editor\" data-id=\"c40cf12\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<ul data-start=\"992\" data-end=\"1095\">\n \t<li data-start=\"992\" data-end=\"1095\" style=\"text-align: justify;\">\n<p data-start=\"994\" data-end=\"1095\"><strong data-start=\"994\" data-end=\"1015\">diagnose (ALL or AML)<\/strong> \u2013 Acute lymphoblastic leukemia (ALL) or acute myeloid leukemia (AML).<\/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-a025352 elementor-widget elementor-widget-heading\" data-id=\"a025352\" 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-13d621d elementor-widget elementor-widget-text-editor\" data-id=\"13d621d\" 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 examine variable <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/data-set#Distributions\">distributions<\/a>; the figure shows a pie chart of total cases, distinguishing AML and AML instances.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-65de6cd elementor-widget elementor-widget-image\" data-id=\"65de6cd\" 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=\"511\" height=\"380\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Leukemia_class-pie-chart.png\" class=\"attachment-large size-large wp-image-19698\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Leukemia_class-pie-chart.png 511w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Leukemia_class-pie-chart-300x223.png 300w\" sizes=\"(max-width: 511px) 100vw, 511px\" \/>\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-7b18e3b elementor-widget elementor-widget-text-editor\" data-id=\"7b18e3b\" 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, ALL cases represent 31.95% of the samples, while AML cases represent approximately 68.06%.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-726f531 elementor-widget elementor-widget-heading\" data-id=\"726f531\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h3 class=\"elementor-heading-title elementor-size-default\">Inputs-targets correlations<\/h3>\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4481208 elementor-widget elementor-widget-text-editor\" data-id=\"4481208\" 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\" target=\"_blank\" rel=\"noopener\">inputs-targets correlations<\/a> indicate which factors most influence whether a patient has AML or AML 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-a8ce020 elementor-widget elementor-widget-image\" data-id=\"a8ce020\" 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=\"600\" height=\"810\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/leukemia_correlations_chart.webp\" class=\"attachment-large size-large wp-image-16492\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/leukemia_correlations_chart.webp 600w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/leukemia_correlations_chart-222x300.webp 222w\" sizes=\"(max-width: 600px) 100vw, 600px\" \/>\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-afd54e9 elementor-widget elementor-widget-text-editor\" data-id=\"afd54e9\" 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 we can see in the previous figure, some genes have a high correlation with the diagnosis. The genes 4847 and 2288 perfectly correlate with the target variable.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f562c8d elementor-widget elementor-widget-text-editor\" data-id=\"f562c8d\" 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;\">This correlation means that these genes greatly impact the target variable.<\/p>\n\n<p style=\"text-align: justify;\">To do that, their values must be logistically separable. A certain probability is attached to the random logistical separability of a column with 72 values. It obeys the formula:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d4a7eb5 elementor-widget elementor-widget-image\" data-id=\"d4a7eb5\" 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=\"792\" height=\"130\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/random-logistic-probability-equation-leukemia-microarrays.webp\" class=\"attachment-large size-large wp-image-16491\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/random-logistic-probability-equation-leukemia-microarrays.webp 792w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/random-logistic-probability-equation-leukemia-microarrays-300x49.webp 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/random-logistic-probability-equation-leukemia-microarrays-768x126.webp 768w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/random-logistic-probability-equation-leukemia-microarrays-600x98.webp 600w\" sizes=\"(max-width: 792px) 100vw, 792px\" \/>\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-0791ce5 elementor-widget elementor-widget-text-editor\" data-id=\"0791ce5\" 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;\">n<sub>1<\/sub> and n<sub>2<\/sub> are the total number of values of AML and ALL, respectively.<\/p>\n\n<p style=\"text-align: justify;\">This would mean that, for a dataset similar to ours, but with its values set randomly, there may be 1.831\u00b710<sup>-15<\/sup> of the variables that are very correlated only by chance and not by actual correlation. In this case, that number is very small and doesn&#8217;t affect our conclusions.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-8eb2e97 elementor-widget elementor-widget-heading\" data-id=\"8eb2e97\" 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-dd69f86 elementor-widget elementor-widget-text-editor\" data-id=\"dd69f86\" 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 neural network is an artificial intelligence model designed to recognize patterns in clinical and genetic data.<\/p>\n\n<p style=\"text-align: justify;\">It processes the data through scaling and probabilistic layers to calculate the probability that a patient has leukemia.<\/p>\n\n<p style=\"text-align: justify;\">This probability provides healthcare professionals with an objective measure to guide further tests or early interventions, effectively distinguishing between patients with ALL and AML.