Machine learning-based clustering and classification of mouse behaviors via respiratory patterns

Janke, Emma; Zhang, Marina Yue; Ryu, Sang Eun; Bhattarai, Janardhan P.; Schreck, Mary; Moberly, Andrew H.; Luo, Wenqin; Ding, Long; Wesson, Daniel W.; Ma, Minghong

doi:10.1016/j.isci.2022.105625

Cited by 4 publications

(3 citation statements)

References 62 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that respiratory patterns are different depending on the vigilance states and emotional content (Bagur et al 2018, 2021; Dupin et al 2020; Girin et al 2021; Hegoburu et al 2011). In addition, Janke et al (2022) have recently demonstrated, using machine learning model, that behaviors in rodents can be accurately predicted based on their respiration patterns, therefore unraveling the strong correlation between the two parameters. In our study, we first verified whether the neurotoxin-induced lesion had altered the rats’ behavioral states.…”

Section: Discussionmentioning

confidence: 99%

“…The association between animal behavior and their specific respiratory outcomes has been described in several studies (Dupin et al 2020;Girin et al 2021;Hegoburu et al 2011;Janke et al 2022). Therefore, during the passive exposure to the experimental cage, we decided to inspect the rats' respiratory signal across three vigilance states: sleep, quiet waking and exploration (Girin et al 2021).…”

Section: Respiratory Signals In Different Behavioral Statesmentioning

confidence: 99%

“…Importantly, none of these studies seem to have taken into consideration the animal behavioral state while recording their respiration. Of note, different teams have shown that different behaviors are associated with specific respiratory patterns (Bagur et al 2018, 2021; Dupin et al 2020; Girin et al 2021; Hegoburu et al 2011; Janke et al 2022; Youngentob et al 1987). For instance, major differences in respiratory frequency and peak flow rate can be observed between sleep, quiet waking or exploration (Girin et al 2021).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

State-dependent alteration of respiration in a rat model of Parkinson disease

Walker,

Meunier,

Garcia

et al. 2023

Preprint

View full text Add to dashboard Cite

Parkinson disease (PD) is the second most frequent neurodegenerative disorder. Besides major deficits in motor coordination, patients may also display sensory and cognitive impairments, which are often overlooked despite being inherently part of the PD symptomatology. Amongst those symptoms, respiration, a key mechanism involved in the regulation of multiple physiological and neuronal processes, appears to be altered. Importantly, breathing patterns are highly correlated with the animal’s behavioral states, and although respiration has been investigated in different models of PD, no study has yet taken into consideration the potential impact of behavioral state on respiration deficits in these models. To explore this variable, we first characterized the respiratory parameters in a neurotoxin-induced rat model of PD (6-OHDA) across different vigilance states: sleep, quiet waking and exploration. We noted a significantly higher respiratory frequency in 6-OHDA rats during quiet waking compared to Sham rats. A higher respiratory amplitude was also observed in 6-OHDA rats during both quiet waking and exploration. No effect of the treatment was noted during sleep. Given the relation between respiration and olfaction and the presence of olfactory deficits in PD patients, we then investigated the odor-evoked sniffing response in PD rats, using an odor habituation/cross-habituation paradigm. No substantial differences were observed in olfactory abilities between the two groups, as assessed through sniffing frequency. These results corroborate the hypothesis that respiratory impairments in 6-OHDA rats are vigilance-dependent. Our results also shed light on the importance of considering the behavioral state as an impacting factor when analyzing respiration.HighlightsSpecific respiratory patterns associated to different vigilance statesSpecific alteration of respiration during quiet waking in a rodent model of PDPreserved olfactory abilities as assessed through sniffing in a rodent model of PD

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Respiratory Signals In Different Behavioral Statesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

State-dependent alteration of respiration in a rat model of Parkinson disease

Walker,

Meunier,

Garcia

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Self‐Learning e‐Skin Respirometer for Pulmonary Disease Detection

Babu,

Kassahun,

Dufour

et al. 2024

Advanced Sensor Research

View full text Add to dashboard Cite

Amid the landscape of respiratory health, lung disorders stand out as the primary contributors to pulmonary intricacies and respiratory diseases. Timely precautions through accurate diagnosis hold the key to mitigating their impact. Nevertheless, the existing conventional methods of lungs monitoring exhibit limitations due to bulky instruments, intrusive techniques, manual data recording, and discomfort in continuous measurements. In this context, an unintrusive organic wearable piezoelectric electronic‐skin respirometer (eSR) exhibiting a high‐sensitivity (385 mV N−1), precise conversion factor (12 mL mV−1), high signal‐to‐noise ratio (58 dB), and a low limit of detection down to 100 mL is demonstrated, which is perfectly suitable to record diverse breathing signals. To empower the eSR with early diagnosis functionality, self‐learning capability is further added by integrating the respirometer with the machine learning algorithms. Among various tested algorithms, gradient boosting regression emerges as the most suitable, leveraging sequential model refinement to achieve an accuracy exceeding 95% in detection of chronic obstructive pulmonary diseases (COPD). From conception to validation, the approach not only provides an alternative pathway for tracking the progression of lung diseases but also has the capability to replace the conventional techniques, with the conformable AI‐empowered respirometer.

show abstract