{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T03:02:52Z","timestamp":1783393372157,"version":"3.54.6"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Patients in Intensive Care Units (ICU) face the threat of decompensation, a rapid decline in health associated with a high risk of death. This study focuses on creating and evaluating machine learning (ML) models to predict decompensation risk in ICU patients. It proposes a novel approach using patient vitals and clinical data within a specified timeframe to forecast decompensation risk sequences. The study implemented and assessed long short-term memory (LSTM) and hybrid convolutional neural network (CNN)-LSTM architectures, along with traditional ML algorithms as baselines. Additionally, it introduced a novel decompensation score based on the predicted risk, validated through principal component analysis (PCA) and k-means analysis for risk stratification. The results showed that, with PPV = 0.80, NPV = 0.96 and AUC-ROC = 0.90, CNN-LSTM had the best performance when predicting decompensation risk sequences. The decompensation score\u2019s effectiveness was also confirmed (PPV = 0.83 and NPV = 0.96). SHAP plots were generated for the overall model and two risk strata, illustrating variations in feature importance and their associations with the predicted risk. Notably, this study represents the first attempt to predict a sequence of decompensation risks rather than single events, a critical advancement given the challenge of early decompensation detection. Predicting a sequence facilitates early detection of increased decompensation risk and pace, potentially leading to saving more lives.<\/jats:p>","DOI":"10.3390\/a17010006","type":"journal-article","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T20:48:37Z","timestamp":1703450917000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Predicting Decompensation Risk in Intensive Care Unit Patients Using Machine Learning"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9374-7078","authenticated-orcid":false,"given":"Nosa","family":"Aikodon","sequence":"first","affiliation":[{"name":"Data Science Research Centre, Liverpool John Moores University, Liverpool L3 3AF, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9927-3209","authenticated-orcid":false,"given":"Sandra","family":"Ortega-Martorell","sequence":"additional","affiliation":[{"name":"Data Science Research Centre, Liverpool John Moores University, Liverpool L3 3AF, UK"},{"name":"Liverpool Centre for Cardiovascular Science, University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool L3 3AF, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5679-7501","authenticated-orcid":false,"given":"Ivan","family":"Olier","sequence":"additional","affiliation":[{"name":"Data Science Research Centre, Liverpool John Moores University, Liverpool L3 3AF, UK"},{"name":"Liverpool Centre for Cardiovascular Science, University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool L3 3AF, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e0744","DOI":"10.1097\/CCE.0000000000000744","article-title":"Artificial Intelligence for the Prediction of In-Hospital Clinical Deterioration: A Systematic Review","volume":"4","author":"Veldhuis","year":"2022","journal-title":"Crit. Care Explor."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kia, A., Timsina, P., Joshi, H.N., Klang, E., Gupta, R.R., Freeman, R.M., Reich, D.L., Tomlinson, M.S., Dudley, J.T., and Kohli-Seth, R. (2020). MEWS++: Enhancing the prediction of clinical deterioration in admitted patients through a machine learning model. J. Clin. Med., 9.","DOI":"10.3390\/jcm9020343"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.jtcvs.2021.10.060","article-title":"Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records","volume":"164","author":"Ruiz","year":"2022","journal-title":"J. Thorac. Cardiovasc. Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e179","DOI":"10.1016\/S2589-7500(20)30018-2","article-title":"Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: A retrospective study of high-frequency data in electronic patient records","volume":"2","author":"Nielsen","year":"2020","journal-title":"Lancet Digit. Health"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ho, L.V., Aczon, M., Ledbetter, D., and Wetzel, R. (2021). Interpreting a recurrent neural network\u2019s predictions of ICU mortality risk. J. Biomed. Inform., 114.","DOI":"10.1016\/j.jbi.2021.103672"},{"key":"ref_6","unstructured":"Leung, K.K., Rooke, C., Smith, J., Zuberi, S., and Volkovs, M. (2021). Temporal Dependencies in Feature Importance for Time Series Predictions. arxiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5929","DOI":"10.1007\/s10462-020-09838-1","article-title":"A review on the long short-term memory model","volume":"53","author":"Mosquera","year":"2020","journal-title":"Artif. Intell. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Solares, J.R.A., Raimondi, F.E.D., Zhu, Y., Rahimian, F., Canoy, D., Tran, J., Gomes, A.C.P., Payberah, A.H., Zottoli, M., and Nazarzadeh, M. (2020). Deep learning for electronic health records: A comparative review of multiple deep neural architectures. J. Biomed. Inform., 101.","DOI":"10.1016\/j.jbi.2019.103337"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci. Data"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2429","DOI":"10.1002\/sim.1519","article-title":"Last observation carry-forward and last observation analysis","volume":"22","author":"Shao","year":"2003","journal-title":"Stat. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s41597-019-0103-9","article-title":"Multitask learning and benchmarking with clinical time series data","volume":"6","author":"Harutyunyan","year":"2019","journal-title":"Sci. Data"},{"key":"ref_12","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer. [3rd ed.]