• Je něco špatně v tomto záznamu ?

A Real-Time Clinical Decision Support System, for Mild Cognitive Impairment Detection, Based on a Hybrid Neural Architecture

CP. Suárez-Araujo, P. García Báez, Y. Cabrera-León, A. Prochazka, N. Rodríguez Espinosa, C. Fernández Viadero, FTAD. Neuroimaging Initiative

. 2021 ; 2021 (-) : 5545297. [pub] 20210621

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc22004202

Clinical procedure for mild cognitive impairment (MCI) is mainly based on clinical records and short cognitive tests. However, low suspicion and difficulties in understanding test cut-offs make diagnostic accuracy being low, particularly in primary care. Artificial neural networks (ANNs) are suitable to design computed aided diagnostic systems because of their features of generating relationships between variables and their learning capability. The main aim pursued in that work is to explore the ability of a hybrid ANN-based system in order to provide a tool to assist in the clinical decision-making that facilitates a reliable MCI estimate. The model is designed to work with variables usually available in primary care, including Minimental Status Examination (MMSE), Functional Assessment Questionnaire (FAQ), Geriatric Depression Scale (GDS), age, and years of education. It will be useful in any clinical setting. Other important goal of our study is to compare the diagnostic rendering of ANN-based system and clinical physicians. A sample of 128 MCI subjects and 203 controls was selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The ANN-based system found the optimal variable combination, being AUC, sensitivity, specificity, and clinical utility index (CUI) calculated. The ANN results were compared with those from medical experts which include two family physicians, a neurologist, and a geriatrician. The optimal ANN model reached an AUC of 95.2%, with a sensitivity of 90.0% and a specificity of 84.78% and was based on MMSE, FAQ, and age inputs. As a whole, physician performance achieved a sensitivity of 46.66% and a specificity of 91.3%. CUIs were also better for the ANN model. The proposed ANN system reaches excellent diagnostic accuracy although it is based only on common clinical tests. These results suggest that the system is especially suitable for primary care implementation, aiding physicians work with cognitive impairment suspicions.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22004202
003      
CZ-PrNML
005      
20220127145436.0
007      
ta
008      
220113s2021 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1155/2021/5545297 $2 doi
035    __
$a (PubMed)34257699
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Suárez-Araujo, Carmen Paz $u Instituto Universitario de Ciencias y Tecnologías Cibernéticas, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
245    12
$a A Real-Time Clinical Decision Support System, for Mild Cognitive Impairment Detection, Based on a Hybrid Neural Architecture / $c CP. Suárez-Araujo, P. García Báez, Y. Cabrera-León, A. Prochazka, N. Rodríguez Espinosa, C. Fernández Viadero, FTAD. Neuroimaging Initiative
520    9_
$a Clinical procedure for mild cognitive impairment (MCI) is mainly based on clinical records and short cognitive tests. However, low suspicion and difficulties in understanding test cut-offs make diagnostic accuracy being low, particularly in primary care. Artificial neural networks (ANNs) are suitable to design computed aided diagnostic systems because of their features of generating relationships between variables and their learning capability. The main aim pursued in that work is to explore the ability of a hybrid ANN-based system in order to provide a tool to assist in the clinical decision-making that facilitates a reliable MCI estimate. The model is designed to work with variables usually available in primary care, including Minimental Status Examination (MMSE), Functional Assessment Questionnaire (FAQ), Geriatric Depression Scale (GDS), age, and years of education. It will be useful in any clinical setting. Other important goal of our study is to compare the diagnostic rendering of ANN-based system and clinical physicians. A sample of 128 MCI subjects and 203 controls was selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The ANN-based system found the optimal variable combination, being AUC, sensitivity, specificity, and clinical utility index (CUI) calculated. The ANN results were compared with those from medical experts which include two family physicians, a neurologist, and a geriatrician. The optimal ANN model reached an AUC of 95.2%, with a sensitivity of 90.0% and a specificity of 84.78% and was based on MMSE, FAQ, and age inputs. As a whole, physician performance achieved a sensitivity of 46.66% and a specificity of 91.3%. CUIs were also better for the ANN model. The proposed ANN system reaches excellent diagnostic accuracy although it is based only on common clinical tests. These results suggest that the system is especially suitable for primary care implementation, aiding physicians work with cognitive impairment suspicions.
650    _2
$a senioři $7 D000368
650    _2
$a senioři nad 80 let $7 D000369
650    _2
$a plocha pod křivkou $7 D019540
650    _2
$a studie případů a kontrol $7 D016022
650    _2
$a kognitivní dysfunkce $x diagnóza $x psychologie $7 D060825
650    _2
$a výpočetní biologie $7 D019295
650    _2
$a databáze faktografické $x statistika a číselné údaje $7 D016208
650    12
$a systémy pro podporu klinického rozhodování $x statistika a číselné údaje $7 D020000
650    _2
$a diagnóza počítačová $x metody $x statistika a číselné údaje $7 D003936
650    _2
$a lidé $7 D006801
650    12
$a neuronové sítě $7 D016571
650    12
$a neuropsychologické testy $x statistika a číselné údaje $7 D009483
650    _2
$a senzitivita a specificita $7 D012680
655    _2
$a časopisecké články $7 D016428
700    1_
$a García Báez, Patricio $u Departamento de Ingeniería Informática y de Sistemas, Universidad de La Laguna, La Laguna, Spain
700    1_
$a Cabrera-León, Ylermi $u Instituto Universitario de Ciencias y Tecnologías Cibernéticas, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Spain
700    1_
$a Prochazka, Ales $u Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University, Prague, Czech Republic $u Department of Computing and Control Engineering, University of Chemistry and Technology, Prague, Czech Republic
700    1_
$a Rodríguez Espinosa, Norberto $u Unidad de Neurología de la Conducta y Memoria, Hospital Universitario Nuestra Señora de Candelaria, Santa Cruz de Tenerife, Spain
700    1_
$a Fernández Viadero, Carlos $u Servicio de Psiquiatría, Hospital Universitario Marqués de Valdecilla, Santander, Spain
700    1_
$a Neuroimaging Initiative, For The Alzheimer's Disease $u Center for Imaging of Neurodegenerative Disease San Francisco VA Medical Center University of California, San Francisco, USA
773    0_
$w MED00173439 $t Computational and mathematical methods in medicine $x 1748-6718 $g Roč. 2021, č. - (2021), s. 5545297
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34257699 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20220113 $b ABA008
991    __
$a 20220127145433 $b ABA008
999    __
$a ok $b bmc $g 1751607 $s 1155351
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2021 $b 2021 $c - $d 5545297 $e 20210621 $i 1748-6718 $m Computational and mathematical methods in medicine $n Comput Math Methods Med $x MED00173439
LZP    __
$a Pubmed-20220113

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...