The Evaluation With Artificial Neural Network of Pain Scales in Children (ANN)

Pain Clinical Trial

— ANN  

Official title:

The Evaluation With Artificial Neural Network of Pain Scales in Children

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT02682875
• Other study ID #: Zehra123
• Status: Recruiting
• Phase: N/A
• First received: January 27, 2016
• Last updated: February 10, 2016
• Start date: November 2015
• Est. completion date: May 2016

Study information

• Verified date: February 2016
• Source: Cukurova University
• Contact: Dilek Özcengiz
• Phone: 05324673220
• Email: dilekozcengiz[@]gmail.com
• Is FDA regulated: No
• Health authority: Turkey: Ethics Committee
• Study type: Observational [Patient Registry]

Clinical Trial Summary

The study evaluates with Artificial Neural Network (ANN) of pain scales in children. Pain of these patients' will be evaluated by many pain scales in the postoperative period.

Description:

Pain of these patients' will be evaluated by many pain scales in the postoperative period. These scales include OUCHER, Visiuel Analog Scale, FLACC, Faces Pain Scale revise, Wong Baker Faces Scale, Faces Pain Scale, Numeric rating Scale, Verbal Rating Scale, CHEOPS and also age, blood pressure, respiratuar rate, heart rate will be recorded.

In the first step of this study, the parameters taken into account on widely used each pain scale practically and importance level of each parameter will be examined. The parameters taken into account in determining the degree of pain and degree of each pain scale will be recorded. Independent t-test of the pain scales will be analyzed whether different statistically. Pain scales used in the application at conclusion statistical analysis will be grouped.

In addition, parameters considered to be effective on pain (pulse, blood pressure, etc.) will be determined and also recorded. The degree of importance on pain of the current scales and other parameters to be determined and as result, new pain scale will be created. While determining the the level of importance will be utilized from the analytic hierarchy process (AHP). Making binary comparisons between AHP and parameters, the level of importance and weightiness score of each parameter will be determined. The mathematical formulation of the pain points will be presented considering AHP weightiness score of each parameter.

Although pain scores obtained mathematically, pain score with Artificial Neural Network (ANN) will be estimated considering the parameters that impact on the pain score.

The final step, the creation of new pain scale comparing the pain scores obtained by mathematical formulation and Artificial Neural Network and, it is intended to be compared with the current scales.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 140
• Est. completion date: May 2016
• Est. primary completion date: March 2016
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: Both
• Age group: 2 Months to 18 Years

Eligibility

Inclusion Criteria:

• 2 months -18 years

• Children undergoing elective surgery

Exclusion Criteria:

• Children with mental and motor development retardation

• Patients scheduled emergency surgery

• Patients and parents, who refused to participate in this study

Study Design

Observational Model: Case-Only, Time Perspective: Prospective

Related Conditions & MeSH terms

• Pain

Locations

Country	Name	City	State
Turkey	Zehra Hatipoglu	Adana

Sponsors (1)

Lead Sponsor	Collaborator
Cukurova University

Country where clinical trial is conducted

Turkey, 

References & Publications (1)

Azimi P, Mohammadi HR, Benzel EC, Shahzadi S, Azhari S, Montazeri A. Artificial neural networks in neurosurgery. J Neurol Neurosurg Psychiatry. 2015 Mar;86(3):251-6. doi: 10.1136/jnnp-2014-307807. Epub 2014 Jul 1. Review. — View Citation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Artificial Neural Network	the creation of new pain scale	4 months	No

External Links

•   Artificial neural networks in neurosurgery