Impression Scores Research Articles

DETECTION OF KERATOCONUS DISEASE DEPENDING ON CORNEAL TOPOGRAPHY USING DEEP LEARNING

Keratoconus is a disease that ML has contributed much in its diagnosis and management. It is not a widely prevalent disease, with a research gap caused by the absence of standardized datasets for model training and evaluation. This work presents a novel dataset, which strengthens the CNN model's resilience and creates standards for assessing keratoconus diagnostic techniques. The research depends on data of patients examined at Jenna Ophthalmic Center in Baghdad. The proposed system works on three stages: pre-processing, feature extraction, and classification with machine learning algorithms including NB, KNN, ADA, DT, and CNN deep learning. The pre-processing stage involves cropping images to retain the relevant maps, which were subjected to contrast enhancement to improve image quality. The pre-processed data is then fed into Machine Learning(ML) algorithms and Convolutional Neural Network(CNN) models, by which the four corneal maps were analyzed. The precision of the ML method was quantified, yielding a precision score of 0.79 for the AdaBoost algorithm and an impressive score of 0.99 for the suggested CNN model exemplifying its high accuracy and ability to surpass all machine learning approaches. Applying PCA for feature extraction before utilizing tradition ML algorithms and CNN helps in achieving high-accuracy results.

Leveraging natural language processing for automated assessment and feedback production in virtual education settings

With the rapid development of online teaching, the traditional teacher face-to-face evaluation and feedback model in online teaching faces problems such as high labor costs, low efficiency, and insufficient personalization. The application of natural language processing technology in the field of education has become a trend. Based on this choice, this article applied natural language processing to achieve automated evaluation and personalized feedback of online teaching processes. This article chose to use recurrent neural network (RNN) algorithm for text generation, and adopted Seq2Seq-based (Sequence-to-Sequence) recurrent neural network framework for automatic text feedback generation. Then, a group of student performance data was collected and divided into a control group and an experimental group, and comparisons were made between manual feedback and automatically generated feedback, respectively. Finally, the effectiveness and impact of automatic evaluation and feedback generation were evaluated by comparing the performance data and analysis results of two groups of students. The average accuracy of the automatic evaluation system designed in this article was 95.6%, which was higher than the 84.5% of manual evaluation. The accuracy of the automatic evaluation system designed in this article was higher, and the time spent on manual evaluation and automatic evaluation was compared. The average time spent on manual evaluation was 62.2 seconds, while automatic evaluation shortened the time to 36.98 seconds. For the feedback results, the graphical curves of the manually generated and automatically generated feedback results in terms of feedback on student grades were basically consistent, which can fully prove that the automatically generated feedback results have high accuracy. The remarkable efficacy of natural language processing (NLP) in online education is vividly illustrated by a recent study, where an NLP model notched an impressive average ROUGE score of 93.8 points. This achievement outstrips the performance of three other algorithmic models in the realm of automatic assessment and feedback generation. Such comparative experiments underscore the transformative potential of NLP technology, significantly boosting teaching efficiency and enriching the learning experience by adeptly tackling the perennial challenges of evaluation and feedback in online education settings.

Modulation of the electronic and magnetic properties of an MnCrNO2 ferromagnetic semiconductor MXene.

MXenes are members of the rapidly expanding family of two-dimensional materials known for their electronic and magnetic properties and hold significant promise for advancements in electronics and spintronics technologies. In this study, we identified a stable MnCrNO2 MXene characterized by a band gap of 2.68 eV, a magnetic moment of 6μB, and a magnetic anisotropy energy of 78.6 μeV per transition metal atom. These properties were computed using density functional theory with an on-site Coulomb potential and HSE06 hybrid functional calculations. Manipulating the band gap and magnetic properties offers considerable advantages for tailoring MXenes for specific applications. Our investigation extended to exploring the property behaviors under biaxial strain, as well as the adsorption of Group-I and Group-II ions onto the newly discovered MXene. Our findings underscore a highly linear relationship between strain and band gap, supported by an impressive R2 score of 0.997 for the best-fit straight line. Moreover, we demonstrated the linear tunability of the material's magnetic anisotropy energy under biaxial strain, achieving an R2 score of 0.982. Adsorption of 2.2% Group-I and Group-II ions onto the MnCrNO2 MXene reveals the potential for a semiconductor-to-half-metal phase transition with K, Rb, Be, Mg, and Ca ions. These results provide pathways for leveraging MXenes for the development of next-generation electronic and spintronic devices.

