OBJECTIVE: This paper presents a machine learning-based approach for the automatic classification of regular and irregular capnogram segments.
METHODS: Herein, we proposed four time- and two frequency-domain features experimented with the support vector machine classifier through ten-fold cross-validation. MATLAB simulation was conducted on 100 regular and 100 irregular 15 s capnogram segments. Analysis of variance was performed to investigate the significance of the proposed features. Pearson's correlation was utilized to select the relatively most substantial ones, namely variance and the area under normalized magnitude spectrum. Classification performance, using these features, was evaluated against two feature sets in which either time- or frequency-domain features only were employed.
RESULTS: Results showed a classification accuracy of 86.5%, which outperformed the other cases by an average of 5.5%. The achieved specificity, sensitivity, and precision were 84%, 89% and 86.51%, respectively. The average execution time for feature extraction and classification per segment is only 36 ms.
CONCLUSION: The proposed approach can be integrated with capnography devices for real-time capnogram-based respiratory assessment. However, further research is recommended to enhance the classification performance.
METHODS AND RESULTS: Effects of GBR, brown rice, and white rice (WR) on fasting plasma glucose and selected genes were studied in type 2 diabetic rats. GBR reduced plasma glucose and weight more than metformin, while WR worsened glycemia over 4 weeks of intervention. Through nutrigenomic suppression, GBR downregulated gluconeogenic genes (Fbp1 and Pck1) in a manner similar to, but more potently than, metformin, while WR upregulated the same genes. Bioactives (gamma-amino butyric acid, acylated steryl glycoside, oryzanol, and phenolics) were involved in GBR's downregulation of both genes. Plasma glucose, Fbp1 and Pck1 changes significantly affected the weight of rats (p = 0.0001).
CONCLUSION: The fact that GBR downregulates gluconeogenic genes similar to metformin, but produces better glycemic control in type 2 diabetic rats, suggests other mechanisms are involved in GBR's antihyperglycemic properties. GBR as a staple could potentially provide enhanced glycemic control in type 2 diabetes mellitus better than metformin.
PATIENTS AND METHODS: Twenty patients presenting with haemorrhagic radiation proctitis and treated with formalin dab were prospectively analysed.
RESULTS: Twelve patients ceased to bleed following one session of formnalin dab. Six patients needed more than one session to effect haemostasis. Two of three patients with torrential bleeding failed to respond to formalin dab and required surgical excision of the rectum.
CONCLUSION: Formalin dab is a simple, effective and safe treatment modality in the management of chronic haemorrhagic radiation proctitis, and hence should be considered as the initial treatment modality for such a condition.
Methods: Mice (n = 48) were fed high-fat diet (HFD) for 25 weeks to induce obesity, after which half were maintained on HFD and half switched to low-fat diet (LFD)while they were given normal water (H2O) or 0.1% (w/v) SCE in water at week 0-4 which was increased to 1% (w/v) at week 5-9. Effects of treatment with SCE were compared between HFDH2O, HFDSCE, LFDH2O and LFDSCE groups. Respiratory exchange ratios (RER) were measured at weeks 0, 5 and 10. Food, water intake and body weight were measured weekly. Plasma lipid profile and organ weights were determined at week 10.
Results: SCE had significantly reduced RER at week 9 (P = 0.011). Food intake, body weight, and abdominal adipose tissue weight were not altered by SCE at weeks 5 and 10. However, significant increase in plasma and liver cholesterol (P < 0.050) was observed.
Conclusion: Our findings suggest that SCE induced lipolysis and body fat oxidation and increased energy expenditure. Further studies in other animal models should be done to confirm the consistency of these results.