Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F17%3A50013664" target="_blank" >RIV/62690094:18450/17:50013664 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.sciencedirect.com/science/article/pii/S0925231216315673" target="_blank" >http://www.sciencedirect.com/science/article/pii/S0925231216315673</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.neucom.2016.09.113" target="_blank" >10.1016/j.neucom.2016.09.113</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets

Popis výsledku v původním jazyce

Rheumatoid Arthritis (RA) is a chronic autoimmune disease that affect joints and muscles, and can result in noticeable disruption of joint structure and function. Early diagnosis of RA is very crucial in preventing disease&apos;s progression. However, it is a complicated task for General Practitioners (GPs) due to the wide spectrum of symptoms, and progressive changes in disease&apos;s direction over time. In order to assist physicians, and to minimize possible errors due to fatigued or less-experienced physicians, this study proposes an advanced decision support tool based on consultations with a group of experienced medical professionals (i.e. orthopedic surgeons and rheumatologists), and using a well-known soft computing method called Fuzzy Cognitive Maps (FCMs). First, a set of criteria for diagnosis of RA, based on previous studies and consultation with medical professionals have been selected. Then, Particle Swarm Optimization (PSO) and FCMs along with medical experts&apos; knowledge were used to model this problem and calculate the severity of the RA disease. Finally, a small-scale test has been conducted at Shohada University Hospital, Iran, for evaluating the accuracy of the proposed tool. Accuracy level of the tool reached to 90% and the results closely matched the medical professionals&apos; opinions. Considering obtained results in real practice, we believe that the proposed decision support tool can assist GPs in an accurate and timely diagnosis of patients with RA. Ultimately, the risk of wrong or late diagnosis will be diminished, and patients’ disease may be prevented from moving through the advanced stages.

Název v anglickém jazyce

Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets

Popis výsledku anglicky

Rheumatoid Arthritis (RA) is a chronic autoimmune disease that affect joints and muscles, and can result in noticeable disruption of joint structure and function. Early diagnosis of RA is very crucial in preventing disease&apos;s progression. However, it is a complicated task for General Practitioners (GPs) due to the wide spectrum of symptoms, and progressive changes in disease&apos;s direction over time. In order to assist physicians, and to minimize possible errors due to fatigued or less-experienced physicians, this study proposes an advanced decision support tool based on consultations with a group of experienced medical professionals (i.e. orthopedic surgeons and rheumatologists), and using a well-known soft computing method called Fuzzy Cognitive Maps (FCMs). First, a set of criteria for diagnosis of RA, based on previous studies and consultation with medical professionals have been selected. Then, Particle Swarm Optimization (PSO) and FCMs along with medical experts&apos; knowledge were used to model this problem and calculate the severity of the RA disease. Finally, a small-scale test has been conducted at Shohada University Hospital, Iran, for evaluating the accuracy of the proposed tool. Accuracy level of the tool reached to 90% and the results closely matched the medical professionals&apos; opinions. Considering obtained results in real practice, we believe that the proposed decision support tool can assist GPs in an accurate and timely diagnosis of patients with RA. Ultimately, the risk of wrong or late diagnosis will be diminished, and patients’ disease may be prevented from moving through the advanced stages.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neurocomputing

ISSN

0925-2312

e-ISSN

—

Svazek periodika

232

Číslo periodika v rámci svazku

April 5

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

9

Strana od-do

104-112

Kód UT WoS článku

000393532800010

EID výsledku v databázi Scopus

2-s2.0-85008474411