Machine learning approaches reveal subtle differences in breathing and sleep fragmentation in Phox2b-derived astrocytes ablated mice

Autor(es):Mostrar menos -

Silva, Talita M. ^{[1, 2]} ; Borniger, Jeremy C. ^[3] ; Alves, Michele Joana ^[2] ; Correa, Diego Alzate ^[2] ; Zhao, Jing ^[4] ; Fadda, Paolo ^[5] ; Toland, Amanda Ewart ^{[5, 6]} ; Takakura, Ana C. ^[7] ; Moreira, Thiago S. ^[1] ; Czeisler, Catherine M. ^[2] ; Otero, Jose Javier ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Biomed Sci, Dept Physiol & Biophys, Sao Paulo - Brazil

^[2] Ohio State Univ, Coll Med, Dept Pathol, Div Neuropathol, Columbus, OH 43210 - USA

^[3] Cold Spring Harbor Lab, POB 100, Cold Spring Harbor, NY 11724 - USA

^[4] Ohio State Univ, Coll Dent, Dept Biomed Informat, Columbus, OH 43210 - USA

^[5] Ohio State Univ, Genom Shared Resource Comprehens Canc Ctr, Columbus, OH 43210 - USA

^[6] Ohio State Univ, Coll Med, Dept Canc Biol & Genet, Columbus, OH 43210 - USA

^[7] Univ Sao Paulo, Inst Biomed Sci, Dept Pharmacol, Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Journal of Neurophysiology; v. 125, n. 4, p. 1164-1179, APR 2021.
• Citações Web of Science: 0

Resumo

Modern neurophysiology research requires the interrogation of high-dimensionality data sets. Machine learning and artificial intelligence (ML/AI) workflows have permeated into nearly all aspects of daily life in the developed world but have not been implemented routinely in neurophysiological analyses. The power of these workflows includes the speed at which they can be deployed, their availability of open-source programming languages, and the objectivity permitted in their data analysis. We used classification-based algorithms, including random forest, gradient boosted machines, support vector machines, and neural networks, to test the hypothesis that the animal genotypes could be separated into their genotype based on interpretation of neurophysiological recordings. We then interrogate the models to identify what were the major features utilized by the algorithms to designate genotype classification. By using raw EEG and respiratory plethysmography data, we were able to predict which recordings came from genotype class with accuracies that were significantly improved relative to the no information rate, although EEG analyses showed more overlap between groups than respiratory plethysmography. In comparison, conventional methods where single features between animal classes were analyzed, differences between the genotypes tested using baseline neurophysiology measurements showed no statistical difference. However, ML/AI workflows successfully were capable of providing successful classification, indicating that interactions between features were different in these genotypes. ML/AI workflows provide new methodologies to interrogate neurophysiology data. However, their implementation must be done with care so as to provide high rigor and reproducibility between laboratories. We provide a series of recommendations on how to report the utilization of ML/AI workflows for the neurophysiology community. NEW \& NOTEWORTHY ML/AI classification workflows are capable of providing insight into differences between genotypes for neurophysiology research. Analytical techniques utilized in the neurophysiology community can be augmented by implementing ML/AI workflows. Random forest is a robust classification algorithm for respiratory plethysmography data. Utilization of ML/AI workflows in neurophysiology research requires heightened transparency and improved community research standards. (AU)

• Processo FAPESP: 15/23376-1 - Núcleo retrotrapezóide, quimiossensibilidade central e automaticidade respiratória
• Beneficiário: Thiago dos Santos Moreira
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 18/03994-0 - Análise ultraestrutural da patologia de axônios de camundongos com depleção seletiva de astrócitos derivados de Phox2b
• Beneficiário: Talita de Melo e Silva
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Pós-Doutorado
• Processo FAPESP: 19/01236-4 - Efeitos de tratamentos farmacológicos e não farmacológicos nas alterações respiratórias observadas em um modelo murino da Doença de Parkinson
• Beneficiário: Ana Carolina Takakura Moreira
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 17/12678-2 - Participação dos astrócitos localizados na superfície ventrolateral do bulbo nas respostas ventilatórias à hipercapnia e hipóxia
• Beneficiário: Talita de Melo e Silva
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado