{"id":3468,"date":"2025-08-28T11:13:00","date_gmt":"2025-08-28T09:13:00","guid":{"rendered":"https:\/\/neuraldesigner.com\/learning\/breast-cancer-diagnosis\/"},"modified":"2026-08-12T11:21:41","modified_gmt":"2026-08-12T09:21:41","slug":"breast-cancer-diagnosis","status":"publish","type":"learning","link":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/","title":{"rendered":"Breast Cancer Diagnosis Machine Learning"},"content":{"rendered":"<style>\n.nds{--nds-code-bg:#f3f7fa;--nds-code-fg:#12354b;width:100vw;margin-left:calc(50% - 50vw);padding:22px 24px 14px;background:#eee;color:#1b2635;font-family:\"Outfit\",\"Roboto\",Arial,sans-serif}\n.nds *{box-sizing:border-box}.nds-wrap{width:min(100%,1200px);margin:0 auto}.nds a{text-decoration:none;color:#2d799f}\n.nds-executive{margin:0 0 34px;padding:32px;border-radius:20px;background:linear-gradient(135deg,#12354b,#245e80);color:#fff}.nds-executive h2{margin:0 0 12px;color:#fff;font-size:30px}.nds-executive p{font-size:18px;line-height:1.55}\n.nds-kpis{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:14px;margin-top:22px}.nds-kpi{padding:18px;border:1px solid rgba(255,255,255,.18);border-radius:14px;background:rgba(255,255,255,.1)}.nds-kpi strong{display:block;font-size:25px}.nds-kpi span{font-size:13px}\n.nds-actions,.nds-audience,.nds-downloads{display:flex;flex-wrap:wrap;justify-content:center;gap:12px;margin:22px 0}.nds-actions a,.nds-downloads a{padding:12px 20px;border-radius:24px;background:#245e80;color:#fff;font-weight:700}.nds-executive .nds-actions a{background:#fff;color:#12354b}\n.nds-toc{display:flex;flex-wrap:wrap;justify-content:center;gap:10px;margin:0 0 42px;padding:0;list-style:none}.nds-toc a,.nds-audience span{display:block;padding:9px 14px;border-radius:20px;background:#e9f2f8;color:#12354b;font-weight:600}\n.nds-card{margin:0 0 54px;scroll-margin-top:90px}.nds-card h2{margin:0 0 20px;padding-bottom:12px;border-bottom:1px solid #dbe5ec;color:#001233;font-size:24px}.nds-card p,.nds-card li{font-size:16.5px;line-height:1.6}.nds-card img{display:block;width:auto;max-width:min(640px,100%);height:auto;margin:24px auto;border-radius:12px}.nds-card img.nds-architecture{width:min(1000px,100%);max-width:100%}\n.nds-value-grid{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:16px;margin:22px 0}.nds-value{padding:20px;border:1px solid #dce8ef;border-radius:14px;background:#f8fbfd}.nds-note{margin:20px 0;padding:18px 20px;border-left:4px solid #56a1c8;border-radius:0 12px 12px 0;background:#f6fafc}.nds-note--warning,.nds-use-boundary{border-left-color:#d79a29;background:#fff9ed}\n.nds-table-scroll{max-width:100%;overflow-x:auto}.nds-card table{width:auto;max-width:100%;margin:24px auto;border-collapse:collapse;background:#fff}.nds-card th,.nds-card td{padding:11px 16px;border-bottom:1px solid #e2e9ee}.nds-card thead th{background:#12354b!important;color:#fff!important}.nds-card tbody th{background:#eaf2f6!important;color:#12354b!important;text-align:left}.nds-card tbody tr:nth-child(even) th{background:#f4f8fa!important}.nds-card tbody td{color:#33424f!important}\n.nds-figure-grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:20px}.nds-figure-grid figure,.nds-architecture-figure{margin:0;padding:16px;border:1px solid #dce8ef;border-radius:15px;background:#f8fbfd}.nds-figure-grid img{width:100%;max-width:100%;margin:0 auto 12px}.nds-card figcaption{color:#405361;font-size:14px;line-height:1.45}\n.nds pre,.nds .wp-block-code,.nds pre[class*=\"language-\"]{display:block;max-width:100%;overflow:auto;padding:18px 20px!important;border:1px solid #d5e2e9!important;border-radius:12px!important;background:var(--nds-code-bg)!important;color:var(--nds-code-fg)!important;box-shadow:none!important;text-shadow:none!important;white-space:pre}\n.nds pre code,.nds pre code *,.nds .wp-block-code code,.nds .wp-block-code code *{border:0!important;background:transparent!important;color:var(--nds-code-fg)!important;box-shadow:none!important;text-shadow:none!important;font-family:Consolas,\"Liberation Mono\",monospace!important;font-size:14px;line-height:1.55}\n.nds :not(pre)>code{padding:.08em .32em;border-radius:4px;background:#e6eef3!important;color:#12354b!important}.nds .nds-expression{max-width:100%;overflow:auto;margin:22px auto;padding:18px 20px;border:1px solid #d5e2e9;border-radius:12px;background:#fff!important;color:#12354b!important;text-align:center}.nds .nds-expression math,.nds .nds-expression mjx-container,.nds .nds-expression .MathJax{background:transparent!important;color:#12354b!important}\n@media(max-width:820px){.nds-kpis{grid-template-columns:repeat(2,minmax(0,1fr))}.nds-value-grid{grid-template-columns:1fr}}@media(max-width:620px){.nds{padding:12px 14px}.nds-kpis,.nds-figure-grid{grid-template-columns:1fr}.nds-executive{padding:24px 20px}.nds-card table{font-size:13px}.nds-card th,.nds-card td{padding:9px 8px}}\n<\/style>\n<style>\n.nds-card h3{margin:27px 0 12px;color:#12354b;font-size:20px}.nds-centered-figure{width:min(720px,100%);margin:24px auto;padding:16px;border:1px solid #dce8ef;border-radius:15px;background:#f8fbfd}.nds-centered-figure img{width:100%;max-width:100%;margin:0 auto 12px}.nds-roc-figure{width:min(600px,100%);margin:24px auto;padding:16px;border:1px solid #dce8ef;border-radius:15px;background:#f8fbfd}.nds-roc-figure img{width:100%;max-width:100%;margin:0 auto 12px}.nds-validation-grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:22px;align-items:start}.nds-flow{display:grid;grid-template-columns:repeat(6,minmax(0,1fr));gap:10px;margin:24px 0}.nds-flow div{position:relative;display:flex;min-height:106px;align-items:center;justify-content:center;padding:14px 9px;border-radius:13px;background:#12354b;color:#fff;text-align:center;font-weight:700}.nds-flow div:not(:last-child):after{content:\"\u2192\";position:absolute;right:-15px;top:50%;z-index:2;transform:translateY(-50%);color:#56a1c8;font-size:21px}.nds-metrics td:nth-child(2),.nds-confusion td{text-align:right;font-variant-numeric:tabular-nums}.nds-calculator{margin:30px 0;padding:24px;border:1px solid #cfe1eb;border-radius:18px;background:#f7fbfd}.nds-calculator-grid{display:grid;grid-template-columns:repeat(3,minmax(0,1fr));gap:15px}.nds-calculator label{display:flex;flex-direction:column;gap:6px;color:#12354b;font-size:13px;font-weight:700}.nds-calculator input{width:100%;min-height:46px;padding:10px 12px;border:1px solid #b9cfdb;border-radius:9px;background:#fff;color:#173246;font:inherit}.nds-calculator input:focus{outline:3px solid rgba(86,161,200,.22);border-color:#2d799f}.nds-calculator .is-invalid{border-color:#c94747;background:#fff8f8}.nds-calculator small{color:#617482;font-size:11px;font-weight:400}.nds-calculator-actions{display:flex;flex-wrap:wrap;justify-content:center;gap:10px;margin:20px 0}.nds-calculator button{padding:11px 19px;border:0;border-radius:24px;background:#245e80;color:#fff;font:inherit;font-weight:700;cursor:pointer}.nds-calculator .nds-secondary-action{background:#e1edf3;color:#12354b}.nds-calculator-error{min-height:24px;margin:0 0 10px;color:#a12828;text-align:center;font-weight:600}.nds-health-score{padding:20px;border:1px solid #d6e4eb;border-radius:13px;background:#fff;text-align:center}.nds-health-score span,.nds-health-score strong{display:block}.nds-health-score strong{margin:7px 0;color:#12354b;font-size:28px}.nds-health-score p{margin:0}.nds-card pre{width:min(760px,100%);margin:22px auto}.nds-card a[target=\"_blank\"]{overflow-wrap:anywhere}@media(max-width:1000px){.nds-flow{grid-template-columns:repeat(3,1fr)}.nds-flow div:after{display:none}.nds-validation-grid{grid-template-columns:1fr}}@media(max-width:760px){.nds-flow,.nds-calculator-grid{grid-template-columns:1fr}.nds-flow div:after{display:none}}\n<\/style>\n<div class=\"nds\" data-health-profile=\"diagnosis\">\n<div class=\"nds-wrap\">\n<section class=\"nds-executive\">\n<h2>Classify historical breast-cytology records with a transparent model<\/h2>\n<p>This reproducible Neural Designer example uses nine ordinal cytology ratings from the Breast Cancer Wisconsin (Original) collection. On 136 internally held-out records, the fixed linear sigmoid model reaches ROC AUC 0.998 and classifies 135 records correctly at score threshold 0.50. It is an educational benchmark\u2014not a clinically validated diagnostic device.<\/p>\n<div class=\"nds-kpis\">\n<div class=\"nds-kpi\"><strong>0.998<\/strong><span>testing ROC AUC (95% CI 0.991\u20131.000)<\/span><\/div>\n<div class=\"nds-kpi\"><strong>136<\/strong><span>testing records, including 52 positive labels<\/span><\/div>\n<div class=\"nds-kpi\"><strong>100%<\/strong><span>testing sensitivity at score 0.50<\/span><\/div>\n<div class=\"nds-kpi\"><strong>98.8%<\/strong><span>testing specificity at score 0.50<\/span><\/div>\n<\/div>\n<div class=\"nds-actions\"><a href=\"#6-clinical-validation\">Review the clinical evidence boundary<\/a><a href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/breastcancer.csv\">Review the data<\/a><\/div>\n<\/section>\n<ul class=\"nds-toc\">\n<li><a href=\"#1-intended-use\">Question and use<\/a><\/li>\n<li><a href=\"#2-cohort-endpoint\">Cohort and endpoint<\/a><\/li>\n<li><a