."},{"key":"ref_13","unstructured":"Murugan, P. (2018). Learning the Sequential Temporal Information with Recurrent Neural Networks. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"17351","DOI":"10.1007\/s00521-020-04867-x","article-title":"A CNN\u2013LSTM model for gold price time-series forecasting","volume":"32","author":"Livieris","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref_16","first-page":"499","article-title":"The National Early Warning Score: From concept to NHS implementation","volume":"22","author":"Williams","year":"2022","journal-title":"Clin. Med. J. R. Coll. Physicians Lond."},{"key":"ref_17","unstructured":"(2023, November 02). Molnar. 9.6 SHAP (SHapley Additive Explanations). A Guide for Making Black Box Models Explainable. Available online: https:\/\/christophm.github.io\/interpretable-ml-book."},{"key":"ref_18","first-page":"4211","article-title":"How can I explain this to you? An empirical study of deep neural network explanation methods","volume":"33","author":"Jeyakumar","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1136\/thoraxjnl-2013-204762","article-title":"Factors associated with clinical deterioration shortly after PE","volume":"69","author":"Kabrhel","year":"2014","journal-title":"Thorax"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"571396","DOI":"10.3389\/fmed.2020.571396","article-title":"Association Between Clinical Characteristics and Short-Term Outcomes in Adult Male COVID-19 Patients With Mild Clinical Symptoms: A Single-Center Observational Study","volume":"7","author":"Yan","year":"2021","journal-title":"Front. Med."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, J.-R., Jung, Y.-K., Hong, S.-B., and Huh, J.W. (2022). Predictors of Repeat Medical Emergency Team Activation in Deteriorating Ward Patients: A Retrospective Cohort Study. J. Clin. Med., 11.","DOI":"10.3390\/jcm11061736"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"670694","DOI":"10.3389\/fmed.2021.670694","article-title":"Investigation of Coagulation Biomarkers to Assess Clinical Deterioration in SARS-CoV-2 Infection","volume":"8","author":"Billoir","year":"2021","journal-title":"Front. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1230854","DOI":"10.3389\/fmed.2023.1230854","article-title":"Sepsis-induced coagulopathy is associated with new episodes of atrial fibrillation in patients admitted to critical care in sinus rhythm","volume":"10","author":"Olier","year":"2023","journal-title":"Front. Med."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Tekle, E., Gelaw, Y., Dagnew, M., Gelaw, A., Negash, M., Kassa, E., Bizuneh, S., Wudineh, D., and Asrie, F. (2022). Risk stratification and prognostic value of prothrombin time and activated partial thromboplastin time among COVID-19 patients. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0272216"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"49","DOI":"10.2147\/HMER.S244596","article-title":"Clinical Implications of Thrombocytopenia for the Cirrhotic Patient","volume":"12","author":"Sigal","year":"2020","journal-title":"Hepatic Med. Evid. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"40","DOI":"10.4291\/wjgp.v12.i3.40","article-title":"Platelet count as a screening tool for compensated cirrhosis in chronic viral hepatitis","volume":"12","author":"Surana","year":"2021","journal-title":"World J. Gastrointest. Pathophysiol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"809","DOI":"10.5306\/wjco.v11.i10.809","article-title":"Critically ill patients with cancer: A clinical perspective","volume":"11","author":"Lespoir","year":"2020","journal-title":"World J. Clin. Oncol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e000018","DOI":"10.1136\/esmoopen-2015-000018","article-title":"Critically ill patients with cancer: Chances and limitations of intensive care medicine\u2014A narrative review","volume":"1","author":"Schellongowski","year":"2016","journal-title":"ESMO Open"},{"key":"ref_29","unstructured":"(2023, November 01). NICE. Platelets\u2014Abnormal Counts and Cancer|Clinical Knowledge Summary|National Institute for Health and Care Excellence (NICE). Available online: https:\/\/cks.nice.org.uk\/topics\/platelets-abnormal-counts-cancer\/."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e622","DOI":"10.3399\/bjgp20X710957","article-title":"Cancer incidence following a high-normal platelet count: Cohort study using electronic healthcare records from English primary care","volume":"70","author":"Mounce","year":"2020","journal-title":"Br. J. Gen. Pract."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Aoun, M., and Tabbah, R. (2016). Case report: Severe bradycardia, a reversible cause of \u201cCardio-Renal-Cerebral Syndrome\u201d. BMC Nephrol., 17.","DOI":"10.1186\/s12882-016-0375-7"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"662","DOI":"10.4254\/wjh.v7.i4.662","article-title":"Arrhythmia risk in liver cirrhosis","volume":"7","author":"Mozos","year":"2015","journal-title":"World J. Hepatol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"704073","DOI":"10.3389\/fcvm.2021.704073","article-title":"Risk Factors of Atrial Arrhythmia in Patients With Liver Cirrhosis: A Retrospective Study","volume":"8","author":"Lu","year":"2021","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"53","DOI":"10.2174\/1573403X09666131117174414","article-title":"Acute Decompensated Heart Failure Update","volume":"11","author":"Teerlink","year":"2015","journal-title":"Curr. Cardiol. Rev."