[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86301-en":3,"doc-seo-86301-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86301,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Imputation-free transformer learning enables robust Alzheimer’s disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts","Accurate diagnostic classification and disease-severity prediction for Alzheimer’s disease are hindered by incomplete and heterogeneous real-world clinical data. Traditional imputation can introduce systematic bias, distort feature relationships, and produce overconfident predictions. NITROGEN is an imputation-free transformer using masked and intersample attention to model within-patient feature dependencies and between-patient relational structure from partially observed multimodal records. Trained on ADNI and evaluated on OASIS-3 and AIBL, it improves calibration and uncertainty quantification while retaining strong discriminative and cognitive-score prediction. A modality-aware uncertainty adjustment increases uncertainty based on absent modalities, enhancing reliable confidence under missing critical information.","arXiv :2607 . 11656v1 [ q-bio .NC] 13 Jul 2026  \nImputation-free transformer learning enables robust Alzheimer’s disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts  \nChristelle Schneuwly Diaz 1,2 ∗, Narmina Baghirova 1,2 , Duy-Thanh V˜u 1,2 , Duy-Cat Can 1,2 , Gilles Allali3 , Philippe Ryvlin4 , and Oliver Y. Ch´en 1,2†  \nfor the Alzheimer’s Disease Neuroimaging Initiative (ADNI) ‡,  \nfor the Australian Imaging, Biomarkers and Lifestyle (AIBL) study, and § for the Open Access Series of Imaging Studies (OASIS) ¶  \n1 Platform of Bioinformatics, Lausanne University Hospital.  \n2 Faculty of Biology and Medicine, University of Lausanne.  \n3 Leenaards Memory Centre, Lausanne University Hospital.  \n4 Department of Clinical Neurosciences, Lausanne University Hospital.  \n∗ christelle.schneuwly@chuv.ch †olivery.chen@chuv.ch  \n‡Part of the data used in this article was from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database ([adni.loni.usc.edu](adni.loni.usc.edu)). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in the analysis or writing of this paper. A complete list of ADNI investigators is available at: [http:](http:)//[adni.loni.usc.edu/wp-content/uploads/how](adni.loni.usc.edu/wp-content/uploads/how to)[ ](adni.loni.usc.edu/wp-content/uploads/how to)[to](adni.loni.usc.edu/wp-content/uploads/how to) apply/ADNI Acknowledgement List.pdf.  \n§ Part of the data used in the preparation of this article was obtained from the Australian Imaging Biomarkers and Lifestyle flagship study of ageing (AIBL) funded by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) which was made available at the ADNI database ([www.loni.usc.edu/ADNI](www.loni.usc.edu/ADNI)). The AIBL researchers contributed data but did not participate in analysis or writing of this report. AIBL researchers are listed at [https://data.aibl.org.au/adni/](https://data.aibl.org.au/adni/)  \n¶ Part of the data used in this article was from the Open Access Series of Imaging Studies (OASIS) ([https://sites.wustl.edu/oasisbrains/](https://sites.wustl.edu/oasisbrains/)).  \n1  \nAbstract  \nAccurate diagnostic classification and disease-severity prediction for Alzheimer’s disease are hampered by the pervasive incompleteness and heterogeneity of real-world clinical data. Left unaddressed, these barriers prevent reliable disease modelling and hinder effective clinical evaluation. Conventional imputation strategies introduce systematic bias, distort inter-feature relationships, and yield overconfident predictions, limitations that are especially consequential in diagnostic settings. Here, we propose NITROGEN ‖, an imputation-free transformer that jointly models within-patient feature dependencies and between-patient relational structure through masked and intersample attention, enabling robust multimodal learning directly from partially observed records. We trained NITROGEN on the Alzheimer’s Disease Neuroimaging Initiative (ADNI; N=7858 scans), and evaluated it, without further retraining, on two independent cohorts: the Open Access Series of Imaging Studies (OASIS-3; N=2675 scans) and the Australian Imaging, Biomarkers and Lifestyle (AIBL; N=1286 scans) study. Across all cohorts and various tasks including binary and multi-class diagnostic classification as well as continuous cognitive score prediction, NITROGEN showed robust probability calibration and uncertainty quantification advantages over tree-based ensemble methods, while maintaining competitive discriminative and continuous cognitive score prediction performance. Moreover, cross-cohort and cross-method analyses identified cortical thickness in the temporal pole, age, and APOE genotype as important, though not individually sufficient, features for robust AD status classification. To address prediction reliability under incomplete data, we further introduced a m","cbCaiecIBoZhRZAo","https://ap.wps.com/l/cbCaiecIBoZhRZAo","pdf",16734260,6,1,52,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does NITROGEN address in Alzheimer’s disease prediction?\",\"answer\":\"NITROGEN addresses pervasive incompleteness and heterogeneity in real-world clinical data that makes diagnostic classification and severity prediction unreliable. It avoids the bias and overconfidence associated with conventional imputation.\"},{\"question\":\"How does NITROGEN learn from incomplete multimodal patient records?\",\"answer\":\"NITROGEN is an imputation-free transformer that uses masked and intersample attention to jointly model within-patient feature dependencies and between-patient relational structure. This enables multimodal learning directly from partially observed records.\"},{\"question\":\"What evaluation results show about calibration and uncertainty quantification?\",\"answer\":\"Across ADNI training and evaluation on OASIS-3 and AIBL without retraining, NITROGEN shows robust probability calibration and uncertainty quantification advantages over tree-based ensembles. It also introduces modality-aware uncertainty adjustment to express calibrated confidence when critical modalities are absent.\"}]",1784210327,131,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"imputation-free-transformer-learning-enables-robust-alzheimers-disease-prediction-and-calibrated-uncertainty-quantification-across-heterogeneous-clinical-cohorts","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/imputation-free-transformer-learning-enables-robust-alzheimers-disease-prediction-and-calibrated-uncertainty-quantification-across-heterogeneous-clinical-cohorts/86301/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does NITROGEN address in Alzheimer’s disease prediction?","Question",{"text":76,"@type":77},"NITROGEN addresses pervasive incompleteness and heterogeneity in real-world clinical data that makes diagnostic classification and severity prediction unreliable. It avoids the bias and overconfidence associated with conventional imputation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does NITROGEN learn from incomplete multimodal patient records?",{"text":81,"@type":77},"NITROGEN is an imputation-free transformer that uses masked and intersample attention to jointly model within-patient feature dependencies and between-patient relational structure. This enables multimodal learning directly from partially observed records.",{"name":83,"@type":74,"acceptedAnswer":84},"What evaluation results show about calibration and uncertainty quantification?",{"text":85,"@type":77},"Across ADNI training and evaluation on OASIS-3 and AIBL without retraining, NITROGEN shows robust probability calibration and uncertainty quantification advantages over tree-based ensembles. It also introduces modality-aware uncertainty adjustment to express calibrated confidence when critical modalities are absent.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]