=Paper=
{{Paper
|id=Vol-1747/IP26_ICBO2016
|storemode=property
|title=Performance Evaluation Clinical Task Ontology(PECTO)
|pdfUrl=https://ceur-ws.org/Vol-1747/IP26_ICBO2016.pdf
|volume=Vol-1747
|authors=Jose F Florez-Arango,Santiago Patiño-Giraldo,Jack W Smith,Sriram Iyengar
|dblpUrl=https://dblp.org/rec/conf/icbo/Florez-ArangoPS16
}}
==Performance Evaluation Clinical Task Ontology(PECTO) ==
https://ceur-ws.org/Vol-1747/IP26_ICBO2016.pdf
Performance Evaluation Clinical Task
Ontology(PECTO)
An approach for building simulation-based evaluation of new technologies and their effect
on health worker performance
Jose F Florez-Arango 1,2 , Santiago Patiño-Giraldo3,4 , M. Sriram Iyengar1 , Jack W Smith1,2
1 College of Medicine 3 Grupo INFORMED
Texas A&M University Facultad de Medicina
College Station, TX, USA Universidad de Antioquia
florezarango@medicine.tamhsc.edu Medellín, Colombia
2 Línea e-salud, Centro Bioingeniería
Escuela de Ciencias de la Salud 4 Hospital Pablo Tobón Uribe
Universidad Pontificia Bolivariana Medellín, Colombia
Medellín, Colombia
Abstract—This poster presents a proposed Clinical Tasks task model of care plans[8], as well as comprehensive approaches
Ontology (PECTO) designed to evaluate effects of technologies to model human factors and workload.
on human performance under controlled conditions, such as
clinical simulation scenarios (CSS), across multiple clinical For the purpose of this research a Clinical Task (task) is defined
domains including prehospital care. In recent years there has been as an action accomplished by a health care provider for the
an explosion of technologies, including Information and purpose of solving a clinical case. A case is a clinical situation that
Communications Technologies (ICTs) that are designed to assist includes provider, patient’s conditions, clinical protocol or
health workers and improve their performance across a spectrum guideline to de followed and resources available. A case is
of clinical activities from pre-hospital care to post-surgical care. expected to have a desirable outcome.
However, each new technology introduces its own requirements Clinical Tasks can be determined by protocols. “Clinical
on the health worker and has the potential to either increase or protocols are agreed statements about a specific issue, with
decrease the perceived workload on the health-worker. Since explicit steps based on clinical guidelines and/or organizational
perceived workload can have significant effects on health worker consensus. A protocol is not specific to a named patient”[6].
performance [4], it is important to carefully measure work-load The PECTO developed here was part of a broader study focused
changes and relate these to health worker performance measures on evaluating use on computerized clinical guidelines by
such as task errors, and procedure compliance. Clinical Simulatio n community health workers [10], [11].
Scenarios are often used to perform controlled experiments in
which health workers’ performance on clinical conditions, PECTO was constructed in Protégé by two clinical experts and is
simulated by various means, including Human Patient Simulators , informed by several previous research studies on task analysis and
is observed and measured with and without the technology being clinical modeling. Each task in the PECTO has 9 possible
studied[5]. The Clinical Tasks Ontology (PECTO) was developed, properties classes, 75 distinct classes and 14 object properties.
among other applications, to help design such evaluation When applied to 30 pre-hospital cases for community health
experiments. A major objective of such studies is to evaluate the workers, following 6 clinical protocols, PECTO resulted in 447
performance of health workers as they perform specific clinical identifiable individual tasks. In a study of task performance by
tasks. In this context, the PECTO presents a novel approach for Community Health Workers, application of PECTO enabled
task classification and analysis since previous approaches [6]–[8] differentiation between learning and technology effects. Another
do not account for sources of workload, and measurement of application of PECTO is the development of a visual
human performance in terms of errors and protocol compliance. representation of case similarity.
An ontological approach was selected to build the classification There are 5 object properties in addition to 9 basic object
system enabling tasks to have multiple properties that can be properties (relationships) between tasks and dimensions, as seen
related to dependent variables. Previous work in task analysis and in Figure 2. PECTO object properties. These object properties
task classification include an ontological approach to plans and allow for additional expressivity for particular inferred task, as a
processes[6], some modeling of event evaluation [7], and a clinical critical task (a task that is indispensable or its not execution ends
in patient death). Or to establish complexity of tasks accordingly II. DISCUSSION AND CONCLUSION
with number of subtask/goal
We developed a Clinical Task Ontology accounting with human
performance factors. One limitation is that this first version is
based on the clinical domain of pre-hospital care in which
Community Health Workers are the primary clinicians. While this
domain is very important in the global health context of
developing countries, the developmental methodology can be
extended to include other clinical domains .
