Assessment of spatiotemporal risks for nationwide groundwater nitrate contamination.

National assessments of groundwater contamination risks are crucial for sustaining high-quality groundwater supplies. However, traditional methods often treat groundwater contamination risk as a steady-state indicator without considering spatiotemporal variation in risk, both geographically and over time, caused by anthropogenic and climatic factors. In this work, XGBoost, a tree-based algorithm, was applied to comprehensively analyze the drivers of groundwater contamination from nitrate, using data on 13 physical features (as used by the index-based ranking method DRASTIC) and 30 anthropogenic features from 1985 to 2010 in the contiguous United States (CONUS). The results indicate that physical features controlling the transport processes, particularly those affecting contaminant travel time from land surface to groundwater (depth to water table and transmissivity), were the dominant factors for nitrate contamination in groundwater. This was followed by features representing the potential nitrogen loading. Positive correlations between most features and the nitrogen loading time (year) were found, suggesting their growing influence on contamination risk. Based on the drivers identified for nitrate concentrations exceeding 10 mg/L in groundwater and their varying temporal contributions, this study proposes a reformulated index-based method for contamination risk assessment. With this method, an overall accuracy of around 70 % was achieved based on the validation data set. The predicted high-risk areas are mainly intensive irrigation regions, such as the High Plains, northern Midwest, and Central Valley. This new approach contributes to a more accurate and effective assessment of the contamination risks of groundwater on a regional and national scale under temporally varying environmental conditions.

Global Burden of Stroke Attributable to Low Physical Activity/High Body Mass Index Among People Aged 55 Years and Older.

BACKGROUND: This study aimed to quantify the global stroke burden attributable to low physical activity and high body mass index in adults aged ≥55 years using data from the Global Burden of Disease 2019 study. METHODS: We extracted data on stroke mortality, disability-adjusted life years, and risk factor exposure from the Global Burden of Disease 2019 study for people aged ≥55 years. We calculated the population-attributable fraction and absolute number of stroke cases and disability-adjusted life years attributable to low physical activity and high body mass index by location, age group, sex, and year. RESULTS: Globally, body mass index and physical inactivity-attributable stroke burden have declined modestly since 1990, but with diverging escalatory regional trajectories. Population growth and aging drive this rising burden. CONCLUSIONS: Multidimensional, context-specific strategies focused on modifiable lifestyle risks are imperative to address the modest declines and escalatory regional trajectories in body mass index and physical inactivity-attributable stroke burden.

Cross-domain pedestrian detection via feature alignment and image quality assessment.

Datasets collected under different sensors, viewpoints, or weather conditions cause different domains. Models trained on domain A applied to tasks of domain B result in low performance. To overcome the domain shift, we propose an unsupervised pedestrian detection method that utilizes CycleGAN to establish an intermediate domain and transform a large gap domain-shift problem into two feature alignment subtasks with small gaps. The intermediate domain trained with labels from domain A, after two rounds of feature alignment using adversarial learning, can facilitate effective detection in domain B. To further enhance the training quality of intermediate domain models, Image Quality Assessment (IQA) is incorporated. The experimental results evaluated on Citypersons, KITTI, and BDD100K show that MR of 24.58%, 33.66%, 28.27%, and 28.25% were achieved in four cross-domain scenarios. Compared with typical pedestrian detection models, our proposed method can better overcome the domain-shift problem and achieve competitive results.

Global, regional and national epidemiology of allergic disorders in children from 1990 to 2019: findings from the Global Burden of Disease study 2019.

OBJECTIVE: This modelling study aimed to estimate the burden for allergic diseases in children during a period of 30 years. DESIGN: Population-based observational study. MAIN OUTCOMES AND MEASURES: The data on the incidence, mortality and disability-adjusted life years (DALYs) for childhood allergic diseases, such as atopic dermatitis (AD) and asthma, were retrieved from the Global Burden of Disease study 2019 online database. This data set spans various groups, including different regions, ages, genders and Socio-Demographic Indices (SDI), covering the period from 1990 to 2019. RESULTS: In 2019, there were approximately 81 million children with asthma and 5.6 million children with AD worldwide. The global incidence of asthma in children was 20 million. Age-standardised incidence rates showed a decrease of 4.17% for asthma, from 1075.14 (95% uncertainty intervals (UI), 724.63 to 1504.93) per 100 000 population in 1990 to 1030.33 (95% UI, 683.66 to 1449.53) in 2019. Similarly, the rates for AD decreased by 5.46%, from 594.05 (95% UI, 547.98 to 642.88) per 100 000 population in 1990 to 561.61 (95% UI, 519.03 to 608.29) in 2019. The incidence of both asthma and AD was highest in children under 5 years of age, gradually decreasing with age. Interestingly, an increase in SDI was associated with a rise in the incidence of both conditions. However, the mortality rate and DALYs for asthma showed a contrasting trend. CONCLUSIONS: Over the past three decades, there has been a worldwide increase in new asthma and AD cases, even though mortality rates have significantly declined. However, the prevalence of these allergic diseases among children varies considerably across regions, countries and age groups. This variation highlights the need for precise prevalence assessments. These assessments are vital in formulating effective strategies for prevention and treatment.

