Application of artificial intelligence methods in vital signs analysis of hospitalized patients: A systematic literature review

Abstract In a hospital environment, patients are monitored continuously by electronic devices and health professionals. Therefore, a large amount of data is collected and stored in electronic health records systems for each patient. Among such data, vital signs are one of the most common and relevant types of information monitored to assess a patient’s health status. Artificial intelligence techniques can be used to analyze and learn useful standards from clinical datasets to provide better evidence to support the decisions of health professionals and thus help to improve patient health outcomes in hospitals. This systematic literature review aims to provide an updated computational perspective of how artificial intelligence has been applied to analyze the vital signs of adult hospitalized patients and the outcomes obtained. To this end, we reviewed 2899 scientific articles published between 2008 and 2018 and selected 78 articles that met our inclusion criteria to answer the research questions. Moreover, we used the information found in the reviewed articles to propose a taxonomy and identified the main concerns, challenges, and opportunities in this field. Our findings demonstrate that many researchers are exploring the use of artificial intelligence methods in tasks related to improving the health outcomes of hospitalized patients in distinct units. Additionally, although vital signs are significant predictors of clinical deterioration, they are not analyzed in isolation to predict or identify a clinical outcome. Our taxonomy and discussion contribute to the achievement of a significant degree of coverage regarding the aspects related to using machine learning to improve health outcomes in hospital environments, while highlighting gaps in the literature for future research.

[1]  R. Righi,et al.  Personal Health Records: A Systematic Literature Review , 2017, Journal of medical Internet research.

[2]  Yixin Chen,et al.  Predicting Hospital Readmission via Cost-Sensitive Deep Learning , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  William Fleischman,et al.  Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach. , 2016, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[4]  Gilles Clermont,et al.  Learning temporal rules to forecast instability in continuously monitored patients , 2017, J. Am. Medical Informatics Assoc..

[5]  G. Clermont,et al.  Dynamic and Personalized Risk Forecast in Step‐Down Units. Implications for Monitoring Paradigms , 2017, Annals of the American Thoracic Society.

[6]  I. Vlahavas,et al.  Machine Learning and Data Mining Methods in Diabetes Research , 2017, Computational and structural biotechnology journal.

[7]  R. Rattan,et al.  Predicting central line‐associated bloodstream infections and mortality using supervised machine learning , 2018, Journal of critical care.

[8]  Taghi M. Khoshgoftaar,et al.  A review of statistical and machine learning methods for modeling cancer risk using structured clinical data , 2018, Artif. Intell. Medicine.

[9]  J. Kline,et al.  Derivation and validation of a multivariate model to predict mortality from pulmonary embolism with cancer: The POMPE-C tool. , 2012, Thrombosis research.

[10]  Hien Nguyen,et al.  From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system , 2014, J. Am. Medical Informatics Assoc..

[11]  Abigail A. Flower,et al.  Using machine learning to predict near-term mortality in cirrhosis patients hospitalized at the University of Virginia health system , 2018, 2018 Systems and Information Engineering Design Symposium (SIEDS).

[12]  Nan Liu,et al.  Prediction of cardiac arrest in critically ill patients presenting to the emergency department using a machine learning score incorporating heart rate variability compared with the modified early warning score , 2012, Critical Care.

[13]  Don Nutbeam,et al.  Health promotion glossary. , 1986, Health promotion.

[14]  Hye Jin Kam,et al.  Learning representations for the early detection of sepsis with deep neural networks , 2017, Comput. Biol. Medicine.

[15]  Maysam F. Abbod,et al.  Brain death prediction based on ensembled artificial neural networks in neurosurgical intensive care unit , 2011 .

[16]  Philip A. Bain,et al.  Reducing COPD Readmissions: A Causal Bayesian Network Model , 2018, IEEE Robotics and Automation Letters.

