Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 20 de 18.281
Filter
1.
Anim Cogn ; 27(1): 62, 2024 Oct 01.
Article in English | MEDLINE | ID: mdl-39352420

ABSTRACT

Parkinson's Disease (PD) is a clinically diagnosed disease that carries a reported misdiagnosis rate of 10-20%. Recent scientific discoveries have provided evidence of volatile organic compounds in sebum that are unique to patients with PD. The primary objective of this study was to determine if companion dogs could be trained to distinguish between sebum samples provided by PD-positive patients and PD-negative human controls. This was a randomized, handler-blind, controlled study. Twenty-three canines of varying breeds, ages, and environmental backgrounds were included. The study period encompassed 200 total working days from 2021 to 2022. Factors investigated included donor gender and levodopa drug affectivity, as well as canine breed, age, and duration of training time. The findings in this study were compiled from data collected during the final two years of a seven-year research program. For this two-year reporting period, when averaged as a group, the 23 dogs were 89% sensitive and 87% specific to olfactory distinction between PD-positive and PD-negative human donor samples. Ten of the twenty-three dogs averaged 90% or higher in both sensitivity and specificity. In 161 separate trials, a dog was presented with both novel PD-positive and PD-negative samples. For these novel exposures, the dogs collectively averaged 86% sensitivity and 89% specificity. PD medication was also investigated and was found to have no discernible impact on canine sensitivity or specificity results. Study findings support the application of companion dogs, trained with force-free, reward-based methodologies, for the detection of PD-positive and PD-negative samples under controlled conditions.


Subject(s)
Parkinson Disease , Dogs , Animals , Parkinson Disease/veterinary , Parkinson Disease/diagnosis , Male , Female , Humans , Pets , Smell , Sensitivity and Specificity , Dog Diseases/diagnosis
2.
Physiol Rep ; 12(19): e70057, 2024 Oct.
Article in English | MEDLINE | ID: mdl-39358841

ABSTRACT

The sense of smell is still considered a fuzzy sensation. Softly wafting aromas can stimulate the appetite and trigger memories; however, there are many unexplored aspects of its underlying mechanisms, and not all of these have been elucidated. Although the final sense of smell takes place in the brain, it is greatly affected during the preliminary stage, when odorants are converted into electrical signals. After signal conversion through ion channels in olfactory cilia, action potentials are generated through other types of ion channels located in the cell body. Spike trains through axons transmit this information as digital signals to the brain, however, before odorants are converted into digital electric signals, such as an action potential, modification of the transduction signal has already occurred. This review focuses on the early stages of olfactory signaling. Modification of signal transduction mechanisms and their effect on the human sense of smell through three characteristics (signal amplification, olfactory adaptation, and olfactory masking) produced by olfactory cilia, which is the site of signal transduction are being addressed in this review.


Subject(s)
Cilia , Signal Transduction , Smell , Humans , Smell/physiology , Animals , Cilia/physiology , Cilia/metabolism , Signal Transduction/physiology , Olfactory Receptor Neurons/physiology , Olfactory Receptor Neurons/metabolism , Odorants
3.
PLoS One ; 19(10): e0309129, 2024.
Article in English | MEDLINE | ID: mdl-39361581

ABSTRACT

Multimodal integration is a core neural process with a keen relevance during ecological tasks requiring learning and memory, such as foraging. The benefits of learning multimodal signals imply solving whether the components come from a single event. This challenge presumably depends on the timing and intensity of the stimuli. Here, we used simultaneous and alternate presentations of olfactory and visual stimuli, at low and high intensities, to understand how temporal and intensity variations affect the learning of a bimodal stimulus and its components. We relied on the conditioning of the proboscis extension response (PER) to train honey bees to an appetitive learning task with bimodal stimuli precisely controlled. We trained bees to stimuli with different synchronicity and intensity levels. We found that synchronicity, order of presentation, and intensity significantly impacted the probability of exhibiting conditioned PER responses and the latency of the conditioned responses. At low intensities, synchronous bimodal inputs produced maximal multisensory enhancement, while asynchronous temporal orders led to lower performances. At high intensities, the relative advantage of the synchronous stimulation diminished, and asynchronous stimuli produced similar performances. Memory retention was higher for the olfactory component and bimodal stimuli compared to the visual component, irrespective of the training's temporal configuration. Bees retained the asynchronous bimodal configuration to a lesser extent than the synchronous one, depending on the stimulus intensity. We conclude that time (synchrony), order of presentation, and intensity have interdependent effects on bee learning and memory performance. This suggests caution when assessing the independent effects of each factor.


