{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:23:05Z","timestamp":1782976985749,"version":"3.54.5"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T00:00:00Z","timestamp":1583366400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T00:00:00Z","timestamp":1583366400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71771034"],"award-info":[{"award-number":["71771034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71421001"],"award-info":[{"award-number":["71421001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Jieyang","award":["2017xm041"],"award-info":[{"award-number":["2017xm041"]}]},{"name":"Scientific and Technological Innovation Foundation of Dalian","award":["2018J11CY009"],"award-info":[{"award-number":["2018J11CY009"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>Clinical prediction tasks such as patient mortality, length of hospital stay, and disease diagnosis are highly important in critical care research. The existing studies for clinical prediction mainly used simple summary statistics to summarize information from physiological time series. However, this lack of statistics leads to a lack of information. In addition, using only maximum and minimum statistics to indicate patient features fails to provide an adequate explanation. Few studies have evaluated which summary statistics best represent physiological time series.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Methods<\/jats:title>\n<jats:p>In this paper, we summarize 14 statistics describing the characteristics of physiological time series, including the central tendency, dispersion tendency, and distribution shape. Then, we evaluate the use of summary statistics of physiological time series as features for three clinical prediction tasks. To find the combinations of statistics that yield the best performances under different tasks, we use a cross-validation-based genetic algorithm to approximate the optimal statistical combination.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>By experiments using the EHRs of 6,927 patients, we obtained prediction results based on both single statistics and commonly used combinations of statistics under three clinical prediction tasks. Based on the results of an embedded cross-validation genetic algorithm, we obtained 25 optimal sets of statistical combinations and then tested their prediction results. By comparing the performances of prediction with single statistics and commonly used combinations of statistics with quantitative analyses of the optimal statistical combinations, we found that some statistics play central roles in patient representation and different prediction tasks have certain commonalities.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Through an in-depth analysis of the results, we found many practical reference points that can provide guidance for subsequent related research. Statistics that indicate dispersion tendency, such as min, max, and range, are more suitable for length of stay prediction tasks, and they also provide information for short-term mortality prediction. Mean and quantiles that reflect the central tendency of physiological time series are more suitable for mortality and disease prediction. Skewness and kurtosis perform poorly when used separately for prediction but can be used as supplementary statistics to improve the overall prediction effect.<\/jats:p>\n<\/jats:sec>","DOI":"10.1186\/s12911-020-1063-x","type":"journal-article","created":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T17:02:42Z","timestamp":1583427762000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["An evaluation of time series summary statistics as features for clinical prediction tasks"],"prefix":"10.1186","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5155-1297","authenticated-orcid":false,"given":"Chonghui","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,3,5]]},"reference":[{"issue":"1","key":"1063_CR1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s12911-019-0733-z","volume":"19","author":"LP Zimmerman","year":"2019","unstructured":"Zimmerman LP, Reyfman PA, Smith AD, Zeng Z, Kho A, Sanchez-Pinto LN, Luo Y. Early prediction of acute kidney injury following icu admission using a multivariate panel of physiological measurements. BMC Med Inf Decis Making. 2019; 19(1):16.","journal-title":"BMC Med Inf Decis Making"},{"issue":"1","key":"1063_CR2","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/1472-6947-10-27","volume":"10","author":"AA Kramer","year":"2010","unstructured":"Kramer AA, Zimmerman JE. A predictive model for the early identification of patients at risk for a prolonged intensive care unit length of stay. BMC Med Inf Decis Making. 