Clinical decision support tool for Co-management signalling

Alexandra Bayão Horta, Cátia Salgado, Marta Fernandes, Susana Vieira, João M. Sousa, Ana Luísa Papoila, Miguel Xavier

Research output: Contribution to journalArticle

Abstract

Introduction: Co-management between internists and surgeons of selected patients is becoming one of the pillars of modern clinical management in large hospitals. Defining the patients to be co-managed is essential. The aim of this study is to create a decision tool using real-world patient data collected in the preoperative period, to support the decision on which patients should have the co-management service offered. Methods: Data was collected from the electronic clinical health records of patients who had an International Classification of Diseases, 9th edition (ICD–9) code of colorectal surgery during the period between January 2012 and October 2014 in a 200 bed private teaching hospital in Lisbon. ICD–9 codes of colorectal surgery [48.5 and 48.6 (anterior rectal resection and abdominoperineal resection), 45.7 (partial colectomy), 45.8 (Total Colectomy), and 45.9 (Bowel Anastomosis)] were used. Only patients above 18 years old were considered. Patients with more than one procedure were excluded from the study. From these data the authors investigated the construction of predictive models using logistic regression and Takagi-Sugeno fuzzy modelling. Results: Data contains information obtained from the clinical records of a cohort of 344 adult patients. Data from 398 emergent and elective surgeries were collected, from which 54 were excluded because they were second procedures for the same patients. Four preoperative variables were identified as being the most predictive of co-management, in multivariable regression analysis. The final model performed well after being internally validated (0.81 AUC, 77% accuracy, 74% sensitivity, 78% specificity, 93% negative predictive value). The results indicate that the decision process can be more objective and potentially automated. Conclusions: The authors developed a prediction model based on preoperative characteristics, in order to support the decision for the co-management of surgical patients in the postoperative ward setting. The model is a simple bedside decision tool that uses only four numerical variables.

Original languageEnglish
Pages (from-to)56-62
Number of pages7
JournalInternational Journal of Medical Informatics
Volume113
DOIs
Publication statusPublished - May 2018

Fingerprint

Clinical Decision Support Systems
Colorectal Surgery
Colectomy
International Classification of Diseases
Preoperative Period
Private Hospitals
Electronic Health Records
Teaching Hospitals
Area Under Curve
Logistic Models

Keywords

  • Co-management
  • Decision support tool
  • Failure to rescue
  • High risk patients
  • Internal Medicine
  • Multistage modelling

Cite this

Horta, Alexandra Bayão ; Salgado, Cátia ; Fernandes, Marta ; Vieira, Susana ; Sousa, João M. ; Papoila, Ana Luísa ; Xavier, Miguel. / Clinical decision support tool for Co-management signalling. In: International Journal of Medical Informatics. 2018 ; Vol. 113. pp. 56-62.
@article{78f1b2ca7fd741af8b2d0f860c8eb207,
title = "Clinical decision support tool for Co-management signalling",
abstract = "Introduction: Co-management between internists and surgeons of selected patients is becoming one of the pillars of modern clinical management in large hospitals. Defining the patients to be co-managed is essential. The aim of this study is to create a decision tool using real-world patient data collected in the preoperative period, to support the decision on which patients should have the co-management service offered. Methods: Data was collected from the electronic clinical health records of patients who had an International Classification of Diseases, 9th edition (ICD–9) code of colorectal surgery during the period between January 2012 and October 2014 in a 200 bed private teaching hospital in Lisbon. ICD–9 codes of colorectal surgery [48.5 and 48.6 (anterior rectal resection and abdominoperineal resection), 45.7 (partial colectomy), 45.8 (Total Colectomy), and 45.9 (Bowel Anastomosis)] were used. Only patients above 18 years old were considered. Patients with more than one procedure were excluded from the study. From these data the authors investigated the construction of predictive models using logistic regression and Takagi-Sugeno fuzzy modelling. Results: Data contains information obtained from the clinical records of a cohort of 344 adult patients. Data from 398 emergent and elective surgeries were collected, from which 54 were excluded because they were second procedures for the same patients. Four preoperative variables were identified as being the most predictive of co-management, in multivariable regression analysis. The final model performed well after being internally validated (0.81 AUC, 77{\%} accuracy, 74{\%} sensitivity, 78{\%} specificity, 93{\%} negative predictive value). The results indicate that the decision process can be more objective and potentially automated. Conclusions: The authors developed a prediction model based on preoperative characteristics, in order to support the decision for the co-management of surgical patients in the postoperative ward setting. The model is a simple bedside decision tool that uses only four numerical variables.",
keywords = "Co-management, Decision support tool, Failure to rescue, High risk patients, Internal Medicine, Multistage modelling",
author = "Horta, {Alexandra Bay{\~a}o} and C{\'a}tia Salgado and Marta Fernandes and Susana Vieira and Sousa, {Jo{\~a}o M.} and Papoila, {Ana Lu{\'i}sa} and Miguel Xavier",
year = "2018",
month = "5",
doi = "10.1016/j.ijmedinf.2018.02.014",
language = "English",
volume = "113",
pages = "56--62",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Science B.V., Amsterdam.",

}

Clinical decision support tool for Co-management signalling. / Horta, Alexandra Bayão; Salgado, Cátia; Fernandes, Marta; Vieira, Susana; Sousa, João M.; Papoila, Ana Luísa; Xavier, Miguel.