Subject(s)
Learning , Memory , Animals , Bees/physiology , Memory/physiology , Learning/physiology , Photic Stimulation , Smell/physiology , Time Factors
4.
Sci Rep ; 14(1): 23511, 2024 10 09.
Article in English | MEDLINE | ID: mdl-39379543

ABSTRACT

To identify the differences between COVID-19-associated and non-COVID-19-associated olfactory dysfunction (OD), we analyzed demographic and clinical characteristics based on the causative virus (COVID versus non-COVID groups) in patients with post-infectious olfactory dysfunction (PIOD) who underwent the olfactory questionnaire and olfactory function test. Out of 169 patients with PIOD, 99 were diagnosed with COVID-19 (COVID group), while 70 were not (non-COVID group). The COVID group was younger and had a higher percentage of male patients as well as patients with parosmia than the non-COVID group. In the initial olfactory function tests, the TDI, discrimination and identification scores were significantly higher in the COVID group than in the non-COVID group. TDI scores were significantly increased in patients with PIOD after treatment, regardless of the group. The threshold score was significantly increased by 1.38 in the COVID group while the identification score was significantly increased by 2.67 in the non-COVID group. Patients with COVID-19-associated OD were younger in age, tended to be male, had a higher incidence of parosmia, and had better initial olfactory function test results compared to those with non-COVID-19-associated OD. Following treatment, odor detection threshold improved in the COVID group, whereas odor identification improved in the non-COVID group.


Subject(s)
COVID-19 , Olfaction Disorders , SARS-CoV-2 , Humans , COVID-19/complications , Male , Middle Aged , Olfaction Disorders/etiology , Olfaction Disorders/virology , Female , Aged , Adult , SARS-CoV-2/isolation & purification , Smell/physiology , Surveys and Questionnaires
6.
Commun Biol ; 7(1): 1252, 2024 Oct 03.
Article in English | MEDLINE | ID: mdl-39363042

ABSTRACT

Pheromones convey rich ethological information and guide insects' search behavior. Insects navigating in turbulent environments are tasked with the challenge of coding the temporal structure of an odor plume, obliging recognition of the onset and offset of whiffs of odor. The coding mechanisms that shape odor offset recognition remain elusive. We designed a device to deliver sharp pheromone pulses and simultaneously measured the response dynamics from pheromone-tuned olfactory receptor neurons (ORNs) in male moths and Drosophila. We show that concentration-invariant stimulus duration encoding is implemented in moth ORNs by spike frequency adaptation at two time scales. A linear-nonlinear model fully captures the underlying neural computations and offers an insight into their biophysical mechanisms. Drosophila use pheromone cis-vaccenyl acetate (cVA) only for very short distance communication and are not faced with the need to encode the statistics of the cVA plume. Their cVA-sensitive ORNs are indeed unable to encode odor-off events. Expression of moth pheromone receptors in Drosophila cVA-sensitive ORNs indicates that stimulus-offset coding is receptor independent. In moth ORNs, stimulus-offset coding breaks down for short ( < 200 ms) whiffs. This physiological constraint matches the behavioral latency of switching from the upwind surge to crosswind cast flight upon losing contact with the pheromone.


Subject(s)
Moths , Olfactory Receptor Neurons , Pheromones , Animals , Olfactory Receptor Neurons/physiology , Moths/physiology , Male , Olfactory Pathways/physiology , Odorants/analysis , Drosophila melanogaster/physiology , Smell/physiology , Drosophila/physiology , Acetates , Oleic Acids
7.
Geriatr Gerontol Int ; 24(10): 1022-1029, 2024 Oct.
Article in English | MEDLINE | ID: mdl-39266228

