Automatic sleep-wake classification and Parkinson's disease recognition using multifeature fusion with support vector machine.

AIMS: Sleep disturbance is a prevalent nonmotor symptom of Parkinson's disease (PD), however, assessing sleep conditions is always time-consuming and labor-intensive. In this study, we performed an automatic sleep-wake state classification and early diagnosis of PD by analyzing the electrocorticography (ECoG) and electromyogram (EMG) signals of both normal and PD rats. METHODS: The study utilized ECoG power, EMG amplitude, and corticomuscular coherence values extracted from normal and PD rats to construct sleep-wake scoring models based on the support vector machine algorithm. Subsequently, we incorporated feature values that could act as diagnostic markers for PD and then retrained the models, which could encompass the identification of vigilance states and the diagnosis of PD. RESULTS: Features extracted from occipital ECoG signals were more suitable for constructing sleep-wake scoring models than those from frontal ECoG (average Cohen's kappa: 0.73 vs. 0.71). Additionally, after retraining, the new models demonstrated increased sensitivity to PD and accurately determined the sleep-wake states of rats (average Cohen's kappa: 0.79). CONCLUSION: This study accomplished the precise detection of substantia nigra lesions and the monitoring of sleep-wake states. The integration of circadian rhythm monitoring and disease state assessment has the potential to improve the efficacy of therapeutic strategies considerably.

Systematic evaluation of combined herbal adjuvant therapy for proliferative diabetic retinopathy.

Objective: To evaluate the efficacy and safety of combined traditional Chinese medicine in the adjuvant treatment of proliferative diabetic retinopathy (PDR) by Meta-analysis. Methods: PubMed, Embase, Web of Science, Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang databases were searched by computer. Random controlled clinical trials (RCTS) using traditional Chinese medicine as adjuvant therapy for proliferative diabetic retinopathy were screened, and Stata16.0 software was used to perform meta-analysis on the final included literatures. Results: A total of 18 studies involving 1392 patients were included. Meta-analysis showed that the clinical effective rate OR=2.99 (CI: 2.18-4.10, I2 = 42.7%, P<0.05); Visual acuity MD=0.10(CI: 0.06-0.13, I2 = 0%, P<0.05); Fundus efficacy OR=5.47 (CI: 1.33-22.51, I2 = 71.4%, P<0.05); Neovascularisation regression rate OR=8 (CI: 3.83-16.71, I2 = 30.1%, P<0.05); Macular foveal thickness MD=-44.24 (CI: -84.55-3.93, I2 = 95.6%, P<0.05); Absorption of vitreous hemorrhage OR=4.7 (CI: 2.26-9.77, I2 = 0%, P<0.05); Fasting blood glucose MD=-0.23, (CI: -0.38-0.07, I2 = 0%, P<0.05); 2h postprandial blood glucose MD=-0.19 (CI: -0.52-0.14, I2 = 0%, P=0.25). From the results, the combined Chinese medicine adjuvant therapy showed better efficacy than the control group. A total of 69 kinds of traditional Chinese medicine were involved in 18 studies, among which the top four applied frequencies were Panax notoginseng, Rehmannia rehmannii, Astragalus membranaceus and Poria cocos. Most of the medicines were sweet and bitter in taste, the qi tended to be slight cold and cold, and the meridian tropism belongs to the liver meridian. Conclusion: The combination of traditional Chinese medicine adjuvant therapy has a good curative effect on PDR patients. However, the relevant clinical trials are few and more high-quality clinical trials are still needed, what's more the attention should be paid to the exploration of its safety.

The efficacy and safety of Chinese herbal medicine in the treatment of painful diabetic neuropathy: A systematic review and meta-analysis.

Objective: The objective of this systematic review and meta-analysis is to assess the effectiveness and security of Chinese herbal medicine (CHM) in the therapy of painful diabetic neuropathy (PDN). Methods: We searched databases for randomized controlled trials (RCTs) of CHM in the treatment of PDN. Outcome indicators included nerve conduction velocity, clinical efficiency, pain score, TCM syndrome score, and adverse events. Stata 16.0 was used to carry out the Meta-analysis. Results: A total of 21 RCTs with 1,737 participants were included. This meta-analysis found that using CHM as adjuvant treatment or as monotherapy for PDN can improve SCV of median nerve [mean difference (MD) = 3.56, 95% Confidence interval (CI) (2.19, 4.92) ], MCV of median nerve [ MD = 3.82, 95% CI (2.51, 5.12) ], SCV of common peroneal nerve [ MD = 4.16, 95% CI (1.62, 6.70) ], MCV of common peroneal nerve [ MD = 4.37, 95% CI (1.82, 6.93) ], SCV of gastrocnemius nerve [ MD = 4.95, 95% CI (3.52, 6.37) ], SCV of tibial nerve [ MD = 3.17, 95% CI (-2.64, 8.99) ], MCV of tibial nerve [MD = 6.30, 95%CI (5.00, 7.60)] and clinical effective rate [ odds ratio (OR) = 4.00, 95% CI (2.89, 5.52) ] and reduce pain score [standardized mean difference (SMD) = -2.23, 95% CI (-3.04, -1.41) ], TCM syndrome score [ MD = -4.70, 95% CI (-6.61, -2.80) ]. In addition, compared to the control group, adverse events of Chinese medicine intervention occurred less. Conclusion: CHM as adjuvant therapy or single treatment has a good curative effect and is safe for patients with PDN, which is worthy of clinical promotion and use, however; higher quality clinical studies are still needed to prove. Systematic Review Registration: https://www.crd.york.ac.uk/, identifier CRD42022327967.