{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T21:52:13Z","timestamp":1793483533870,"version":"4.5.0"},"reference-count":43,"publisher":"BMJ","issue":"3","license":[{"start":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T00:00:00Z","timestamp":1710374400000},"content-version":"unspecified","delay-in-days":13,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"the Chinese National Key Technology R&D Program, Ministry of Science and Technology","award":["2021YFC2501300"],"award-info":[{"award-number":["2021YFC2501300"]}]},{"name":"the Chinese National Key Technology R&D Program, Ministry of Science and Technology","award":["2021YFC2501302"],"award-info":[{"award-number":["2021YFC2501302"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2023,11,30]]},"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop an interpretable deep learning model of lupus nephritis (LN) relapse prediction based on dynamic multivariable time-series data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A single-centre, retrospective cohort study in China.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>A Chinese central tertiary hospital.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>The cohort study consisted of 1694 LN patients who had been registered in the Nanjing Glomerulonephritis Registry at the National Clinical Research Center of Kidney Diseases, Jinling Hospital from January 1985 to December 2010.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a deep learning algorithm to predict LN relapse that consists of 59 features, including demographic, clinical, immunological, pathological and therapeutic characteristics that were collected for baseline analysis. A total of 32\u2009227 data points were collected by the sliding window method and randomly divided into training (80%), validation (10%) and testing sets (10%). We developed a deep learning algorithm-based interpretable multivariable long short-term memory model for LN relapse risk prediction considering censored time-series data based on a cohort of 1694 LN patients. A mixture attention mechanism was deployed to capture variable interactions at different time points for estimating the temporal importance of the variables. Model performance was assessed according to C-index (concordance index).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The median follow-up time since remission was 4.1 (IQR, 1.7\u20136.7) years. The interpretable deep learning model based on dynamic multivariable time-series data achieved the best performance, with a C-index of 0.897, among models using only variables at the point of remission or time-variant variables. The importance of urinary protein, serum albumin and serum C3 showed time dependency in the model, that is, their contributions to the risk prediction increased over time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning algorithms can effectively learn through time-series data to develop a predictive model for LN relapse. The model provides accurate predictions of LN relapse for different renal disease stages, which could be used in clinical practice to guide physicians on the management of LN patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2023-071821","type":"journal-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T23:00:11Z","timestamp":1710457211000},"page":"e071821","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":19,"title":["Deep learning model to predict lupus nephritis renal flare based on dynamic multivariable time-series data"],"prefix":"10.1136","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7569-8042","authenticated-orcid":false,"given":"Siwan","family":"Huang","sequence":"first","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghua","family":"Chen","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4422-6349","authenticated-orcid":false,"given":"Yanan","family":"Song","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiange","family":"Chen","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxiao","family":"Jia","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai-Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan-Dan","family":"Liang","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cai-Hong","family":"Zeng","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Ping An Healthcare Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"National Clinical Research Centre of