href=\"#3-model\">Model<\/a><\/li>\n<li><a href=\"#4-training\">Training<\/a><\/li>\n<li><a href=\"#5-selection\">Selection<\/a><\/li>\n<li><a href=\"#6-clinical-validation\">Validation<\/a><\/li>\n<li><a href=\"#7-workflow\">Workflow<\/a><\/li>\n<li><a href=\"#8-safety\">Safety and validity<\/a><\/li>\n<\/ul>\n<section id=\"1-intended-use\" class=\"nds-card\">\n<h2>1. Clinical question and intended use<\/h2>\n<p>The model ranks records from the supplied historical cytology table toward the processed malignant label. Its defensible role is software demonstration and retrospective method benchmarking. It may illustrate how a compact multivariable score could support research review, but it cannot establish or exclude breast cancer for a patient.<\/p>\n<div class=\"nds-value-grid\">\n<div class=\"nds-value\">\n<h3>Reproducible benchmark<\/h3>\n<p>Inspect the exact data split, preprocessing, trained coefficients and regenerated test analyses.<\/p>\n<\/div>\n<div class=\"nds-value\">\n<h3>Transparent scoring<\/h3>\n<p>Use a direct nine-input sigmoid model whose complete calculation can be reproduced in Python or the browser.<\/p>\n<\/div>\n<div class=\"nds-value\">\n<h3>Workflow education<\/h3>\n<p>Demonstrate why measurement quality, threshold policy, calibration and confirmatory review remain separate requirements.<\/p>\n<\/div>\n<\/div>\n<div class=\"nds-audience\"><span>Clinical data science<\/span><span>Digital pathology research<\/span><span>Biostatistics<\/span><span>Laboratory informatics<\/span><span>Medical ML education<\/span><\/div>\n<div class=\"nds-note nds-use-boundary\"><strong>Intended-use boundary.<\/strong> This example supports retrospective research and software verification only. It does not replace cytopathology, histopathology, multidisciplinary review or any locally approved diagnostic pathway.<\/div>\n<\/section>\n<section id=\"2-cohort-endpoint\" class=\"nds-card\">\n<h2>2. Cohort, measurements and endpoint<\/h2>\n<p>The source is the <a href=\"https:\/\/archive.ics.uci.edu\/dataset\/15\/breast%2Bcancer%2Bwisconsin%2Boriginal\">Breast Cancer Wisconsin (Original) data set<\/a>, donated to UCI in 1992 from cases reported by Dr William H. Wolberg at University of Wisconsin Hospitals. UCI lists 699 original records, nine integer features, a sample-code identifier, class codes 2 (benign) and 4 (malignant), and missing values in <code>bare_nuclei<\/code>.<\/p>\n<p>The processed Neural Designer table removes the identifier, excludes the 16 records with missing values and recodes the target to <code>diagnose=0<\/code> for benign and <code>diagnose=1<\/code> for malignant. It therefore contains 683 complete records: 444 negative labels (65.0%) and 239 positive labels (35.0%).<\/p>\n<div class=\"nds-table-scroll\">\n<table>\n<thead>\n<tr>\n<th>Subset<\/th>\n<th>Records<\/th>\n<th>Benign label<\/th>\n<th>Malignant label<\/th>\n<th>Purpose<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>Training<\/th>\n<td>411<\/td>\n<td>270<\/td>\n<td>141<\/td>\n<td>Estimate model parameters<\/td>\n<\/tr>\n<tr>\n<th>Selection<\/th>\n<td>136<\/td>\n<td>90<\/td>\n<td>46<\/td>\n<td>Monitor optimization<\/td>\n<\/tr>\n<tr>\n<th>Testing<\/th>\n<td>136<\/td>\n<td>84<\/td>\n<td>52<\/td>\n<td>Internal final evaluation<\/td>\n<\/tr>\n<tr>\n<th>Total<\/th>\n<td>683<\/td>\n<td>444<\/td>\n<td>239<\/td>\n<td>Complete-case processed table<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<div class=\"nds-table-scroll\">\n<table>\n<thead>\n<tr>\n<th>Input field<\/th>\n<th>Scale<\/th>\n<th>Recorded cytology characteristic<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th><code>clump_thickness<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Clump thickness rating<\/td>\n<\/tr>\n<tr>\n<th><code>cell_size_uniformity<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Uniformity-of-cell-size rating<\/td>\n<\/tr>\n<tr>\n<th><code>cell_shape_uniformity<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Uniformity-of-cell-shape rating<\/td>\n<\/tr>\n<tr>\n<th><code>marginal_adhesion<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Marginal-adhesion rating<\/td>\n<\/tr>\n<tr>\n<th><code>single_epithelial_cell_size<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Single epithelial-cell-size rating<\/td>\n<\/tr>\n<tr>\n<th><code>bare_nuclei<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Bare-nuclei rating<\/td>\n<\/tr>\n<tr>\n<th><code>bland_chromatin<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Bland-chromatin rating<\/td>\n<\/tr>\n<tr>\n<th><code>normal_nucleoli<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Normal-nucleoli rating<\/td>\n<\/tr>\n<tr>\n<th><code>mitoses<\/code><\/th>\n<td>1\u201310<\/td>\n<td>Mitoses rating<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<div class=\"nds-figure-grid\">\n<figure><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-class-distribution-2026.png\" alt=\"Distribution of benign and malignant labels in 683 processed cytology records\"><figcaption>The processed table contains 65.0% benign and 35.0% malignant labels; this prevalence must not be assumed for another clinical setting.