Novel Transfer Learning Approach for Detecting Infected and Healthy Maize Crop Using Leaf Images.

Maize is a staple crop worldwide, essential for food security, livestock feed, and industrial uses. Its health directly impacts agricultural productivity and economic stability. Effective detection of maize crop health is crucial for preventing disease spread and ensuring high yields. This study presents VG-GNBNet, an innovative transfer learning model that accurately detects healthy and infected maize crops through a two-step feature extraction process. The proposed model begins by leveraging the visual geometry group (VGG-16) network to extract initial pixel-based spatial features from the crop images. These features are then further refined using the Gaussian Naive Bayes (GNB) model and feature decomposition-based matrix factorization mechanism, which generates more informative features for classification purposes. This study incorporates machine learning models to ensure a comprehensive evaluation. By comparing VG-GNBNet's performance against these models, we validate its robustness and accuracy. Integrating deep learning and machine learning techniques allows VG-GNBNet to capitalize on the strengths of both approaches, leading to superior performance. Extensive experiments demonstrate that the proposed VG-GNBNet+GNB model significantly outperforms other models, achieving an impressive accuracy score of 99.85%. This high accuracy highlights the model's potential for practical application in the agricultural sector, where the precise detection of crop health is crucial for effective disease management and yield optimization.

In Silico Investigation and MD Simulation Approaches of Newly Designed Quercetin–Imidazole Analogs for Anticancer and Antifungal Efficacy

AbstractMolecules with potency and low toxicity are the leading army in the battlefield of multidrug resistance. Quercetin is found in abundance in the nature as a potent flavonoid and bears the tag of flavonoid paradox due to the poor bioavailability, however, it still possess distinct systemic actions, and this marks curiosity in the research field. The present study elaborates targeted in silico and simulation approaches of newly designed quercetin analogs toward their anticancer and antifungal properties by screening against human epidermal growth factor receptor and lanosterol C14‐alpha demethylase receptors. The molecules were investigated pharmacokinetically via drug‐likeness, toxicity prediction (lethal dose, LD50), PASS prediction, molecular docking, molecular dynamics simulation, and their quantum mechanics have been measured using molecular orbital calculations through highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO) calculations. The prediction from Pa > Pi scores displayed its potential for squalene epoxide inhibitors, antimycobacterial, and antineoplastic activities and also showed prospectively better molecular docking scores against the selected targeted enzymes. Among the series, QIz II stood out as a compelling inhibitor; showcasing highest binding affinity with fungal protein by impressive docking score of −10.7 kcal/mol. Compound QIz XX demonstrated the highest binding affinity of −9.31 kcal/mol with the anticancer protein.

Azithromycin in the Management of Upper Respiratory Tract Infections (URTIs): Indian Real-Life Experience.

Upper Respiratory Tract Infections (URTIs) pose a significant public health challenge worldwide. Azithromycin has been approved for its management due to broad-spectrum antibacterial properties and favorable pharmacokinetics. This study aims to evaluate the effectiveness and safety of Azithromycin in treatment of URTIs in a real-world setting. This multicenter, retrospective, observational study was conducted across 184 Ear, Nose, and Throat (ENT) clinics in India. Medical records of adults (≥18 years) who received Azithromycin 500 mg for 5 days to treat URTIs and provided consent were retrieved. Sore throat, fever, and interference with daily activities were assessed alongside clinical signs (pharyngeal erythema, tonsillar erythema, and exudates/plugs on tonsils). Clinical global impression of change was evaluated using a 7-point rating scale. Statistical analyses included paired t-tests for mean score changes and the McNemar-Bowker test to evaluate symptom improvement from baseline to day 5. Data from 884 patients were analyzed. With 5 days of Azithromycin therapy, significant reduction in proportion of patients reporting URTI symptoms and signs was noted. Proportion of patients reporting sore throat was reduced from 95.8% to 10.4%; work absenteeism dropped from 47.9% to 1%; and fever subsided in 97.4% of patients. Clinical signs also improved notably, with moderate-to-severe pharyngeal erythema (90.9% of patients at baseline to 13.6% at day 5), tonsillar erythema (84% ofpatients at baseline to 9.6%), and tonsillar exudates (58.3% patients at baseline to 4.4%). Also, 97.2% of patients showed considerable improvement in their Clinical Global Impression score with Azithromycin. Adverse events were reported by 2.37% of patients. Azithromycin demonstrates a significant improvement in clinical manifestations of URTIs, with a low incidence of adverse events.