2010; 10(1):27.","journal-title":"BMC Med Inf Decis Making"},{"key":"1063_CR3","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/BF01709751","volume":"22","author":"J-L Vincent","year":"1996","unstructured":"Vincent J-L, Moreno R, Takala J, Willatts S, De Mendon\u00e7a A, Bruining H, Reinhart C, Suter P, Thijs L. The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction\/failure. Intensive Care Med. 1996; 22:707\u201310.","journal-title":"Intensive Care Med"},{"issue":"1","key":"1063_CR4","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/1472-6947-8-56","volume":"8","author":"T Verplancke","year":"2008","unstructured":"Verplancke T, Looy SV, Benoit D, Vansteelandt S, Depuydt P, Turck FD, Decruyenaere J. Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies. BMC Med Inf Decis Making. 2008; 8(1):56.","journal-title":"BMC Med Inf Decis Making"},{"issue":"24","key":"1063_CR5","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1001\/jama.1993.03510240069035","volume":"270","author":"J-R Le Gall","year":"1993","unstructured":"Le Gall J-R, Lemeshow S, Saulnier F. A new simplified acute physiology score (SAPS II) based on a european\/north american multicenter study. JAMA. 1993; 270(24):2957\u201363.","journal-title":"JAMA"},{"issue":"2","key":"1063_CR6","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1097\/00024382-199808000-00001","volume":"10","author":"AE Baue","year":"1998","unstructured":"Baue AE, Durham R, Faist E. Systemic inflammatory response syndrome (SIRS), multiple organ dysfunction syndrome (MODS), multiple organ failure (MOF): are we winning the battle. Shock. 1998; 10(2):79\u201389.","journal-title":"Shock"},{"issue":"1","key":"1063_CR7","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1186\/s12911-017-0566-6","volume":"17","author":"S Sakr","year":"2017","unstructured":"Sakr S, Elshawi R, Ahmed AM, Qureshi WT, Brawner CA, Keteyian SJ, Blaha MJ, Al-Mallah MH. Comparison of machine learning techniques to predict all-cause mortality using fitness data: the henry ford exercise testing (fit) project. BMC Med Inf Decis Making. 2017; 17(1):174.","journal-title":"BMC Med Inf Decis Making"},{"key":"1063_CR8","volume-title":"International Conference on Pattern Recognition and Machine Intelligence","author":"S Chandrakala","year":"2009","unstructured":"Chandrakala S, Sekhar CC. Classification of multi-variate varying length time series using descriptive statistical features. In: International Conference on Pattern Recognition and Machine Intelligence. Berlin: Springer: 2009. p. 13\u20138."},{"key":"1063_CR9","unstructured":"Harutyunyan H, Khachatrian H, Kale DC, Galstyan A. Multitask learning and benchmarking with clinical time series data. 2017. arXiv preprint arXiv:1703.07771. https:\/\/arxiv.org\/abs\/1703.07771."},{"key":"1063_CR10","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.jbi.2018.04.007","volume":"83","author":"S Purushotham","year":"2018","unstructured":"Purushotham S, Meng C, Che Z, Liu Y. Benchmarking deep learning models on large healthcare datasets. J Biomed Inf. 2018; 83:112\u201334.","journal-title":"J Biomed Inf"},{"issue":"5","key":"1063_CR11","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1097\/00003246-199605000-00004","volume":"24","author":"MM Pollack","year":"1996","unstructured":"Pollack MM, Patel KM, Ruttimann UE. PRISM III: an updated pediatric risk of mortality score. Crit Care Med. 1996; 24(5):743\u201352.","journal-title":"Crit Care Med"},{"key":"1063_CR12","volume-title":"Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE","author":"VJ Ribas","year":"2011","unstructured":"Ribas VJ, L\u00f3pez JC, Ruiz-Sanmart\u00edn A, Ruiz-Rodr\u00edguez JC, Rello J, Wojdel A, Vellido A. Severe sepsis mortality prediction with relevance vector machines. In: Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE. Piscataway: IEEE: 2011. p. 100\u20133."},{"issue":"18","key":"1063_CR13","doi-asserted-by":"publisher","first-page":"13158","DOI":"10.1016\/j.eswa.2012.05.086","volume":"39","author":"AS Fialho","year":"2012","unstructured":"Fialho AS, Cismondi F, Vieira SM, Reti SR, Sousa JM, Finkelstein SN. Data mining using clinical physiology at discharge to predict ICU readmissions. Expert Syst Appl. 2012; 39(18):13158\u201365.","journal-title":"Expert Syst Appl"},{"key":"1063_CR14","first-page":"481","volume":"39","author":"A Bosnjak","year":"2012","unstructured":"Bosnjak A, Montilla G. Predicting mortality of ICU patients using statistics of physiological variables and support vector machines. Comput Cardiol. 