<\/figcaption><\/figure>\n<figure><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-input-target-correlations-2026.png\" alt=\"Pearson correlations between nine cytology ratings and the encoded diagnosis label\"><figcaption>Cell-size uniformity, cell-shape uniformity and bare nuclei have the largest univariate correlations. These associations are not causal effects or proof of biological importance.<\/figcaption><\/figure>\n<\/div>\n<div class=\"nds-note nds-note--provenance\"><strong>Endpoint and provenance.<\/strong> The processed target preserves the UCI benign\/malignant class coding, but the downloadable table no longer contains the source identifier, acquisition date, patient linkage or diagnostic-adjudication details. Independent pathology confirmation and repeated-patient structure cannot be reconstructed from this file. UCI releases the data under CC BY 4.0 (DOI 10.24432\/C5HP4Z).<\/div>\n<\/section>\n<section id=\"3-model\" class=\"nds-card\">\n<h2>3. Model<\/h2>\n<p>All nine inputs use mean-and-standard-deviation scaling. They connect directly to one sigmoid output, with no hidden layer. The model contains ten trainable parameters: nine weights and one bias. It is a logistic classifier represented in Neural Designer&#8217;s network framework.<\/p>\n<div class=\"nds-note\"><strong>Output contract.<\/strong> Larger values rank a record toward <code>diagnose=1<\/code>, the processed malignant label. No independent calibration analysis is supplied, so the sigmoid value is a model score\u2014not an individual probability of malignancy.<\/div>\n<figure class=\"nds-architecture-figure\" data-model-stage=\"initial\"><img decoding=\"async\" class=\"nds-architecture\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-network-architecture-2026.png\" alt=\"Direct breast-cytology classifier with nine standardized inputs and one sigmoid output\"><figcaption>Fixed base and final architecture: nine standardized cytology ratings connected directly to one sigmoid score. No neuron-selection or architecture-selection experiment was performed.<\/figcaption><\/figure>\n<\/section>\n<section id=\"4-training\" class=\"nds-card\">\n<h2>4. Training strategy<\/h2>\n<p>The stored training strategy minimizes class-weighted squared error with the quasi-Newton method and L2 regularization weight 0.01. The processed positive and negative classes receive weights 1.4289 and 0.7691, respectively.<\/p>\n<p>Across 17 stored epochs (0\u201316), training error decreases from 0.7707 to 0.0847. Selection error starts at 0.0476, reaches its lowest displayed value at the beginning, and finishes at 0.0579. The stopping criterion is minimum loss decrease.<\/p>\n<figure class=\"nds-centered-figure\"><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-training-history-2026.png\" alt=\"Weighted squared training and selection error histories for the fixed cytology classifier\"><figcaption>The selection curve does not improve after its initial value. The article reports the stored final export rather than implying that the last epoch is an independently selected optimum.<\/figcaption><\/figure>\n<\/section>\n<section id=\"5-selection\" class=\"nds-card\">\n<h2>5. Model selection and baseline<\/h2>\n<p><strong>No neuron selection, input selection or architecture selection was performed.<\/strong> The direct 9\u20131 sigmoid model is both the base and final architecture. The selection subset monitors optimization only.<\/p>\n<div class=\"nds-table-scroll\">\n<table>\n<thead>\n<tr>\n<th>Reference<\/th>\n<th>Testing accuracy<\/th>\n<th>Interpretation<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>Majority-class baseline<\/th>\n<td>61.8%<\/td>\n<td>Always predict the benign label represented by 84 of 136 testing records<\/td>\n<\/tr>\n<tr>\n<th>Fixed 9\u20131 model<\/th>\n<td>99.3%<\/td>\n<td>135 of 136 testing records classified correctly at score 0.50<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>The compact model is adequate for this internal split. Extra hidden neurons would add complexity without resolving the larger evidence limitations: exact-vector overlap, historical sampling and absence of external validation.