Lost in Translation? From Conventional Scoring Tools to Modern Data-Driven Risk Assessment in Critical Care Medicine

High-resolution, longitudinal health data became widely available in intensive care units in the past years. Patient risk assessment, however, is still primarily based on conventional scores that take into account only a few parameters taken at single time points, which frequently causes inaccurate predictions in the clinical practice. Likewise, the contribution of AI-approaches remains sparse, as current machine learning models are inherently difficult to deduce and even impressive results rarely contribute to disease understanding. This review focusses on the limitations of conventional risk scores, and on recent developments and challenges of novel, data-driven assessment tools.

[1]  Alexander D'Amour,et al.  Underspecification Presents Challenges for Credibility in Modern Machine Learning , 2020, J. Mach. Learn. Res..

[2]  Slav Petrov,et al.  Measuring and Reducing Gendered Correlations in Pre-trained Models , 2020, ArXiv.

[3]  G. Koh.  Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score , 2020, BMJ.

[4]  Jordan J. Clark,et al.  Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score , 2020, BMJ.

[5]  M. Krauthammer,et al.  Timing COVID-19 - Synchronization of longitudinal patient data to the underlying disease progression using CRP as a temporal marker , 2020, medRxiv.

[6]  Brian E Dixon,et al.  Generalization of Machine Learning Approaches to Identify Notifiable Conditions from a Statewide Health Information Exchange. , 2020, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[7]  Monica Adya,et al.  Decision making under stress: the role of information overload, time pressure, complexity, and uncertainty , 2020, J. Decis. Syst..

[8]  Shalmali Joshi,et al.  Ethical limitations of algorithmic fairness solutions in health care machine learning. , 2020, The Lancet. Digital health.

[9]  R. Ranganath,et al.  A Review of Challenges and Opportunities in Machine Learning for Health. , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[10]  Helena Canhão,et al.  AliClu - Temporal sequence alignment for clustering longitudinal clinical data , 2019, BMC Medical Informatics and Decision Making.

[11]  Suman V. Ravuri,et al.  A Clinically Applicable Approach to Continuous Prediction of Future Acute Kidney Injury , 2019, Nature.

[12]  Phillip M Cheng,et al.  Artificial Intelligence for Medical Image Analysis: A Guide for Authors and Reviewers. , 2019, AJR. American journal of roentgenology.

[13]  I. Shrier,et al.  Causal inference for clinicians , 2019, BMJ Evidence-Based Medicine.

[14]  G. Maddern,et al.  Fatal flaws in clinical decision making , 2018, ANZ journal of surgery.

[15]  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).

[16]  Judea Pearl,et al.  Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution , 2018, WSDM.

[17]  F. Cabitza,et al.  Unintended Consequences of Machine Learning in Medicine , 2017, JAMA.

[18]  C. Sprung,et al.  The status of intensive care medicine research and a future agenda for very old patients in the ICU , 2017, Intensive Care Medicine.

[19]  Matthew M Churpek,et al.  The value of vital sign trends for detecting clinical deterioration on the wards. , 2016, Resuscitation.

[20]  Dinggang Shen,et al.  State-space model with deep learning for functional dynamics estimation in resting-state fMRI , 2016, NeuroImage.

[21]  Michael Krauthammer,et al.  Controlling testing volume for respiratory viruses using machine learning and text mining , 2016, AMIA.

[22]  K. Borgwardt,et al.  Machine Learning in Medicine , 2015, Mach. Learn. under Resour. Constraints Vol. 3.

[23]  G. Westphal,et al.  Systematic screening is essential for early diagnosis of severe sepsis and septic shock , 2015, Revista Brasileira de terapia intensiva.

[24]  A. Rapsang,et al.  Scoring systems in the intensive care unit: A compendium , 2014, Indian journal of critical care medicine : peer-reviewed, official publication of Indian Society of Critical Care Medicine.

[25]  Martha Sajatovic,et al.  Clinical Prediction Models , 2013 .

[26]  Thomas M. Gill,et al.  The central role of prognosis in clinical decision making. , 2012, JAMA.

[27]  M. Wolff,et al.  [Scoring systems in intensive care medicine : principles, models, application and limits]. , 2011, Der Anaesthesist.

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

[29]  J. Norrie,et al.  Assessment of the performance of five intensive care scoring models within a large Scottish database , 2000, Critical care medicine.

[30]  STATUS OF IN , 2000 .

[31]  P Croskerry,et al.  Clinical decision making: an emergency medicine perspective. , 1999, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[32]  R. Oggioni,et al.  Scoring systems in intensive care , 1998 .

[33]  E. Orav,et al.  Issues of variability and bias affecting multisite measurement of quality of care. , 1996, Medical care.

[34]  S. Lemeshow,et al.  A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. , 1993, JAMA.

[35]  M A Hlatky,et al.  Clinical experience and predicting survival in coronary disease. , 1989, Archives of internal medicine.

[36]  E. Draper,et al.  APACHE II: A severity of disease classification system , 1985, Critical care medicine.