A simplified critical illness severity scoring system (CISSS): Development and internal validation

Spyridon Fortis; Amy M.J O'Shea; Brice F Beck; Rajeshwari Nair; Michihiko Goto; Gregory A Schmidt; Peter J Kaboli; Eli N Perencevich; Heather Schacht Reisinger; Mary Vaughan Sarrazin

doi:10.1016/j.jcrc.2020.09.029

Back

A simplified critical illness severity scoring system (CISSS): Development and internal validation

Journal article

Peer reviewed

A simplified critical illness severity scoring system (CISSS): Development and internal validation

Spyridon Fortis, Amy M.J O'Shea, Brice F Beck, Rajeshwari Nair, Michihiko Goto, Gregory A Schmidt, Peter J Kaboli, Eli N Perencevich, Heather Schacht Reisinger and Mary Vaughan Sarrazin

Journal of critical care, Vol.61, pp.21-28

02/2021

DOI: 10.1016/j.jcrc.2020.09.029

PMID: 33049489

View Online

Abstract

To create a simplified critical illness severity scoring system with high prediction accuracy for 30-day mortality using only commonly available variables. This is a retrospective cohort study of ICU admissions 2010–2015 in 306 ICUs in 117 Veterans Affairs (VA) hospitals. We randomly divided our cohort into a training dataset (75%) and a validation dataset (25%). We created a critical illness severity scoring system (CISSS) using age, comorbidities, heart rate, mean arterial blood pressure, temperature, respiratory rate, hematocrit, white blood cell count, creatinine, sodium, glucose, albumin, bilirubin, bicarbonate, use of invasive mechanical ventilation, and whether the admission was surgical or not. We validated the performance of CISSS to predict 30-day mortality internally. After excluding 31,743 re-admissions, we divided our sample (n = 534,001) into a training (n = 400,613) and a validation dataset (n = 133,388). In the training dataset, the area under the curve (AUC) of CISSS was 0.847(95%CI = 0.845–0.850). In the validation dataset, the AUC was 0.848 (95%CI = 0.844–0.852), the standardized mortality ratio (SMR) was 1.00 (95%CI = 0.98–1.02), and Brier's score for 30-day mortality was 0.058 (95%CI = 0.057–0.059). CISSS calibration was acceptable. CISSS has very good performance and requires only commonly used variables that can be easily extracted by electronic health records. •Traditional critical illness severity scoring systems are not easily obtainable.•We created a critical illness severity score using only commonly available variables.•CISSS has very good performance to predict 30-day mortality.•CISSS can be easily calculated using electronic health records.

Computerized

Intensive care units

Illness severity score

Automated

Mortality

APACHE

critical illness severity scoring system (CISSS)

Details

Title: Subtitle: A simplified critical illness severity scoring system (CISSS): Development and internal validation
Creators: Spyridon Fortis - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Amy M.J O'Shea - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Brice F Beck - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Rajeshwari Nair - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Michihiko Goto - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Gregory A Schmidt - Department of Internal Medicine, Division of Pulmonary, Critical Care and Occupational Medicine, University of Iowa Roy J. and Lucille A. Carver College of Medicine, Iowa City, IA, USA
Peter J Kaboli - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Eli N Perencevich - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Heather Schacht Reisinger - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Mary Vaughan Sarrazin - Center for Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA
Resource Type: Journal article
Publication Details: Journal of critical care, Vol.61, pp.21-28
Publisher: Elsevier Inc
DOI: 10.1016/j.jcrc.2020.09.029
PMID: 33049489
ISSN: 0883-9441
eISSN: 1557-8615
Grant note: name: VA Tele-ICU Program and Center for Comprehensive Access & Delivery Research & Evaluation, award: CIN-13-412; DOI: 10.13039/100000738, name: Department of Veterans Affairs, award: 14380; DOI: 10.13039/100007217, name: Health Services Research and development, award: CIN 13-412
Language: English
Date published: 02/2021
Academic Unit: Infectious Diseases; Health Management and Policy; Epidemiology; Center for Social Science Innovation; Internal Medicine
Record Identifier: 9984001182402771

Metrics

53 Record Views

5 Times Cited - Web of Science