<\/p>\n<\/section>\n<section id=\"6-clinical-validation\" class=\"nds-card\">\n<h2>6. Clinical validation<\/h2>\n<p>The final model is evaluated on 136 testing records: 52 malignant labels (38.2% testing prevalence) and 84 benign labels. Neural Designer reports ROC AUC 0.998 with a 95% confidence interval of 0.991\u20131.000.<\/p>\n<figure class=\"nds-roc-figure\"><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-roc-curve-2026.png\" alt=\"Testing ROC curve with area under the curve 0.998\"><figcaption>The marked \u201coptimal\u201d point is chosen from this testing ROC curve and is descriptive. A clinical threshold would need to be prespecified or selected on separate data and then validated externally.<\/figcaption><\/figure>\n<h3>Operating point at score 0.50<\/h3>\n<p>The confusion matrix below uses the fixed reference threshold 0.50. The ROC task also reports a test-derived threshold of 0.33; it produces the same confusion counts in this split but must not be presented as an unbiased clinical cutoff.<\/p>\n<div class=\"nds-validation-grid\">\n<div class=\"nds-table-scroll\">\n<table class=\"nds-confusion\">\n<thead>\n<tr>\n<th>Actual \/ predicted at 0.50<\/th>\n<th>Positive<\/th>\n<th>Negative<\/th>\n<th>Total<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>Malignant label<\/th>\n<td>52<\/td>\n<td>0<\/td>\n<td>52<\/td>\n<\/tr>\n<tr>\n<th>Benign label<\/th>\n<td>1<\/td>\n<td>83<\/td>\n<td>84<\/td>\n<\/tr>\n<tr>\n<th>Total<\/th>\n<td>53<\/td>\n<td>83<\/td>\n<td>136<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<div class=\"nds-table-scroll\">\n<table class=\"nds-metrics\">\n<thead>\n<tr>\n<th>Testing metric<\/th>\n<th>Value<\/th>\n<th>Count-based reading<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>Sensitivity<\/th>\n<td>100%<\/td>\n<td>52 of 52 malignant labels detected<\/td>\n<\/tr>\n<tr>\n<th>Specificity<\/th>\n<td>98.8%<\/td>\n<td>83 of 84 benign labels rejected<\/td>\n<\/tr>\n<tr>\n<th>Precision \/ observed PPV<\/th>\n<td>98.1%<\/td>\n<td>52 of 53 positive calls match the malignant label<\/td>\n<\/tr>\n<tr>\n<th>Observed NPV<\/th>\n<td>100%<\/td>\n<td>83 of 83 negative calls match the benign label<\/td>\n<\/tr>\n<tr>\n<th>Accuracy<\/th>\n<td>99.3%<\/td>\n<td>135 of 136 records classified correctly<\/td>\n<\/tr>\n<tr>\n<th>F1 score<\/th>\n<td>0.990<\/td>\n<td>Harmonic summary of precision and sensitivity<\/td>\n<\/tr>\n<tr>\n<th>ROC AUC<\/th>\n<td>0.998<\/td>\n<td>Threshold-independent discrimination; 95% CI 0.991\u20131.000<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<\/div>\n<div class=\"nds-figure-grid\"><\/div>\n<div class=\"nds-note\"><strong>Clinical interpretation.<\/strong> Discrimination is excellent inside this processed random split, but predictive values reflect its 38.2% testing prevalence. Moreover, 49 of the 136 testing rows share an exact nine-feature vector with at least one training row. The result therefore demonstrates internal record-level performance, not independent patient-level diagnostic validity.<\/div>\n<\/section>\n<section id=\"7-workflow\" class=\"nds-card\">\n<h2>7. Workflow and reproducibility<\/h2>\n<p>A responsible real-world analogue would start after an eligible specimen has entered an approved diagnostic pathway. It would verify specimen identity, measurement provenance and the nine-field schema, check completeness and ranges, calculate a versioned score, detect unsupported inputs, and route the result to specialist review and an established confirmatory method.<\/p>\n<div class=\"nds-flow\">\n<div>Eligible specimen and governance<\/div>\n<div>Traceable cytology measurements<\/div>\n<div>Schema, missingness and range checks<\/div>\n<div>Versioned model score<\/div>\n<div>Abstention or specialist review<\/div>\n<div>Approved confirmatory pathway<\/div>\n<\/div>\n<h3>Reproducible score example<\/h3>\n<p>The vector 5, 1, 1, 1, 2, 1, 1, 1, 1 produces a malignant-class score of 0.034283. This exact feature vector appears in more than one subset, so it verifies the calculation but is not an independent validation case.<\/p>\n<div id=\"nds-bc-calculator\" class=\"nds-calculator\">\n<h3>Try the exported cytology classifier<\/h3>\n<p>Enter the nine ordinal ratings used by the processed data. The default vector reproduces Neural Designer&#8217;s exported calculation.<\/p>\n<div class=\"nds-note\"><strong>Research demonstration.