2012; 39:481\u20134.","journal-title":"Comput Cardiol"},{"key":"1063_CR15","volume-title":"Advances in Neural Information Processing Systems","author":"J Wiens","year":"2012","unstructured":"Wiens J, Horvitz E, Guttag JV. Patient risk stratification for hospital-associated c. diff as a time-series classification task. In: Advances in Neural Information Processing Systems. Cambridge: MIT: 2012. p. 467\u201375."},{"key":"1063_CR16","first-page":"315","volume":"21","author":"E Gultepe","year":"2013","unstructured":"Gultepe E, Green JP, Nguyen H, Adams J, Albertson T, Tagkopoulos I. From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system. JAMA. 2013; 21:315\u201325.","journal-title":"JAMA"},{"issue":"1","key":"1063_CR17","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/S2213-2600(14)70239-5","volume":"3","author":"R Pirracchio","year":"2015","unstructured":"Pirracchio R, Petersen ML, Carone M, Rigon MR, Chevret S, van der Laan MJ. Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study. Lancet Respir Med. 2015; 3(1):42\u201352.","journal-title":"Lancet Respir Med"},{"issue":"5","key":"1063_CR18","first-page":"0127428","volume":"10","author":"J Lee","year":"2015","unstructured":"Lee J, Maslove DM, Dubin JA. Personalized mortality prediction driven by electronic medical data and a patient similarity metric. PloS ONE. 2015; 10(5):0127428.","journal-title":"PloS ONE"},{"key":"1063_CR19","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.jbi.2015.05.021","volume":"56","author":"NM Arzeno","year":"2015","unstructured":"Arzeno NM, Lawson KA, Duzinski SV, Vikalo H. Designing optimal mortality risk prediction scores that preserve clinical knowledge. J Biomed Inf. 2015; 56:145\u201356.","journal-title":"J Biomed Inf"},{"key":"1063_CR20","unstructured":"Lipton ZC, Kale DC, Elkan C, Wetzel R. Learning to diagnose with LSTM recurrent neural networks. 2015. arXiv preprint arXiv:1511.03677. https:\/\/arxiv.org\/abs\/1511.03677."},{"key":"1063_CR21","volume-title":"Secondary Analysis of Electronic Health Records","author":"J Lee","year":"2016","unstructured":"Lee J, Dubin JA, Maslove DM. Mortality prediction in the ICU. In: Secondary Analysis of Electronic Health Records. Cambridge: Springer: 2016. p. 315\u201324."},{"key":"1063_CR22","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.ijmedinf.2017.10.002","volume":"108","author":"A Awad","year":"2017","unstructured":"Awad A, Bader-El-Den M, McNicholas J, Briggs J. Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach. Int J Med Inform. 2017; 108:185\u201395.","journal-title":"Int J Med Inform"},{"key":"1063_CR23","unstructured":"Morid MA, Sheng ORL, Abdelrahman S. PPMF: A Patient-based Predictive Modeling Framework for Early ICU Mortality Prediction. 2017. arXiv preprint arXiv:1704.07499. Available from https:\/\/arxiv.org\/abs\/1704.07499."},{"key":"1063_CR24","volume-title":"AMIA Annual Symposium Proceedings, vol 2017","author":"E Sherman","year":"2017","unstructured":"Sherman E, Gurm H, Balis U, Owens S, Wiens J. Leveraging clinical time-series data for prediction: a cautionary tale. In: AMIA Annual Symposium Proceedings, vol 2017. Bethesda: American Medical Informatics Association: 2017. p. 1571."},{"key":"1063_CR25","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jbi.2017.11.015","volume":"78","author":"MB Mayhew","year":"2018","unstructured":"Mayhew MB, Petersen BK, Sales AP, Greene JD, Liu VX, Wasson TS. Flexible, cluster-based analysis of the electronic medical record of sepsis with composite mixture models. J Biomed Inf. 2018; 78:33\u201342.","journal-title":"J Biomed Inf"},{"key":"1063_CR26","volume-title":"AMIA Annual Symposium Proceedings, vol 2009","author":"CW Hug","year":"2009","unstructured":"Hug CW, Szolovits P. ICU acuity: real-time models versus daily models. In: AMIA Annual Symposium Proceedings, vol 2009. Bethesda: American Medical Informatics Association: 2009. p. 260."},{"key":"1063_CR27","volume-title":"Computing in Cardiology (CinC)","author":"S McMillan","year":"2012","unstructured":"McMillan S, Chia C-C, Van Esbroeck A, Rubinfeld I, Syed Z. ICU mortality prediction using time series motifs. In: Computing in Cardiology (CinC). Piscataway: IEEE: 2012. p. 265\u201368."