ABSTRACT

AIM: Chemosensory anhedonia refers to the lack of hedonic ability to experience pleasure through the senses of smell and taste, which reduces the pleasure and comfort of food, and increases the risk of nutritional and immune deficiencies. However, there is no direct scientific evidence regarding chemosensory anhedonia in patients with late-life depression (LLD). The aim of this study was to investigate chemosensory anhedonia in patients with LLD, and its potential association with depressive symptoms and cognitive function. METHODS: A total of 114 patients with LLD and 92 normal controls were included in this study. They experienced clinical assessment, Chemosensory Pleasure Scale assessment, 17-item Hamilton Depression Rating Scale assessment and cognitive assessments, which contain the Verbal Fluency Test. The associations between chemosensory pleasure and depressive symptoms or cognitive function in patients with LLD were explored using partial correlation analysis and mediation analysis. RESULTS: The Chemosensory Pleasure Scale scores were lower in the LLD group than in the normal control group, and were negatively correlated with the total scores and factors' scores (retardation, cognitive bias and anxiety/somatization) of the 17-item Hamilton Depression Rating Scale, and positively correlated with the Verbal Fluency Test scores. The scores for the Food and Imagination dimensions of the Chemosensory Pleasure Scale showed partial mediating effects on the differences in Cognitive bias (a factor of the 17-item Hamilton Depression Rating Scale) between patients with LLD and normal controls. CONCLUSIONS: Patients with LLD showed significant chemosensory anhedonia, and both depressive symptoms and cognitive impairment were associated with the severity of chemosensory anhedonia. Enhancing chemosensory pleasure in patients with LLD could potentially ameliorate their depressive symptoms. Geriatr Gerontol Int 2024; 24: 1022-1029.


Subject(s)
Anhedonia , Cognitive Dysfunction , Depression , Humans , Male , Female , Aged , Anhedonia/physiology , Cognitive Dysfunction/psychology , Depression/psychology , Case-Control Studies , Psychiatric Status Rating Scales , Aged, 80 and over , Middle Aged , Smell/physiology , Taste/physiology
8.
J Vis Exp ; (211)2024 Sep 13.
Article in English | MEDLINE | ID: mdl-39345116

ABSTRACT

Olfactory impairment is a significant public health problem and independently predicts the risk of neurodegenerative diseases. Inhaled environmental pollutants exposure may impair olfaction; thereby, there is an urgent need for methods to evaluate the effects of inhaled environmental pollutants exposure on olfaction. Mice are ideal models for olfactory experiments because of their highly developed olfactory system and behavioral characteristics. To assess the effects of inhaled environmental pollutants exposure on olfactory function in mice, a detailed buried food test and social odor discrimination experiment is provided, including the experiment preparation, the selection and construction of experimental facilities, the testing process, and indexes of time. Meanwhile, timekeeping equipment, operational details, and the experimental environment are discussed to ensure the success of the assay. Zinc sulfate is used as the treatment to demonstrate the feasibility of the experimental approach. The protocol provides a simple and clear operational process for assessing the effects of inhaled environmental pollutants on olfactory function in mice.


Subject(s)
Smell , Animals , Mice , Smell/drug effects , Smell/physiology , Environmental Pollutants/toxicity , Zinc Sulfate/toxicity , Zinc Sulfate/administration & dosage , Male , Inhalation Exposure/adverse effects , Air Pollutants/toxicity , Odorants/analysis , Olfaction Disorders/chemically induced , Olfaction Disorders/physiopathology
11.
PLoS One ; 19(9): e0310254, 2024.
Article in English | MEDLINE | ID: mdl-39325742

ABSTRACT

Animals navigating turbulent odor plumes exhibit a rich variety of behaviors, and employ efficient strategies to locate odor sources. A growing body of literature has started to probe this complex task of localizing airborne odor sources in walking mammals to further our understanding of neural encoding and decoding of naturalistic sensory stimuli. However, correlating the intermittent olfactory information with behavior has remained a long-standing challenge due to the stochastic nature of the odor stimulus. We recently reported a method to record real-time olfactory information available to freely moving mice during odor-guided navigation, hence overcoming that challenge. Here we combine our odor-recording method with head-motion tracking to establish correlations between plume encounters and head movements. We show that mice exhibit robust head-pitch motions in the 5-14Hz range during an odor-guided navigation task, and that these head motions are modulated by plume encounters. Furthermore, mice reduce their angles with respect to the source upon plume contact. Head motions may thus be an important part of the sensorimotor behavioral repertoire during naturalistic odor-source localization.