Dementia Identification using a Class of CNN based Methods and Transfer Learning

Through the use of transfer learning techniques and multiple Convolutional Neural Networks (CNNs), our study offers a novel method for the early identification of dementia. Through data augmentation, we ensure robustness and enhance the model's ability to extract complex patterns from MRI data by utilizing pre-trained models such as VGG19, ResNet50, and Inception V3. We improve the identification of dementia-related patterns by utilizing well-established models, presenting promising advances in our field. In addition, our study explores the theoretical underpinnings of using MRI imaging to differentiate between different phases of dementia, offering important new perspectives on the course of the disease. We initialized the models with weights of pre-trained image net equivalents and perform dataset pre-processing, segmentation. Our results well exceeds with VGG19 topping with 91.5% accuracy followed by Inception V3 as 87.19%. ResNet50 also got an impressive score of 74.76%. The future work shows the potential to identify clearer differences to be used as early diagnostic aid for Dementia in patients who don’t have neurological symptoms with mere CNNs using transfer learning.

Folinic acid as a treatment for autism in children: A within-subjects open-label study on safety and efficacy.

The folate cycle has been implicated in the pathophysiology of autism due to its role in the glutathione oxidative stress pathway, amino acid and DNA methylation reactions, and neurotransmitter synthesis pathway. Previous research on folinic acid supplementation in autistic children has suggested potential benefits. The primary aim of this pilot study was to determine the safety, feasibility and efficacy of oral folinic acid in improving communication and behaviour in autistic children. Ten autistic children were recruited into an open-label pre-post treatment within-subjects design study. At T = 0, 12 and 24 weeks, participants underwent safety evaluations, standardized assessments of language, autism symptoms, adaptive skills and global illness severity, and eye-gaze tracking. During the control period (0-12 weeks), participants continued with standard care. In the treatment period (12-24 weeks), participants took oral folinic acid at 2mg/kg/day. All 10 children (nine boys, one girl; aged 4-8years), successfully consumed oral folinic acid supplements with no adverse events. There was a reduction in Pervasive Developmental Disorder Behavior Inventory (PDDBI) Autism Composite T-score with treatment (mean [SD] T-score 49.2 [8.89] pre-treatment, 44.6 [6.19] post-treatment, p = 0.103). Although this difference was not statistically significant due to the small sample size, the effect size was medium-large, indicating that, as a group, there were clinically meaningful changes in PDDBI T-scores. There were also trends towards gains in communication scores and overall Clinical Global Impression scores. Folinic acid is a safe and feasible potential treatment for autism, and results from this pilot justify the need for a larger placebo-controlled trial.

An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework

Abstract Anomaly detection (AD) plays a crucial role in time series applications, primarily because time series data is employed across real-world scenarios. Detecting anomalies poses significant challenges since anomalies take diverse forms making them hard to pinpoint accurately. Previous research has explored different AD models, making specific assumptions with varying sensitivity toward particular anomaly types. To address this issue, we propose a novel model selection for unsupervised AD using a combination of time series forest (TSF) and reinforcement learning (RL) approaches that dynamically chooses an AD technique. Our approach allows for effective AD without explicitly depending on ground truth labels that are often scarce and expensive to obtain. Results from the real-time series dataset demonstrate that the proposed model selection approach outperforms all other AD models in terms of the F1 score metric. For the synthetic dataset, our proposed model surpasses all other AD models except for KNN, with an impressive F1 score of 0.989. The proposed model selection framework also exceeded the performance of GPT-4 when prompted to act as an anomaly detector on the synthetic dataset. Exploring different reward functions revealed that the original reward function in our proposed AD model selection approach yielded the best overall scores. We evaluated the performance of the six AD models on an additional three datasets, having global, local, and clustered anomalies respectively, showing that each AD model exhibited distinct performance depending on the type of anomalies. This emphasizes the significance of our proposed AD model selection framework, maintaining high performance across all datasets, and showcasing superior performance across different anomaly types.

