Machine learning-Based model for prediction of Narcolepsy Type 1 in Patients with Obstructive Sleep Apnea with Excessive Daytime Sleepiness.

Background: Excessive daytime sleepiness (EDS) forms a prevalent symptom of obstructive sleep apnea (OSA) and narcolepsy type 1 (NT1), while the latter might always be overlooked. Machine learning (ML) models can enable the early detection of these conditions, which has never been applied for diagnosis of NT1. Objective: The study aimed to develop ML prediction models to help non-sleep specialist clinicians identify high probability of comorbid NT1 in patients with OSA early. Methods: Totally, clinical features of 246 patients with OSA in three sleep centers were collected and analyzed for the development of nine ML models. LASSO regression was used for feature selection. Various metrics such as the area under the receiver operating curve (AUC), calibration curve, and decision curve analysis (DCA) were employed to evaluate and compare the performance of these ML models. Model interpretability was demonstrated by Shapley Additive explanations (SHAP). Results: Based on the analysis of AUC, DCA, and calibration curves, the Gradient Boosting Machine (GBM) model demonstrated superior performance compared to other machine learning (ML) models. The top five features used in the GBM model, ranked by feature importance, were age of onset, total limb movements index, sleep latency, non-REM (Rapid Eye Movement) sleep stage 2 and severity of OSA. Conclusion: The study yielded a simple and feasible screening ML-based model for the early identification of NT1 in patients with OSA, which warrants further verification in more extensive clinical practices.

Development and validation of a machine learning model for prediction of comorbid major depression disorder among narcolepsy type 1.

BACKGROUND: Major depression disorder (MDD) forms a common psychiatric comorbidity among patients with narcolepsy type 1 (NT1), yet its impact on patients with NT1 is often overlooked by neurologists. Currently, there is a lack of effective methods for accurately predicting MDD in patients with NT1. OBJECTIVE: This study utilized machine learning (ML) algorithms to identify critical variables and developed the prediction model for predicting MDD in patients with NT1. METHODS: The study included 267 NT1 patients from four sleep centers. The diagnosis of comorbid MDD was based on Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5). ML models, including six full models and six compact models, were developed using a training set. The performance of these models was compared in the testing set, and the optimal model was evaluated in the testing set. Various evaluation metrics, such as Area under the receiver operating curve (AUC), precision-recall (PR) curve and calibration curve were employed to assess and compare the performance of the ML models. Model interpretability was demonstrated using SHAP. RESULT: In the testing set, the logistic regression (LG) model demonstrated superior performance compared to other ML models based on evaluation metrics such as AUC, PR curve, and calibration curve. The top eight features used in the LG model, ranked by feature importance, included social impact scale (SIS) score, narcolepsy severity scale (NSS) score, total sleep time, body mass index (BMI), education years, age of onset, sleep efficiency, sleep latency. CONCLUSION: The study yielded a straightforward and practical ML model for the early identification of MDD in patients with NT1. A web-based tool for clinical applications was developed, which deserves further verification in diverse clinical settings.

Sudden unexpected death in epilepsy disclosure causes anxiety in patients with epilepsy: a Chinese questionnaire survey.

Background and objective: Sudden unexpected death in epilepsy (SUDEP) has been regarded as a leading cause of premature death in patients with epilepsy (PWE). Although patients, relatives and caregivers have the right to be informed of SUDEP, neurologists prefer not to release the facts for fear of associated anxiety. In the study, a Chinese questionnaire survey was carried out to elucidate effect of SUDEP disclosure on anxiety in PWE and variables determining the anxiety of patients and provided suggestions for SUDEP disclosure. Methods: A survey study in China was conducted. We recruited 305 PWE from 3 tertiary epilepsy centers who attended outpatient clinic from December 2021 to February 2022. Two hundred and thirty-two PWE completed the screening evaluation, survey and Hamilton anxiety rating scale (HAMA) twice with 171 PWE completing third HAMA at follow-up. HAMA scores at baseline, T1, T2 were compared using analysis of variance and dependent samples t-test. The variables related to anxiety were screened out by univariate analysis and used for multivariate logistic regression. Result: We found 127 (54.7%) among the 232 participants experienced anxiety after SUDEP disclosure. HAMA scores at T1 were significantly higher than at baseline and T2, while there was no statistical difference between baseline and T2. Medical insurance, seizure severity, and whether the PWE supported SUDEP being disclosed to their relatives and caregivers only were associated with the occurrence of anxiety. Conclusion: SUDEP disclosures may cause short-term acute anxiety, but have no long-term effects in PWE. Acute anxiety caused by SUDEP disclosure may be more common in PWE with NCMI and severe seizures. Meanwhile, compared with indirect SUDEP disclosure to their relatives and caregivers, direct SUDEP disclosure to PWE reduces the risk of anxiety. Recommendations are provided to avoid anxiety caused by SUDEP disclosure.

