Machine learning for accurate detection of small airway dysfunction-related respiratory changes: an observational study.

BACKGROUND: The use of machine learning(ML) methods would improve the diagnosis of small airway dysfunction(SAD) in subjects with chronic respiratory symptoms and preserved pulmonary function(PPF). This paper evaluated the performance of several ML algorithms associated with the impulse oscillometry(IOS) analysis to aid in the diagnostic of respiratory changes in SAD. We also find out the best configuration for this task. METHODS: IOS and spirometry were measured in 280 subjects, including a healthy control group (n = 78), a group with normal spirometry (n = 158) and a group with abnormal spirometry (n = 44). Various supervised machine learning (ML) algorithms and feature selection strategies were examined, such as Support Vector Machines (SVM), Random Forests (RF), Adaptive Boosting (ADABOOST), Navie Bayesian (BAYES), and K-Nearest Neighbors (KNN). RESULTS: The first experiment of this study demonstrated that the best oscillometric parameter (BOP) was R5, with an AUC value of 0.642, when comparing a healthy control group(CG) with patients in the group without lung volume-defined SAD(PPFN). The AUC value of BOP in the control group was 0.769 compared with patients with spirometry defined SAD(PPFA) in the PPF population. In the second experiment, the ML technique was used. In CGvsPPFN, RF and ADABOOST had the best diagnostic results (AUC = 0.914, 0.915), with significantly higher accuracy compared to BOP (p < 0.01). In CGvsPPFA, RF and ADABOOST had the best diagnostic results (AUC = 0.951, 0.971) and significantly higher diagnostic accuracy (p < 0.01). In the third, fourth and fifth experiments, different feature selection techniques allowed us to find the best IOS parameters (R5, (R5-R20)/R5 and Fres). The results demonstrate that the performance of ADABOOST remained essentially unaltered following the application of the feature selector, whereas the diagnostic accuracy of the remaining four classifiers (RF, SVM, BAYES, and KNN) is marginally enhanced. CONCLUSIONS: IOS combined with ML algorithms provide a new method for diagnosing SAD in subjects with chronic respiratory symptoms and PPF. The present study's findings provide evidence that this combination may help in the early diagnosis of respiratory changes in these patients.

Glutamatergic synapses from the insular cortex to the basolateral amygdala encode observational pain.

Empathic pain has attracted the interest of a substantial number of researchers studying the social transfer of pain in the sociological, psychological, and neuroscience fields. However, the neural mechanism of empathic pain remains elusive. Here, we establish a long-term observational pain model in mice and find that glutamatergic projection from the insular cortex (IC) to the basolateral amygdala (BLA) is critical for the formation of observational pain. The selective activation or inhibition of the IC-BLA projection pathway strengthens or weakens the intensity of observational pain, respectively. The synaptic molecules are screened, and the upregulated synaptotagmin-2 and RIM3 are identified as key signals in controlling the increased synaptic glutamate transmission from the IC to the BLA. Together, these results reveal the molecular and synaptic mechanisms of a previously unidentified neural pathway that regulates observational pain in mice.

Neurotensin Attenuates Nociception by Facilitating Inhibitory Synaptic Transmission in the Mouse Spinal Cord.

Neurotensin (NT) is an endogenous tridecapeptide in the central nervous system. NT-containing neurons and NT receptors are widely distributed in the spinal dorsal horn (SDH), indicating their possible modulatory roles in nociception processing. However, the exact distribution and function of NT, as well as NT receptors (NTRs) expression in the SDH, have not been well documented. Among the four NTR subtypes, NTR2 is predominantly involved in central analgesia according to previous reports. However, the expression and function of NTR2 in the SDH has not yet been directly elucidated. Specifically, it remains unclear how NT-NTR2 interactions contribute to NT-mediated analgesia. In the present study, by using immunofluorescent histochemical staining and immunohistochemical staining with in situ hybridization histochemical staining, we found that dense NT- immunoreactivity (NT-ir) and moderate NTR2-ir neuronal cell bodies and fibers were localized throughout the superficial laminae (laminae I-II) of the SDH at the light microscopic level. In addition, γ-aminobutyric acid (GABA) and NTR2 mRNA were colocalized in some neuronal cell bodies, predominantly in lamina II. Using confocal and electron microscopy, we also observed that NT-ir terminals made both close contacts and asymmetrical synapses with the local GABA-ir neurons. Second, electrophysiological recordings showed that NT facilitated inhibitory synaptic transmission but not glutamatergic excitatory synaptic transmission. Inactivation of NTR2 abolished the NT actions on both GABAergic and glycinergic synaptic release. Moreover, a behavioral study revealed that intrathecal injection of NT attenuated thermal pain, mechanical pain, and formalin induced acute inflammatory pain primarily by activating NTR2. Taken together, the present results provide direct evidence that NT-containing terminals and fibers, as well as NTR2-expressing neurons are widely distributed in the spinal dorsal horn, GABA-containing neurons express NTR2 mainly in lamina II, GABA coexists with NTR2 mainly in lamina II, and NT may directly increase the activity of local inhibitory neurons through NTR2 and induce analgesic effects.