University Of Bonn Research Articles

Epileptic Seizure Classification Based on Random Neural Networks Using Discrete Wavelet Transform for Electroencephalogram Signal Decomposition

An epileptic seizure is a brief episode of symptoms and signs caused by excessive electrical activity in the brain. One of the major chronic neurological diseases, epilepsy, affects millions of individuals worldwide. Effective detection of seizure events is critical in the diagnosis and treatment of patients with epilepsy. Neurologists monitor the electrical activity in the brains of patients to identify epileptic seizures by employing advanced sensing techniques, including electroencephalograms and electromyography. Machine learning-based classification of the EEG signal can help differentiate between normal signals and the patterns associated with epileptic seizures. This work presents a novel approach for the classification of epileptic seizures using random neural network (RNN). The proposed model has been trained and tested using two publicly available datasets: CHB-MIT and BONN, provided by Children’s Hospital Boston-Massachusetts Institute of Technology and the University of Bonn, respectively. The results obtained from multiple experiments highlight that the proposed scheme outperformed traditional classification schemes such as artificial neural network and support vector machine. The proposed RNN-based model achieved accuracies of 93.27% and 99.84% on the CHB-MIT and BONN datasets, respectively.

Automatic detection of epileptic seizure using machine learning-based IANFIS-LightGBM system

A sudden increase in electrical activity in the brain is a defining feature of one of the severe neurological diseases known as epilepsy. This abnormality appears as a seizure, and identifying seizures is an important field of research. An essential technique for examining the features of neurological issues brain activities, and epileptic seizures is electroencephalography (EEG). In EEG data, analyzing epileptic irregularities visually requires a lot of time from neurologists. For accurate detection of epileptic seizures, numerous scientific techniques have been used with EEG data, and most of these techniques have produced promising results. For EEG signal classification with a high classification accuracy rate, the present research proposes an enhanced machine learning-based epileptic seizure detection model. The present research provides a hybrid Improved Adaptive Neuro-Fuzzy Inference System (IANFIS)-Light Gradient Boosting Machine (LightGBM) technique for automatically detecting and diagnosing epilepsy from EEG data. The experimental findings were supported by EEG records made available by the German University of Bonn and scalp EEG data acquired at Children’s Hospital Boston. The suggested IANFIS-LightGBM, according to the results, offers the most significant classification accuracy ratings in both situations.

Implementation of a non-linear SVM classification for seizure EEG signal analysis on FPGA

An automatic detection method for disease diagnosis plays an important role in the medical field. A computer-aided diagnosis (CAD) system for seizure detection using electroencephalogram (EEG) data is significant in protecting patients' lives. This paper presents machine learning algorithm-based seizure detection approach implemented in both software and hardware using EEG recordings. The input EEG signal is subjected to pre-processing, decomposition using wavelet transform and classification by a support vector machine (SVM) classifier. The maximum and variance statistical values of the decomposed EEG sub-bands are computed to generate a feature vector, while classification accuracy and computational complexity are taken into account. Gaussian Radial Basis Function (RBF) kernel based Non-Linear SVM (NLSVM) is used in this proposed approach to solve both two-class and three-class classification problems. In three-class classification, the one-against-one (OAO) technique is used. The competency of the proposed technique is evaluated using two distinct datasets provided by Bonn University, Germany & Neurology and Sleep Centre, New Delhi. The adequate parameters of the NLSVM classifier model are determined by using MATLAB software in the training phase and the best performing NLSVM model is selected for implementation on the Field-Programmable Gate Array (FPGA). The proposed seizure detection method is implemented with Verilog code and examined on a Xilinx Zynq-7000 XC7Z020 FPGA board to evaluate its performance. The experimental results show that the proposed method with a minimal number of features achieved a good performance metric for seizure detection and is comparable with that of the state-of-the-art methods.