A Strategy of On-Demand Immune Activation for Antifungal Treatment Using Near-Infrared Responsive Conjugated Polymer Nanoparticles.

Pathogenic fungal infection is a major clinical threat because pathogenic fungi have developed resistant mechanisms to evade the innate immune response, especially interactions with macrophages. Herein, a strategy to activate immune responses of macrophages to fungi based on near-infrared (NIR) responsive conjugated polymer nanoparticles (CPNs-M) is reported for antifungal immunotherapy. Under NIR light irradiation, CPNs-M exposes ß-glucan on the surface of fungal conidia by photothermal damage and drug released from CPNs-M. The exposed ß-glucan elicits macrophage recognition and subsequently activates calcium-calmodulin (Ca2+-CaM) signaling followed by the LC3-associated phagocytosis (LAP) pathway to kill fungal conidia. Consequently, a remarkable elimination of intracellular fugal conidia and successful treatment of fungal pneumonia are achieved. This remote regulation strategy to restore pathogen-immune cell interaction on demand provides a new insight into combatting intractable intracellular infections.

Tracing and quantifying the sources of heavy metals in the upper and middle reaches of the Pearl River Basin: New insights from Sr-Nd-Pb multi-isotopic systems.

A method based on Sr, Nd and Pb multi-isotopic systems indicates that the different rock types (carbonate rock, basalt and black rock series) and sulfide deposits exposed in the Pearl River Basin show markedly different Sr, Nd and Pb isotopic characteristics. By establishing the mass balance equations of heavy metal content and isotope ratios, we use the inverse method to obtain the contribution that natural weathering of carbonate rocks, basalts and black rock series as well as the mining of sulfide deposits have on heavy metal content in riverbed sediments in the Pearl River Basin. Even though carbonate rocks constitute more than 60% of the exposed area in the upper reaches of the Pearl River Basin, this lithology only contributes 9% of the heavy metal content in sediments due to the relatively low content of heavy metals found in this rock type. Basalt weathering on average contributes 64% of the Cr content and 42% of the Ni content found in the sediments, while 53% of the Cd content is derived from the weathering of the black rock series. The negative impact mining has on this environment cannot be ignored as it is the most important source of As (71%) and Pb (60%) in all samples. This is especially the case in the Diaojiang River Basin, where sulfide mining activities still contribute more than 90% of the content of Zn, Pb, Cd and As within the sediments even though many mining sites have been closed since 2000.

A Multipath Fusion Strategy Based Single Shot Detector.

Object detection has wide applications in intelligent systems and sensor applications. Compared with two stage detectors, recent one stage counterparts are capable of running more efficiently with comparable accuracy, which satisfy the requirement of real-time processing. To further improve the accuracy of one stage single shot detector (SSD), we propose a novel Multi-Path fusion Single Shot Detector (MPSSD). Different from other feature fusion methods, we exploit the connection among different scale representations in a pyramid manner. We propose feature fusion module to generate new feature pyramids based on multiscale features in SSD, and these pyramids are sent to our pyramid aggregation module for generating final features. These enhanced features have both localization and semantics information, thus improving the detection performance with little computation cost. A series of experiments on three benchmark datasets PASCAL VOC2007, VOC2012, and MS COCO demonstrate that our approach outperforms many state-of-the-art detectors both qualitatively and quantitatively. In particular, for input images with size 512 × 512, our method attains mean Average Precision (mAP) of 81.8% on VOC2007 test, 80.3% on VOC2012 test, and 33.1% mAP on COCO test-dev 2015.

