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.

[Correlation analysis between continuous cropping obstacle of Gastrodia elata and Ilyonectria fungi and relieving strategy].

The continuous cropping obstacle of Gastrodia elata is outstanding, but its mechanism is still unclear. In this study, microbial changes in soils after G. elata planting were investigated to explore the mechanism correlated with continuous cropping obstacle. The changes of species and abundance of fungi and bacteria in soils planted with G. elata after 1, 2, and 3 years were compared. The pathogenic fungi that might cause continuous cropping diseases of G. elata were isolated. Finally, the prevention and control measures of soil-borne fungal diseases of G. elata were investigated with the rotation planting pattern of "G. elata-Phallus impudicus". The results showed that G. elata planting resulted in the decrease in bacterial and fungal community stability and the increase in harmful fungus species and abundance in soils. This change was most obvious in the second year after G. elata planting, and the soil microbial community structure could not return to the normal level even if it was left idle for another two years. After G. elata planting in soils, the most significant change was observed in Ilyonectria cyclaminicola. The richness of the Ilyonectria fungus in soils was significantly positively correlated with the incidence of G. elata diseases. When I. cyclaminicola was inoculated in the sterile soil, the rot rate of G. elata was also significantly increased. After planting one crop of G. elata and one to three crops of P. impudicus, the fungus community structure in soils gradually recovered, and the abundance of I. cyclaminicola decreased year by year. Furthermore, the disease rate of G. elata decreased. The results showed that the cultivation of G. elata made the Ilyonectria fungi the dominant flora in soils, and I. cyclaminicola served as the main pathogen of continuous cropping diseases of G. elata, which could be reduced by rotation planting with P. impudicus.

[Construction of protoplast genetic transformation system for Mycena--symbiont of Gastrodia elata].

Mycena, a symbiont of Gastrodia elata, promotes seed germination of G. elata and plays a crucial role in the sexual reproduction of G. elata. However, the lack of genetic transformation system of Mycena blocks the research on the interaction mechanism of the two. In order to establish the protoplast transformation system of Mycena, this study analyzed the protoplast enzymatic hydrolysis system, screened the resistance markers and regeneration medium, and explored the transient transformation. After hydrolysis of Mycena hyphae with complexes enzymes for 8 h and centrifugation at 4 000 r·min~(-1), high-concentration and quality protoplast was obtained. The optimum regeneration medium for Mycena was RMV, and the optimum resistance marker was 50 mg·mL~(-1) hygromycin. The pLH-HygB-HuSHXG-GFP-HdSHXG was transformed into the protoplast of Mycena which then expressed GFP. The established protoplast transformation system of Mycena laid a foundation for analyzing the functional genes of Mycena and the molecular mechanism of the symbiosis of Mycena and G. elata.

Impulse oscillometry for detection of small airway dysfunction in subjects with chronic respiratory symptoms and preserved pulmonary function.

BACKGROUND: Subjects with chronic respiratory symptoms and preserved pulmonary function (PPF) may have small airway dysfunction (SAD). As the most common means to detect SAD, spirometry needs good cooperation and its reliability is controversial. Impulse oscillometry (IOS) may complete the deficiency of spirometry and have higher sensitivity. We aimed to explore the diagnostic value of IOS to detect SAD in symptomatic subjects with PPF. METHODS: The evaluation of symptoms, spirometry and IOS results in 209 subjects with chronic respiratory symptoms and PPF were assessed. ROC curves of IOS to detect SAD were analyzed. RESULTS: 209 subjects with chronic respiratory symptoms and PPF were included. Subjects who reported sputum had higher R5-R20 and Fres than those who didn't. Subjects with dyspnea had higher R5, R5-R20 and AX than those without. CAT and mMRC scores correlated better with IOS parameters than with spirometry. R5, R5-R20, AX and Fres in subjects with SAD (n = 42) significantly increased compared to those without. Cutoff values for IOS parameters to detect SAD were 0.30 kPa/L s for R5, 0.015 kPa/L s for R5-R20, 0.30 kPa/L for AX and 11.23 Hz for Fres. Fres has the largest AUC (0.665, P = 0.001) among these parameters. Compared with spirometry, prevalence of SAD was higher when measured with IOS. R5 could detect the most SAD subjects with a prevalence of 60.77% and a sensitivity of 81% (AUC = 0.659, P = 0.002). CONCLUSION: IOS is more sensitive to detect SAD than spirometry in subjects with chronic respiratory symptoms and PPF, and it correlates better with symptoms. IOS could be an additional method for SAD detection in the early stage of diseases.