Impact of Influencers Marketing on Consumers Beahvior and Purchase Intention: Mediating Role of Influencer Credibility

In the realm of digital marketing, influencer marketing has risen to prominence, particularly on platforms like TikTok, which wield considerable influence among younger demographics. This study focused on the faculty and students from four different public and private universities in KPK. Employing a non-probability simple random sampling technique for sample selection, the study utilized an adopted questionnaire to measure responses, confirming the reliability of the measurement scales with an impressive Cronbach's Alpha score of 0.967. Results of the study revealed that influencer marketing significantly and positively impacts consumer attitudes toward brands and their purchase intentions. Further influencer credibility has significantly mediated the effect of influencer marketing on attitude towards brand and purchase intention. This underscores the critical need for culturally tailored influencer marketing strategies to maximize relevance and effectiveness in the Pakistani market. Moreover, it highlights the untapped potential of TikTok as a powerful platform for influencer marketing. These results offer invaluable, actionable insights for marketers and significantly advance our theoretical understanding of influencer marketing's profound impact on consumer behavior, laying the groundwork for future research on emerging social media platforms.

Development of an Environmental Odour Nuisance Measurement Instrument Utilizing the Panel Method

Abstract Environmental odour is a significant element of air nuisance that can disrupt human well-being by irritating the nasal passages and negatively impacting their quality of life. The objective of the project is to develop an environmental odour nuisance measuring instrument utilizing the panel method. The measurement of environmental odour level was conducted using a survey or panel approach as well as by utilizing a smart sensor gas monitor to assess the NH3 and H2S gas concentrations. The odour nuisance measuring equipment was designed to facilitate the panelists in obtaining accurate odour impressions. The wind speed variations on the tool were categorized into three repetitions, i.e. the first repetition had a wind speed of 0 m/sec, the second repetition had a wind speed of 1 m/sec, whereas the third repetition had a wind speed of 2 m/sec. The panelists were categorized based on two factors, i.e. gender and age. A series of odour level measurements were conducted over a span of 5 consecutive days, using 5 distinct types of odour sources. The odour impression scores, ranked from the lowest to highest, are as follows: adult age category with an average score of - 2.6, female gender category with an average score of -2.4, school age children category with an average score of -2.3, and male gender category with an average score of -2.2. The highest NH3 and H2S gas concentrations detected by smart sensor gas monitor were 15 and 25.5 ppm in the third repetitions. The odor impression assessment of the four categories of panelists had no significant difference with a P-value > 0.05. The hedonism scale and odor gas concentration had a high correlation with R2 > 0.8.

A NOVELTY METHOD FOR PCB DEFECT DETECTION ON YOLOv8 BASIS

To tackle the challenges in PCB defect detection, I’ve developed a new algorithm built on an improved YOLOv8 framework. This approach is aimed at boosting detection accuracy while reducing model complexity, making it well-suited for detecting smaller targets and functioning effectively in environments with limited resources. The algorithm starts by introducing a refined neck network structure, which cuts down on the number of model parameters and computational demands, improving how efficiently resources are used. Additionally, the inclusion of ShuffleAttention and a BiFPN structure strengthens the model's ability to fuse features at multiple scales, significantly enhancing its performance with smaller targets. On top of that, I’ve replaced the commonly used CIoU loss function with a WIoU loss function, which makes the model more accurate and robust in its detection capabilities. In tests, this enhanced model achieved impressive results, with mAP50 and mAP90-95 scores reaching 93.4% and 48.3%, respectively. What's more, model parameters, GFLOPs, and weight size were reduced by 33%, 12%, and 32%, respectively, bringing them down to 1.882M, 7.0, and 4.3M. This makes the solution not only highly efficient and accurate but also lightweight—perfect for use in constrained environments like mobile devices and embedded systems.

Pelatihan Manajemen Pengelolaan Masjid Era Modern di Kecamatan Pangandaran: Mengokohkan Eksistensi dan Pelayanan Masjid

Mosque management in the modern era demands extensive adaptation to long-established religious and community functions while introducing advanced technology integration to meet the continuously evolving needs and expectations of its congregation. This research focuses on the development and implementation of the training "Modern Mosque Management: Strengthening Existence and Service," aimed at enhancing the mosque administrators' abilities to manage religious and social activities more effectively. Through an approach of extension and training, this program teaches modern management principles and the use of technological tools like Google Workspace to enhance the operational efficiency of mosques. The results indicate a significant improvement in mosque management competence, as evident from the impressive N-Gain scores. These scores not only reflect an increase in participants' understanding of effective mosque management but also the practical skills acquired during the training. The conclusion of this study underscores the importance of well-designed training programs in preparing mosque administrators to meet the challenges of a dynamic and changing environment, and in supporting the strategic role of the mosque as a center of spiritual and social activities in the community.