In: International Journal of Medical Informatics, Vol. 113, 05.2018, p. 56-62.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Clinical decision support tool for Co-management signalling

AU - Horta, Alexandra Bayão

AU - Salgado, Cátia

AU - Fernandes, Marta

AU - Vieira, Susana

AU - Sousa, João M.

AU - Papoila, Ana Luísa

AU - Xavier, Miguel

PY - 2018/5

Y1 - 2018/5

N2 - Introduction: Co-management between internists and surgeons of selected patients is becoming one of the pillars of modern clinical management in large hospitals. Defining the patients to be co-managed is essential. The aim of this study is to create a decision tool using real-world patient data collected in the preoperative period, to support the decision on which patients should have the co-management service offered. Methods: Data was collected from the electronic clinical health records of patients who had an International Classification of Diseases, 9th edition (ICD–9) code of colorectal surgery during the period between January 2012 and October 2014 in a 200 bed private teaching hospital in Lisbon. ICD–9 codes of colorectal surgery [48.5 and 48.6 (anterior rectal resection and abdominoperineal resection), 45.7 (partial colectomy), 45.8 (Total Colectomy), and 45.9 (Bowel Anastomosis)] were used. Only patients above 18 years old were considered. Patients with more than one procedure were excluded from the study. From these data the authors investigated the construction of predictive models using logistic regression and Takagi-Sugeno fuzzy modelling. Results: Data contains information obtained from the clinical records of a cohort of 344 adult patients. Data from 398 emergent and elective surgeries were collected, from which 54 were excluded because they were second procedures for the same patients. Four preoperative variables were identified as being the most predictive of co-management, in multivariable regression analysis. The final model performed well after being internally validated (0.81 AUC, 77% accuracy, 74% sensitivity, 78% specificity, 93% negative predictive value). The results indicate that the decision process can be more objective and potentially automated. Conclusions: The authors developed a prediction model based on preoperative characteristics, in order to support the decision for the co-management of surgical patients in the postoperative ward setting. The model is a simple bedside decision tool that uses only four numerical variables.

AB - Introduction: Co-management between internists and surgeons of selected patients is becoming one of the pillars of modern clinical management in large hospitals. Defining the patients to be co-managed is essential. The aim of this study is to create a decision tool using real-world patient data collected in the preoperative period, to support the decision on which patients should have the co-management service offered. Methods: Data was collected from the electronic clinical health records of patients who had an International Classification of Diseases, 9th edition (ICD–9) code of colorectal surgery during the period between January 2012 and October 2014 in a 200 bed private teaching hospital in Lisbon. ICD–9 codes of colorectal surgery [48.5 and 48.6 (anterior rectal resection and abdominoperineal resection), 45.7 (partial colectomy), 45.8 (Total Colectomy), and 45.9 (Bowel Anastomosis)] were used. Only patients above 18 years old were considered. Patients with more than one procedure were excluded from the study. From these data the authors investigated the construction of predictive models using logistic regression and Takagi-Sugeno fuzzy modelling. Results: Data contains information obtained from the clinical records of a cohort of 344 adult patients. Data from 398 emergent and elective surgeries were collected, from which 54 were excluded because they were second procedures for the same patients. Four preoperative variables were identified as being the most predictive of co-management, in multivariable regression analysis. The final model performed well after being internally validated (0.81 AUC, 77% accuracy, 74% sensitivity, 78% specificity, 93% negative predictive value). The results indicate that the decision process can be more objective and potentially automated. Conclusions: The authors developed a prediction model based on preoperative characteristics, in order to support the decision for the co-management of surgical patients in the postoperative ward setting. The model is a simple bedside decision tool that uses only four numerical variables.

KW - Co-management

KW - Decision support tool

KW - Failure to rescue

KW - High risk patients

KW - Internal Medicine

KW - Multistage modelling

UR - http://www.scopus.com/inward/record.url?scp=85042691172&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2018.02.014

DO - 10.1016/j.ijmedinf.2018.02.014

M3 - Article

VL - 113

SP - 56

EP - 62

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

ER -