<\/p>\n\n<p style=\"text-align: justify;\">The network itself is not shown due to the large number of input variables.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3acb392 elementor-widget elementor-widget-heading\" data-id=\"3acb392\" 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-c2d1f1c elementor-widget elementor-widget-text-editor\" data-id=\"c2d1f1c\" 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;\">Training a neural network for leukemia classification involves a loss function and optimization algorithm to learn while avoiding overfitting.<\/p>\n\n<p style=\"text-align: justify;\">Given the large number of variables, the model has not yet been trained; once carefully selected and trained, it will accurately distinguish ALL from AML, supporting clinical decisions.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0bb548f elementor-widget elementor-widget-heading\" data-id=\"0bb548f\" 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-5a6fe4e elementor-widget elementor-widget-text-editor\" data-id=\"5a6fe4e\" 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 objective of\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/model-selection\">model selection<\/a>\u00a0is to find the network architecture with the best generalization properties, which minimizes the error on the\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/data-set#SelectionInstances\">selected instances<\/a>\u00a0of the data set.<\/p>\n\n<p style=\"text-align: justify;\">Given that the selection error we have achieved so far is minimal at 0.233, we don\u2019t need to apply <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/model-selection#OrderSelection\">order selection<\/a>\u00a0or\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/model-selection#InputsSelection\">input selection<\/a>\u00a0here.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f2a1b69 elementor-widget elementor-widget-image\" data-id=\"f2a1b69\" 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=\"690\" height=\"130\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-4.png\" class=\"attachment-large size-large wp-image-19312\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-4.png 690w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-4-300x57.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/Network-architecture-4-600x113.png 600w\" sizes=\"(max-width: 690px) 100vw, 690px\" \/>\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-f284615 elementor-widget elementor-widget-text-editor\" data-id=\"f284615\" 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 final training and selection errors are <b>training error = 0.039 WSE<\/b>\u00a0and\u00a0<b>selection error = 0.233 WSE<\/b>, respectively.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f02cfb5 elementor-widget elementor-widget-heading\" data-id=\"f02cfb5\" 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-a4a4d54 elementor-widget elementor-widget-text-editor\" data-id=\"a4a4d54\" 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 objective of the\u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis\">testing analysis<\/a>\u00a0is to validate the generalization performance 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-42ee60d elementor-widget elementor-widget-heading\" data-id=\"42ee60d\" 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-f9d8e27 elementor-widget elementor-widget-text-editor\" data-id=\"f9d8e27\" 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 to evaluate a classification model, showing how well it distinguishes between two classes by comparing predicted results with actual outcomes, such as patients with ALL or AML.<\/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-e3f73ec elementor-widget elementor-widget-image\" data-id=\"e3f73ec\" 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-5.png\" class=\"attachment-large size-large wp-image-19313\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-5.png 540w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-5-300x300.png 300w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-5-150x150.png 150w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-5-100x100.png 100w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/ROC-chart-5-120x120.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-afd61af elementor-widget elementor-widget-text-editor\" data-id=\"afd61af\" 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 <strong>AUC<\/strong> is <strong>1<\/strong>, showing that the model performs exceptionally well at distinguishing between patients with ALL and AML.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c9399ba elementor-widget elementor-widget-heading\" data-id=\"c9399ba\" 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-11c3c9c elementor-widget elementor-widget-text-editor\" data-id=\"11c3c9c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"67\" data-end=\"180\" style=\"text-align: justify;\">The \u00a0<a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis#ConfusionMatrix\">confusion matrix<\/a>\u00a0shows the model\u2019s performance by comparing predicted and actual diagnoses. It includes:<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4aa496f elementor-widget elementor-widget-text-editor\" data-id=\"4aa496f\" 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=\"182\" data-end=\"254\" style=\"text-align: justify;\">\n<p data-start=\"184\" data-end=\"254\"><strong data-start=\"184\" data-end=\"203\">True positives:<\/strong> patients correctly identified as having leukemia<\/p>\n<\/li>\n \t<li data-start=\"255\" data-end=\"330\" style=\"text-align: justify;\">\n<p data-start=\"257\" data-end=\"330\"><strong data-start=\"257\" data-end=\"277\">False positives:<\/strong> patients incorrectly identified as having leukemia<\/p>\n<\/li>\n \t<li data-start=\"331\" data-end=\"418\" style=\"text-align: justify;\">\n<p data-start=\"333\" data-end=\"418\"><strong data-start=\"333\" data-end=\"353\">False negatives:<\/strong> patients