{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T06:55:54Z","timestamp":1781938554847,"version":"3.54.5"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University","award":["IMSIU-DDRSP2601"],"award-info":[{"award-number":["IMSIU-DDRSP2601"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate prediction of Chronic Kidney Disease (CKD) development is essential for prompt therapeutic intervention; nevertheless, it is difficult due to the highly individualized disease trajectories and intricate multivariate risk profiles. Contemporary deep learning models provide substantial predictive capability; yet, they frequently exhibit computational inefficiency and a lack of interpretability, akin to a \u201cblack box.\u201d To overcome these limitations, we present the Eigen-Guided Transformer, an innovative architecture that systematically enhances model topology by data-driven eigenvalue analysis of clinical feature correlations. Our methodology independently establishes: (1) the optimal quantity of attention heads by ascertaining the intrinsic dimensionality necessary to account for 95% of data variance (h\u2009=\u200911), (2) an eigenvector-informed weight initialization to encapsulate a priori feature interactions, and (3) validation-driven depth optimization. Upon assessing daily-aggregated longitudinal sequences from the MIMIC-IV dataset for creatinine prediction, the model attained a Mean Squared Error (MSE) of 0.089\u2009\u00b1\u20090.004 and a Mean Absolute Error (MAE) of 0.132\u2009+\u20090.0001, indicating an 11.1% enhancement over the most robust baseline (TFT). The Eigen-Guided Transformer exhibited exceptional parameter efficiency, achieving a FLOPs\/accuracy ratio of 142.4M, markedly lower than that of TFT (300M) and Autoformer (1.0B). External validation of the eICU dataset demonstrated strong cross-institutional generalizability (MSE 0.0117\u2009\u00b1\u20090.0001; MAE 0.0254\u2009+\u20090.0008). To guarantee clinical dependability, we incorporated Monte Carlo Dropout for uncertainty quantification, resulting in precisely calibrated prediction intervals with 95.8% observed coverage. Additionally, a demographic fairness audit encompassing age, gender, and ethnicity demonstrated equitable performance, with a maximum discrepancy ratio of merely 1.32. The Eigen-Guided Transformer offers a transparent, efficient, and reliable paradigm for the individualized therapy of chronic renal disease by matching attention mechanisms with the intrinsic biological structure of clinical data.<\/jats:p>","DOI":"10.1371\/journal.pone.0348886","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:31:01Z","timestamp":1779384661000},"page":"e0348886","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Eigen-guided transformer: A data-driven approach for chronic kidney disease forecasting"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7319-8340","authenticated-orcid":true,"given":"Fahman","family":"Saeed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sultan","family":"Aldera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"issue":"6","key":"pone.0348886.ref001","doi-asserted-by":"crossref","first-page":"2918","DOI":"10.1111\/j.1523-1755.2005.00774.x","article-title":"The global challenge of chronic kidney disease","volume":"68","author":"M El Nahas","year":"2005","journal-title":"Kidney Int"},{"issue":"1","key":"pone.0348886.ref002","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1186\/s12889-025-21851-z","article-title":"Global, regional, and national burden of chronic kidney disease and its underlying etiologies from 1990 to 2021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"25","author":"L Deng","year":"2025","journal-title":"BMC Public Health"},{"issue":"15","key":"pone.0348886.ref003","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1001\/jama.2011.451","article-title":"A predictive model for progression of chronic kidney disease to kidney failure","volume":"305","author":"N Tangri","year":"2011","journal-title":"JAMA"},{"issue":"2","key":"pone.0348886.ref004","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1001\/jamapediatrics.2017.4083","article-title":"Use of the kidney failure risk equation to determine the risk of progression to end-stage renal disease in children with chronic kidney disease","volume":"172","author":"E Winnicki","year":"2018","journal-title":"JAMA Pediatr"},{"issue":"1","key":"pone.0348886.ref005","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41591-018-0239-8","article-title":"Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data","volume":"25","author":"S Ravizza","year":"2019","journal-title":"Nat Med"},{"key":"pone.0348886.ref006","doi-asserted-by":"crossref","first-page":"102900","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: A review","volume":"154","author":"S Nerella","year":"2024","journal-title":"Artif Intell Med"},{"issue":"1","key":"pone.0348886.ref007","doi-asserted-by":"crossref","first-page":"11862","DOI":"10.1038\/s41598-019-48263-5","article-title":"Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning","volume":"9","author":"M Makino","year":"2019","journal-title":"Sci