Дело Ульрике Геро: попытки публичной казни

The case of Ulrike Guérot, which has become an administrative case, which highlights the problematic nature of current university policy in Germany and beyond (the policy of direct and indirect restrictions and sanctions imposed on manifestations of free, non-standard thinking in the public space of a modern democratic society), is described by the author in its unique facticity for Germany — correlated except with the wave of prohibitions on the profession and the expulsion of dissidents in 1977 (the case of Peter Bruckner, etc.). The essay sets itself and tries to answer the following structurally significant and rooted in the specifics of the analyzed case: (1) How, when and why is Professor (political scientist Ulrike Guérot) labeled “controversial” (#umstritten)? (2) What impact does public pressure have on the decision of the (Bonn) University to dismiss? (3) What happens to a democratic society in which scientists and intellectuals are no longer free and cannot participate in public discussions without self-censorship? In search of answers to these questions, the author comes to a statement of a characteristic and symptomatic circumstance for the current moment: through a media campaign promoting his case professionally (but laterally, divergently) analyzing the current political realities (Germany, Europe, etc.) the political scientist is being pushed out by both the mainstream media and the university community “into that segment of society whose representatives began to be called ‘outside the box’ in a negative and exclusive way [from ‘normality’] even during the polarized discussion about coronavirus…” As a result: “Alliances and communities that previously seemed unthinkable suddenly arose, The classic political categories of the ‘right’ and ‘left’ are mixed up… Which once again underlines the complexity of the social dynamics that have arisen: which side is ‘wrong’ in a democracy?”

An Epileptic EEG Detection Method Based on Data Augmentation and Lightweight Neural Network.

Epilepsy, an enduring neurological disorder, afflicts approximately 65 million individuals globally, significantly impacting their physical and mental wellbeing. Traditional epilepsy detection methods are labor-intensive, leading to inefficiencies. Although deep learning techniques for brain signal detection have gained traction in recent years, their clinical application advancement is hindered by the significant requirement for high-quality data and computational resources during training. The neural network training initially involved merging two datasets of different data quality, namely Bonn University datasets and CHB-MIT datasets, to bolster its generalization capabilities. To tackle the issues of dataset size and class imbalance, we employed small window segmentation and Synthetic Minority Over-sampling Technique (SMOTE). algorithms to augment and equalize the data. A streamlined neural network architecture was then proposed, drastically reducing the model's training parameters. Notably, a model trained with a mere 9,371 parameters yielded impressive results. The three-classification task on the combined dataset delivered an accuracy of 98.52%, sensitivity of 97.99%, specificity of 99.35%, and precision of 98.44%. The experimental findings of this study underscore the superiority of the proposed method over existing approaches in both model size reduction and accuracy enhancement. As a result, it is more apt for deployment in low-cost, low computational hardware devices, including wearable technology, and various clinical applications. Clinical and Translational Impact Statement- This study is a Pre-Clinical Research. The lightweight neural network is easily deployed on hardware device for real-time epileptic EEG detection.

A novel brain EEG clustering based on Minkowski distance to improve intelligent epilepsy diagnosis

This paper introduces a novel clustering approach based on Minkowski's mathematical similarity to improve EEG feature selection for classification and have efficient Particle Swarm Optimization (PSO) in the context of machine learning. Given the intricacy of high-dimensional medical datasets, feature selection plays a critical role in preventing disease and promoting public health. By employing Minkowski clustering, the objective is to group dataset records into two clusters exhibiting high feature coherence, thereby improving accuracy by applying optimization techniques like PSO to select the most optimal features. Furthermore, the proposed model can be extended to intelligent datasets, including EEG and others. As fewer features are needed for precise categorization, intelligent feature selection is an advanced step of machine learning. This paper investigates the key factors influencing feature selection in the EEG Bonn University dataset. The proposed system is compared against various optimization and feature selection methods, demonstrating superior performance in analyzing and classifying EEG signals based on accuracy measures. The experimental results have confirmed the effectiveness of the suggested model as a valuable tool for EEG data classification, achieving up to 100% accuracy. The outcomes of this research have the potential to benefit medical experts in related specialties by streamlining the process of identifying and diagnosing brain disorders. Technically, the machine learning algorithms RF, KNN, SVM, NB, and DT are employed to classify the selected features.

