Evaluation of Biomarkers in Critical Care and Perioperative Medicine.

Interest in developing and using novel biomarkers in critical care and perioperative medicine is increasing. Biomarkers studies are often presented with flaws in the statistical analysis that preclude them from providing a scientifically valid and clinically relevant message for clinicians. To improve scientific rigor, the proper application and reporting of traditional and emerging statistical methods (e.g., machine learning) of biomarker studies is required. This Readers' Toolbox article aims to be a starting point to nonexpert readers and investigators to understand traditional and emerging research methods to assess biomarkers in critical care and perioperative medicine.

[1]  B. van Calster,et al.  Regression shrinkage methods for clinical prediction models do not guarantee improved performance: Simulation study , 2020, Statistical methods in medical research.

[2]  Richard D Riley,et al.  Calculating the sample size required for developing a clinical prediction model , 2020, BMJ.

[3]  Lucila Ohno-Machado,et al.  A tutorial on calibration measurements and calibration models for clinical prediction models , 2020, J. Am. Medical Informatics Assoc..

[4]  G. Rosman,et al.  Artificial Intelligence in Anesthesiology , 2020, Anesthesiology.

[5]  Dirk Timmerman,et al.  Predictive analytics in health care: how can we know it works? , 2019, J. Am. Medical Informatics Assoc..

[6]  C. Pannucci,et al.  Assessment of Anti-Factor Xa Levels of Patients Undergoing Colorectal Surgery Given Once-Daily Enoxaparin Prophylaxis: A Clinical Study Examining Enoxaparin Pharmacokinetics. , 2019, JAMA surgery.

[7]  Ò. Miró,et al.  High-Sensitivity Cardiac Troponin I Assay for Early Diagnosis of Acute Myocardial Infarction. , 2019, Clinical chemistry.

[8]  Johannes B Reitsma,et al.  Forcing dichotomous disease classification from reference standards leads to bias in diagnostic accuracy estimates: A simulation study. , 2019, Journal of clinical epidemiology.

[9]  Matthieu Komorowski,et al.  Artificial intelligence in intensive care: are we there yet? , 2019, Intensive Care Medicine.

[10]  Jeremy C. Weiss,et al.  Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis. , 2019, JAMA.

[11]  A. Perner,et al.  The use of clustering algorithms in critical care research to unravel patient heterogeneity , 2019, Intensive Care Medicine.

[12]  K. Ho,et al.  Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care , 2019, Critical Care.

[13]  Boris P. Hejblum,et al.  Benefits of dimension reduction in penalized regression methods for high-dimensional grouped data: a case study in low sample size , 2019, Bioinform..

[14]  Jie Ma,et al.  A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. , 2019, Journal of clinical epidemiology.

[15]  T. Carrel,et al.  Clinical Relevance of Troponin T Profile Following Cardiac Surgery , 2018, Front. Cardiovasc. Med..

[16]  Ben J. Marafino,et al.  Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data , 2018, JAMA network open.

[17]  Yuan Luo,et al.  Big Data and Data Science in Critical Care. , 2018, Chest.

[18]  Jing Wang,et al.  Supervised Machine-learning Predictive Analytics for Prediction of Postinduction Hypotension , 2018, Anesthesiology.

[19]  J. Rinehart,et al.  Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis , 2018, Anesthesiology.

[20]  Pierre Baldi,et al.  Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality , 2018, Anesthesiology.

[21]  A. Mebazaa,et al.  Methods used to assess the performance of biomarkers for the diagnosis of acute kidney injury: a systematic review and meta-analysis , 2018, Biomarkers : biochemical indicators of exposure, response, and susceptibility to chemicals.

[22]  J. Laffey,et al.  Acute respiratory distress syndrome subphenotypes and differential response to simvastatin: secondary analysis of a randomised controlled trial. , 2018, The Lancet. Respiratory medicine.

[23]  Nancy R Cook,et al.  Quantifying the added value of new biomarkers: how and how not , 2018, Diagnostic and Prognostic Research.

[24]  J. Wiemer,et al.  Adherence to a procalcitonin-guided antibiotic treatment protocol in patients with severe sepsis and septic shock , 2018, Annals of Intensive Care.

[25]  Liangping Li,et al.  Value of urinary KIM-1 and NGAL combined with serum Cys C for predicting acute kidney injury secondary to decompensated cirrhosis , 2018, Scientific Reports.

[26]  K. Reinhart,et al.  Influence of pathogen and focus of infection on procalcitonin values in sepsis patients with bacteremia or candidemia , 2018, Critical Care.

[27]  I. Kohane,et al.  Big Data and Machine Learning in Health Care. , 2018, JAMA.

[28]  A. Mebazaa,et al.  Determinants of long-term outcome in ICU survivors: results from the FROG-ICU study , 2018, Critical Care.

[29]  Karel G M Moons,et al.  A closed testing procedure to select an appropriate method for updating prediction models , 2017, Statistics in medicine.

[30]  Andrew J Vickers,et al.  The Brier score does not evaluate the clinical utility of diagnostic tests or prediction models , 2017, Diagnostic and Prognostic Research.