with leukemia incorrectly identified as not having it<\/p>\n<\/li>\n \t<li data-start=\"419\" data-end=\"498\" style=\"text-align: justify;\">\n<p data-start=\"421\" data-end=\"498\"><strong data-start=\"421\" data-end=\"440\">True negatives:<\/strong> patients correctly identified as not having leukemia<\/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-52350f9 elementor-widget elementor-widget-text-editor\" data-id=\"52350f9\" 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-8bb2b74 e-flex e-con-boxed e-con e-parent\" data-id=\"8bb2b74\" 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-225fbc2 elementor-widget elementor-widget-text-editor\" data-id=\"225fbc2\" 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;\">5<\/td><td style=\"text-align: right;\">0<\/td><\/tr><tr><th style=\"text-align: left;\">Real negative<\/th><td style=\"text-align: right;\">0<\/td><td style=\"text-align: right;\">9<\/td><\/tr><\/tbody><\/table>\t\t\t\t\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-a3db55d elementor-widget elementor-widget-text-editor\" data-id=\"a3db55d\" 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;\">In this case, <b>100% <\/b>of cases were\u00a0<strong>correctly classified<\/strong>\u00a0and\u00a0<strong>0%<\/strong> were\u00a0\u00a0<strong>misclassified<\/strong>.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-4bb55e6 elementor-widget elementor-widget-text-editor\" data-id=\"4bb55e6\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<h3>Binary classification<\/h3>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-7fac91a elementor-widget elementor-widget-text-editor\" data-id=\"7fac91a\" 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 performance of this <a href=\"https:\/\/www.neuraldesigner.com\/learning\/tutorials\/testing-analysis#BinaryClassificationTests\">binary classification<\/a> model is summarized with standard measures.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3efcd32 elementor-widget elementor-widget-text-editor\" data-id=\"3efcd32\" 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=\"204\" data-end=\"266\" style=\"text-align: justify;\">\n<p data-start=\"206\" data-end=\"266\"><strong data-start=\"206\" data-end=\"219\">Accuracy:<\/strong> 100% of patients were correctly classified.<\/p>\n<\/li>\n \t<li data-start=\"267\" data-end=\"320\" style=\"text-align: justify;\">\n<p data-start=\"269\" data-end=\"320\"><strong data-start=\"269\" data-end=\"284\">Error rate:<\/strong> 0% of cases were misclassified.<\/p>\n<\/li>\n \t<li data-start=\"321\" data-end=\"399\" style=\"text-align: justify;\">\n<p data-start=\"323\" data-end=\"399\"><strong data-start=\"323\" data-end=\"339\">Sensitivity:<\/strong> 100% of patients with leukemia were correctly identified.<\/p>\n<\/li>\n \t<li data-start=\"400\" data-end=\"480\" style=\"text-align: justify;\">\n<p data-start=\"402\" data-end=\"480\"><strong data-start=\"402\" data-end=\"418\">Specificity:<\/strong> 100% of patients without leukemia were correctly identified.<\/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-0572347 elementor-widget elementor-widget-text-editor\" data-id=\"0572347\" 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 distinguishing between patients with ALL and AML.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0f7c475 elementor-widget elementor-widget-heading\" data-id=\"0f7c475\" 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-e133bef elementor-widget elementor-widget-text-editor\" data-id=\"e133bef\" 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;\">Once validated, the neural network can be deployed to predict ALL or AML from new patient gene expression data, providing reliable diagnostic support.<\/p>\n\n<p style=\"text-align: justify;\">Although the network cannot be practically visualized due to the large number of genes, it can be automatically exported from <a href=\"https:\/\/www.neuraldesigner.com\/my-account\/\">Neural Designer<\/a> for use on new datasets.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-666447d e-grid e-con-boxed e-con e-parent\" data-id=\"666447d\" data-element_type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t<div class=\"elementor-element elementor-element-3581417 e-con-full e-flex e-con e-child\" data-id=\"3581417\" data-element_type=\"container\">\n\t\t\t\t<div class=\"elementor-element elementor-element-acf0dae elementor-widget__width-initial boton_descarga elementor-widget-mobile__width-initial elementor-widget elementor-widget-button\" data-id=\"acf0dae\" 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-35fea6f elementor-widget elementor-widget-heading\" data-id=\"35fea6f\" 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-c23644a elementor-widget elementor-widget-text-editor\" data-id=\"c23644a\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t\t\t\t\t\t<p data-start=\"208\" data-end=\"462\" style=\"text-align: justify;\">The leukemia diagnosis model, developed from gene expression data, achieved perfect performance (AUC = 1, accuracy = 100%), accurately distinguishing ALL from AML.<\/p>\n<p data-start=\"208\" data-end=\"462\" style=\"text-align: justify;\">Specific gene markers, such as 4847 and 2288, were strongly associated with leukemia type, aligning with current medical knowledge.<\/p>\n<p data-start=\"208\" data-end=\"462\" style=\"text-align: justify;\">This machine learning model can support early and precise classification, complementing traditional diagnostics and guiding treatment decisions.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6d9447a elementor-widget elementor-widget-heading\" data-id=\"6d9447a\" 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-bbd5806 elementor-widget elementor-widget-text-editor\" data-id=\"bbd5806\" 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;\">Golub,T.R., Slonim,D.K., Tamayo,P., &#8220;Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring&#8221;, Science, Vol. 286, pp. 531-537 (1998).