{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:12:10Z","timestamp":1785881530423,"version":"3.56.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Acute kidney injury (AKI) is one of the most severe consequences of kidney injury, and it will also cause or aggravate the complications by the fast decline of kidney excretory function. Accurate AKI prediction, including the AKI case, AKI stage, and AKI onset time interval, can provide adequate support for effective interventions. Besides, discovering how the medical features affect the AKI result may also provide supporting information for disease treatment. An attention-based temporal neural network approach was employed in this study for AKI prediction and for the analysis of the impact of medical features from temporal electronic health record (EHR) data of patients before AKI diagnosis. We used the publicly available dataset provided by the Medical Information Mart for Intensive Care (MIMIC) for model training, validation, and testing, and then the model was applied in clinical practice. The improvement of AKI case prediction is around 5% AUC (area under the receiver operating characteristic curve), and the AUC value of AKI stage prediction on AKI stage 3 is over 82%. We also analyzed the data by two steps: the associations between the medical features and the AKI case (positive or inverse) and the extent of the impact of medical features on AKI prediction result. It shows that features, such as lactate, glucose, creatinine, blood urea nitrogen (BUN), prothrombin time (PT), and partial thromboplastin time (PTT), are positively associated with the AKI case, while there are inverse associations between the AKI case and features such as platelet, hemoglobin, hematocrit, urine, and international normalized ratio (INR). The laboratory test features such as urine, glucose, creatinine, sodium, and blood urea nitrogen and the medication features such as nonsteroidal anti-inflammatory drugs, agents acting on the renin\u2013angiotensin system, and lipid-lowering medication were detected to have higher weights than other features in the proposed model, which may imply that these features have a great impact on the AKI case.<\/jats:p>","DOI":"10.3389\/fmed.2021.658665","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T07:34:34Z","timestamp":1622792074000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Analysis of the Impact of Medical Features and Risk Prediction of Acute Kidney Injury for Critical Patients Using Temporal Electronic Health Record Data With Attention-Based Neural Network"],"prefix":"10.3389","volume":"8","author":[{"given":"Zhimeng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuri","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xieli","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuna","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinqiong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuren","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinting","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiahong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"key":"B1","first-page":"687","article-title":"Acute kidney injury: diagnosis and management","volume":"100","author":"Mercado","year":"2019","journal-title":"Am Fam Phys."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1007\/s00134-015-3934-7","volume":"41","year":"2015","journal-title":"Intens. Care Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"12","DOI":"10.2215\/CJN.02730313","article-title":"Incidence, outcomes, and comparisons across definitions of AKI in hospitalized individuals","volume":"9","author":"Zeng","year":"2014","journal-title":"Clin J Am Soc Nephrol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-016-0277-4","article-title":"Prediction and detection models for acute kidney injury in hospitalized older adults","volume":"16","author":"Kate","year":"2016","journal-title":"BMC Med Inform Decis Mak"},{"key":"B5","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/cpt.1826","article-title":"Predicting inpatient medication orders from electronic health record data","volume":"108","author":"Rough","year":"2020","journal-title":"Clin Pharmacol Ther."},{"key":"B6","article-title":"Predicting discharge medications at admission time based on deep learning","author":"Yang","year":"2017"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/srep26094","article-title":"Deep patient: an unsupervised representation to predict the future of patients from the electronic health records","volume":"6","author":"Miotto","year":"2016","journal-title":"Sci Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"3268","DOI":"10.1109\/JBHI.2020.2984931","article-title":"TAPER: Time-aware patient EHR representation","volume":"24","author":"Darabi","year":"2020","journal-title":"IEEE J Biomed Heal Informatics."