Interaction of reed litter and biochar presences on performances of constructed wetlands.

Constructed wetlands (CWs) are frequently used for effective biological treatment of nitrogen-rich wastewater with external carbon source addition; however, these approaches often neglect the interaction between plant litter and biochar in biochar-amended CW environments. To address this, we conducted a comprehensive study to assess the impacts of single or combined addition of common reed litter and reed biochar (pyrolyzed at 300 and 500 °C) on nitrogen removal, greenhouse gas emission, dissolved organic matter (DOM) dynamics, and microbial activity. The results showed that combined addition of reed litter and biochar to CWs significantly improved nitrate and total nitrogen removal compared with biochar addition alone. Compared to those without reed litter addition, CWs with reed litter addition had more low-molecular-weight and less aromatic DOM and more protein-like fluorescent DOM, which favored the enrichment of bacteria associated with denitrification. The improved nitrogen removal could be attributed to increases in denitrifying microbes and the relative abundance of functional denitrification genes with litter addition. Moreover, the combined addition of reed litter and 300 °C-heated biochar significantly decreased nitrous oxide (30.7 %) and methane (43.9 %) compared to reed litter addition alone, while the combined addition of reed litter and 500 °C-heated biochar did not. This study demonstrated that the presences of reed litter and biochar in CWs could achieve both high microbial nitrogen removal and relatively low greenhouse gas emissions.

The changing nature of groundwater in the global water cycle.

In recent decades, climate change and other anthropogenic activities have substantially affected groundwater systems worldwide. These impacts include changes in groundwater recharge, discharge, flow, storage, and distribution. Climate-induced shifts are evident in altered recharge rates, greater groundwater contribution to streamflow in glacierized catchments, and enhanced groundwater flow in permafrost areas. Direct anthropogenic changes include groundwater withdrawal and injection, regional flow regime modification, water table and storage alterations, and redistribution of embedded groundwater in foods globally. Notably, groundwater extraction contributes to sea level rise, increasing the risk of groundwater inundation in coastal areas. The role of groundwater in the global water cycle is becoming more dynamic and complex. Quantifying these changes is essential to ensure sustainable supply of fresh groundwater resources for people and ecosystems.

Fertilizer management for global ammonia emission reduction.

Crop production is a large source of atmospheric ammonia (NH3), which poses risks to air quality, human health and ecosystems1-5. However, estimating global NH3 emissions from croplands is subject to uncertainties because of data limitations, thereby limiting the accurate identification of mitigation options and efficacy4,5. Here we develop a machine learning model for generating crop-specific and spatially explicit NH3 emission factors globally (5-arcmin resolution) based on a compiled dataset of field observations. We show that global NH3 emissions from rice, wheat and maize fields in 2018 were 4.3 ± 1.0 Tg N yr-1, lower than previous estimates that did not fully consider fertilizer management practices6-9. Furthermore, spatially optimizing fertilizer management, as guided by the machine learning model, has the potential to reduce the NH3 emissions by about 38% (1.6 ± 0.4 Tg N yr-1) without altering total fertilizer nitrogen inputs. Specifically, we estimate potential NH3 emissions reductions of 47% (44-56%) for rice, 27% (24-28%) for maize and 26% (20-28%) for wheat cultivation, respectively. Under future climate change scenarios, we estimate that NH3 emissions could increase by 4.0 ± 2.7% under SSP1-2.6 and 5.5 ± 5.7% under SSP5-8.5 by 2030-2060. However, targeted fertilizer management has the potential to mitigate these increases.

Antisite-Defects Control of Magnetic Properties in MnSb2Te4.