Subject(s)
Head Movements , Odorants , Animals , Odorants/analysis , Mice , Head Movements/physiology , Smell/physiology , Male , Mice, Inbred C57BL , Head/physiology , Behavior, Animal/physiology
12.
Article in English | MEDLINE | ID: mdl-39313183

ABSTRACT

As more physiologists start to incorporate animal behavior into their experiments, especially in the olfactory behavior research field, some considerations are often overlooked, partly due to the inherited way that physiological experiments are traditionally designed and performed. Here we highlight some of these subtle but important considerations and make a case for why these might affect the results collected from behavioral assays. Our aim is to provide useful suggestions for increased standardization of methods so they can be more easily replicated among different experiments and laboratories. We have focused on areas that are less likely to be mentioned in the materials and methods section of a manuscript such as starvation, preliminary experiments, appropriate sample sizes and considerations when choosing an odorant for an assay. Additionally, we are strongly cautioning against the use of alarm cue to generate behavioral responses due to its highly unstable chemical properties/potency. Instead, we suggest using pure chemicals (made up of one known molecule) such as amino acids, bile acids, or polyamines that are commercially available and easier to make up in known concentrations. Lastly, we strongly suggest using environmentally relevant concentrations of these odorants. We believe these guidelines will help standardize these assays and improve replication of experiments within and between laboratories.


Subject(s)
Behavior, Animal , Odorants , Smell , Animals , Odorants/analysis , Smell/physiology , Physiology, Comparative/methods , Aquatic Organisms/physiology
13.
J Agric Food Chem ; 72(40): 22250-22257, 2024 Oct 09.
Article in English | MEDLINE | ID: mdl-39344091

ABSTRACT

Beer and wine are popular beverages with clearly different aroma characters, the molecular background of which has not yet been systematically investigated. A comprehensive literature survey returned 14 845 concentration values obtained from 160 beer and 904 wine samples, covering 42 basic beer and 42 basic wine odorants, among which 40 were common to both beverages. Based on mean concentrations and a comparison with threshold data, 29 beer and 32 wine odorants were finally selected to build aroma base models that reflected the basic olfactory difference between beer and wine. Orthonasal concentration leveling tests applied to groups of odorants with similar odor characteristics finally revealed the crucial role of fruity smelling compounds. When 11 fruity compounds, predominantly esters, in the beer aroma base model were adjusted to the respective concentration levels in the wine aroma base model, the sensory panel no longer described the sample as beer-like but as wine-like.


Subject(s)
Beer , Odorants , Smell , Wine , Beer/analysis , Wine/analysis , Odorants/analysis , Humans , Volatile Organic Compounds/chemistry , Volatile Organic Compounds/analysis , Flavoring Agents/chemistry , Taste
14.
Trends Neurosci ; 47(10): 834-848, 2024 Oct.
Article in English | MEDLINE | ID: mdl-39245626

ABSTRACT

Many animal species use olfaction to extract information about objects in their environment. Yet, the specific molecular signature that any given object emits varies due to various factors. Here, we detail why such variability makes chemosensory-mediated object recognition such a hard problem, and we propose that a major function of the elaborate chemosensory network is to overcome it. We describe previous work addressing different elements of the problem and outline future research directions that we consider essential for a full understanding of object-oriented olfaction. In particular, we call for extensive representation of olfactory object variability in chemical, behavioral, and electrophysiological analyses. While written with an emphasis on macrosmatic mammalian species, our arguments apply to all organisms that employ chemosensation to navigate complex environments.


Subject(s)
Smell , Animals , Smell/physiology , Humans , Olfactory Pathways/physiology , Odorants , Olfactory Perception/physiology
15.
J Exp Biol ; 227(19)2024 Oct 01.
Article in English | MEDLINE | ID: mdl-39238479

ABSTRACT

Pacific salmon are well known for their homing migrations; juvenile salmon learn odors associated with their natal streams prior to seaward migration, and then use these retained odor memories to guide them back from oceanic feeding grounds to their river of origin to spawn several years later. This memory formation, termed olfactory imprinting, involves (at least in part) sensitization of the peripheral olfactory epithelium to specific odorants. We hypothesized that this change in peripheral sensitivity is due to exposure-dependent increases in the expression of odorant receptor (OR) proteins that are activated by specific odorants experienced during imprinting. To test this hypothesis, we exposed juvenile coho salmon, Oncorhynchus kisutch, to the basic amino acid odorant l-arginine during the parr-smolt transformation (PST), when imprinting occurs, and assessed sensitivity of the olfactory epithelium to this and other odorants. We then identified the coho salmon ortholog of a basic amino acid odorant receptor (BAAR) and determined the mRNA expression levels of this receptor and other transcripts representing different classes of OR families. Exposure to l-arginine during the PST resulted in increased sensitivity to that odorant and a specific increase in BAAR mRNA expression in the olfactory epithelium relative to other ORs. These results suggest that specific increases in ORs activated during imprinting may be an important component of home stream memory formation and this phenomenon may ultimately be useful as a marker of successful imprinting to assess management strategies and hatchery practices that may influence straying in salmon.


