A classification model for prediction of clinical severity level using qSOFA medical score
| DOI | https://doi.org/10.1108/IDD-02-2019-0013 |
| Date | 06 February 2020 |
| Published date | 06 February 2020 |
| Pages | 41-77 |
| Author | Diana Olivia,Ashalatha Nayak,Mamatha Balachandra,Jaison John |
| Subject Matter | Library & information science,Library & information services,Lending,Document delivery,Collection building & management,Stock revision,Consortia |
A classification model for prediction of clinical
severity level using qSOFA medical score
Diana Olivia
Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education,
Manipal, India
Ashalatha Nayak and Mamatha Balachandra
Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education,
Manipal, India, and
Jaison John
Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education,
Manipal, India
Abstract
Purpose –The purpose of this study is to develop an efficient prediction model using vital signs and standard medical score systems, which
predicts the clinical severity level of the patient in advance based on the quick sequential organ failure assessment (qSOFA) medical score
method.
Design/methodology/approach –To predict the clinical severity level of the patient in advance, the authors have formulated a training da taset
that is constructed based on the qSOFA medical score method. Further, along with the multiple vital signs, different standard medical scores and
their correlation features are used to build and improve the accuracy of the prediction model. It is made sure that the constructed training set is
suitable for the severity level prediction because the formulated dataset has different clusters each corresponding to different severity levels
according to qSOFA score.
Findings –From the experimental result, it is found that the inclusion of the standard medical scores and their correlation along with multiple vital
signs improves the accuracy of the clinical severity level prediction model. In addition, the authors showed that the training dataset formulated from
the temporal data (which includes vital signs and medical scores) based on the qSOFA medical scoring system has the clusters which correspond to
each severity level in qSOFA score. Finally, it is found that RAndom k-labELsets multi-label classification performs better prediction of severity level
compared to neural network-based multi-label classification.
Originality/value –This paper helps in identifying patient’clinical status.
Keywords Statistical analysis, Clinical severity level, Medical score, qSOFA, Ensemble multi-label classifier
Paper type Research paper
1. Introduction
The emergency department (ED) necessitates intensely ill
patients of essential, lifesaving treatments. Increase in the
number of casualty visits to ED has led to overcrowding and
delay in providing the necessary medical attention and care.
EDs often have a number of staff compared to other hospital
units. However, real-world limitations restrict the number of
nurses and doctors attendingto the patients in the ED. The ED
is a mainly challenging environment because each patient’s
severity of illness is constantly changing, subsequently leading
to increased mortality, morbidity and poor process measures
across the clinical conditions. Delay in care turns critically ill
patients more vulnerable, and their health deteriorates. At the
ED, the triage procedure is used to identify the medical
condition of the ill patients and decide on further medical
treatment based on the severity of their condition. Accurate
triage process must be maintained at EDs to quickly identify
and prioritize patients so that critical patients are given more
priority compared to the patients with less urgency. Even
though the triageis a simpleprocess, it is challenging because of
the limited time and limited information, and it completely
relies upon one’s perception.
The medical group generally applies a “Simple Triage and
Rapid Treatment (START)”(Sakanushi et al.,2012) method
to assess the patient’s medicalcondition. The START protocol
uses three physiological signs,i.e. pulse rate, breathing rate and
mental status to sort the patients. Based on the conditions of
these signs, patients are categorized into four groups which
indicate the priorities of patientstreated. However, over a time,
the casualty needs to be triaged again because the casualty’s
medical condition may change over time. Hence, the paper-
Thecurrentissueandfulltextarchiveofthisjournalisavailableon
Emerald Insight at: https://www.emerald.com/insight/2398-6247.htm
Information Discovery and Delivery
48/1 (2020) 41–47
© Emerald Publishing Limited [ISSN 2398-6247]
[DOI 10.1108/IDD-02-2019-0013]
Received 1 February 2019
Revised 3 May 2019
22 August 2019
17 November 2019
Accepted 4 December 2019
41
To continue reading
Request your trial