},{"key":"B9","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1093\/jamia\/ocw112","article-title":"Using recurrent neural network models for early detection of heart failure onset","volume":"24","author":"Choi","year":"2017","journal-title":"J Am Med Informatics Assoc."},{"key":"B10","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/JBHI.2016.2633963","article-title":"Deepr: a convolutional net for medical records","volume":"21","author":"Nguyen","year":"2017","journal-title":"IEEE J Biomed Heal Informatics."},{"key":"B11","first-page":"683","article-title":"Early prediction of acute kidney injury in critical care setting using clinical notes","volume-title":"Proc - 2018 IEEE Int Conf Bioinforma Biomed BIBM","author":"Li","year":"2019"},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1007\/11671299_34","article-title":"NLP (Natural Language Processing) for NLP (Natural Language Programming)","volume-title":"Computational Linguistics and Intelligent Text Processing, 7th International Conference, CICLing 2006","author":"Mihalcea","year":"2006"},{"key":"B13","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","article-title":"A clinically applicable approach to continuous prediction of future acute kidney injury","volume":"572","author":"Toma\u0161ev","year":"2019","journal-title":"Nature."},{"key":"B14","doi-asserted-by":"publisher","first-page":"103361","DOI":"10.1016\/j.jbi.2019.103361","article-title":"Identifying sub-phenotypes of acute kidney injury using structured and unstructured electronic health record data with memory networks","volume":"102","author":"Xu","year":"2020","journal-title":"J Biomed Inform."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1097\/CCM.0000000000003123","article-title":"The development of a machine learning inpatient acute kidney injury prediction model","volume":"46","author":"Koyner","year":"2018","journal-title":"Crit Care Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"R204","DOI":"10.1186\/cc2872","article-title":"Acute renal failure - definition, outcome measures, animal models, fluid therapy and information technology needs: the Second International Consensus Conference of the Acute Dialysis Quality Initiative (ADQI) Group","volume":"8","author":"Bellomo","year":"2004","journal-title":"Crit Care."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1038\/sj.ki.5002231","article-title":"Modified RIFLE criteria in critically ill children with acute kidney injury","volume":"71","author":"Akcan-Arikan","year":"2007","journal-title":"Kidney Int."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1016\/S0140-6736(09)60751-0","article-title":"GFR shot by RIFLE: errors in staging acute kidney injury","volume":"373","author":"Pickering","year":"2009","journal-title":"Lancet."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1159\/000339789","article-title":"Kidney disease:. KDIGO clinical practice guideline for acute kidney injury","volume":"2","author":"Kellum","year":"2012","journal-title":"Kidney Int Suppl."},{"key":"B20","doi-asserted-by":"publisher","first-page":"247","DOI":"10.7326\/0003-4819-145-4-200608150-00004","article-title":"Using standardized serum creatinine values in the modification of diet in renal disease study equation for estimating glomerular filtration rate","volume":"145","author":"Levey","year":"2006","journal-title":"Ann Intern Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data."},{"key":"B22","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1039\/c3mb70490d","article-title":"A hybrid method for prediction and repositioning of drug Anatomical Therapeutic Chemical classes","volume":"10","author":"Chen","year":"2014","journal-title":"Mol Biosyst."},{"key":"B23","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1177\/009286159803200317","article-title":"Comparison and analysis of the national drug code systems among drug information databases","volume":"32","author":"Guo","year":"1998","journal-title":"Drug Inf Assoc."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.1371\/journal.pmed.0050045","article-title":"Initial severity and antidepressant benefits: a meta-analysis of data submitted to the food and drug administration","volume":"5","author":"Kirsch","year":"2008","journal-title":"PLoS Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"042050","DOI":"10.1088\/1742-6596\/1213\/4\/042050","article-title":"Temporal convolutional networks for anomaly detection in time series","volume":"1213","author":"He","year":"2019","journal-title":"J Phys Conf Ser."