Bibliometric analysis of the relationship between metabolic study and urolithiasis. A key tool in patient management

Objective: Our objective was doing an analysis of available bibliography to understand tendencies in publications regarding the role of metabolic evaluation in the management of urolithiasis. Materials and Methods: A retrospective bibliometric analysis of the available medical literature ranging from the year 2001 to 2022 was performed on the Web of Science platform. The graph analysis was done using Microsoft Excel and the bibliographic mapping analysis was done on the VOSviewer software. Results: A total of 120 references were found in 63 journals, with a decrease in the rate of publications in the last 5 years. The country, journal, and institution with the largest number of manuscripts were the United States, Journal of Urology, and the University of Bonn, respectively. The author with the largest number of publications was Sarica Kemal. The mapping and analysis of the keyword evolution with respect to the timeline centered on the terms: “prevention”, “metabolic risk factors”, “obesity”, “primary hyperoxaluria”, and “medical management”. Conclusion: Metabolic evaluation is a fundamental tool in the overall approach of these patients. Despite the decrease in the rate of research on the association between metabolic evaluation and urolithiasis in recent years, the importance of a complete assessment of these patients from the first symptomatic episode has been demonstrated, as it helps to determine the risk of recurrence of the disease, and to establish a treatment plan focused on prevention. This first bibliometric analysis on metabolic evaluation and urolithiasis depicts the importance of giving continuity to research on the risk factors of urolithiasis that may be modified and treated.

Epileptic seizure classification using fuzzy lattices and Neural Reinforcement Learning

ABSTRACT This work uses Fuzzy Lattices and Neural Reinforcement Learning techniques for seizure classification. EEG database of Bonn University and CHB-MIT has been used for the evaluation of the proposed method. Here, features are represented in the form of fuzzy lattices, and feature vectors are created in the form of Kinetic Energy (K.E.) using Schrödinger equation. Then, the highest K.E.-based seven fuzzy lattices have been used for classification using Neural Reinforcement Learning classifier. Neural Reinforcement Learning classifier is a self-learner method that classifies different seizure sub-classes (healthy eyes open, healthy eye closed, Epileptogenic Zone, hippocampal formation of opposite hemisphere, epileptic seizure). The effectiveness of the proposed method has been tested on two different public datasets. The average classification accuracy achieved is 97.6% and 97.5% for Bonn and CHB-MIT datasets, respectively. Results are compared with existing techniques to show the precedence of proposed approach. Also, computation speed of proposed classifier is more than 1.5 times compared to Fuzzy Q Learning classifier. The objective is to develop a hybrid model integrating fuzzy lattices and neural reinforcement learning (adaptive methods) for accurate classification, aiming to enhance and speeding up seizure detection and diagnosis to improve patient care through advanced computational techniques.

Survey analysis for optimization algorithms applied to electroencephalogram

<span lang="EN-US">This paper presents a survey for optimization approaches that analyze and classify Electroencephalogram (EEG) signals. The automatic analysis of EEG presents a significant challenge due to the high-dimensional data volume. Optimization algorithms seek to achieve better accuracy by selecting practical features and reducing unwanted features. Forty-seven reputable research papers are provided in this work, emphasizing the developed and executed techniques divided into seven groups based on the applied optimization algorithm particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), grey wolf optimizer (GWO), Bat, Firefly, and other optimizer approaches). The main measures to analyze this paper are accuracy, precision, recall, and F1-score assessment. Several datasets have been utilized in the included papers like EEG Bonn University, CHB-MIT, electrocardiography (ECG) dataset, and other datasets. The results have proven that the PSO and GWO algorithms have achieved the highest accuracy rate of around 99% compared with other techniques.</span>