[17]  Sunday O. Olatunji,et al.  Prediction models aided postoperative decision making based on neural network and support vector machines , 2017, 2017 International Conference on Informatics, Health & Technology (ICIHT).

[18]  Hester F. Lingsma,et al.  Evaluation of hospital outcomes: the relation between length-of-stay, readmission, and mortality in a large international administrative database , 2018, BMC Health Services Research.

[19]  Ying Zhang,et al.  Patient-specific learning in real time for adaptive monitoring in critical care , 2008, J. Biomed. Informatics.

[20]  Heiko Wersing,et al.  Incremental on-line learning: A review and comparison of state of the art algorithms , 2018, Neurocomputing.

[21]  Zygmunt Ciota,et al.  Classification support algorithms for patient's general condition based on Artificial Neural network , 2013, Proceedings of the 20th International Conference Mixed Design of Integrated Circuits and Systems - MIXDES 2013.

[22]  Vitaly Herasevich,et al.  Multicenter derivation and validation of an early warning score for acute respiratory failure or death in the hospital , 2018, Critical Care.

[23]  Shyam Visweswaran,et al.  Learning patient-specific predictive models from clinical data , 2010, J. Biomed. Informatics.

[24]  Kevin M. Heard,et al.  A trial of a real-time alert for clinical deterioration in patients hospitalized on general medical wards. , 2013, Journal of hospital medicine.

[25]  Peyman Rezaei-Hachesu,et al.  Decision support system for triage management: A hybrid approach using rule-based reasoning and fuzzy logic , 2018, Int. J. Medical Informatics.

[26]  Jimeng Sun,et al.  Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review , 2018, J. Am. Medical Informatics Assoc..

[27]  Maia Angelova,et al.  Risk factors and prediction of very short term versus short/intermediate term post-stroke mortality: A data mining approach , 2014, Comput. Biol. Medicine.

[28]  G. Clermont,et al.  Cardiorespiratory instability in monitored step-down unit patients: using cluster analysis to identify patterns of change , 2018, Journal of Clinical Monitoring and Computing.

[29]  Shen-Tsu Wang,et al.  Construct an Optimal Triage Prediction Model: A Case Study of the Emergency Department of a Teaching Hospital in Taiwan , 2013, Journal of Medical Systems.

[30]  Donald E. Brown,et al.  Preconditions and multilevel models in studying post-surgical adverse outcomes , 2015, Network Modeling Analysis in Health Informatics and Bioinformatics.

[31]  Cristiano André da Costa,et al.  OmniPHR: A distributed architecture model to integrate personal health records , 2017, J. Biomed. Informatics.

[32]  Peter Sprivulis,et al.  Arti fi cial intelligence and machine learning in emergency medicine , 2022 .

[33]  David A. Clifton,et al.  A Two-Class Approach to the Detection of Physiological Deterioration in Patient Vital Signs, With Clinical Label Refinement , 2012, IEEE Transactions on Information Technology in Biomedicine.

[34]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[35]  Gil Alterovitz,et al.  An artificial intelligence tool to predict fluid requirement in the intensive care unit: a proof-of-concept study , 2008, Critical care.

[36]  Ahmed M. Alaa,et al.  Personalized Risk Scoring for Critical Care Prognosis Using Mixtures of Gaussian Processes , 2016, IEEE Transactions on Biomedical Engineering.

[37]  Cristiano André da Costa,et al.  Internet of Health Things: Toward intelligent vital signs monitoring in hospital wards , 2018, Artif. Intell. Medicine.

[38]  Jun Guo,et al.  Diagnosis labeling with disease-specific characteristics mining , 2018, Artif. Intell. Medicine.

[39]  Aaron Zalewski,et al.  Estimating patient's health state using latent structure inferred from clinical time series and text , 2017, 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI).

[40]  Min Chi,et al.  Recent Temporal Pattern Mining for Septic Shock Early Prediction , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[41]  Huan Liu,et al.  Feature Engineering for Machine Learning and Data Analytics , 2018 .