Computational analysis of controlled drug release from porous polymeric carrier with the aid of Mass transfer and Artificial Intelligence modeling

Controlled release of a desired drug from porous polymeric biomaterials was analyzed via computational method. The method is based on simulation of mass transfer and utilization of artificial intelligence (AI). This study explores the efficacy of three regression models, i.e., Kernel Ridge Regression (KRR), Gaussian Process Regression (GPR), and Gradient Boosting (GB) in determining the concentration of a chemical substance (C) based on coordinates (r, z). Leveraging Firefly Optimization (FFA) for hyperparameter optimization, the models are fine-tuned to maximize their predictive performance. The findings unveil notable disparities in the performance metrics of the models, with GB showcasing the most impressive R2 score of 0.9977, indicative of a remarkable alignment with the data. GPR closely trails with an R2 score of 0.88754, while KRR falls short with an R2 score of 0.76134. Additionally, GB manifests the most modest Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) among the trio of models, further cementing its supremacy in predictive precision. These outcomes accentuate the significance of judiciously selecting regression methodologies and optimization approaches for adeptly modeling intricate spatial datasets.

Machine learning insights into scapular stabilization for alleviating shoulder pain in college students

Non-specific shoulder pain is a common musculoskeletal condition, especially among college students, and it can have a negative impact on the patient’s life. Therapists have used scapular stabilization exercises (SSE) to enhance scapular control and mobility. This study investigates the prediction of the impact of scapular stability exercises in treating non-specific shoulder pain, leveraging advanced machine learning techniques for comprehensive evaluation and analysis. Using a diverse range of regression models, including Gamma Regressor, Tweedie Regressor, Poisson Regressor, and others, the study examines the relationship between the effectiveness of various exercises and their impact on shoulder pain management. Furthermore, the study employs optimization techniques, such as Hyperopt, scikit-optimize, optunity, GPyOpt, and Optuna, to fine-tune the exercise protocols for optimal outcomes. The results reveal that scapular stabilization exercises, when optimized using machine learning algorithms, significantly contribute to reducing shoulder pain in college students. Among the optimization techniques, scikit-optimize demonstrated the best performance, resulting in a mean squared error of 0.0085, a mean absolute error of 0.0712, and an impressive R2 score of 0.8501. This indicates that the scikit-optimize approach yielded the most accurate predictions and effectively captured the relationship between the exercises and shoulder pain management. The findings highlight the critical role of scapular stabilization exercise interventions in ameliorating non-specific shoulder pain and underscore the potential of machine learning techniques in optimizing therapeutic strategies for musculoskeletal health management. The utilization of scikit-optimize, in particular, showcases its effectiveness in fine-tuning the exercise protocols for optimal outcomes. The study’s results serve as a crucial stepping stone in developing personalized rehabilitation programs for non-specific shoulder pain, emphasizing the importance of integrating machine learning methodologies in the assessment and treatment of musculoskeletal disorders among college students.

Educational effectiveness of remote training with smart glasses for impression-taking.

To compare the educational outcomes of remote instruction (RI) in impression-taking using smart glasses with those of face-to-face instruction (FI) and paper-based self-learning (SL) and analyze the educational effects, aiming to develop a remote clinical training strategy. Participants were recruited from among the dental residents who were trained in the first-year clinical program at the university hospital in 2023. The participants were divided into three groups as the original skill level was equal, and the groups were assigned RI, FI, printed guidance, and SL. All the participants took impressions of the jaw models attached to the mannequin using alginate impression material. Next, assigned instructions were provided. Then again, the trainees took impressions of the jaw models. The pre- and postinstruction impressions of each participant were evaluated, and the change in the impression score was statistically analyzed. The pre- and postinstruction scores of the trainees in the RI and FI groups showed a significant increase (p<0.05), whereas no significant difference was observed in the score changes in the SL group. In the intergroup comparisons, the score changes of the RI and FI groups were greater than those of the SL group, although no significant difference was found between the score changes of the RI and FI groups (p<0.05). RI in impression-taking using smart glasses has a greater educational effectiveness than paper-based SL. It has also been suggested that RI can have educational efficacy similar to FI.