<\/strong> The calculation runs locally with the exact exported weights and preprocessing. Values outside the validated domain are rejected. The result is not a diagnosis, does not replace pathology review and must not guide care.<\/div>\n<div class=\"nds-calculator-fields\" role=\"group\" aria-label=\"Cytology model inputs\">\n<div class=\"nds-calculator-grid\"><label for=\"nds-bc-clump_thickness\">Clump thickness<input id=\"nds-bc-clump_thickness\" name=\"clump_thickness\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"5\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-cell_size_uniformity\">Cell-size uniformity<input id=\"nds-bc-cell_size_uniformity\" name=\"cell_size_uniformity\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-cell_shape_uniformity\">Cell-shape uniformity<input id=\"nds-bc-cell_shape_uniformity\" name=\"cell_shape_uniformity\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-marginal_adhesion\">Marginal adhesion<input id=\"nds-bc-marginal_adhesion\" name=\"marginal_adhesion\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-single_epithelial_cell_size\">Single epithelial-cell size<input id=\"nds-bc-single_epithelial_cell_size\" name=\"single_epithelial_cell_size\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"2\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-bare_nuclei\">Bare nuclei<input id=\"nds-bc-bare_nuclei\" name=\"bare_nuclei\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-bland_chromatin\">Bland chromatin<input id=\"nds-bc-bland_chromatin\" name=\"bland_chromatin\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-normal_nucleoli\">Normal nucleoli<input id=\"nds-bc-normal_nucleoli\" name=\"normal_nucleoli\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><label for=\"nds-bc-mitoses\">Mitoses<input id=\"nds-bc-mitoses\" name=\"mitoses\" type=\"number\" min=\"1\" max=\"10\" step=\"1\" value=\"1\" required><small>Integer rating from 1 to 10<\/small><\/label><\/div>\n<div class=\"nds-calculator-actions\"><button type=\"button\" data-action=\"calculate\">Calculate model score<\/button><button type=\"button\" class=\"nds-secondary-action\" data-action=\"reset\">Reset example<\/button><\/div>\n<div class=\"nds-calculator-error\" role=\"alert\" aria-live=\"assertive\"><\/div>\n<\/div>\n<div class=\"nds-health-score\" aria-live=\"polite\"><\/div>\n<\/div>\n<p> <script data-noptimize=\"1\">(() => { const root=document.getElementById('nds-bc-calculator'); if(!root||root.dataset.ready==='1')return; root.dataset.ready='1'; const c={\"names\":[\"clump_thickness\",\"cell_size_uniformity\",\"cell_shape_uniformity\",\"marginal_adhesion\",\"single_epithelial_cell_size\",\"bare_nuclei\",\"bland_chromatin\",\"normal_nucleoli\",\"mitoses\"],\"multipliers\":[0.3547734618,0.3264879584,0.3348524272,0.3493486643,0.4501543939,0.2746354938,0.408513397,0.3278226256,0.5775639415],\"offsets\":[-1.575964093,-1.028701544,-1.076627612,-0.9887126088,-1.455916405,-0.9734894633,-1.407369494,-0.9407492876,-0.9259620309],\"weights\":[0.6817435622,0.6269319654,0.7747536898,0.6282728314,0.5428068638,0.7717344165,0.7051243186,0.5704482794,0.3795729578],\"bias\":-0.02939736471}; const error=root.querySelector('.nds-calculator-error'); const result=root.querySelector('.nds-health-score'); const calculateButton=root.querySelector('[data-action=\"calculate\"]'); const resetButton=root.querySelector('[data-action=\"reset\"]'); const field=name=>root.querySelector('[name=\"'+name+'\"]'); const render=score=>{ const relation=score>=0.5?'at or above':'below'; const label=document.createElement('span'); const value=document.createElement('strong'); const detail=document.createElement('div'); label.textContent='Malignant-class model score'; value.textContent=score.toFixed(6); detail.textContent='This score is '+relation+' the article reference threshold of 0.50. It is not a calibrated probability or a diagnosis.'; result.replaceChildren(label,value,detail); }; const calculate=()=>{ try { error.textContent=''; const values=c.names.map(name=>{ const el=field(name); el.classList.remove('is-invalid'); const value=Number(el.value); if(!Number.isInteger(value)||value<1||value>10){el.classList.add('is-invalid'); throw new Error('All fields must be integer ratings from 1 to 10.');} return value; }); let logit=c.bias; values.forEach((value,i)=>{logit+=c.weights[i]*(value*c.multipliers[i]+c.offsets[i]);}); render(1\/(1+Math.exp(-logit))); } catch(exception){error.textContent=exception.message; result.replaceChildren();} }; calculateButton.addEventListener('click',calculate); resetButton.addEventListener('click',()=>{ c.names.forEach(name=>{ const el=field(name); el.value=el.defaultValue; el.classList.remove('is-invalid'); }); calculate(); }); calculate(); })();<\/script><\/p>\n<h3>Reproduce the inference<\/h3>\n<p>The Python package contains the exact export, ordered schema, reference input and expected score. The Neural Designer package preserves the 411\/136\/136 split, trained parameters and regenerated analyses.