[42]  Steen Andreassen,et al.  Automatic learning of mortality in a CPN model of the systemic inflammatory response syndrome. , 2017, Mathematical biosciences.

[43]  Christos Faloutsos,et al.  HeartCast: Predicting acute hypotensive episodes in intensive care units , 2016 .

[44]  Y. Fujisawa,et al.  Deep‐learning‐based, computer‐aided classifier developed with a small dataset of clinical images surpasses board‐certified dermatologists in skin tumour diagnosis , 2018, The British journal of dermatology.

[45]  William Holderbaum,et al.  Application of data fusion techniques and technologies for wearable health monitoring. , 2017, Medical engineering & physics.

[46]  Derek C Angus,et al.  Fusing Randomized Trials With Big Data: The Key to Self-learning Health Care Systems? , 2015, JAMA.

[47]  Ram Akella,et al.  Dynamically Modeling Patient's Health State from Electronic Medical Records: A Time Series Approach , 2015, KDD.

[48]  C. Moore,et al.  Predictive models for severe sepsis in adult ICU patients , 2015, 2015 Systems and Information Engineering Design Symposium.

[49]  Filipe Portela,et al.  Preventing patient Cardiac Arrhythmias by using data mining techniques , 2014, 2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES).

[50]  Jian-Bo Yang,et al.  Belief rule-based inference for predicting trauma outcome , 2016, Knowl. Based Syst..

[51]  Junyu Dong,et al.  An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning , 2016, ArXiv.

[52]  Abdul Hanan Abdullah,et al.  A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care , 2017, Journal of Medical Systems.

[53]  João Paulo Carvalho,et al.  Daily prediction of ICU readmissions using feature engineering and ensemble fuzzy modeling , 2017, Expert Syst. Appl..

[54]  Aditya Patel,et al.  A weighted similarity measure approach to predict intensive care unit transfers , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[55]  Girish N. Nadkarni,et al.  Incorporating temporal EHR data in predictive models for risk stratification of renal function deterioration , 2014, J. Biomed. Informatics.

[56]  Joachim Denzler,et al.  Deep Learning on Small Datasets without Pre-Training using Cosine Loss , 2019, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[57]  Laura E. Barnes,et al.  Optimization of sepsis risk assessment for ward patients , 2016, 2016 IEEE Systems and Information Engineering Design Symposium (SIEDS).

[58]  Gül E. Okudan Kremer,et al.  Model comparison in Emergency Severity Index level prediction , 2013, Expert Syst. Appl..

[59]  Peter C Austin,et al.  Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. , 2013, Journal of clinical epidemiology.

[60]  D. Lake,et al.  Identifying the low risk patient in surgical intensive and intermediate care units using continuous monitoring , 2018, Surgery.

[61]  Bo Hu,et al.  Predicting Acute Hypotensive Episodes Based on Multi GP , 2015, ISICA.

[62]  H. Aveyard.  Doing a literature review in health and social care : a practical guide , 2015 .

[63]  Nitesh V. Chawla,et al.  Data Mining for Imbalanced Datasets: An Overview , 2005, The Data Mining and Knowledge Discovery Handbook.

[64]  Mohd Alauddin Mohd Ali,et al.  Comparison of adaptive neuro-fuzzy inference system and artificial neutral networks model to categorize patients in the emergency department , 2013, SpringerPlus.

[65]  P. Williamson,et al.  A taxonomy has been developed for outcomes in medical research to help improve knowledge discovery , 2017, Journal of clinical epidemiology.

[66]  M.R. Ebenezar Jebarani,et al.  A review on prediction and diagnosis of heart failure , 2017, 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS).

[67]  Jane C. Deng,et al.  Prediction of Clinical Deterioration in Hospitalized Adult Patients with Hematologic Malignancies Using a Neural Network Model , 2016, PloS one.

