Requirements Federated Learning and mUlti-party computation Techniques for prostatE cancer
0.1.0 - ci-build
Requirements Federated Learning and mUlti-party computation Techniques for prostatE cancer, published by HL7 Europe. This guide is not an authorized publication; it is the continuous build for version 0.1.0 built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/hl7-eu/flute-requirements/ and changes regularly. See the Directory of published versions
| Draft as of 2023-10-25 |
{
"resourceType" : "Requirements",
"id" : "F-PIL-22",
"text" : {
"status" : "extensions",
"div" : "<div xmlns=\"http://www.w3.org/1999/xhtml\">\n\n <div style=\"display: inline-block;\n background-color: #d9e0e7; \n padding: 6px; \n margin: 4px; \n border: 1px solid #8da1b4;\n border-radius: 5px; \n line-height: 60%;\n width: 100%;\">\n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>ID</b>: F-PIL-22\n </p>\n \n \n\n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Publisher</b>: HL7 Europe\n </p>\n \n \n <table style=\"width: 100%;\" class=\"grid\">\n <tr style=\"background-color: #333f4c; color: #ffffff;\">\n <th style=\"text-align: center;\"><b>Contact Name</b></th>\n <th style=\"text-align: center;\"><b>Contact Points</b></th>\n </tr>\n \n <tr style=\"background-color: #ffffff;\">\n <td> HL7 Europe </td>\n <td>\n <ul>\n \n <li>\n \n <a href=\"https://www.hl7.eu\">https://www.hl7.eu</a>\n \n </li>\n \n </ul>\n </td>\n </tr>\n \n </table>\n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Description</b>:\n </p>\n <div><p>Platform shall ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there. Data User shall not see, directly access or download the data, i.e. the AI model shall only be trained in the local node.</p>\n</div>\n \n \n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Purpose</b>:\n </p>\n <div><p>FLUTE specific requirements for FLUTE pilot studies and the platform are outlined based on discussions with stakeholders participating in the case studies, in particular representatives of technical partners participating in WP5 (Quibim) and medical researchers from the three participating hospitals CHUL, IRST and VHIR, which also act as data owners.</p>\n</div>\n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Copyright Label</b>: Federated Learning and mUlti-party computation Techniques for prostatE cancer\n </p>\n \n\n \n\n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Actor for these requirements</b>: \n \n <code><a href=\"ActorDefinition-AD-FLUTEPlatform.html\">FLUTE Platform</a></code> \n \n </p>\n \n </div><br/>\n\n <div style=\"display: inline-block;\n padding: 6px; \n margin: 4px; \n width: 100%;\">\n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Statements</b>: \n </p>\n \n <blockquote>\n <p style=\"padding-bottom: 0px; margin: 0px;\"><b>ID</b>: F-PIL-22a</p>\n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Label</b>: As a FLUTE platform, I SHALL ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there.\n </p>\n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\"><b>Sources</b>:</p>\n <ul>\n \n <li>\n HL7 Europe\n </li>\n \n </ul>\n \n <table style=\"width: 100%;\">\n <tr style=\"background-color: #333f4c; color: #ffffff;\">\n \n <th><b>Conformance</b></th> \n <th><b>Requirement</b></th>\n \n \n \n </tr>\n <tr style=\"background-color: #ffffff;\">\n \n \n <td>\n \n <code>SHALL</code> \n \n </td>\n \n <td><div><p>ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there</p>\n</div></td>\n \n \n \n </tr>\n </table>\n </blockquote>\n \n <blockquote>\n <p style=\"padding-bottom: 0px; margin: 0px;\"><b>ID</b>: F-PIL-22b</p>\n \n <p style=\"padding-bottom: 0px; margin: 0px;\">\n <b>Label</b>: Data User SHALL not see, directly access or download the data, i.e. the AI model shall only be trained in the local node.\n </p>\n \n \n \n <p style=\"padding-bottom: 0px; margin: 0px;\"><b>Sources</b>:</p>\n <ul>\n \n <li>\n HL7 Europe\n </li>\n \n </ul>\n \n <table style=\"width: 100%;\">\n <tr style=\"background-color: #333f4c; color: #ffffff;\">\n \n <th><b>Conformance</b></th> \n <th><b>Requirement</b></th>\n \n \n \n </tr>\n <tr style=\"background-color: #ffffff;\">\n \n \n <td>\n \n <code>SHALL</code> \n \n </td>\n \n <td><div><p>not see, directly access or download the data, i.e. the AI model shall only be trained in the local node</p>\n</div></td>\n \n \n \n </tr>\n </table>\n </blockquote>\n \n \n </div>\n</div>"
},
"url" : "https://flute.com/Requirements/F-PIL-22",
"version" : "0.1.0",
"name" : "F_PIL_22",
"title" : "F-PIL-22",
"status" : "draft",
"date" : "2023-10-25T10:31:30.239Z",
"publisher" : "HL7 Europe",
"contact" : [
{
"name" : "HL7 Europe",
"telecom" : [
{
"system" : "url",
"value" : "https://www.hl7.eu"
}
]
}
],
"description" : "Platform shall ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there. Data User shall not see, directly access or download the data, i.e. the AI model shall only be trained in the local node.",
"purpose" : "FLUTE specific requirements for FLUTE pilot studies and the platform are outlined based on discussions with stakeholders participating in the case studies, in particular representatives of technical partners participating in WP5 (Quibim) and medical researchers from the three participating hospitals CHUL, IRST and VHIR, which also act as data owners.",
"copyright" : "HL7 Europe",
"copyrightLabel" : "Federated Learning and mUlti-party computation Techniques for prostatE cancer",
"actor" : [
🔗 "https://flute.com/ActorDefinition/AD-FLUTEPlatform"
],
"statement" : [
{
"key" : "F-PIL-22a",
"label" : "As a FLUTE platform, I SHALL ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there.",
"conformance" : [
"SHALL"
],
"requirement" : "ensure that the training data remains on the federated node and any processing, analysis and AI training is performed there",
"source" : [
{
"display" : "HL7 Europe"
}
]
},
{
"key" : "F-PIL-22b",
"label" : "Data User SHALL not see, directly access or download the data, i.e. the AI model shall only be trained in the local node.",
"conformance" : [
"SHALL"
],
"requirement" : "not see, directly access or download the data, i.e. the AI model shall only be trained in the local node",
"source" : [
{
"display" : "HL7 Europe"
}
]
}
]
}