},{"issue":"1","key":"1063_CR28","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/cc8864","volume":"14","author":"MJ Cohen","year":"2010","unstructured":"Cohen MJ, Grossman AD, Morabito D, Knudson MM, Butte AJ, Manley GT. Identification of complex metabolic states in critically injured patients using bioinformatic cluster analysis. Crit Care. 2010; 14(1):10.","journal-title":"Crit Care"},{"key":"1063_CR29","volume-title":"AAAI","author":"Y Luo","year":"2016","unstructured":"Luo Y, Xin Y, Joshi R, Celi LA, Szolovits P. Predicting ICU mortality risk by grouping temporal trends from a multivariate panel of physiologic measurements. In: AAAI. Menlo Park: AAAI: 2016. p. 42\u201350."},{"issue":"2","key":"1063_CR30","doi-asserted-by":"publisher","first-page":"91","DOI":"10.2174\/157340908784533256","volume":"4","author":"MA Demel","year":"2008","unstructured":"Demel MA, Janecek AG, Thai K-M, Ecker GF, Gansterer WN. Predictive qsar models for polyspecific drug targets: The importance of feature selection. Curr Comput Aided Drug Des. 2008; 4(2):91\u2013110.","journal-title":"Curr Comput Aided Drug Des"},{"issue":"1","key":"1063_CR31","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/j.engappai.2012.01.017","volume":"26","author":"MJ Abdi","year":"2013","unstructured":"Abdi MJ, Giveki D. Automatic detection of erythemato-squamous diseases using PSO\u2013SVM based on association rules. Eng Appl Artif Intell. 2013; 26(1):603\u20138.","journal-title":"Eng Appl Artif Intell"},{"key":"1063_CR32","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2019.08.047","volume":"368","author":"W Wei","year":"2019","unstructured":"Wei W, Guo C. A text semantic topic discovery method based on the conditional co-occurrence degree. Neurocomputing. 2019; 368:11\u201324.","journal-title":"Neurocomputing"},{"issue":"5","key":"1063_CR33","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1002\/cem.1180060506","volume":"6","author":"R Leardi","year":"1992","unstructured":"Leardi R, Boggia R, Terrile M. Genetic algorithms as a strategy for feature selection. J Chemom. 1992; 6(5):267\u201381.","journal-title":"J Chemom"},{"issue":"1","key":"1063_CR34","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s12911-015-0227-6","volume":"15","author":"M Mohammadi","year":"2015","unstructured":"Mohammadi M, Alazab F, Raahemi B, Richards G, Jaworska N, Smith D, Salle SDL, Blier P, Knott V. Data mining eeg signals in depression for their diagnostic value. BMC Med Inf Dec Making. 2015; 15(1):108.","journal-title":"BMC Med Inf Dec Making"},{"issue":"5","key":"1063_CR35","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1007\/s00521-016-2780-z","volume":"30","author":"D Ke\u010do","year":"2018","unstructured":"Ke\u010do D, Subasi A, Kevric J. Cloud computing-based parallel genetic algorithm for gene selection in cancer classification. Neural Comput Applic. 2018; 30(5):1601\u201310.","journal-title":"Neural Comput Applic"},{"key":"1063_CR36","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.measurement.2016.07.043","volume":"94","author":"L Lu","year":"2016","unstructured":"Lu L, Yan J, de Silva CW. Feature selection for ECG signal processing using improved genetic algorithm and empirical mode decomposition. Measurement. 2016; 94:372\u201381.","journal-title":"Measurement"},{"issue":"1","key":"1063_CR37","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.dsp.2012.07.008","volume":"23","author":"A \u00d6z\u00e7ift","year":"2013","unstructured":"\u00d6z\u00e7ift A, G\u00fclten A. Genetic algorithm wrapped bayesian network feature selection applied to differential diagnosis of erythemato-squamous diseases. Digit Signal Process. 2013; 23(1):230\u20137.","journal-title":"Digit Signal Process"},{"key":"1063_CR38","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson AE, Pollard TJ, Shen L, Li-wei HL, Feng M, Ghassemi M, Moody B, Szolovits P, Celi LA, Mark RG. MIMIC-III, a freely accessible critical care database. Sci Data. 2016; 3:160035.","journal-title":"Sci Data"},{"key":"1063_CR39","unstructured":"Johnson AE, Pollard TJ, Mark RG. Reproducibility in critical care: a mortality prediction case study. In: Proceedings of the 2nd Machine Learning for Healthcare Conference. Boston: 2017. p. 361\u201376. http:\/\/proceedings.mlr.press\/v68\/johnson17a.html."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-1063-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-020-1063-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-020-1063-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:09:39Z","timestamp":1614902979000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-020-1063-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,5]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1063"],"URL":"https:\/\/doi.org\/10.1186\/s12911-020-1063-x","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,5]]},"assertion":[{"value":"21 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}