PREDICTION OF EPILEPSY BASED ON EEMD AND LSSVM DOUBLE CLASSIFICATION

Epilepsy seizures are caused by abnormal, excessive, or synchronized neuronal activity in the brain, which is difficult to treat and is extremely stubborn. Therefore, studying the activity of epilepsy can greatly contribute to its diagnosis and treatment. The original signal is decomposed into IMFs and residual by ensemble empirical mode decomposition (EEMD), and then the first three intrinsic mode functions (IMF) are selected to replace the original signal, and the nonlinear and non-stationary problems of the original signal are solved. The Least Squares Support Vector Machine (LSSVM) was used as the classifier, its parameters (gam and sig2) are optimized by Particle Swarm Optimization (PSO). The experiment used the EEG database published by the University of Bonn (UoB) to realize the classification of normal, interictal and ictal periods. When PSO was employed, the recognition accuracy of the test set was 93.33%, with a classification time of 0.035 s and the Information Transfer Rate (ITR) of 3.77 bpm in training 70 classes with 100 samples each. In contrast, without PSO, the recognition accuracy of the test set was 92%, with a classification time of 0.039 s and the ITR of 2.88 bpm without PSO in training 70 classes with 100 samples each. The experimental results show that EEMD and LSSVM can effectively implement the three-classification problem and provide an effective means for the onset prediction of epilepsy patients.

Classification of epileptic EEG signals with the utilization of Bonferroni mean based fuzzy pattern tree

The Electroencephalogram (EEG) is an essential tool used to detect and investigate multiple neurological disorders within the human brain. However, examination and visualization of any such abnormalities in the brain through inspecting these EEG signals is a time-consuming and repetitive task for a neurologist. Hence, there is a need to develop a model that can automatically classify brain disorders based on the EEG signals. In this study, a novel fuzzy classification model is proposed for classifying the EEG signals. First, the discrete wavelet transform (DWT) technique is employed to decompose the signal into time–frequency sub-bands. Then, by utilizing these sub-bands, seven meaningful statistical features are extracted effectively for additional investigation purposes. Then, the retrieved features are provided to the fuzzy pattern tree classifier to obtain meaningful inferences from the data. Here, a distinctive structure of a fuzzy pattern tree is proposed by utilizing the interrelationship handling aggregation operators. More precisely, we utilize the Bonferroni mean (BM) aggregation operator for the enlargement or expansion of the tree while considering the concatenation between the parent and the slave tree. To the best of our knowledge, this is the first work that presents such an interrelationship handling fuzzy logic-based classifier model for EEG signal classification. The proposed algorithm is evaluated using two publicly available datasets, namely the Bonn University (Bonn) epileptic datasets and the Temple University Hospital (TUH) EEG subcorpus of abnormal (TUAB) and epilepsy (TUEP) datasets. This study considers different frames of the binary problem (i.e., healthy vs. seizure detection) and multi-class problem (i.e., healthy vs. seizure free vs. seizure) over the Bonn dataset and achieves more than 99% accuracy over the binary model by testing over all possible combinations of the available experimental dataset and 97.8% accuracy in multi-class model. In the case of TUAB and TUEP categories, the model achieves an accuracy of 88% in predicting normal to abnormal activities and 86% in detecting epilepsy and non-epilepsy within the signals. The outcomes derived from the proposed model outperform some existing studies available in the literature for EEG signal classification. Also, the model is efficient as it considers the uncertainty and association among the features while framing the classifier model.

Implementation of a piritramide based patient-controlled analgesia (PCA) as a standard of care for pain control in late abortion induction: A prospective cohort study from a patient perspective

ObjectiveTo assess whether the implementation of patient-controlled analgesia (PCA) with piritramide using an automatic pump system under routine conditions is effective to reduce pain in late abortion inductions Study designProspective observational cohort study SettingPatients requiring medically indicated abortion induction from 14 weeks of pregnancy onwards between July 2019 and July 2020 at the department of Obstetrics and Prenatal Medicine of the Bonn University Hospital in Germany. MethodsEvaluation of pain management after implementation of a PCA system compared with previous nurse-controlled tramadol-based standard under routine conditions. Patients answered a validated pain questionnaire and requirement of rescue analgesics was assessed. Pain intensity and satisfaction were measured on a ten-point numeric rating scale. Main Outcome Measure Maximal pain intensity ResultsForty patients were included. Patients using Piritramide-PCA complained of higher pain sores than those in the standard group (6.90 (± 2.34) vs. 4.83 (± 2.87), (p < 0.05)). In both groups the level of satisfaction with the analgesia received was comparable (8.00 (± 2.45) vs 7.67 (± 2.62), (p = 0.7)). Patients in the PCA group suffered more nausea (63.2 % vs 30 % respectively, OR 4.0, 95 % CI 1.05–15.20, p < 0.05) and expressed more the desire for more analgesic support compared to the control group (OR 5.7 (1–33.25), p = 0.05). ConclusionWomen with abortion induction after 14 weeks of gestation suffer from relevant severe pain, which requires adequate therapy. However, addition of PCA does not seem to bring any advantage in patients undergoing this procedure.

Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG.

Epilepsy is a chronic brain disease, and identifying seizures based on electroencephalogram (EEG) signals would be conducive to implement interventions to help patients reduce impairment and improve quality of life. In this paper, we propose a classification algorithm to apply dynamical graph neural network with attention mechanism to single channel EEG signals. Empirical mode decomposition (EMD) are adopted to construct graphs and the optimal adjacency matrix is obtained by model optimization. A multilayer dynamic graph neural network with attention mechanism is proposed to learn more discriminative graph features. The MLP-pooling structure is proposed to fuse graph features. We performed 12 classification tasks on the epileptic EEG database of the University of Bonn, and experimental results showed that using 25 runs of ten-fold cross-validation produced the best classification results with an average of 99.83[Formula: see text] accuracy, 99.91[Formula: see text] specificity, 99.78[Formula: see text] sensitivity, 99.87[Formula: see text] precision, and 99.47[Formula: see text] [Formula: see text] score for the 12 classification tasks.

Cell scientist to watch – Charlotte Aumeier

ABSTRACT Charlotte Aumeier is an Assistant Professor of Biochemistry at the University of Geneva, Switzerland. After completing her PhD at the University of Bonn, Germany, studying the cytoskeleton of diatoms, Charlotte moved to the University of Grenoble, France, for a postdoc, where she became hooked on microtubules. In 2018, she established her own lab in Geneva, where she and her team work to uncover the dynamics and regulatory mechanisms of microtubule networks using a variety of approaches, including synthetic biology and non-standard model organisms. We spoke with Charlotte over Zoom to learn more about her work, her love of diatoms and how she views some of the biggest challenges of her career as her biggest advantages as a scientist.

PERCEPTION OF INDIA IN CHINA AND GERMANY

Due to the spread of Buddhism and Buddhist culture to the East, Chinese travellers and pilgrims started visiting India in pursuit of Buddhist scriptures and learning of Buddhist philosophy as early as the first half of the first millennium of Common Era. These pilgrims and travellers also left the description of their travel. In the medieval and modern period also Chinese travellers, diplomats and scholars continued their journey towards India. However, the situation and perception both were different in these two periods from previous ancient era. German travellers to India started with the participation of the German soldiers in the British East India Company from the army of the Electorate of Hanover in 1782. The German nationalism grew as a reaction to the political and cultural domination of France and Britain. In their quest to find the roots of their language, they started looking at Sanskrit, Indian philosophy and culture. During the early 19th Century several German Romantics and scholars showed interest in Sanskrit literature. Some of the prominent names among them are Friedrich and August Wilhelm Schlegel, Johann Wolfgang von Goethe, Max Müller, Alexander and Wilhelm von Humboldt and Johann Gottfried Herder. Friedrich von Schlegel studied Sanskrit for over forty years and in 1808 he published the book Über die Sprache und Weisheit der Indier, wherein he argued that the prototypical “Aryans” founded the ancient European civilizations. With August Wilhelm Schlegel, the first Indology chair was started in the University of Bonn in 1819. Karl August Schlegel, the elder brother of Friedrich and August Wilhelm Schlegel prepared a military survey of southern India for the East India Company which proved very useful.

Survey Analysis on smart features selection for machine learning techniques mainly applied to EEG.

This research presents a survey for analyzing and classifying the EEG signal based on feature selection approaches. Moreover, The increasing complexity of high-dimensional medical datasets necessitates efficient feature selection methods for early disease detection and safeguarding public health. Intelligent feature selection represents an advanced stage in machine learning and innovative computer applications, as it reduces the number of features required for accurate classification. Generally, The main goal of feature selection is to improve the predictive model's performance and reduce the computational cost of modeling. This paper contains a survey of considerable research several on feature selection. The main measures to analyze this paper are Accuracy, precision, Recall, and F1-score assessment. In order to evaluate performance used stander dataset are EEG Bonn University. The results have proven that they have achieved the highest accuracy rate of around 99% compared with different techniques.