Optimization of Tourism Destination Recommendations in Batang Regency Using Content-Based Filtering

In an era where tourism plays a pivotal role in economic development, the need for effective navigation through diverse attractions has never been more critical. This research presents a cutting-edge tourism recommendation system tailored for Batang Regency, leveraging Content-Based Filtering (CBF) to deliver personalized suggestions that enhance the tourist experience. By categorizing tourist attractions into Culinary, Culture, Accommodation, Nature, and Leisure, and employing the Haversine formula for precise geographical calculations, our system prioritizes recommendations based on user preferences and proximity. Recommendation testing yielded an impressive average F1 Score of 0.965, underscoring the system's accuracy and relevance, particularly in straightforward user scenarios. However, the research also identifies challenges in more complex cases, suggesting the need for future enhancements through hybrid models and the integration of user feedback. This innovative approach not only streamlines the decision-making process for tourists but also aims to boost local tourism, making it an invaluable tool for both visitors and the Batang Regency community. Join us in exploring how technology can transform the way we experience travel, ensuring that every journey is tailored to individual desires and needs.

Molecular docking, ADME properties and synthesis of thiophene sulfonamide derivatives

This study investigates the drug-like properties of target molecules containing thiophene sulfonamide groups (7a–7s) using computational molecular docking techniques. The binding interactions of these derivatives were assessed using protein 2NSD (Enoyl acyl carrier protein reductase InhA, complexed with N-(4-methylbenzoyl)-4-benzylpiperidine, PDB DOI: 10.2210/pdb2NSD/pdb) as the receptor. Molecular docking results revealed notable docking scores for all compounds, ranging from −6 to −12 kcal/mol. Compounds 7e, 7i, and 7f, in particular, demonstrated impressive glide scores (>11 kcal/mol) and were selected for further analysis through molecular dynamics simulations, which provided deeper insights into their dynamic behavior and stability. The drug-like properties of these molecules were evaluated based on Lipinski’s Rule of Five and ADME (Absorption, Distribution, Metabolism, and Excretion) criteria and compared with known drugs. Additionally, we synthesized these target molecules (7a–7s) using Suzuki-Miyaura coupling with a nickel catalyst replacing palladium. The chemical structures of the synthesized compounds were confirmed through elemental analysis, LC-MS,1H-NMR, and 13C-NMR spectroscopy.

Assessing the ability of GPT-4o to visually recognize medications and provide patient education.

Various studies have investigated the ability of ChatGPT (OpenAI) to provide medication information; however, a new promising feature has now been added, which allows visual input and is yet to be evaluated. Here, we aimed to qualitatively assess its ability to visually recognize medications, through medication picture input, and provide patient education via written and visual output. The responses were evaluated by accuracy, precision and clarity using a 4-point Likert-like scale. In regards to handling visual input and providing written responses, GPT-4o was able to recognize all 20 tested medications from packaging pictures, even with blurring, retrieve their active ingredients, identify formulations and dosage forms and provide detailed, yet concise enough, patient education in an almost completely accurate, precise and clear manner with a score of 3.55 ± 0.605 (85%). In contrast, the visual output through GPT-4o generated images illustrating usage instructions contained many errors that would either hinder the effectiveness of the medication or cause direct harm to the patient with a poor score of 1.5 ± 0.577 (16.7%). In conclusion, GPT-4o is capable of identifying medications from pictures and exhibits contrasting patient education performance between written and visual output with very impressive and poor scores, respectively.

The effectiveness and safety of botulinum toxin injections for managing motor disorders of patients with Parkinson's disease: A meta-analysis of randomized controlled trials.

This study aimed to assess the effectiveness and safety of botulinum toxin (BTX) injections for managing motor disorders in patients with Parkinson's disease (PD). An electronic search was conducted based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Data from available randomized controlled trials (RCTs) assessing BTX injections for motor disorders in PD patients were extracted for meta-analysis. Ultimately, 215 patients from eight RCTs were enrolled. Pooled analyses indicated that BTX was more effective than placebo in improving tremor (standardized mean difference [SMD] = 0.96, 95% CI [0.34, 1.58], p < 0.01), whereas no notable differences were observed between BTX and placebo regarding freezing of gait (SMD = 0.66, 95% CI [-0.26, 1.58], p = 0.162), United Parkinson's Disease Rate Scale (UPDRS) III score (SMD = -0.20, 95% CI [-1.17, 0.76], p = 0.68) and clinical global impression (CGI) score (SMD = 0.84, 95% CI [-0.74, 2.42], p = 0.298). Adverse events related to BTX injections were comparable to placebo (OR = 1.74, 95% CI [0.59, 5.14], p = 0.32). The current evidence suggests that BTX is effective and safe in treating PD tremor but fails to provide therapeutic benefits for freezing of gait and motor functional scores in PD patients. Furthermore, the limited number of included studies and heterogeneity in BTX intervention protocols suggest more research is needed, with additional standardized RCTs, to better understand and optimize BTX injections for motor disorders in PD.