[31]  M. Cohen,et al.  Derivation and validation of a two-biomarker panel for diagnosis of ARDS in patients with severe traumatic injuries , 2017, Trauma Surgery & Acute Care Open.

[32]  P. Collinson,et al.  Cardiac Troponin Release is Associated with Biomarkers of Inflammation and Ventricular Dilatation During Critical Illness , 2017, Shock.

[33]  O. Langeron,et al.  Comparison of the Prognostic Significance of Initial Blood Lactate and Base Deficit in Trauma Patients , 2017, Anesthesiology.

[34]  Douglas G. Altman,et al.  No rationale for 1 variable per 10 events criterion for binary logistic regression analysis , 2016, BMC Medical Research Methodology.

[35]  John-Michael Sauer,et al.  Net Reclassification Index and Integrated Discrimination Index Are Not Appropriate for Testing Whether a Biomarker Improves Predictive Performance. , 2016, Toxicological sciences : an official journal of the Society of Toxicology.

[36]  Douglas G. Altman,et al.  Adequate sample size for developing prediction models is not simply related to events per variable , 2016, Journal of clinical epidemiology.

[37]  Gary S Collins,et al.  Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model , 2016, Statistics in medicine.

[38]  Johannes B Reitsma,et al.  Bias due to composite reference standards in diagnostic accuracy studies , 2016, Statistics in medicine.

[39]  Wentao Bao.  Multivariable fractional polynomial method for regression model. , 2016, Annals of translational medicine.

[40]  Paul Landais,et al.  Preoperative Score to Predict Postoperative Mortality (POSPOM): Derivation and Validation , 2016, Anesthesiology.

[41]  Ewout W Steyerberg,et al.  Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests , 2016, British Medical Journal.

[42]  Jérémie F. Cohen,et al.  STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies. , 2015, Clinical chemistry.

[43]  Gareth Ambler,et al.  Review and evaluation of penalised regression methods for risk prediction in low‐dimensional data with few events , 2015, Statistics in medicine.

[44]  V. Serebruany,et al.  Clopidogrel Response Variability: Impact of Genetic Polymorphism and Platelet Biomarkers for Predicting Adverse Outcomes Poststenting , 2015, American journal of therapeutics.

[45]  F. Tubach,et al.  Prognostic value of procalcitonin in respiratory tract infections across clinical settings , 2015, Critical Care.

[46]  Douglas G. Altman,et al.  Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) , 2015, Circulation.

[47]  Ewout W Steyerberg,et al.  Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints , 2014, BMC Medical Research Methodology.

[48]  Thomas A Gerds,et al.  A note on the evaluation of novel biomarkers: do not rely on integrated discrimination improvement and net reclassification index , 2014, Statistics in medicine.

[49]  C. Parikh,et al.  Key concepts and limitations of statistical methods for evaluating biomarkers of kidney disease. , 2014, Journal of the American Society of Nephrology : JASN.

[50]  Kevin Delucchi,et al.  Subphenotypes in acute respiratory distress syndrome: latent class analysis of data from two randomised controlled trials. , 2014, The Lancet. Respiratory medicine.

[51]  M. Amin,et al.  Urine kidney injury molecule-1: a potential non-invasive biomarker for patients with renal cell carcinoma , 2014, International Urology and Nephrology.

[52]  Douglas G Altman,et al.  Reporting recommendations for tumor marker prognostic studies (REMARK): explanation and elaboration , 2012, BMC Medicine.

[53]  Yan Ma,et al.  Beyond Repeated-Measures Analysis of Variance: Advanced Statistical Methods for the Analysis of Longitudinal Data in Anesthesia Research , 2011, Regional Anesthesia & Pain Medicine.

[54]  Margaret S Pepe,et al.  Problems with risk reclassification methods for evaluating prediction models. , 2011, American journal of epidemiology.

[55]  T. Houle,et al.  Statistical Evaluation of a Biomarker , 2010, Anesthesiology.

[56]  S. Waikar,et al.  Creatinine kinetics and the definition of acute kidney injury. , 2009, Journal of the American Society of Nephrology : JASN.

[57]  Elena B. Elkin,et al.  Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers , 2008, BMC Medical Informatics Decis. Mak..

[58]  Nancy A Obuchowski,et al.  An ROC‐type measure of diagnostic accuracy when the gold standard is continuous‐scale , 2006, Statistics in medicine.

[59]  M. Pencina,et al.  Overall C as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation , 2004, Statistics in medicine.

[60]  Ewout W Steyerberg,et al.  Internal and external validation of predictive models: a simulation study of bias and precision in small samples. , 2003, Journal of clinical epidemiology.

[61]  J. Concato,et al.  A simulation study of the number of events per variable in logistic regression analysis. , 1996, Journal of clinical epidemiology.

[62]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[63]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[64]  Ewout W. Steyerberg,et al.  Evaluation of Performance , 2019, Statistics for Biology and Health.

[65]  Joseph W Hogan,et al.  Standards should be applied in the prevention and handling of missing data for patient-centered outcomes research: a systematic review and expert consensus. , 2014, Journal of clinical epidemiology.

[66]  Y. Manach,et al.  Perioperative Hemodynamic Monitoring and Goal Directed Therapy: Statistical methods in hemodynamic research , 2014 .