[68]  ChengXiang Zhai,et al.  Temporal reflected logistic regression for probabilistic heart failure survival score prediction , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[69]  Nan Liu,et al.  Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events , 2017, Cognitive Computation.

[70]  Vincent S. Tseng,et al.  Disease Risk Prediction by Mining Personalized Health Trend Patterns: A Case Study on Diabetes , 2012, 2012 Conference on Technologies and Applications of Artificial Intelligence.

[71]  David O. Meltzer,et al.  Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards , 2016, Critical care medicine.

[72]  Xingyu Zhang,et al.  Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks , 2017, Methods of Information in Medicine.

[73]  Michael J. Pencina,et al.  Predicting mortality over different time horizons: which data elements are needed? , 2017, J. Am. Medical Informatics Assoc..

[74]  R. Kozol,et al.  Using artificial intelligence to predict prolonged mechanical ventilation and tracheostomy placement. , 2018, The Journal of surgical research.

[75]  Albion Dervishi,et al.  Fuzzy risk stratification and risk assessment model for clinical monitoring in the ICU , 2017, Comput. Biol. Medicine.

[76]  Mu-Chun Su,et al.  Prediction of survival of ICU patients using computational intelligence , 2014, Comput. Biol. Medicine.

[77]  E. Tacconelli.  Systematic reviews: CRD's guidance for undertaking reviews in health care , 2010 .

[78]  Li-Wei H. Lehman,et al.  Predicting and Understanding Unexpected Respiratory Decompensation in Critical Care Using Sparse and Heterogeneous Clinical Data , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[79]  N. A. Khovanova,et al.  Machine Learning for Predictive Modelling based on Small Data in Biomedical Engineering , 2015 .

[80]  E. Santiago,et al.  Physiologically-based, predictive analytics using the heart-rate-to-Systolic-Ratio significantly improves the timeliness and accuracy of sepsis prediction compared to SIRS. , 2017, American journal of surgery.

[81]  David A. Clifton,et al.  Gaussian process clustering for the functional characterisation of vital-sign trajectories , 2013, 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

[82]  Anthea Sutton,et al.  Systematic Approaches to a Successful Literature Review , 2012 .

[83]  Isaac S Kohane,et al.  Artificial Intelligence in Healthcare , 2019, Artificial Intelligence and Machine Learning for Business for Non-Engineers.

[84]  Matthew D. Stanley,et al.  Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics. , 2017, Journal of electrocardiology.

[85]  Ali Jalali,et al.  Advanced analytics for outcome prediction in intensive care units , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[86]  K. Chellappan,et al.  A preliminary dengue fever prediction model based on vital signs and blood profile , 2016, 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[87]  Mohamed Bader-El-Den,et al.  Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach , 2017, Int. J. Medical Informatics.

[88]  Hyeoun-Ae Park,et al.  Use of electronic critical care flow sheet data to predict unplanned extubation in ICUs , 2018, Int. J. Medical Informatics.

[89]  Filipe Portela,et al.  Real-Time Data Mining Models for Predicting Length of Stay in Intensive Care Units , 2014, KMIS.

[90]  R. Bellomo,et al.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). , 2016, JAMA.

[91]  Antonello Pasini,et al.  Artificial neural networks for small dataset analysis. , 2015, Journal of thoracic disease.

[92]  Mohammad Hassan Moradi,et al.  Mortality prediction in intensive care units (ICUs) using a deep rule-based fuzzy classifier , 2018, J. Biomed. Informatics.

[93]  José Luis Rojo-Álvarez,et al.  Predicting colorectal surgical complications using heterogeneous clinical data and kernel methods , 2016, J. Biomed. Informatics.

[94]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.

[95]  A. Salcedo-Bernal,et al.  Clinical Data Analysis: An Opportunity to Compare Machine Learning Methods , 2016 .