},{"key":"B26","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"B27","doi-asserted-by":"publisher","first-page":"103957","DOI":"10.1016\/j.compbiomed.2020.103957","article-title":"Automated prediction of sepsis using temporal convolutional network","volume":"2020","author":"Kok","year":"2020","journal-title":"Comput Biol Med"},{"key":"B28","unstructured":"RazavianN\n            SontagD\n          Temporal Convolutional Neural Networks for Diagnosis from Lab Tests2015"},{"key":"B29","first-page":"5999","article-title":"Attention is all you need","volume":"2017","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B31","unstructured":"Adaptive dropout for training deep neural networks\n            BaJ\n            FreyB\n          Advances in Neural Information Processing Systems2013"},{"key":"B32","unstructured":"Convergence analysis of two-layer neural networks with ReLU Activation597607\n            LiY\n            YuanY\n          Princeton, NJAdvances in Neural Information Processing Systems2017"},{"key":"B33","unstructured":"A empirical study of binary neural networks' optimisation\n            AlizadehM\n            Fern\u00e1ndez-Marqu\u00e9sJ\n            LaneND\n            GalY\n          OxfordInternational Conference on Learning Representations2018"},{"key":"B34","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/s10994-018-5704-6","article-title":"Learning to predict soccer results from relational data with gradient boosted trees","volume":"108","author":"Hub\u00e1\u010dek","year":"2019","journal-title":"Mach Learn"},{"key":"B35","doi-asserted-by":"publisher","first-page":"956","DOI":"10.2307\/353415","article-title":"A tutorial in logistic regression","volume":"57","author":"DeMaris","year":"1995","journal-title":"J Marriage Fam"},{"key":"B36","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/01431160412331269698","article-title":"Random forest classifier for remote sensing classification","volume":"26","author":"Pal","year":"2005","journal-title":"Int J Remote Sens"},{"key":"B37","first-page":"1","article-title":"Learning to diagnose with LSTM recurrent neural networks","volume-title":"4th International Conference on Learn Represent ICLR 2016 - Conf Track Proceedings","author":"Lipton","year":"2016"},{"key":"B38","unstructured":"TensorFlow: a system for large-scale machine learning26583\n            AbadiM\n            BarhamP\n            ChenJ\n            ChenZ\n            DavisA\n            DeanJ\n          Savannah, GA{USENIX} Association12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16)2016"},{"key":"B39","article-title":"{API} design for machine learning software: experiences from the SCIKIT-learn project","author":"Buitinck","year":"2013","journal-title":"CoRR"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1681\/ASN.2014070724","article-title":"Classifying AKI by urine output versus serum creatinine level","volume":"26","author":"Kellum","year":"2015","journal-title":"J Am Soc Nephrol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/S0828-282X(10)70357-3","article-title":"Impact of admission serum glucose level on in-hospital outcomes following coronary artery bypass grafting surgery","volume":"26","author":"Imran","year":"2010","journal-title":"Can J Cardiol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1111\/j.1463-1326.2009.01037.x","article-title":"A randomized clinical trial comparing the effect of basal insulin and inhaled mealtime insulin on glucose variability and oxidative stress","volume":"11","author":"Siegelaar","year":"2010","journal-title":"Diabetes Obes Metab"},{"key":"B43","doi-asserted-by":"publisher","first-page":"e82992","DOI":"10.1371\/journal.pone.0082992","article-title":"Risk factors for acute kidney injury in severe rhabdomyolysis","volume":"8","author":"Rodr\u00edguez","year":"2013","journal-title":"PLoS ONE."},{"key":"B44","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s11739-020-02462-5","article-title":"Serum sodium variability and acute kidney injury: a retrospective observational cohort study on a hospitalized population","volume":"16","author":"Lombardi","year":"2020","journal-title":"Intern Emerg Med"},{"key":"B45","first-page":"400","article-title":"Time for a comeback of NSAIDs in proteinuric chronic kidney disease?","volume":"68","author":"Vogt","year":"2010","journal-title":"Neth J Med."},{"key":"B46","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1002\/14651858.CD010480","article-title":"HMG CoA reductase inhibitors (statins) for preventing acute kidney injury after surgical procedures requiring cardiac bypass: a systematic review and meta-analysis","volume":"19","author":"Lewicki","year":"2014","journal-title":"Nephrology"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.658665\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T07:34:45Z","timestamp":1622792085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.658665\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,4]]},"references-count":46,"alternative-id":["10.3389\/fmed.2021.658665"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2021.658665","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,4]]},"article-number":"658665"}}