Subject(s)
Odorants , Oncorhynchus kisutch , Receptors, Odorant , Animals , Receptors, Odorant/genetics , Receptors, Odorant/metabolism , Oncorhynchus kisutch/genetics , Oncorhynchus kisutch/physiology , Odorants/analysis , Arginine/metabolism , Smell , Fish Proteins/genetics , Fish Proteins/metabolism , Imprinting, Psychological , Olfactory Mucosa/metabolism , Olfactory Mucosa/physiology , Gene Expression Regulation , RNA, Messenger/genetics , RNA, Messenger/metabolism
16.
Chem Senses ; 492024 Jan 01.
Article in English | MEDLINE | ID: mdl-39292252

ABSTRACT

Most patients report "taste" changes after undergoing metabolic surgeries. Yet, most studies that used validated sensory evaluation techniques, including ours, found no changes in perceived taste intensity from before to after surgery. However, we assessed participants with pure gustatory stimuli and after an overnight fast, which raises questions about whether patients' self-reported "taste" changes are due to conflating changes in retronasal smell/"flavor" with taste changes or whether they only manifest during the fed state. To investigate this, we conducted a cross-sectional study comparing sensory responses in women who underwent metabolic surgery 2 to 6 yr ago (n = 15) with 2 nonoperated control groups: one with a body mass index (BMI) equivalent (n = 15) and one with a healthy BMI (n = 15). Participants attended 2 sessions, one fed and one fasted. Using a sip-and-spit method, women tasted liquid samples containing gustatory and olfactory stimuli and puddings with varying fat content with and without nose clips. They used separate general labeled magnitude scales to rate their perceived intensity of taste, smell, flavor, and liking. Mixed ANOVAs indicated that the surgery and BMI equivalent groups rated retronasal smell intensity of coffee stronger than the healthy BMI group (P ≤ 0.015). However, there were no differences in taste/flavor intensity or liking ratings among groups. Additionally, feeding conditions did not significantly affect perceived intensity ratings. Our findings suggest that changes in the sensory-discriminatory component of taste or taste-odor interactions are not significant contributors to dietary modifications following metabolic surgery.


Subject(s)
Odorants , Smell , Taste , Humans , Female , Adult , Taste/physiology , Odorants/analysis , Middle Aged , Smell/physiology , Cross-Sectional Studies , Body Mass Index
17.
Nutr J ; 23(1): 105, 2024 Sep 11.
Article in English | MEDLINE | ID: mdl-39261883

ABSTRACT

BACKGROUND: Child food neophobia, i.e., rejection or avoidance of novel foods at a young age, is a prevalent nutrition problem that affects the quality of children's diet and impedes the development of healthy food preferences. Sensory sensitivity can relate to the degree of food neophobia, but previous studies rarely focused on the olfactory component of this problem in children. OBJECTIVE: We aimed to thoroughly examine the relationship between various aspects of olfactory sensitivity and food neophobia in children. METHODS: 246 children aged between three and nine years took part in a food neophobia assessment as well as in a comprehensive, psychophysical olfactory testing. RESULTS: We found that certain smell perception aspects such as lower odor liking, poorer odor identification ability as well as lower sensitivity to an unknown non-food odor all significantly predicted higher food neophobia in children. Among individual characteristics of either a child or a caregiver, only the child's age significantly and positively predicted food neophobia. The exploratory model looking into the role of family environment factors predicting self-reported food neophobia in children revealed that food neophobia was associated with lower control given to a child in this child's feeding process, as well as with a more frequent use of food as a reward in feeding. CONCLUSIONS: We suggest that suppressed olfactory perception and performance can play a unique role in child nutritional difficulties. The study inspires further considerations of olfaction-engaging interventions to counteract food-neophobia in children.