Kidney Diseases, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,3,14]]},"reference":[{"key":"2025121220360788000_14.3.e071821.1","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.180145"},{"key":"2025121220360788000_14.3.e071821.2","doi-asserted-by":"publisher","DOI":"10.1002\/art.10142"},{"key":"2025121220360788000_14.3.e071821.3","doi-asserted-by":"publisher","DOI":"10.1002\/art.20364"},{"key":"2025121220360788000_14.3.e071821.4","doi-asserted-by":"publisher","DOI":"10.1177\/0961203315606985"},{"key":"2025121220360788000_14.3.e071821.5","doi-asserted-by":"publisher","DOI":"10.1177\/0961203313476357"},{"key":"2025121220360788000_14.3.e071821.6","doi-asserted-by":"publisher","DOI":"10.2215\/CJN.00490109"},{"key":"2025121220360788000_14.3.e071821.7","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1080\/1744666X.2020.1865156","article-title":"Predicting lupus flares: epidemiological and disease related risk factors","volume":"17","author":"Andrade","year":"2021","journal-title":"Expert Rev Clin Immunol"},{"key":"2025121220360788000_14.3.e071821.8","doi-asserted-by":"publisher","DOI":"10.2215\/CJN.05040513"},{"key":"2025121220360788000_14.3.e071821.9","doi-asserted-by":"crossref","DOI":"10.3390\/jcm10040670","article-title":"Management of lupus nephritis","volume":"10","author":"Tamirou","year":"2021","journal-title":"J Clin Med"},{"key":"2025121220360788000_14.3.e071821.10","unstructured":"Prediction of lupus renal flares study, NCT05362812 [ClinicalTrials]. 2022. Available: https:\/\/classic.clinicaltrials.gov\/ct2\/show\/NCT05362812 [Accessed 10 May 2022]."},{"key":"2025121220360788000_14.3.e071821.11","doi-asserted-by":"crossref","DOI":"10.1186\/s13075-017-1442-6","article-title":"Predictive biological markers of systemic lupus erythematosus flares: a systematic literature review","volume":"19","author":"Gensous","year":"2017","journal-title":"Arthritis Res Ther"},{"key":"2025121220360788000_14.3.e071821.12","doi-asserted-by":"publisher","DOI":"10.1159\/000513566"},{"key":"2025121220360788000_14.3.e071821.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1390-1"},{"key":"2025121220360788000_14.3.e071821.14","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1016\/S2213-2600(18)30300-X","article-title":"Machine learning for real-time prediction of complications in critical care: a retrospective study","volume":"6","author":"Meyer","year":"2018","journal-title":"Lancet Respir Med"},{"key":"2025121220360788000_14.3.e071821.15","doi-asserted-by":"crossref","DOI":"10.1186\/s12967-023-03931-z","article-title":"Incorporating knowledge of disease-defining Hub genes and regulatory network into a machine learning-based model for predicting treatment response in lupus nephritis after the first renal flare","volume":"21","author":"Lee","year":"2023","journal-title":"J Transl Med"},{"key":"2025121220360788000_14.3.e071821.16","doi-asserted-by":"crossref","first-page":"108966","DOI":"10.1016\/j.intimp.2022.108966","article-title":"Clinical predictive model to estimate probability of remission in patients with lupus nephritis","volume":"110","author":"Kang","year":"2022","journal-title":"Int Immunopharmacol"},{"key":"2025121220360788000_14.3.e071821.17","doi-asserted-by":"crossref","unstructured":"Collett D . Modelling survival data in medical research. In: Modelling survival data in medical research, 3rd ed. Boca Raton: CRC Press, Taylor & Francis Group, 2015. doi:10.1201\/b18041","DOI":"10.1201\/b18041"},{"key":"2025121220360788000_14.3.e071821.18","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1038\/s41551-018-0315-x","article-title":"Towards trustable machine learning","volume":"2","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"2025121220360788000_14.3.e071821.19","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.001593"},{"key":"2025121220360788000_14.3.e071821.20","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7797"},{"key":"2025121220360788000_14.3.e071821.