The intrinsic magnetic topological materials Mn(Sb/Bi)2n+2Te3n+4 have attracted extensive attention due to their topological quantum properties. Although, the Mn-Sb/Bi antisite defects have been frequently reported to exert significant influences on both magnetism and band topology, their formation mechanism and the methods to manipulate their distribution and concentration remain elusive. Here, we present MnSb2Te4 as a typical example and demonstrate that Mn-Sb antisite defects and magnetism can be tuned by controlling the crystal growth conditions. The cooling rate is identified as the primary key parameter. Magnetization and chemical analysis demonstrate that a slower cooling rate would lead to a higher Mn concentration, a higher magnetic transition temperature, and a higher saturation moment. Further analysis indicates that the Mn content at the original Mn site (MnMn, 3a site) varies more significantly with the cooling rate than the Mn content at the Sb site (MnSb, 6c site). Based on experimental observations, magnetic phase diagrams regarding MnMn and MnSb concentrations are constructed. With the assistance of first-principles calculations, it is demonstrated that the Mn-Sb mixing states primarily result from the mixing entropy and the growth kinetics. The present findings offer valuable insights into defects engineering for preparation of two-dimensional quantum materials.

Analysis of the global burden of disease study highlights the global, regional, and national trends of idiopathic epilepsy epidemiology from 1990 to 2019.

Epilepsy is a profound disorder, accounting for roughly 1% of the global disease burden. It can result in premature death and significant disability. To comprehensively understand the current dynamics and trends of idiopathic epilepsy, a deep insight into its epidemiological attributes is vital. We evaluated the incidence, prevalence, mortality, and disability-adjusted life years associated with idiopathic epilepsy from 1990 to 2019 using data and methodologies from the Global Burden of Disease Study. In 2019, there were approximately 2,898,222 individuals diagnosed with idiopathic epilepsy. Intriguingly, from 1990 to 2019, the age-standardized incidence rate of idiopathic epilepsy was consistently lower in women compared to men. Over these three decades, global mortality connected to idiopathic epilepsy increased by 13.95%. However, within the same period, age-standardized death rates for idiopathic epilepsy decreased from 1.94 per 100,000 population to 1.46 per 100,000 population. Predictions indicate an increase in the incidence of idiopathic epilepsy across all age brackets through 2035, especially among the elderly aged 80 and above. Mortality rates are projected to climb for those aged 80 and above while remaining relatively unchanged in other age demographics. Idiopathic epilepsy continues to be a significant contributor to both disability and death. The findings of our study underscore the critical importance of incorporating idiopathic epilepsy management into modern healthcare frameworks. Such strategic inclusion can enhance public awareness of relevant risk factors and the range of available therapeutic interventions.

Global, regional, and national epidemiology of migraine and tension-type headache in youths and young adults aged 15-39 years from 1990 to 2019: findings from the global burden of disease study 2019.

BACKGROUND: In recent years, headache disorders have garnered significant attention as a pressing global health issue. This concern is especially pronounced in low- to middle-income countries and exhibits a notable increase in prevalence among adolescents and young adults. Such a surge in these disorders has invariably diminished the quality of life for affected individuals. Despite its global impact, comprehensive studies exploring the ramifications of headache disorders in the younger population remain scant. Our study endeavored to quantify the global prevalence of headache disorders in individuals between the ages of 15 and 39, over a three-decade span from 1990 to 2019. METHODS: Our study, conducted from 1990 to 2019, evaluated the impact of headache disorders, specifically migraines and tension-type headaches (TTH), in 204 different countries and territories. This comprehensive assessment included a detailed analysis of incidence rates, prevalence, and disability-adjusted life-years (DALYs) across various demographics such as age, gender, year, geographical location, and Socio-demographic Index (SDI). RESULTS: In 2019, there were an estimated 581,761,847.2 migraine cases globally (95% UI: 488,309,998.1 to 696,291,713.7), marking a 16% increase from 1990. Concurrently, TTH cases numbered at 964,808,567.1 (95% UI: 809,582,531.8 to 1,155,235,337.2), reflecting a 37% rise since 1990. South Asia reported the highest migraine prevalence with 154,490,169.8 cases (95% UI: 130,296,054.6 to 182,464,065.6). High SDI regions exhibited the most substantial migraine prevalence rates both in 1990 (22,429 per 100,000 population) and 2019 (22,606 per 100,000 population). Among the five SDI classifications, the middle SDI region recorded the highest tally of TTH cases in both 1990 (210,136,691.6 cases) and 2019 (287,577,250 cases). Over the past 30 years, East Asia experienced the most pronounced surge in the number of migraine cases. On the whole, there was a discernible positive correlation between the disease burden of migraine and TTH and the SDI. CONCLUSION: Migraine and TTH represent formidable challenges in global health. The intensity of their impact exhibits marked disparities across nations and is distinctly elevated among women, individuals within the 30-39 age bracket, and populations characterized by a high SDI. The results of our research emphasize the imperative of assimilating migraine and TTH management into contemporary healthcare paradigms. Such strategic integration holds the potential to amplify public cognizance regarding pertinent risk factors and the spectrum of therapeutic interventions at hand.