<\/p>\n<pre><code>from model import NeuralNetwork\n\nratings = [5, 1, 1, 1, 2, 1, 1, 1, 1]\nmalignant_class_score = NeuralNetwork().calculate_outputs(ratings)[0]<\/code><\/pre>\n<div class=\"nds-downloads\"><a href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-python-model-2026.zip\">Download Python model (ZIP)<\/a><br \/>\n<a href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2026\/08\/breast-cancer-neural-designer-project-2026.zip\">Download Neural Designer project (ZIP)<\/a><br \/>\n<a href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/09\/breastcancer.csv\">Download breastcancer.csv<\/a><\/div>\n<\/section>\n<section id=\"8-safety\" class=\"nds-card\">\n<h2>8. Safety, generalizability and governance<\/h2>\n<ul>\n<li><strong>Internal random split only.<\/strong> No independent hospital, laboratory, time period, instrument or prospective cohort is evaluated.<\/li>\n<li><strong>Exact-vector overlap.<\/strong> The 683 rows collapse to 449 unique input vectors; 49 testing rows reproduce a vector already present in training. This can make internal performance optimistic.<\/li>\n<li><strong>Patient grouping cannot be verified.<\/strong> The processed table removes the source identifier, so repeated records from one patient or specimen cannot be audited or kept in one subset.<\/li>\n<li><strong>Complete-case restriction.<\/strong> Sixteen of the 699 UCI records are excluded because the source reports missing <code>bare_nuclei<\/code>. Performance does not cover incomplete inputs.<\/li>\n<li><strong>Reference-standard detail is incomplete.<\/strong> The processed file does not retain diagnostic-adjudication, biopsy, pathology, timing or follow-up metadata.<\/li>\n<li><strong>Scores are uncalibrated.<\/strong> The sigmoid output ranks the supplied class but has not been tested as an individual probability. PPV and NPV will change with prevalence.<\/li>\n<li><strong>No subgroup evidence.<\/strong> Age, ancestry, tumour subtype, lesion spectrum, operator, laboratory and device information are unavailable.<\/li>\n<li><strong>No clinical-utility evaluation.<\/strong> The example does not compare against pathologist performance, assess workflow impact, quantify net benefit or evaluate patient outcomes.<\/li>\n<\/ul>\n<div class=\"nds-note nds-note--warning\"><strong>Decision boundary.<\/strong> Use this model for reproducible education and retrospective method research only. Any consequential interpretation requires external validation, calibration, a prespecified threshold, specialist review and an appropriate confirmatory clinical method.<\/div>\n<\/section>\n<section id=\"references\" class=\"nds-card\">\n<h2>References<\/h2>\n<ul>\n<li><a href=\"https:\/\/archive.ics.uci.edu\/dataset\/15\/breast%2Bcancer%2Bwisconsin%2Boriginal\">UCI Machine Learning Repository: Breast Cancer Wisconsin (Original)<\/a>. DOI <a href=\"https:\/\/doi.org\/10.24432\/C5HP4Z\">10.24432\/C5HP4Z<\/a>; CC BY 4.0.<\/li>\n<li>Wolberg WH, Mangasarian OL. <a href=\"https:\/\/doi.org\/10.1073\/pnas.87.23.9193\">Multisurface method of pattern separation for medical diagnosis applied to breast cytology<\/a>. <em>Proceedings of the National Academy of Sciences<\/em>. 1990;87(23):9193\u20139196.<\/li>\n<\/ul>\n<\/section>\n<\/div>\n<\/div>\n","protected":false},"author":13,"featured_media":2529,"template":"","categories":[29],"tags":[38],"class_list":["post-3468","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>Breast Cancer Diagnosis Machine Learning<\/title>\n<meta name=\"description\" content=\"Build a machine learning model for breast cancer diagnosis based on whether a lump could be malignant (cancerous) or benign (non-cancerous).\" \/>\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\/breast-cancer-diagnosis\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Breast cancer diagnosis machine learning example\" \/>\n<meta property=\"og:description\" content=\"This example aims to assess whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous) from digitized images of a fine-needle aspiration biopsy.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/\" \/>\n<meta property=\"og:site_name\" content=\"Neural Designer\" \/>\n<meta property=\"article:modified_time\" content=\"2026-08-12T09:21:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.