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2017.11.023"},{"key":"2025121220360788000_14.3.e071821.22","doi-asserted-by":"publisher","DOI":"10.1038\/kisup.2012.25"},{"key":"2025121220360788000_14.3.e071821.23","doi-asserted-by":"publisher","DOI":"10.1038\/nrneph.2012.220"},{"key":"2025121220360788000_14.3.e071821.24","doi-asserted-by":"publisher","DOI":"10.1002\/1529-0131(200110)44:10<2342::AID-ART397>3.0.CO;2-8"},{"key":"2025121220360788000_14.3.e071821.25","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1177\/0961203319868531","article-title":"Autoantibodies in SLE: prediction and the P value matrix","volume":"28","author":"Choi","year":"2019","journal-title":"Lupus"},{"key":"2025121220360788000_14.3.e071821.26","doi-asserted-by":"publisher","DOI":"10.1007\/s12026-012-8345-z"},{"key":"2025121220360788000_14.3.e071821.27","doi-asserted-by":"publisher","DOI":"10.1038\/nrrheum.2017.125"},{"key":"2025121220360788000_14.3.e071821.28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jtauto.2020.100042","article-title":"Urinary biomarkers in lupus nephritis","volume":"3","author":"Arag\u00f3n","year":"2020","journal-title":"J Transl Autoimmun"},{"key":"2025121220360788000_14.3.e071821.29","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/kel351"},{"key":"2025121220360788000_14.3.e071821.30","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.091028"},{"key":"2025121220360788000_14.3.e071821.31","doi-asserted-by":"publisher","DOI":"10.5114\/ceji.2014.43730"},{"key":"2025121220360788000_14.3.e071821.32","doi-asserted-by":"crossref","DOI":"10.1186\/s12882-017-0736-x","article-title":"Uric acid causes kidney injury through inducing fibroblast expansion, Endothelin-1 expression, and inflammation","volume":"18","author":"Romi","year":"2017","journal-title":"BMC Nephrol"},{"key":"2025121220360788000_14.3.e071821.33","doi-asserted-by":"publisher","DOI":"10.1161\/ATVBAHA.117.309128"},{"key":"2025121220360788000_14.3.e071821.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2020.05.034"},{"key":"2025121220360788000_14.3.e071821.35","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1007\/s00296-010-1373-x","article-title":"Association of serum uric acid with lupus nephritis in systemic lupus erythematosus","volume":"31","author":"Yang","year":"2011","journal-title":"Rheumatol Int"},{"key":"2025121220360788000_14.3.e071821.36","doi-asserted-by":"crossref","first-page":"2715","DOI":"10.1007\/s00296-011-1987-7","article-title":"Associations of serum urea, creatinine and uric acid with clinical and laboratory features in patients with systemic lupus erythematosus","volume":"32","author":"Yang","year":"2012","journal-title":"Rheumatol Int"},{"key":"2025121220360788000_14.3.e071821.37","doi-asserted-by":"crossref","first-page":"57099","DOI":"10.18632\/oncotarget.19051","article-title":"The prevalence, subtypes and associated factors of hyperuricemia in lupus nephritis patients at chronic kidney disease stages 1-3","volume":"8","author":"Liu","year":"2017","journal-title":"Oncotarget"},{"key":"2025121220360788000_14.3.e071821.38","doi-asserted-by":"crossref","first-page":"773","DOI":"10.3390\/jcm9030773","article-title":"Serum uric acid is associated with renal prognosis of lupus nephritis in women but not in men","volume":"9","author":"Oh","year":"2020","journal-title":"JCM"},{"key":"2025121220360788000_14.3.e071821.39","first-page":"1547","article-title":"Predictive value of the neutrophil-to-lymphocyte ratio and hemoglobin Insystemic lupus erythematosus","volume":"16","author":"Yu","year":"2018","journal-title":"Exp Ther Med"},{"key":"2025121220360788000_14.3.e071821.40","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1007\/s10067-014-2822-9","article-title":"Basophil count, a marker for disease activity in systemic lupus erythematosus","volume":"34","author":"Liang","year":"2015","journal-title":"Clin Rheumatol"},{"key":"2025121220360788000_14.3.e071821.41","doi-asserted-by":"publisher","DOI":"10.1016\/j.kint.2016.05.017"},{"key":"2025121220360788000_14.3.e071821.42","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1038\/s41572-019-0141-9","article-title":"Lupus nephritis","volume":"6","author":"Anders","year":"2020","journal-title":"Nat Rev Dis Primers"},{"key":"2025121220360788000_14.3.e071821.43","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e318258f812"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2023-071821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T04:36:14Z","timestamp":1765600574000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2023-071821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":43,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3,14]]},"published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10.1136\/bmjopen-2023-071821"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2023-071821","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}