Groundwater Quality and Health: Making the Invisible Visible.

Linking groundwater quality to health will make the invisible groundwater visible, but there are knowledge gaps to understand the linkage which requires cross-disciplinary convergent research. The substances in groundwater that are critical to health can be classified into five types according to the sources and characteristics: geogenic substances, biogenic elements, anthropogenic contaminants, emerging contaminants, and pathogens. The most intriguing questions are related to quantitative assessment of human health and ecological risks of exposure to the critical substances via natural or induced artificial groundwater discharge: What is the list of critical substances released from discharging groundwater, and what are the pathways of the receptors' exposure to the critical substances? How to quantify the flux of critical substances during groundwater discharge? What procedures can we follow to assess human health and ecological risks of groundwater discharge? Answering these questions is fundamental for humans to deal with the challenges of water security and health risks related to groundwater quality. This perspective provides recent progresses, knowledge gaps, and future trends in understanding the linkage between groundwater quality and health.

Early passive orthostatic training prevents diaphragm atrophy and dysfunction in intensive care unit patients on mechanical ventilation: A retrospective case‒control study.

BACKGROUND: Intensive care unit (ICU) patients on mechanical ventilation (MV), who are always bedridden, easily develop diaphragm atrophy and dysfunction. However, few studies have assessed diaphragmatic thickness and functional changes after early passive orthostatic training. OBJECTIVES: This is the first study to investigate the efficacy of early passive orthostatic training in preventing diaphragm atrophy and dysfunction in ICU patients on MV. METHODS: In this randomized retrospective case‒control study, 81 ICU patients on MV for 8 days or longer were enrolled. Forty-four patients received early passive orthostatic training initiated within 72 h of MV initiation (training group), and 37 patients did not receive training (no-training group). The protocol was performed for seven days, once a day for 30 min. The primary outcomes were diaphragmatic thickness and diaphragm contractile fraction (TFdi). The ventilatory parameters were secondary outcomes. RESULTS: This study included 81 (45 male) ICU patients on MV [(mean ± SD) age = (60.63 ± 7.88) years]. The training group had a larger diaphragmatic thickness at end-expiration (Tdi,ee) and a smaller magnitude of decrease in Tdi,ee and TFdi (p = 0.001, 0.029, and <0.001, respectively) than the no-training group after 7 days of training. The mean arterial pressure, fraction of inspired oxygen, and white blood cell levels were decreased in the training group compared with the no-training group (p = 0.003, 0.001, and 0.026, respectively), but lactic acid levels decreased slightly in the training group with no significant difference (p = 0.708). CONCLUSIONS: Early passive orthostatic training is suitable to ameliorate diaphragm atrophy and dysfunction in ICU patients on MV.

Temporal trends of migraine and tension-type headache burden across the BRICS: implications from the Global Burden of Disease study 2019.