An important application, among others, of the PECTO is the
ability to create metrics to compare cases from a human
performance perspective.
Future work include extending type of task model in order to have
a reasoner-based classification of task depending on additional
properties, instead of simply asserting the task type.
Figure 1 PECTO Fully expanded
III. REFERENCES
[1] S. Ajami and F. Teimouri, “Features and application of wearable
biosensors in medical care,” J. Res. Med. Sci., vol. 20, no. 12, pp.
1208–1215, Dec. 2015.
[2] B. C. W. Kot, M . T. C. Ying, and F. M . Brook, “A comparison
of portable ultrasound and fully -equipped clinical ultrasound
unit in the thyroid size measurement of the Indo-Pacific
bottlenose dolphin,” PLoS One, vol. 7, no. 1, 2012.
[3] S. P. Bhavnani, J. Narula, and P. P. Sengupta, “M obile
technology and the digitization of healthcare.,” Eur. Heart J.,
vol. 37, no. 18, pp. 1428–1438, 2016.
[4] X. M ao, P. Jia, L. Zhang, P. Zhao, Y. Chen, and M . Zhang, “An
evaluation of the effects of human factors and ergonomics on
health care and patient safety practices: A systematic review,”
PLoS One, vol. 10, no. 6, pp. 1–19, 2015.
[5] A. Alaraj, M . K. Tobin, and D. M . Birk, “The Comprehensive
Figure 2. PECTO object properties Textbook of Healthcare Simulation,” Compr. Textb. Healthc.
Simul., no. Chapter 28, pp. 415–423, 2013.
[6] J. Fox, A. Alabassi, V. Patkar, T. Rose, and E. Black, “An
ontological approach to modelling tasks and goals,” Comput.
A. Extrinsic Evaluation Biol. Med., vol. 36, no. 7–8, pp. 837–856, 2006.
For extrinsic evaluation a total of 982 tasks (individuals) were [7] L. Pellegrin, N. Bonnardel, F. Antonini, J. Albanese, C. M artin,
derived from 30 clinical cases. Each task was assigned at least a and H. Chaudet, “Event Oriented Representation for
leaf class of each of 9 main domains. A total of 200 ontological Collaborative Activities (EORCA) - A M ethod for Describing
distinctive task were obtained after applying reasoner. The most M edical Activities in Severely -injured Patient M anagement,”
Methods Inf. Med., vol. 46, no. 5, pp. 506–515, 2007.
frequent task for the study particular data set was “Verify If Pulse
[8] D. M . Stein, J. O. Wrenn, P. D. Stetson, and S. Bakken, “What
is Present”, is it a task present in 20 out of the 30 cases. An ‘to-do’ with physician task lists: clinical task model development
ontological representation of such task is shown in Example 1. and electronic health record design implications.,” AMIA Annu.
Verify If Pulse is Present Symp. Proc., vol. 2009, pp. 624–628, 2009.
is_a Task [9] S. G. Hart, “Development of NASA-TLX: Results of Empirical
hasGoal Detection and Theoretical Research,” 1988.
is_a DecideAlternativeHypotesis [10] J. F. Florez-Arango, M . S. Iyengar, K. Dunn, and J. Zhang,
is_a KnowledgeGoal “Performance factors of mobile rich media job aids for
requiresSkill ManualSkill community health workers.,” J. Am. Med. Inform. Assoc., vol.
hasComplexity Simple
hasPhysicalDemand FinePrecision 18, no. 2, pp. 131–7, Jan. 2011.
is_a Physical_activity [11] J. F. Florez-Arango, “Workload and Performance Factors
hasTemporalContrains EmergentNotDiferable Associated with M ultimedia Jobs Aids for Community Health
hasCriticality Indispensable Workers,” The University of Texas Health Science Center at
requieresCognitiveProcess PerceptionAction Houston, 2009.
hasTaskType ClinicalExamination
Example 1. Ontological representation of a task [12] R. Islam, C. Weir, and G. Del Fiol, “Clinical Complexity in
is_a InformativeActions M edicine: A M easurement M odel of Task and Patient
is_a TaskAsAction
Complexity.,” Method Inf. Med., pp. 1–9, 2016.
is_a TypeOfTask