Subject(s)
Avoidant Restrictive Food Intake Disorder , Food Preferences , Odorants , Smell , Humans , Female , Child , Male , Food Preferences/psychology , Child, Preschool , Smell/physiology , Olfactory Perception/physiology
18.
Commun Biol ; 7(1): 1133, 2024 Sep 13.
Article in English | MEDLINE | ID: mdl-39271812

ABSTRACT

There is a growing interest in the effects of climate warming on olfaction, as temperature may affect this essential sense. In insects, the response of the olfactory system to developmental temperature might be mediated by body size or mass because body size and mass are negatively affected by developmental temperature in most ectotherms. We tested this hypothesis of a mass-mediated effect of developmental temperature on olfaction in the moth Spodoptera littoralis. We measured the olfactory sensitivity of male to female sex pheromone and five plant odors using electroantennography. We compared males reared at an optimal temperature (25 °C with a daily fluctuation of ±5 °C) and at a high temperature (33 ± 5 °C) close to the upper limit of S. littoralis. On average, the olfactory sensitivity of males did not differ between the two developmental temperatures. However, our analyses revealed an interaction between the effects of developmental temperature and body mass on the detection of the six chemicals tested. This interaction is explained by a positive relationship between antennal sensitivity and body mass observed only with the high developmental temperature. Our results show that the effect of developmental temperature may not be detected when organism size is ignored.


Subject(s)
Smell , Spodoptera , Temperature , Animals , Male , Smell/physiology , Female , Spodoptera/growth & development , Spodoptera/physiology , Body Weight , Sex Attractants/metabolism , Odorants , Body Size , Arthropod Antennae/physiology , Arthropod Antennae/growth & development , Moths/growth & development , Moths/physiology
19.
Chem Senses ; 492024 Jan 01.
Article in English | MEDLINE | ID: mdl-39311704

ABSTRACT

The Social Odor Scale (SOS) is a 12-item questionnaire initially developed and validated in Italian and German to investigate self-reported awareness of social odors, which are odors emanating from the human body that convey diverse information and evoke various emotional responses. The scale includes a total score and 3 subscales representing social odors in the respective categories: romantic partner, familiar, and strangers. Here, we aimed to (i) replicate the validation of the Italian and German versions of the SOS, (ii) translate and validate the SOS into multiple additional languages (French, English, Dutch, Swedish, Chinese), and (iii) explore whether the factor structure of each translated version aligns with the original versions. Confirmatory Factor Analysis (CFA) supported the scale's structure, yielding a good fit across all languages. Notable differences in SOS mean scores were observed among the different languages: Swedish participants exhibited lower social odor awareness compared to the other groups, whereas Chinese participants reported higher social odor awareness compared to Dutch and Swedish participants. Furthermore, SOS scores correlated with respondents' geographical location, with higher (i.e. northern) latitudes linked to lower social odor awareness. These results corroborate the SOS as a valid and reliable instrument, especially for the SOS total score and the Familiar and Partner factors, emphasizing the influence of individual and geographic factors on social odor awareness.


Subject(s)
Language , Odorants , Humans , Odorants/analysis , Male , Female , Adult , Surveys and Questionnaires , Young Adult , Translations , Middle Aged , Smell/physiology , Olfactory Perception/physiology , Adolescent
20.
ACS Sens ; 9(9): 4934-4946, 2024 Sep 27.
Article in English | MEDLINE | ID: mdl-39248698

ABSTRACT

This study introduces a novel deep learning framework for lung health evaluation using exhaled gas. The framework synergistically integrates pyramid pooling and a dual-encoder network, leveraging SHapley Additive exPlanations (SHAP) derived feature importance to enhance its predictive capability. The framework is specifically designed to effectively distinguish between smokers, individuals with chronic obstructive pulmonary disease (COPD), and control subjects. The pyramid pooling structure aggregates multilevel global information by pooling features at four scales. SHAP assesses feature importance from the eight sensors. Two encoder architectures handle different feature sets based on their importance, optimizing performance. Besides, the model's robustness is enhanced using the sliding window technique and white noise augmentation on the original data. In 5-fold cross-validation, the model achieved an average accuracy of 96.40%, surpassing that of a single encoder pyramid pooling model by 10.77%. Further optimization of filters in the transformer convolutional layer and pooling size in the pyramid module increased the accuracy to 98.46%. This study offers an efficient tool for identifying the effects of smoking and COPD, as well as a novel approach to utilizing deep learning technology to address complex biomedical issues.


Subject(s)
Pulmonary Disease, Chronic Obstructive , Humans , Pulmonary Disease, Chronic Obstructive/diagnosis , Deep Learning , Smoking , Lung , Breath Tests/methods , Male , Smell
SELECTION OF CITATIONS
SEARCH DETAIL