Background: Headache disorders have become a significant global public health issue, with a notably high prevalence observed in developing countries. However, few studies have assessed headache disorders trends in Brazil, Russia, India, China and South Africa (BRICS). This study aimed to assess the prevalence of headache disorders in individuals across the BRICS, spanning the years 1990 to 2019. Methods: We obtained headache disorders data from the Global Burden of Disease 2019 study (GBD2019). This evaluation examined incidence rates, prevalence, and disability-adjusted life-years (DALYs) for migraine and tension-type headache (TTH) across demographic factors like age, gender, year, and country. Migraine and TTH were diagnosed based on the International Classification of Headache Disorders (ICHD-3) criteria. We used disease codes from the International Classification of Diseases, 10th revision to identify migraine and TTH cases. Statistical analyzes included calculating age-standardized rates and estimated annual percentage changes. Future disease burden was projected using a log-linear age-period-cohort model. Results: In 2019, India had the highest prevalence of migraine (213890207.93 cases) and TTH (374,453,700 cases). Brazil had the highest migraine age-standardized prevalence rate (18,331 per 100,000) and incidence rate (1,489 per 100,000). For TTH, India had the highest prevalence (26,160 per 100,000) while Russia had the highest incidence (11,512 per 100,000). From 1990 to 2019, China showed the greatest increase in migraine and TTH prevalence. India had the highest migraine (7,687,692) and TTH (741,392) DALYs in 2019. Conclusion: Migraine and TTH remain highly prevalent in BRICS nations, inflicting considerable disability burden. While India and China face mounting disease prevalence, Brazil contends with high incidence rates. Tailored interventions based on country-specific epidemiological profiles are warranted to mitigate the public health impact.

Affection of Surgical Decompressive Scale of Optic Canal to Traumatic Optic Neuropathy.

Traumatic optic neuropathy (TON) is damage to the optic nerve that is caused by external violence to the optic nerve during cranial and facial trauma. This kind of injury may result in impaired vision, has a high risk of blindness, and significantly impairs the neurological function of the patient. The treatment of TON is controversial, and many different approaches have been suggested. No one is considered best because the traumatic mechanism is not clear. Methods: In this retrospective study, the clinical features of 37 patients diagnosed with TON without light perception who were treated at the Ninth People's Hospital of Shanghai Jiao Tong University School of Medicine were investigated. A comparison was made between the patient's visual results before and after therapy. In addition, using a multifactorial linear regression model, the independent risk variables for the degree of improvement in visual acuity (IDVA) following surgery were determined. Results: After the operation, 17 people's visual acuity (VA) was lightless, 20 people's visual acuity was improved, and 13 people's visual acuity reached the standard of decerebrate. The efficiency of total optic nerve decompression was 54.1%, and the unblinded rate was 35.1%. Multiple linear regression analysis revealed that fractures of the optic canal and orbit were independent predictors of postoperative VA and IDVA. Conclusions: Total optic canal decompression may efficiently and safely enhance the vision of patients who have TON. Patients with TON who do not have fractures of the optic canal and orbit prior to decompression had a more favorable surgical prognosis.

Enhanced deep residual network for bone classification and abnormality detection.

PURPOSE: A two-stage deep learning framework for bone classification and abnormality detection is proposed based on X-rays. The primary focus is on improving the speed of orthopedic disease diagnosis and helping physicians reduce the probability of false diagnoses. METHODS: The method is based on two stages. In the first stage, one classifier with ResNeXt50 as the backbone is used to classify bones to eliminate the effect of bone type differences on abnormality detection. In the second stage, seven anomaly detectors are trained based on each type of training data. The seven detectors tested the seven results of the first stage, respectively. Pretrained models, data augmentation, focal loss, label smoothing loss, LR-attenuation and early stopping are used to improve performance and reduce the risk of overfitting. RESULTS: Experiments are based on the largest dataset for bone abnormality detection, MURA. In the first stage for bone classification, we got an accuracy of 96.69%, a sensitivity of 96.69%, a specificity of 99.46%, and an F1 score of 96.42%. In the second stage for abnormality detection, we got an accuracy of 84.15%, a sensitivity of 84.15%, a specificity of 87.50%, an F1 score of 84.10%, a Cohen's Kappa of 0.72, and an area under the ROC curve (AUC) score of 0.90. CONCLUSIONS: Compared with other excellent convolutional neural network models, the framework's effectiveness was verified with better accuracy, sensitivity, specificity, F1 score, Cohen's Kappa score, and AUC score for bone classification and abnormality detection.

Sucralose as an oxidative-attenuation tracer for characterizing the application of in situ chemical oxidation for the treatment of 1,4-dioxane.

