Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning

John E. Eaton, Mette Vesterhus, Bryan M. McCauley, Elizabeth J. Atkinson, Erik M. Schlicht, Brian D. Juran, Andrea A. Gossard, Nicholas F La Russo, Gregory James Gores, Tom H. Karlsen, Konstantinos N Lazaridis

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95% confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95% CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95% CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95% CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95% CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95% CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.

Original languageEnglish (US)
JournalHepatology
DOIs
StateAccepted/In press - Jan 1 2019

Fingerprint

Sclerosing Cholangitis
Validation Studies
Confidence Intervals
Bilirubin
Alkaline Phosphatase
Machine Learning
End Stage Liver Disease
Cholangiocarcinoma
Liver
Brain Diseases
Aspartate Aminotransferases
Ascites
Serum Albumin
Hemoglobins
Blood Platelets
Biomarkers
Sodium
Hemorrhage

ASJC Scopus subject areas

  • Hepatology

Cite this

Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease : A Derivation and Validation Study Using Machine Learning. / Eaton, John E.; Vesterhus, Mette; McCauley, Bryan M.; Atkinson, Elizabeth J.; Schlicht, Erik M.; Juran, Brian D.; Gossard, Andrea A.; La Russo, Nicholas F; Gores, Gregory James; Karlsen, Tom H.; Lazaridis, Konstantinos N.

In: Hepatology, 01.01.2019.

Research output: Contribution to journalArticle

Eaton, John E. ; Vesterhus, Mette ; McCauley, Bryan M. ; Atkinson, Elizabeth J. ; Schlicht, Erik M. ; Juran, Brian D. ; Gossard, Andrea A. ; La Russo, Nicholas F ; Gores, Gregory James ; Karlsen, Tom H. ; Lazaridis, Konstantinos N. / Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease : A Derivation and Validation Study Using Machine Learning. In: Hepatology. 2019.
@article{a9317f1d43824986bde0efecc7194e3f,
title = "Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease: A Derivation and Validation Study Using Machine Learning",
abstract = "Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95{\%} confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95{\%} CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95{\%} CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95{\%} CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95{\%} CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95{\%} CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.",
author = "Eaton, {John E.} and Mette Vesterhus and McCauley, {Bryan M.} and Atkinson, {Elizabeth J.} and Schlicht, {Erik M.} and Juran, {Brian D.} and Gossard, {Andrea A.} and {La Russo}, {Nicholas F} and Gores, {Gregory James} and Karlsen, {Tom H.} and Lazaridis, {Konstantinos N}",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/hep.30085",
language = "English (US)",
journal = "Hepatology",
issn = "0270-9139",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Primary Sclerosing Cholangitis Risk Estimate Tool (PREsTo) Predicts Outcomes of the Disease

T2 - A Derivation and Validation Study Using Machine Learning

AU - Eaton, John E.

AU - Vesterhus, Mette

AU - McCauley, Bryan M.

AU - Atkinson, Elizabeth J.

AU - Schlicht, Erik M.

AU - Juran, Brian D.

AU - Gossard, Andrea A.

AU - La Russo, Nicholas F

AU - Gores, Gregory James

AU - Karlsen, Tom H.

AU - Lazaridis, Konstantinos N

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95% confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95% CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95% CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95% CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95% CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95% CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.

AB - Improved methods are needed to risk stratify and predict outcomes in patients with primary sclerosing cholangitis (PSC). Therefore, we sought to derive and validate a prediction model and compare its performance to existing surrogate markers. The model was derived using 509 subjects from a multicenter North American cohort and validated in an international multicenter cohort (n = 278). Gradient boosting, a machine-based learning technique, was used to create the model. The endpoint was hepatic decompensation (ascites, variceal hemorrhage, or encephalopathy). Subjects with advanced PSC or cholangiocarcinoma (CCA) at baseline were excluded. The PSC risk estimate tool (PREsTo) consists of nine variables: bilirubin, albumin, serum alkaline phosphatase (SAP) times the upper limit of normal (ULN), platelets, aspartate aminotransferase (AST), hemoglobin, sodium, patient age, and number of years since PSC was diagnosed. Validation in an independent cohort confirms that PREsTo accurately predicts decompensation (C-statistic, 0.90; 95% confidence interval [CI], 0.84-0.95) and performed well compared to Model for End-Stage Liver Disease (MELD) score (C-statistic, 0.72; 95% CI, 0.57-0.84), Mayo PSC risk score (C-statistic, 0.85; 95% CI, 0.77-0.92), and SAP <1.5 × ULN (C-statistic, 0.65; 95% CI, 0.55-0.73). PREsTo continued to be accurate among individuals with a bilirubin <2.0 mg/dL (C-statistic, 0.90; 95% CI, 0.82-0.96) and when the score was reapplied at a later course in the disease (C-statistic, 0.82; 95% CI, 0.64-0.95). Conclusion: PREsTo accurately predicts hepatic decompensation (HD) in PSC and exceeds the performance among other widely available, noninvasive prognostic scoring systems.

UR - http://www.scopus.com/inward/record.url?scp=85059273044&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059273044&partnerID=8YFLogxK

U2 - 10.1002/hep.30085

DO - 10.1002/hep.30085

M3 - Article

AN - SCOPUS:85059273044

JO - Hepatology

JF - Hepatology

SN - 0270-9139

ER -