Rep"},{"key":"pone.0348886.ref008","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0348886.ref009","article-title":"Multivariate time series imputation with generative adversarial networks","volume":"31","author":"Y Luo","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0348886.ref010","article-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting","volume":"32","author":"S Li","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"12","key":"pone.0348886.ref011","doi-asserted-by":"crossref","first-page":"11106","DOI":"10.1609\/aaai.v35i12.17325","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","volume":"35","author":"H Zhou","year":"2021","journal-title":"AAAI"},{"key":"pone.0348886.ref012","first-page":"22419","article-title":"Autoformer: decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"H Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0348886.ref013","article-title":"Pyraformer: low-complexity pyramidal attention for long-range time series modeling and forecasting.","author":"S Liu","year":"2022","journal-title":"International Conference on Learning Representations (ICLR 2022)"},{"issue":"01","key":"pone.0348886.ref014","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1609\/aaai.v34i01.5400","article-title":"Learning the graphical structure of electronic health records with graph convolutional transformer","volume":"34","author":"E Choi","year":"2020","journal-title":"AAAI"},{"issue":"4","key":"pone.0348886.ref015","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting.","volume":"37","author":"B Lim","year":"2021","journal-title":"Int J Forecast."},{"issue":"1","key":"pone.0348886.ref016","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.jiixd.2023.10.002","article-title":"AutoML: a systematic review on automated machine learning with neural architecture search","volume":"2","author":"I Salehin","year":"2024","journal-title":"Journal of Information and Intelligence"},{"key":"pone.0348886.ref017","article-title":"Darts: differentiable architecture search","author":"H Liu","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0348886.ref018","article-title":"Neural architecture optimization","volume":"31","author":"R Luo","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"pone.0348886.ref019","article-title":"Neural architecture search without training","author":"J Mellor","year":"2021","journal-title":"International conference on machine learning"},{"issue":"3","key":"pone.0348886.ref020","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1007\/s10618-021-00737-9","article-title":"Dataset2vec: learning dataset meta-features","volume":"35","author":"HS Jomaa","year":"2021","journal-title":"Data Mining and Knowledge Discovery"},{"key":"pone.0348886.ref021","article-title":"Picking winning tickets before training by preserving gradient flow","author":"C Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0348886.ref022","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1109\/CVPRW56347.2022.00309","article-title":"ResNeSt: split-attention networks","author":"H Zhang","year":"2022","journal-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"pone.0348886.ref023","doi-asserted-by":"crossref","first-page":"109269","DOI":"10.1109\/ACCESS.2024.3440226","article-title":"Adaptive renewable energy forecasting utilizing a data-driven PCA-transformer architecture","volume":"12","author":"F Saeed","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0348886.ref024","doi-asserted-by":"crossref","first-page":"41344","DOI":"10.1109\/ACCESS.2021.3065273","article-title":"Automatic diabetic retinopathy diagnosis using adaptive fine-tuned convolutional neural network","volume":"9","author":"F Saeed","year":"2021","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0348886.ref025","doi-asserted-by":"crossref","first-page":"22091","DOI":"10.1038\/s41598-023-49271-2","article-title":"Prediction of chronic kidney disease progression using recurrent neural network and electronic health records","volume":"13","author":"Y Zhu","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0348886.ref026","article-title":"Benchmarking with MIMIC-IV, an irregular, spare clinical time series dataset","author":"H Bui","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0348886.ref027","doi-asserted-by":"crossref","first-page":"180178","DOI":"10.1038\/sdata.2018.178","article-title":"The eICU Collaborative Research Database, a freely available multi-center database for critical care research","volume":"5","author":"TJ Pollard","year":"2018","journal-title":"Sci Data"},{"issue":"2","key":"pone.0348886.ref028","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1007\/s43995-025-00118-z","article-title":"Proactive healthcare: machine learning-driven insights into kidney failure prediction","volume":"16","author":"H Alghamdi","year":"2025","journal-title":"J Umm Al-Qura Univ EngArchit"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:31:07Z","timestamp":1779384667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348886"}},"subtitle":[],"editor":[{"given":"Agnese","family":"Sbrollini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":28,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348886","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]}}}