The influence of natural weathering on the behavior of heavy metals in small basaltic watersheds: A comparative study from different regions in China.

This paper investigates the dynamics between basalt weathering and heavy metal accumulation through a comparative study of 37 small basaltic watersheds within different climate zones in the Yungui (the Pearl River Basin in southwest China), Xuyi (the Huaihe River Basin in east China) and Leiqiong regions (Hainan Island in south China). From a comprehensive sampling regime of stream water, riverbed sediments and bedrock, this study shows that the concentrations of heavy metals in river water are far below the national surface water quality standard and WHO quality standard for drinking water, indicating no significant ecological risk for water body in these basaltic areas. In contrast, the riverbed sediments exhibit varying degrees of heavy metal enrichment in the process of weathering from bedrock to sediments: without enrichment for Cr, Ni, Cu and Zn, but significant enrichment for Cd, As and Pb. Cd exhibits the largest ecological risk of all the heavy metals in the basaltic watersheds especially in the Yungui region, which can be mainly attributed to the high geological background values in this area. Comparative studies of some major basalt watersheds in the world show that temperature, runoff and elevation differences significantly affect the chemical weathering rates and thus the accumulation of heavy metals.

The impact of natural weathering and mining on heavy metal accumulation in the karst areas of the Pearl River Basin, China.

This paper presents the heavy metal content in river water, sediment and bedrock in the karst area of the Pearl River Basin in China to evaluate the long-term impact of natural weathering and mining on the ecological environment. The results show that Cd and As is 2-3 times more enriched within the carbonate bedrock of the Pearl River Basin compared to the upper continental crust (UCC), which is indicative of high geological background values. Within the river water of the upper reaches of the Diaojiang River (a tributary of the Pearl River), which flows through the Dachang super-large orefield, Zn, As, Cd and Sb exceeds the environmental quality standards for surface water (WQS) by more than an order of magnitude. Among these, Zn and Cd sharply decreases to within the WQS in the lower reaches of the river, but the content of As and Sb in the estuary is still several times higher than the WQS. Cd in the sediments of the small carbonate watersheds and in the mainstream of the Pearl River only present a low-moderate ecological risk. In contrast, severe heavy metal pollution of the sediments of the Diaojiang River Basin is observed. Even in the lower reaches, remote from the mining area, the content of Pb, Zn, As and Cd in the sediments is still two orders of magnitude higher than the soil background values. The content of both Cd and As presents a very high ecological risk, indicating that under the cumulative effect of high geological background values and mining, full restoration of the ecological environment in the Diaojiang River Basin is a complex and long-term process.

The behavior of metals/metalloids during natural weathering: A systematic study of the mono-lithological watersheds in the upper Pearl River Basin, China.

The Pearl River Basin is a region with elevated geochemical baseline levels due to high metals/metalloids content in the sediments and soils. In this paper we systematically analyzed the behavior of these metals/metalloid (Cr, Ni, Cu, Zn, Cd, As, and Pb) in bedrock, riverbed sediments, soils, and river water in three different mono-lithological areas (carbonate, basalt, and mud-shale). The results show that the content of transition elements (Cr, Ni, Cu, and Zn) in carbonate rocks are much lower than for shales and basalts, but these metals produce higher enrichment levels in sediments and soils through rapid weathering. Furthermore, Cd, As and Pb are significantly enriched in the upper soils of the carbonate profile and the watersheds dispersed with black shales have distinctly higher Cd enrichment levels. This secondary enrichment of metals through the weathering and pedogenesis of carbonate rocks, and the discharge of metal elements by the weathering of the black rock series, leads to metal pollution in the Pearl River. Most of the small watersheds in the upper reaches of the Pearl River exhibit low or moderate ecological risk but considerable ecological risk exist in the watersheds dispersed with these black shales. Among all the trace elements, Cd generate the highest ecological risk in the individual small watersheds in the upper reaches of the Pearl River.