[96]  Der-Chiang Li,et al.  Rebuilding sample distributions for small dataset learning , 2018, Decis. Support Syst..

[97]  Joshua C Denny,et al.  Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals , 2017, J. Am. Medical Informatics Assoc..

[98]  Cristiano André da Costa,et al.  Survey of conversational agents in health , 2019, Expert Syst. Appl..

[99]  Tadahiro Goto,et al.  Machine learning approaches for predicting disposition of asthma and COPD exacerbations in the ED , 2018, The American journal of emergency medicine.

[100]  Scott Levin,et al.  Machine‐Learning‐Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index , 2017, Annals of emergency medicine.

[101]  Jean-Marie Aerts,et al.  Prediction of Clinical Conditions after Coronary Bypass Surgery using Dynamic Data Analysis , 2010, Journal of Medical Systems.

[102]  S. Lodha,et al.  Definition of Key Terms , 2019 .

[103]  Gary B. Smith,et al.  Decision-tree early warning score (DTEWS) validates the design of the National Early Warning Score (NEWS). , 2014, Resuscitation.

[104]  Yixin Chen,et al.  An integrated data mining approach to real-time clinical monitoring and deterioration warning , 2012, KDD.

[105]  Jimeng Sun,et al.  RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data , 2018, KDD.

[106]  R. Unger,et al.  Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: An Acute Coronary Syndrome Israeli Survey data mining study. , 2017, International journal of cardiology.

[107]  James L Rudolph,et al.  Vital signs in older patients: age-related changes. , 2011, Journal of the American Medical Directors Association.

[108]  T. Schultz,et al.  Vital signs to monitor hospital patients: a systematic review. , 2008, JBI library of systematic reviews.

[109]  Patrick D. McDaniel,et al.  Making machine learning robust against adversarial inputs , 2018, Commun. ACM.

[110]  Rajkumar Buyya,et al.  Hierarchical data fusion for Smart Healthcare , 2019, Journal of Big Data.

[111]  Susana M. Vieira,et al.  Short-term prediction of low kidney function in ICU patients , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[112]  Sreela Sasi,et al.  Stroke in-patients' transfer to the ICU using ensemble based model , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).

[113]  Jing Zhang,et al.  Prediction of Adverse Events in Patients Undergoing Major Cardiovascular Procedures , 2017, IEEE Journal of Biomedical and Health Informatics.

[114]  Vincent Liu,et al.  Development and validation of an electronic medical record-based alert score for detection of inpatient deterioration outside the ICU , 2016, J. Biomed. Informatics.

[115]  J. Mauro,et al.  Survival prediction of trauma patients: a study on US National Trauma Data Bank , 2017, European Journal of Trauma and Emergency Surgery.

[116]  Eric T. Carlson,et al.  Early Deterioration Indicator: Data-driven approach to detecting deterioration in general ward. , 2018, Resuscitation.

[117]  Rodrigo da Rosa Righi,et al.  Context awareness in healthcare: a systematic literature review , 2019, Universal Access in the Information Society.

[118]  Shen-Tsu Wang,et al.  Abnormal diagnosis of Emergency Department triage explored with data mining technology: An Emergency Department at a Medical Center in Taiwan taken as an example , 2010, Expert Syst. Appl..

[119]  Yu Tian,et al.  Semi-supervised learning to improve generalizability of risk prediction models , 2019, J. Biomed. Informatics.

[120]  Chia-Lun Lo,et al.  Predicting the prolonged length of stay of general surgery patients: a supervised learning approach , 2018, Int. Trans. Oper. Res..

[121]  Mehul Motani,et al.  Learning Deep Representations from Heterogeneous Patient Data for Predictive Diagnosis , 2017, BCB.

[122]  Douglas E. Lake,et al.  Hemorrhage Prediction Models in Surgical Intensive Care: Bedside Monitoring Data Adds Information to Lab Values , 2017, IEEE Journal of Biomedical and Health Informatics.