[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-376056-105":59,"doc-detail-376056-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","enhancing-noninvasive-pancreatic-cystic-neoplasm-diagnosis-with-multimodal-machine-learning","Enhancing noninvasive pancreatic cystic neoplasm diagnosis with multimodal machine learning","","Pancreatic cystic neoplasms comprise lesions with a wide malignancy spectrum, making accurate subtype differentiation essential to avoid unnecessary surgery or treatment delays. A non-invasive multimodal machine learning model was developed using 449 MRI and 568 CT scans from adult patients (2009–2022). Results show the multimodal approach outperforms single-source models, reaching 91.2% accuracy, 91.7% precision, 88.9% sensitivity, and 96.5% specificity, with 100% prediction accuracy for mucinous cystic neoplasms on either MRI or CT. External validation on an additional pancreatic cancer dataset supports generality and supports early MCN screening.",{"@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/enhancing-noninvasive-pancreatic-cystic-neoplasm-diagnosis-with-multimodal-machine-learning/376056/",{"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/enhancing-noninvasive-pancreatic-cystic-neoplasm-diagnosis-with-multimodal-machine-learning/376056.png","ImageObject",300,407,{"name":92,"@type":93},"Putri","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-24","2026-09-24",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},"Why is noninvasive, accurate PCN subtype diagnosis important?","Question",{"text":112,"@type":113},"Misdiagnosis can lead to unnecessary surgeries or delayed treatment, worsening patient outcomes and quality of life.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What data were used to build the multimodal machine learning model?",{"text":117,"@type":113},"The study trained the model on 449 MRI scans and 568 CT scans from adult patients collected between 2009 and 2022.",{"name":119,"@type":110,"acceptedAnswer":120},"How did the multimodal model perform versus single-source approaches?",{"text":121,"@type":113},"It achieved state-of-the-art classification performance with an average accuracy of 91.2%, precision 91.7%, sensitivity 88.9%, and specificity 96.5%.","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},376056,1790622326,{"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},962085571259,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nEnhancing noninvasive pancreatic cystic neoplasm diagnosis with multimodal machine learning  \nWei Huang1,5, Yue Xu1,5, Zhao Li2􀀍, Jun Li3, Qing Chen3, Qiang Huang4, Yaping Wu4 & HongtanChen1􀀍  \nPancreatic cystic neoplasms (PCNs) are a complex group of lesions with a spectrum of malignancy. Accurate differentiation of PCN types is crucial for patient management, as misdiagnosis can result in unnecessary surgeries or treatment delays, affecting the quality of life. The significance of developing anon-invasive, accurate diagnostic model is underscored by the need to improve patient outcomes and reduce the impact of these conditions. We developed a machine learning model capable of accurately identifying different types of PCNs in a non-invasive manner, by using a dataset comprising 449 MRI and 568 CT scans from adult patients, spanning from 2009 to 2022. The study’s results indicate that our multimodal machine learning algorithm, which integrates both clinical and imaging data, significantly outperforms single-source data algorithms. Specifically, it demonstrated state-of-the-art performance in classifying PCN types, achieving an average accuracy of 91.2%, precision of 91.7%, sensitivity of 88.9%, and specificity of 96.5%. Remarkably, for patients with mucinous cystic neoplasms (MCNs), regardless of undergoing MRI or CT imaging, the model achieved a 100% prediction accuracy rate. It indicates that our non-invasive multimodal machine learning model offers strong support for the early screening of MCNs, and represents a significant advancement in PCN diagnosis for improving clinical practice and patient outcomes. We also achieved the best results on an additional pancreatic cancer dataset, which further proves the generality of our model.  \nKeywords Pancreatic cystic neoplasms, Machine learning, Diagnostic classification, Multimodal data, Clinical screening  \nPancreatic cystic neoplasms (PCNs) can be histologically categorized into serous cystic neoplasms (SCNs), mucinous cystic neoplasms (MCNs), intraductal papillary mucinous neoplasms (IPMNs), and other rare tumorous cystic lesions1. In recent years, due to the increasing availability of medical screenings and the widespread utilization of imaging modalities such as abdominal computed tomography (CT), the incidence of PCNs has exhibited a steady annual increase. PCNs are estimated to be present in 2%–45% of the general population2. Within this cohort, IPMNs account for about 21%–41%, MCNs for 10%–45%, and SCNs for 18.3%–39%. Collectively, these three types constitute more than 90% of all PCN instances. It is worth noting that the distribution of PCN types may exhibit slight variations across different geographic regions2–4.  \nNonetheless, there exists a notable disparity in the likelihood of malignancy across various types of PCNs. Specifically, MCNs exhibit a malignancy rate of 10%-39%, whereas IPMNs have the highest potential for malignancy, ranging from 36%-100%2,5. Regarding SCNs, they are generally regarded as benign (malignancy rate less than 1%6) . PCNs are commonly acknowledged as precursors to invasive pancreatic cancer7. However, owing to the generally delayed manifestation of symptoms, only a small proportion of patients, approximately 15% to 20%, are able to be diagnosed with PCNs and undergo prompt resection of the lesion8.  \nAt present, PCNs present two clinical issues: one is the low diagnostic accuracy of PCNs, and the other is the difficulty of risk stratification9, 10. According to reports, utilizing radiological features to infer the type of PCNs still leads to an incorrect diagnosis in nearly 1/3 of cases11. Despite adhering to currently accepted guidelines for PCN treatment2, 10, 12, hich may involve surgical resection or other interventions, postoperative pathology often reveals cases of overtreatment or delayed treatment. The European guidelines for pancreatic cystic tumors  \n1D","cbCaipWswlIaKtvb","https://ap.wps.com/l/cbCaipWswlIaKtvb","pdf",2429164,14,"English","# Background\n## Clinical importance of accurate PCN subtype diagnosis\n## Distribution and malignancy rates of PCN types\n## Current diagnostic challenges and guideline limitations\n# Methods\n## Multimodal machine learning model development using MRI and CT data\n# Results\n## Performance compared with single-source approaches\n## Subtype-specific outcomes for MCNs\n## External validation on an additional pancreatic cancer dataset\n# Implications\n## Support for early screening and improved clinical practice","[{\"question\":\"Why is noninvasive, accurate PCN subtype diagnosis important?\",\"answer\":\"Misdiagnosis can lead to unnecessary surgeries or delayed treatment, worsening patient outcomes and quality of life.\"},{\"question\":\"What data were used to build the multimodal machine learning model?\",\"answer\":\"The study trained the model on 449 MRI scans and 568 CT scans from adult patients collected between 2009 and 2022.\"},{\"question\":\"How did the multimodal model perform versus single-source approaches?\",\"answer\":\"It achieved state-of-the-art classification performance with an average accuracy of 91.2%, precision 91.7%, sensitivity 88.9%, and specificity 96.5%.\"}]","Enhancing noninvasive pancreatic cystic neoplasm diagnosis with multimodal machine learning | PDF",1790217138,35]