<\/li>\n<\/ul>\t\t\t\t\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-3dde712 e-grid e-con-boxed e-con e-parent\" data-id=\"3dde712\" 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-ba0d757 elementor-widget elementor-widget-text-editor\" data-id=\"ba0d757\" 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 development of this application has been funded by the <a href=\"https:\/\/nemhesys.usal.es\/\">NEMHESYS &#8211; NGS Establishment in Multidisciplinary Healthcare Education System<\/a> project.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b4f08d7 elementor-widget elementor-widget-image\" data-id=\"b4f08d7\" 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=\"431\" height=\"115\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/references.png\" class=\"attachment-large size-large wp-image-16488\" alt=\"\" srcset=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/references.png 431w, https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/08\/references-300x80.png 300w\" sizes=\"(max-width: 431px) 100vw, 431px\" \/>\t\t\t\t\t\t\t\t\t\t\t\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-749af69 elementor-widget elementor-widget-heading\" data-id=\"749af69\" 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<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"author":13,"featured_media":1926,"template":"","categories":[29],"tags":[38],"class_list":["post-3504","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>Machine learning leukemia diagnosis from microarray data<\/title>\n<meta name=\"description\" content=\"Build a machine learning model to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding.\" \/>\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\/leukemia-microarray\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Leukemia diagnosis from microarray data using machine learning\" \/>\n<meta property=\"og:description\" content=\"The purpose of this example is to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding using machine learning.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/\" \/>\n<meta property=\"og:site_name\" content=\"Neural Designer\" \/>\n<meta property=\"article:modified_time\" content=\"2026-02-11T11:01:08+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.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=\"Leukemia diagnosis from microarray data using machine learning\" \/>\n<meta name=\"twitter:description\" content=\"The purpose of this example is to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding using machine learning.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp\" \/>\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\/leukemia-microarray\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/\",\"name\":\"Machine learning leukemia diagnosis from microarray data\",\"isPartOf\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp\",\"datePublished\":\"2025-09-02T09:12:58+00:00\",\"dateModified\":\"2026-02-11T11:01:08+00:00\",\"description\":\"Build a machine learning model to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp\",\"width\":1200,\"height\":628},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#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\":\"Machine learning leukemia diagnosis from microarray data\"}]},{\"@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":"Machine learning leukemia diagnosis from microarray data","description":"Build a machine learning model to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding.","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\/leukemia-microarray\/","og_locale":"en_US","og_type":"article","og_title":"Leukemia diagnosis from microarray data using machine learning","og_description":"The purpose of this example is to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding using machine learning.","og_url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/","og_site_name":"Neural Designer","article_modified_time":"2026-02-11T11:01:08+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp","type":"image\/webp"}],"twitter_card":"summary_large_image","twitter_title":"Leukemia diagnosis from microarray data using machine learning","twitter_description":"The purpose of this example is to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding using machine learning.","twitter_image":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp","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\/leukemia-microarray\/","url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/","name":"Machine learning leukemia diagnosis from microarray data","isPartOf":{"@id":"https:\/\/www.neuraldesigner.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage"},"thumbnailUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp","datePublished":"2025-09-02T09:12:58+00:00","dateModified":"2026-02-11T11:01:08+00:00","description":"Build a machine learning model to diagnose the leukemia of patients, ALL or AML, depending on their DNA coding.","breadcrumb":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#primaryimage","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/microarray-example.webp","width":1200,"height":628},{"@type":"BreadcrumbList","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/leukemia-microarray\/#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":"Machine learning leukemia diagnosis from microarray data"}]},{"@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\/3504","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\/13"}],"version-history":[{"count":4,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3504\/revisions"}],"predecessor-version":[{"id":21894,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3504\/revisions\/21894"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media\/1926"}],"wp:attachment":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media?parent=3504"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/categories?post=3504"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/tags?post=3504"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}