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=\"Breast cancer diagnosis machine learning example\" \/>\n<meta name=\"twitter:description\" content=\"This example aims to assess whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous) from digitized images of a fine-needle aspiration biopsy.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp\" \/>\n<meta name=\"twitter:site\" content=\"@NeuralDesigner\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"6 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\/breast-cancer-diagnosis\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/\",\"name\":\"Breast Cancer Diagnosis Machine Learning\",\"isPartOf\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp\",\"datePublished\":\"2025-08-28T09:13:00+00:00\",\"dateModified\":\"2026-08-12T09:21:41+00:00\",\"description\":\"Build a machine learning model for breast cancer diagnosis based on whether a lump could be malignant (cancerous) or benign (non-cancerous).\",\"breadcrumb\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp\",\"width\":1200,\"height\":628,\"caption\":\"Breast cancer analysis\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#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\":\"Breast Cancer Diagnosis Machine Learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\",\"url\":\"https:\/\/www.neuraldesigner.com\/\",\"name\":\"Neural Designer\",\"description\":\"Explainable 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":"Breast Cancer Diagnosis Machine Learning","description":"Build a machine learning model for breast cancer diagnosis based on whether a lump could be malignant (cancerous) or benign (non-cancerous).","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\/breast-cancer-diagnosis\/","og_locale":"en_US","og_type":"article","og_title":"Breast cancer diagnosis machine learning example","og_description":"This example aims to assess whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous) from digitized images of a fine-needle aspiration biopsy.","og_url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/","og_site_name":"Neural Designer","article_modified_time":"2026-08-12T09:21:41+00:00","og_image":[{"width":1200,"height":628,"url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp","type":"image\/webp"}],"twitter_card":"summary_large_image","twitter_title":"Breast cancer diagnosis machine learning example","twitter_description":"This example aims to assess whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous) from digitized images of a fine-needle aspiration biopsy.","twitter_image":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp","twitter_site":"@NeuralDesigner","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/","url":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/","name":"Breast Cancer Diagnosis Machine Learning","isPartOf":{"@id":"https:\/\/www.neuraldesigner.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage"},"thumbnailUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp","datePublished":"2025-08-28T09:13:00+00:00","dateModified":"2026-08-12T09:21:41+00:00","description":"Build a machine learning model for breast cancer diagnosis based on whether a lump could be malignant (cancerous) or benign (non-cancerous).","breadcrumb":{"@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#primaryimage","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/breast-cancer-analysis.webp","width":1200,"height":628,"caption":"Breast cancer analysis"},{"@type":"BreadcrumbList","@id":"https:\/\/www.neuraldesigner.com\/learning\/examples\/breast-cancer-diagnosis\/#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":"Breast Cancer Diagnosis Machine Learning"}]},{"@type":"WebSite","@id":"https:\/\/www.neuraldesigner.com\/#website","url":"https:\/\/www.neuraldesigner.com\/","name":"Neural Designer","description":"Explainable 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\/3468","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":10,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3468\/revisions"}],"predecessor-version":[{"id":23247,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/learning\/3468\/revisions\/23247"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media\/2529"}],"wp:attachment":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media?parent=3468"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/categories?post=3468"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/tags?post=3468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}