Artificial Neural Networks Coupled with MALDI-TOF MS Serum Fingerprinting To Classify and Diagnose Pathological Pain Subtypes in Preclinical Models

Varování

Publikace nespadá pod Ekonomicko-správní fakultu, ale pod Lékařskou fakultu. Oficiální stránka publikace je na webu muni.cz.
Autoři

DEULOFEU FIGUERAS Meritxell PENA-MÉNDEZ Eladia M. VAŇHARA Petr HAVEL Josef MORÁŇ Lukáš PEČINKA Lukáš BAGÓ-MAS Anna VERDÚ Enrique SALVADÓ Victoria BOADAS-VAELLO Pere

Rok publikování 2023
Druh Článek v odborném periodiku
Časopis / Zdroj ACS Chemical Neuroscience
Fakulta / Pracoviště MU

Lékařská fakulta

Citace
www https://pubs.acs.org/doi/full/10.1021/acschemneuro.2c00665?cookieSet=1
Doi http://dx.doi.org/10.1021/acschemneuro.2c00665
Klíčová slova neuropathic pain; fibromyalgia; mass spectrometry; artificial intelligence; MALDI-TOF MS; diagnostics
Popis Pathological pain subtypes can be classified as either neuropathic pain, caused by a somatosensory nervous system lesion or disease, or nociplastic pain, which develops without evidence of somatosensory system damage. Since there is no gold standard for the diagnosis of pathological pain subtypes, the proper classification of individual patients is currently an unmet challenge for clinicians. While the determination of specific biomarkers for each condition by current biochemical techniques is a complex task, the use of multimolecular techniques, such as matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), combined with artificial intelligence allows specific fingerprints for pathological pain-subtypes to be obtained, which may be useful for diagnosis. We analyzed whether the information provided by the mass spectra of serum samples of four experimental models of neuropathic and nociplastic pain combined with their functional pain outcomes could enable pathological pain subtype classification by artificial neural networks. As a result, a simple and innovative clinical decision support method has been developed that combines MALDI-TOF MS serum spectra and pain evaluation with its subsequent data analysis by artificial neural networks and allows the identification and classification of pathological pain subtypes in experimental models with a high level of specificity.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.