[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-336828-105":59,"doc-detail-336828-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","multicohort-study-testing-the-generalisability-of-the-saskit-ml-stroke-and-pdac-prognostic-model-pipeline-to-other-chronic-diseases","Multicohort study testing the generalisability of the SASKit-ML stroke and PDAC prognostic model pipeline to other chronic diseases","","Validation of the SASKit-ML pipeline is conducted to test its generalisability for predicting health deterioration after stroke or pancreatic adenocarcinoma, and to identify biomarkers linked to deterioration across chronic diseases. A predefined validation protocol is applied to multiple public datasets using longitudinal cohorts for type 2 diabetes, inflammatory bowel disease, rheumatoid arthritis and diverse cancers, integrated into predictive features with 10-fold cross-validated random survival forests. Disease-specific clinical endpoints guide outcome assessment, including HbA1c and glucose measures, colitis and RA activity indices, and progression-free interval for TCGA. Results evaluate predictive performance across cohorts, demonstrating disease-dependent effectiveness.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/multicohort-study-testing-the-generalisability-of-the-saskit-ml-stroke-and-pdac-prognostic-model-pipeline-to-other-chronic-diseases/336828/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/multicohort-study-testing-the-generalisability-of-the-saskit-ml-stroke-and-pdac-prognostic-model-pipeline-to-other-chronic-diseases/336828.png","ImageObject",300,407,{"name":92,"@type":93},"Rowan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the goal of the study?","Question",{"text":112,"@type":113},"To validate and test whether the SASKit-ML pipeline can generalise to identify biomarkers of health deterioration in chronic diseases beyond the original stroke and PDAC setting.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the pipeline validated?",{"text":117,"@type":113},"A predefined validation protocol was applied to multiple public longitudinal datasets, with features generated and predictive modelling performed using 10-fold cross-validated random survival forests.",{"name":119,"@type":110,"acceptedAnswer":120},"What outcomes were used to assess health deterioration across cohorts?",{"text":121,"@type":113},"Outcomes used disease-specific clinical markers, including HbA1c and glucose criteria in HMP-T2D, severity index worsening in HMP-IBD, disease activity score or questionnaire-based worsening in RA-MAP, and progression-free interval across TCGA cancers.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},336828,1790292880,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":44,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","Open access Original research  \n Multicohort study testing the  \ngeneralisability of the SASKit-ML stroke and PDAC prognostic model pipeline to other chronic diseases  \nDaniel Palmer,1 Larissa Henze,2,3 Hugo Murua Escobar,2 Uwe Walter,4 Axel Kowald,1 Georg Fuellen  1  \nTo cite: Palmer D, Henze L, Murua Escobar H, et al. Multicohort study testing the generalisability of the SASKitML stroke and PDAC prognostic model pipeline to other chronic diseases. BMJ Open 2024;14:e088181 . doi:10 . 1136/ bmjopen-2024-088181  \n► Prepublication history and additional supplemental material for this paper are available online. To view these files, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[bmjopen-2024-088181](bmjopen-2024-088181)) .  \nReceived 29 April 2024 Accepted 30 August 2024  \n© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.  \nFor numbered affiliations see end of article.  \nCorrespondence to  \nDr Georg Fuellen;  \n[fuellen@uni-rostock.de](fuellen@uni-rostock.de)  \nABSTRACT  \nObjectives To validate and test the generalisability of the SASKit-ML pipeline, a prepublished feature selection and machine learning pipeline for the prediction of health deterioration after a stroke or pancreatic adenocarcinoma event, by using it to identify biomarkers of health deterioration in chronic disease.  \nDesign This is a validation study using a predefined protocol applied to multiple publicly available datasets, including longitudinal data from cohorts with type 2 diabetes (T2D), inflammatory bowel disease (IBD), rheumatoid arthritis (RA) and various cancers. The datasets were chosen to mimic as closely as possible the SASKit cohort, a prospective, longitudinal cohort study.  \nData sources Public data were used from the T2D (77 patients with potential pre-diabetes and 18 controls) and IBD (49 patients with IBD and 12 controls) branches of the Human Microbiome Project (HMP), RA Map (RA-MAP, 92 patients with RA, 22 controls) and The Cancer Genome Atlas (TCGA, 16 cancers) .  \nMethods Data integration steps were performed in accordance with the prepublished study protocol, generating features to predict disease outcomes using 10-fold cross-validated random survival forests.  \nOutcome measures Health deterioration was assessed using disease-specific clinical markers and endpoints across different cohorts. In the HMP-T2D cohort, the worsening of glycated haemoglobin (HbA1c) levels (5 .7% or more HbA1c in the blood), fasting plasma glucose (at least 100 mg/dL) and oral glucose tolerance test (at least 140) results were considered. For the HMP-IBD cohort, a worsening by at least 3 points of a disease-specific severity measure, the \"Simple Clinical Colitis Activity Index\" or \"Harvey-Bradshaw Index\" indicated an event. For the RA-MAP cohort, the outcome was defined as the worsening of the \"Disease Activity Score 28\" or \"Simple Disease Activity Index\" by at least five points, or the worsening of the \"Health Assessment Questionnaire\" score or an increase in the number of swollen/tender joints were evaluated. Finally, the outcome for all TCGA datasets was the progression-free interval.  \nResults Models for the prediction of health deterioration in T2D, IBD, RA and 16 cancers were produced. The T2D (C-index of 0.633 and Integrated Brier Score (IBS) of 0.107) and the RA (C-index of 0.654 and IBS of 0.150) models were modestly predictive. The IBD model was  \nSTRENGTHS AND LIMITATIONS OF THIS STUDY   \n⇒ Prepublished protocol reduces the chance of false positive results.  \n⇒ Chosen feature integration methods are inherently explainable, avoiding ‘black box’ machine learning.  \n⇒ Comparatively low sample sizes in many of the analysed cohorts.  \n⇒ Following a prepublished protocol restricts the use of newer methods.  \nuninformative. TCGA models tended towards modest predictive power.  \nConclusions The SASKit-ML p","cbCairhuRKn6DmWw","https://ap.wps.com/l/cbCairhuRKn6DmWw","pdf",1107344,"English","# Abstract\n## Objectives\n## Design and Data Sources\n## Methods\n## Outcome Measures\n## Results\n## Strengths and Limitations\n## Conclusions\n# Introduction\n## SASKit project overview","[{\"question\":\"What is the goal of the study?\",\"answer\":\"To validate and test whether the SASKit-ML pipeline can generalise to identify biomarkers of health deterioration in chronic diseases beyond the original stroke and PDAC setting.\"},{\"question\":\"How was the pipeline validated?\",\"answer\":\"A predefined validation protocol was applied to multiple public longitudinal datasets, with features generated and predictive modelling performed using 10-fold cross-validated random survival forests.\"},{\"question\":\"What outcomes were used to assess health deterioration across cohorts?\",\"answer\":\"Outcomes used disease-specific clinical markers, including HbA1c and glucose criteria in HMP-T2D, severity index worsening in HMP-IBD, disease activity score or questionnaire-based worsening in RA-MAP, and progression-free interval across TCGA cancers.\"}]","Multicohort study testing the generalisability of the SASKit-ML stroke and PDAC prognostic model pipeline to other chronic diseases | PDF",1790016767,23,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ebc5140f6dacc89634146e9e07241823.webp",983,1310,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dfd08c869abb78b0c2319f5cbe1f47f9.webp",982,1309,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cfd98697213b0a1923908fc469fe99f7.webp",981,1308,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/29f5ce95878618b61c2ac850f37a88b1.webp",980,1306]