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1002\/ejhf.2206","article-title":"Patient profiling in heart failure for tailoring medical therapy. A consensus document of the Heart Failure Association of the European Society of Cardiology","volume":"23","author":"Rosano","year":"2021","journal-title":"Eur. J. Heart Fail."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1161\/CIRCHEARTFAILURE.108.830349","article-title":"Atrial Fibrillation and Acute Decompensated Heart Failure","volume":"2","author":"DiMarco","year":"2009","journal-title":"Circ. Heart Fail."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"897709","DOI":"10.3389\/fcvm.2022.897709","article-title":"Development of a Risk Prediction Model for New Episodes of Atrial Fibrillation in Medical-Surgical Critically Ill Patients Using the AmsterdamUMCdb","volume":"9","author":"Pieroni","year":"2022","journal-title":"Front. Cardiovasc. Med."},{"key":"ref_38","first-page":"315","article-title":"Atrial fibrillation in decompensated heart failure: Associated factors and in-hospital outcome","volume":"103","author":"Mendes","year":"2014","journal-title":"Arq. Bras. Cardiol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2816","DOI":"10.1002\/ehf2.13354","article-title":"Heart failure and atrial fibrillation: Tachycardia-mediated acute decompensation","volume":"8","author":"Park","year":"2021","journal-title":"ESC Heart Fail."},{"key":"ref_40","first-page":"282","article-title":"Identifying risk and management of acute haemodynamic decompensation during catheter ablation of ventricular tachycardia","volume":"7","author":"Muser","year":"2018","journal-title":"Arrhythmia Electrophysiol. Rev."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"euad122-339","DOI":"10.1093\/europace\/euad122.339","article-title":"Periprocedural acute hemodynamic decompensation associated with substrate-based ablation of ventricular tachycardia in patients with structural heart disease\u2014Rare and nonpredictable event","volume":"25","author":"Wichterle","year":"2023","journal-title":"Europace"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1007\/s10741-023-10303-8","article-title":"Infection as an under-recognized precipitant of acute heart failure: Prognostic and therapeutic implications","volume":"28","author":"Bezati","year":"2023","journal-title":"Heart Fail. Rev."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40885-019-0132-x","article-title":"Blood pressure and heart failure","volume":"26","author":"Oh","year":"2020","journal-title":"Clin. Hypertens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"e2160","DOI":"10.1097\/MD.0000000000002160","article-title":"High Blood Pressure and All-Cause and Cardiovascular Disease Mortalities in Community-Dwelling Older Adults","volume":"94","author":"Wu","year":"2015","journal-title":"Medicine"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"111","DOI":"10.15420\/ecr.2019.11.1","article-title":"Hypertension and Stroke: Update on Treatment","volume":"14","author":"Wajngarten","year":"2019","journal-title":"Eur. Cardiol. Rev."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"31","DOI":"10.23876\/j.krcp.21.099","article-title":"Association between blood pressure and the risk of chronic kidney disease in treatment-na\u00efve hypertensive patients","volume":"41","author":"Lee","year":"2022","journal-title":"Kidney Res. Clin. Pract."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"e007571","DOI":"10.1136\/bmjopen-2015-007571","article-title":"The correlation between blood pressure and kidney function decline in older people: A registry-based cohort study","volume":"5","author":"Vaes","year":"2015","journal-title":"BMJ Open"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1093\/cvr\/cvac135","article-title":"Blood pressure and risk of venous thromboembolism: A cohort analysis of 5.5 million UK adults and Mendelian randomization studies","volume":"119","author":"Nazarzadeh","year":"2022","journal-title":"Cardiovasc. Res."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1161\/CIRCULATIONAHA.121.056546","article-title":"Blood Pressure, Hypertension, and the Risk of Aortic Dissection Incidence and Mortality: Results From the J-SCH Study, the UK Biobank Study, and a Meta-Analysis of Cohort Studies","volume":"145","author":"Hibino","year":"2022","journal-title":"Circulation"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"e011991","DOI":"10.1161\/JAHA.119.011991","article-title":"Cardiogenic Shock","volume":"8","author":"Vahdatpour","year":"2019","journal-title":"J. Am. Heart Assoc."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1161\/HYPERTENSIONAHA.111.188151","article-title":"Orthostatic hypotension as a risk factor for incident heart failure: The atherosclerosis risk in communities study","volume":"59","author":"Jones","year":"2012","journal-title":"Hypertension"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1007\/s00134-018-5218-5","article-title":"The relationship between ICU hypotension and in-hospital mortality and morbidity in septic patients","volume":"44","author":"Maheshwari","year":"2018","journal-title":"Intensiv. Care Med."},{"key":"ref_53","first-page":"118","article-title":"Monitoring, management, and outcome of hypotension in Intensive Care Unit patients, an international survey of the European Society of Intensive Care Medicine","volume":"67","author":"Schuurmans","year":"2021","journal-title":"J. Crit. Care"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:40:47Z","timestamp":1760132447000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/17\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["a17010006"],"URL":"https:\/\/doi.org\/10.3390\/a17010006","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,22]]}}}