In situ chemical oxidation (ISCO) has become a widely used soil and groundwater remediation method. Oxidative-attenuation tracers can be used to provide real-time, explicit delineation of contaminant mass-transfer and transformation behavior during an ISCO remediation project. The objective of this study was to evaluate the potential of employing sucralose, a widely used artificial sweetener, as an oxidative-attenuation tracer to characterize the remediation efficiency of 1,4-dioxane (dioxane) by persulfate-based ISCO. Batch and miscible-displacement experiments were conducted to examine the degradation rate and transport behavior of sucralose compared to that of dioxane. Comparable magnitudes and rates of degradation were observed for sucralose and dioxane in batch-reactor experiments with soil and persulfate. The breakthrough curves of sucralose and dioxane transport in a soil-packed column were coincident. The retardation factors were 1.1 for both compounds, indicating limited sorption for both sucralose and dioxane by the soil. Limited degradation was observed in the miscible-displacement experiments, consistent with the short residence time compared to the half-lives of sucralose and dioxane. Persulfate transport and decomposition behavior in the soil-packed columns was similar in the presence of sucralose or dioxane. A simulated tracer test was conducted to illustrate the application of sucralose as an oxidative-attenuation tracer at the pilot scale. These results demonstrate the potential of sucralose as an oxidative-attenuation tracer to support the robust design of ISCO applications for dioxane. The oxidative-attenuation tracer test method is anticipated to be an effective approach for characterizing mass-removal behavior of other emerging contaminants with appropriate selection of tracer.

Self-assembly of Ni(II) metallacycles (a square and a triangle) supported by tetrazine radical bridges.

Two Ni(II) molecular metallacycles of [Ni4(bpz*tz˙-)4(N3)4] (1) and [Ni3(bpzPhtz˙-)3(pzPh(Cl)tz˙-)3]·1.3CH3OH·9.3H2O (2) (bpz*tz = 3,6-bis(3,5-dimethyl-pyrazolyl)-1,2,4,5-tetrazine; bpzPhtz = 3,6-bis(3-phenyl-pyrazolyl)-1,2,4,5-tetrazine; and pzPh(Cl)tz = 3-bis(3-phenyl-pyrazolyl)-6-Cl-1,2,4,5-tetrazine) are reported. The single-crystal X-ray diffraction study reveals that 1 displays a square structure while 2 shows a triangle structure due to the steric effect, both bearing tetrazine radical bridges. Furthermore, magnetic studies reveal that the Ni-radical interaction in 1 is strongly ferromagnetic with a coupling constant (J) of 90.8 cm-1 in the 2J formalist, while the overall antiferromagnetic behaviour of 2 is presumably due to the compete ferromagnetic (for the Ni-radicalbridging interaction with J1 = 95.4 cm-1) and antiferromagnetic (for the Ni-radicalterminal interaction, J2 = -57.5 cm-1) couplings.

High Sensitivity, Rapid Detection of Virus in High Traffic Environments.

The global pandemic caused by the SARS-CoV-2 virus has underscored the need for rapid, simple, scalable, and high-throughput multiplex diagnostics in non-laboratory settings. Here we demonstrate a multiplex reverse-transcription loop-mediated isothermal amplification (RT-LAMP) coupled with a gold nanoparticle-based lateral flow immunoassay (LFIA) capable of detecting up to three unique viral gene targets in 15 min. RT-LAMP primers associated with three separate gene targets from the SARS-CoV-2 virus (Orf1ab, Envelope, and Nucleocapsid) were added to a one-pot mix. A colorimetric change from red to yellow occurs in the presence of a positive sample. Positive samples are run through a LFIA to achieve specificity on a multiplex three-test line paper assay. Positive results are indicated by a characteristic crimson line. The device is almost fully automated and is deployable in any community setting with a power source.

Vision-Based Finger Tapping Test in Patients With Parkinson's Disease via Spatial-Temporal 3D Hand Pose Estimation.

Finger tapping test is crucial for diagnosing Parkinson's Disease (PD), but manual visual evaluations can result in score discrepancy due to clinicians' subjectivity. Moreover, applying wearable sensors requires making physical contact and may hinder PD patient's raw movement patterns. Accordingly, a novel computer-vision approach is proposed using depth camera and spatial-temporal 3D hand pose estimation to capture and evaluate PD patients' 3D hand movement. Within this approach, a temporal encoding module is leveraged to extend A2J's deep learning framework to counter the pose jittering problem, and a pose refinement process is utilized to alleviate dependency on massive data. Additionally, the first vision-based 3D PD hand dataset of 112 hand samples from 48 PD patients and 11 control subjects is constructed, fully annotated by qualified physicians under clinical settings. Testing on this real-world data, this new model achieves 81.2% classification accuracy, even surpassing that of individual clinicians in comparison, fully demonstrating this proposition's effectiveness. The demo video can be accessed at https://github.com/ZhilinGuo/ST-A2J.