External validation of a prediction model that identifies adverse outcomes in hospitalised patients with diabetes

Research output: Contribution to journalAbstractpeer-review

Standard

External validation of a prediction model that identifies adverse outcomes in hospitalised patients with diabetes. / Nirantharakumar, Krishnarajah; Adderley, Nicola; Marshall, Tom; Rayman, Gerry; Mallett, Susan; Ghosh, Sandip; Akiboye, Funke; Bellary, Srikanth; Toulis, Konstantinos; Coleman, Jamie.

In: Diabetic Medicine, Vol. 34, No. Suppl. 1, A4 (P376), 08.03.2017, p. 6.

Research output: Contribution to journalAbstractpeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{37d4e317e69a46ce9d2c132903c320b2,
title = "External validation of a prediction model that identifies adverse outcomes in hospitalised patients with diabetes",
abstract = "Aim: To externally validate a prediction model that identifies adverse outcomes in hospitalised patients with diabetes.Methods: Data source: Inpatient data for 2014 from Heart of England Foundation Trust (HEFT) and Ipswich General Hospital.Participants: Patients with a diagnostic code of diabetes.Candidate variables: Age; gender; ethnicity; admission type; ITU admission; insulin therapy; albumin; sodium; potassium; haemoglobin; C-Reactive Protein; Estimated Glomerular Filtration Rate; and neutrophil count.Outcome definition: Adverse outcome is a composite outcome (excessive length of stay or death).Performance assessment: To assess discrimination, a receiver operating characteristic curve was constructed and Area Under the Curve (AUC) calculated. Calibration was assessed by plotting predicted probabilities of outcome against observed probabilities of outcome.Results: There were 16,568 admissions with diabetes to HEFT in 2014. The model discriminated well between those with and without an adverse outcome in HEFT (AUC:0.758, 95% CI: 0.747–0.768; sensitivity: 72.6%; specificity: 66.0%; and Positive Predictive Value (PPV): 45.1%). These are in comparison to the internally validated model derived at University Hospitals Birmingham NHS Foundation Trust (AUC: 0.802; sensitivity: 76%; specificity: 70%; and PPV: 49%). Calibration plot suggested predicted probabilities were similar to observed probabilities. Ipswich General Hospital produced comparable results to that of HEFT.Conclusion: The externally validated prediction model is a novel tool that can be used to improve care pathways for inpatients with diabetes. Further research utilising the model to develop care pathways and assess clinical utility is needed.",
keywords = "diabetes, Inpatient, Prediction model, validation",
author = "Krishnarajah Nirantharakumar and Nicola Adderley and Tom Marshall and Gerry Rayman and Susan Mallett and Sandip Ghosh and Funke Akiboye and Srikanth Bellary and Konstantinos Toulis and Jamie Coleman",
year = "2017",
month = mar,
day = "8",
doi = "10.1111/dme.13303",
language = "English",
volume = "34",
pages = "6",
journal = "Diabetic Medicine",
issn = "0742-3071",
publisher = "Wiley",
number = "Suppl. 1",

}

RIS

TY - JOUR

T1 - External validation of a prediction model that identifies adverse outcomes in hospitalised patients with diabetes

AU - Nirantharakumar, Krishnarajah

AU - Adderley, Nicola

AU - Marshall, Tom

AU - Rayman, Gerry

AU - Mallett, Susan

AU - Ghosh, Sandip

AU - Akiboye, Funke

AU - Bellary, Srikanth

AU - Toulis, Konstantinos

AU - Coleman, Jamie

PY - 2017/3/8

Y1 - 2017/3/8

N2 - Aim: To externally validate a prediction model that identifies adverse outcomes in hospitalised patients with diabetes.Methods: Data source: Inpatient data for 2014 from Heart of England Foundation Trust (HEFT) and Ipswich General Hospital.Participants: Patients with a diagnostic code of diabetes.Candidate variables: Age; gender; ethnicity; admission type; ITU admission; insulin therapy; albumin; sodium; potassium; haemoglobin; C-Reactive Protein; Estimated Glomerular Filtration Rate; and neutrophil count.Outcome definition: Adverse outcome is a composite outcome (excessive length of stay or death).Performance assessment: To assess discrimination, a receiver operating characteristic curve was constructed and Area Under the Curve (AUC) calculated. Calibration was assessed by plotting predicted probabilities of outcome against observed probabilities of outcome.Results: There were 16,568 admissions with diabetes to HEFT in 2014. The model discriminated well between those with and without an adverse outcome in HEFT (AUC:0.758, 95% CI: 0.747–0.768; sensitivity: 72.6%; specificity: 66.0%; and Positive Predictive Value (PPV): 45.1%). These are in comparison to the internally validated model derived at University Hospitals Birmingham NHS Foundation Trust (AUC: 0.802; sensitivity: 76%; specificity: 70%; and PPV: 49%). Calibration plot suggested predicted probabilities were similar to observed probabilities. Ipswich General Hospital produced comparable results to that of HEFT.Conclusion: The externally validated prediction model is a novel tool that can be used to improve care pathways for inpatients with diabetes. Further research utilising the model to develop care pathways and assess clinical utility is needed.

AB - Aim: To externally validate a prediction model that identifies adverse outcomes in hospitalised patients with diabetes.Methods: Data source: Inpatient data for 2014 from Heart of England Foundation Trust (HEFT) and Ipswich General Hospital.Participants: Patients with a diagnostic code of diabetes.Candidate variables: Age; gender; ethnicity; admission type; ITU admission; insulin therapy; albumin; sodium; potassium; haemoglobin; C-Reactive Protein; Estimated Glomerular Filtration Rate; and neutrophil count.Outcome definition: Adverse outcome is a composite outcome (excessive length of stay or death).Performance assessment: To assess discrimination, a receiver operating characteristic curve was constructed and Area Under the Curve (AUC) calculated. Calibration was assessed by plotting predicted probabilities of outcome against observed probabilities of outcome.Results: There were 16,568 admissions with diabetes to HEFT in 2014. The model discriminated well between those with and without an adverse outcome in HEFT (AUC:0.758, 95% CI: 0.747–0.768; sensitivity: 72.6%; specificity: 66.0%; and Positive Predictive Value (PPV): 45.1%). These are in comparison to the internally validated model derived at University Hospitals Birmingham NHS Foundation Trust (AUC: 0.802; sensitivity: 76%; specificity: 70%; and PPV: 49%). Calibration plot suggested predicted probabilities were similar to observed probabilities. Ipswich General Hospital produced comparable results to that of HEFT.Conclusion: The externally validated prediction model is a novel tool that can be used to improve care pathways for inpatients with diabetes. Further research utilising the model to develop care pathways and assess clinical utility is needed.

KW - diabetes

KW - Inpatient

KW - Prediction model

KW - validation

U2 - 10.1111/dme.13303

DO - 10.1111/dme.13303

M3 - Abstract

VL - 34

SP - 6

JO - Diabetic Medicine

JF - Diabetic Medicine

SN - 0742-3071

IS - Suppl. 1

M1 - A4 (P376)

ER -