[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-338579-105":59,"doc-detail-338579-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","automated-real-world-data-integration-improves-cancer-outcome-prediction-research-report","Automated real-world data integration improves cancer outcome prediction - Research Report","","Digitization of health records and widespread tumour DNA sequencing enable richer studies of cancer outcomes, but patient data are often trapped in unstructured text and siloed systems. The study combines natural language processing annotations with structured medication, demographics, tumour registry and tumour genomic data from 24,950 patients at Memorial Sloan Kettering to build MSK-CHORD. The dataset supports clinicogenomic discoveries and machine-learning survival prediction, showing NLP-derived features can outperform models using genomic data or stage alone. It also enables automated radiology-report annotation to identify metastasis predictors, establishing a public resource for real-world oncology research.",{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/automated-real-world-data-integration-improves-cancer-outcome-prediction-research-report/338579/",{"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/automated-real-world-data-integration-improves-cancer-outcome-prediction-research-report/338579.png","ImageObject",300,407,{"name":92,"@type":93},"Genevieve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What data sources are combined to create the MSK-CHORD dataset?","Question",{"text":112,"@type":113},"MSK-CHORD integrates NLP annotations with structured medication data, patient-reported demographics, tumour registry information, and tumour genomic data.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How many patients and cancer types are included in MSK-CHORD?",{"text":117,"@type":113},"The dataset includes 24,950 patients and covers non-small-cell lung, breast, colorectal, prostate, and pancreatic cancers.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the approach improve cancer outcome prediction?",{"text":121,"@type":113},"Machine-learning models using features derived from natural language processing, such as disease sites, outperform models based on genomic data or stage alone in cross-validation and an external multi-institution test set.","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},338579,1790455905,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article  \nAutomated real-world data integration improves cancer outcome prediction  \n\n| [https://doi.org/10.1038/s41586-024-08167-5](https://doi.org/10.1038/s41586-024-08167-5)\u003Cbr>Received: 9 January 2024 Accepted: 8 October 2024 Published online: 6 November 2024 Open access\u003Cbr> Check for updates | Justin Jee1,5, Christopher Fong1,5, Karl Pichotta1,5, Thinh Ngoc Tran1,5, Anisha Luthra1,5, Michele Waters1, Chenlian Fu1, Mirella Altoe1, Si-Yang Liu1, Steven B. Maron1,2, MehnajAhmed1, Susie Kim1, Mono Pirun1, Walid K. Chatila1, Ino de Bruijn1, Arfath Pasha1, Ritika Kundra1, Benjamin Gross1, Brooke Mastrogiacomo1, Tyler J. Aprati2, David Liu2, JianJiong Gao3,\u003Cbr>Marzia Capelletti3, Kelly Pekala1, Lisa Loudon1, Maria Perry1, Chaitanya Bandlamudi1,\u003Cbr>Mark Donoghue1, Baby AnushaSatravada1, Axel Martin1, Ronglai Shen1, Yuan Chen1,\u003Cbr>A. Rose Brannon1, Jason Chang1, Lior Braunstein1,2, Anyi Li1, AntonSafonov1, Aaron Stonestrom1, Pablo Sanchez-Vela1, Clare Wilhelm1, Mark Robson1,2, Howard Scher1,2, Marc Ladanyi1,\u003Cbr>Jorge S. Reis-Filho1, David B. Solit1, David R. Jones1, Daniel Gomez1, Helena Yu1,\u003Cbr>Debyani Chakravarty1, Rona Yaeger1,4, Wassim Abida1,4, Wungki Park1,4, Eileen M. O’Reilly1,4, Julio Garcia-Aguilar1,4, Nicholas Socci1, Francisco Sanchez-Vega1, Jian Carrot-Zhang1,\u003Cbr>Peter D. Stetson1, Ross Levine1,4, Charles M. Rudin1,4, Michael F. Berger1, Sohrab P. Shah1, Deborah Schrag1,4, Pedram Razavi1,4, Kenneth L. Kehl2, Bob T. Li1,4, Gregory J. Riely1,4, Nikolaus Schultz1 ✉ & MSK Cancer Data Science Initiative Group*\u003Cbr>The digitization of health records and growing availability of tumour DNA sequencing provide an opportunity to study the determinants of cancer outcomes with unprecedented richness. Patient data are often stored in unstructured text and siloed datasets. Here we combine natural language processing annotations1,2 with structured medication, patient-reported demographic, tumour registry and tumour genomic data from 24,950 patients at MemorialSloan Kettering Cancer Center to generatea clinicogenomic, harmonized oncologic real-world dataset (MSK-CHORD) .\u003Cbr>MSK-CHORD includes data for non-small-cell lung (n = 7,809), breast (n = 5,368), colorectal (n = 5,543), prostate (n = 3,211) and pancreatic (n = 3,109) cancers and enables discovery of clinicogenomic relationships not apparent in smaller datasets. Leveraging MSK-CHORD to train machine learning models to predict overall survival, we find that models including features derived from natural language processing, such as sites of disease, outperform those based on genomic data or stage alone as tested by cross-validation and an external, multi-institution dataset. By annotating 705,241 radiology reports, MSK-CHORD also uncovers predictors of metastasis to specific organ sites, including a relationship between SETD2 mutation and lower metastatic potential in immunotherapy-treated lung adenocarcinoma corroborated in independent datasets. We demonstrate the feasibility of automated annotation from unstructured notes and its utility in predicting patient outcomes. The resulting data are provided asa public resource for real-world oncologic research. |  |\n| --- | --- | --- |\n| The ubiquity of electronic health records offers a largely untapped |  | of care for many patients because of their potential to guide therapy. |\n| data substrate for translational medicine. Although abstraction of key |  | Combining real-world data (RWD) has enormous potential to aid in |\n| elements from free-text patient visit, radiology, histopathology and |  | prediction of tumour trajectories. |\n| procedural notes has traditionally limited analysis, natural language |  | The separation of hospital, academic and commercial entities |\n| processing (NLP) now allows for automatic annotation of such fea- |  | responsible for genomic sequencing, radiology, histopathology and |\n| tures1,2. Massive, context-aware transformer architectures3, including |  | electronic health record data is a hurdle to integ","cbCaitmGWu1oyhy6","https://ap.wps.com/l/cbCaitmGWu1oyhy6","pdf",10605718,25,"English","# Introduction\n# Building the MSK-CHORD dataset\n# Modeling and prediction results\n# Automated radiology report annotation\n# Dataset availability and impact","[{\"question\":\"What data sources are combined to create the MSK-CHORD dataset?\",\"answer\":\"MSK-CHORD integrates NLP annotations with structured medication data, patient-reported demographics, tumour registry information, and tumour genomic data.\"},{\"question\":\"How many patients and cancer types are included in MSK-CHORD?\",\"answer\":\"The dataset includes 24,950 patients and covers non-small-cell lung, breast, colorectal, prostate, and pancreatic cancers.\"},{\"question\":\"How does the approach improve cancer outcome prediction?\",\"answer\":\"Machine-learning models using features derived from natural language processing, such as disease sites, outperform models based on genomic data or stage alone in cross-validation and an external multi-institution test set.\"}]","Automated real-world data integration improves cancer outcome prediction - Research Report | PDF",1790024338,63]