ricu: R’s interface to intensive care data

Providing computational infrastructure for handling diverse intensive care unit (ICU) datasets, the R package ricu enables writing dataset-agnostic analysis code, thereby facilitating multi-center training and validation of machine learning models. The package is designed with an emphasis on extensibility both to new datasets as well as clinical data concepts, and currently supports the loading of around 100 patient variables corresponding to a total of 319,402 ICU admissions from 4 data sources collected in Europe and the United States. By allowing for the addition of user-specified medical concepts and data sources the aim of ricu is to foster robust, data-based intensive care research, allowing the user to externally validate their method or conclusion with relative ease, and in turn facilitating reproducible and therefore transparent work in this field.

[1]  Mohammed Saeed,et al.  Open-access MIMIC-II database for intensive care research , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Marzyeh Ghassemi,et al.  MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III , 2019, CHIL.

[3]  M. Kuiper,et al.  Cumulative lactate and hospital mortality in ICU patients , 2013, Annals of Intensive Care.

[4]  Karsten M. Borgwardt,et al.  Early prediction of circulatory failure in the intensive care unit using machine learning , 2020, Nature Medicine.

[5]  Tom J. Pollard,et al.  A Comparative Analysis of Sepsis Identification Methods in an Electronic Database* , 2018, Critical care medicine.

[6]  A. Dreher.  Modeling Survival Data Extending The Cox Model , 2016 .

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

[8]  Laura E. Barnes,et al.  Predictive Models of Sepsis in Adult ICU Patients , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[9]  G. Moody,et al.  A database to support development and evaluation of intelligent intensive care monitoring , 1996, Computers in Cardiology 1996.

[10]  G. Clermont,et al.  Sharing ICU Patient Data Responsibly Under the Society of Critical Care Medicine/European Society of Intensive Care Medicine Joint Data Science Collaboration: The Amsterdam University Medical Centers Database (AmsterdamUMCdb) Example* , 2021, Critical care medicine.

[11]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[12]  C. Sprung,et al.  The ACCP-SCCM consensus conference on sepsis and organ failure. , 1992, Chest.

[13]  Shamim Nemati,et al.  An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU , 2017, Critical care medicine.

[14]  Michael Bailey,et al.  Dynamic lactate indices as predictors of outcome in critically ill patients , 2011, Critical care.

[15]  T. Lange,et al.  Severe hyperlactatemia, lactate clearance and mortality in unselected critically ill patients , 2016, Intensive Care Medicine.

[16]  U. Kyriacos,et al.  Validation of a modified early warning score‐linked Situation‐Background‐Assessment‐Recommendation communication tool: A mixed methods study , 2017, Journal of clinical nursing.

[17]  Alistair E. W. Johnson,et al.  The eICU Collaborative Research Database, a freely available multi-center database for critical care research , 2018, Scientific Data.

[18]  Katherine A. Heller,et al.  An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection , 2017, MLHC.

[19]  Mark Hoogendoorn,et al.  Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy , 2020, Intensive Care Medicine.

[20]  Mike Jones,et al.  NEWSDIG: The National Early Warning Score Development and Implementation Group. , 2012, Clinical medicine.

[21]  R S Evans,et al.  Electronic Health Records: Then, Now, and in the Future , 2016, Yearbook of Medical Informatics.

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

[23]  Paul Brown,et al.  Closing the data loop: An integrated open access analysis platform for the MIMIC database , 2016, 2016 Computing in Cardiology Conference (CinC).

[24]  L. Blanch,et al.  A universal definition of ARDS: the PaO2/FiO2 ratio under a standard ventilatory setting—a prospective, multicenter validation study , 2013, Intensive Care Medicine.

[25]  Brian W. Pickering,et al.  Data Utilization for Medical Decision Making at the Time of Patient Admission to ICU* , 2013, Critical care medicine.

[26]  C. Subbe,et al.  Validation of a modified Early Warning Score in medical admissions. , 2001, QJM : monthly journal of the Association of Physicians.

[27]  Jeroen Ooms,et al.  The jsonlite Package: A Practical and Consistent Mapping Between JSON Data and R Objects , 2014, ArXiv.

[28]  Haipeng Shen,et al.  Artificial intelligence in healthcare: past, present and future , 2017, Stroke and Vascular Neurology.

[29]  Uli K. Chettipally,et al.  Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach , 2016, JMIR medical informatics.

[30]  Edzer Pebesma,et al.  Measurement Units in R , 2016, R J..

[31]  J. Donnelly,et al.  External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients. , 2021, JAMA internal medicine.

[32]  J. Vincent,et al.  The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure , 1996, Intensive Care Medicine.