Second Generation Current Controlled Current Conveyor Based Low Pass Filter Design For The Processing of EEG Signals

EEG signals are noisy signals that allow brain activity to be analyzed. In recent years, it has been seen that current conveyor-based circuits, which have many advantages such as wide bandwidth, high linearity, low power consumption, have been used instead of operational amplifiers in the analysis of these signals. In this study, a second-generation current controlled current conveyor (CCCII+) low pass filter circuit with a cut-off frequency of 100 Hz has been presented for the analysis of EEG signals. The simulation of the circuit was carried out with the Orcad pspice program. In addition, the application circuit of this low-pass filter circuit has been made and oscilloscope images have been obtained for some frequency values. AD844 IC is used as current conveyor in the application circuit. The data of epilepsy patients and normal people taken from the University of Bonn were applied to the CCCII+ low pass filter circuit and the frequency bands of these signals were examined. It has been predicted that if this CCCII+ low pass filter circuit is used in EEG measurements, it will give good results in the diagnosis of neurological diseases such as epilepsy.

Impact of glazing on wear, fracture load, and optical properties of a new fully crystallized lithium disilicate ceramic material

ObjectivesLithium disilicate (LDS) based glass ceramics are indispensable materials in the field of prosthetic dentistry due to their strength and excellent esthetics. Recently, novel fully crystallized LDS for the milling process have been introduced to the market, requiring only chairside polishing before delivery. Since limited data is available about subjecting this material to glazing, this study aimed to evaluate the wear properties, fracture resistance, and optical properties of the newly introduced fully crystallized LDS after glazing. MethodsLithium disilicate glass-ceramics (fully crystallized (LiSiCAD) and partially crystallized types (EmaxCAD), of shade A3, were used in the present study. The fully crystallized specimens were subjected to a glazing firing cycle in a furnace (LiSiCAD-G) and compared to a polished fully crystallized counterpart (LiSiCAD-P, negative control) and a glazed partially crystallized LDS (EmaxCAD, positive control). Rectangular-shaped ceramic specimens (n = 10, 12 × 6.5 × 1.5 mm) and enamel antagonists were used to test the wear resistance in a specially designed wear machine built at the Department of Oral Technology, University of Bonn, Germany. The volumetric enamel loss of antagonists was measured by means of overlapping virtual 3D models derived from micro-CT scans for the teeth before and after the wear test. The weight loss of ceramic specimens in milligrams was measured after 100,000 and 200,000 wear cycles. A spectrophotometer was used to calculate the CIELAB color parameters of the ceramic specimens against black and white backgrounds to measure the translucency. Fracture resistance was also assessed after thermodynamic fatigue using a universal testing machine until fracture at a 1 mm/min crosshead speed. Statistical analysis was performed using one-way ANOVA and the significance level was set at α = 0.05. ResultsEmaxCAD and LisiCAD-G groups showed significantly higher mean ceramic weight loss after 100,000 cycles (2 ± 0.3 mg and 1.93 ± 0.2 mg, respectively) than LisiCAD-P group (0.78 ± 0.19 mg). Glazed LiSiCAD specimens demonstrated significantly higher ΔE values from shade A3 compared to polished LiSiCAD. There was no significant difference in ΔE between LiSiCAD-G and EmaxCAD. For fracture resistance, no significant difference was observed between LiSiCAD-G and LiSiCAD-P before or after aging. ConclusionsThe glazed fully crystallized LDS was superior to the partially crystallized one with regard to wear resistance but showed more color changes than the polished fully crystallized one. Furthermore, polishing of fully crystallized LDS could still be considered a better option than glazing when aesthetics is a primary prerequisite.

An Epileptic Seizure Detection Technique Using EEG Signals with Mobile Application Development

Epileptic seizure detection classification distinguishes between epileptic and non-epileptic signals and is an important step that can aid doctors in diagnosing and treating epileptic seizures. In this paper, we studied the existing epileptic seizure detection methods in terms of challenges and processes developed based on electroencephalograph (EEG) signals. To identify the research deficiencies and provide a feasible solution, we surveyed the existing techniques at each phase, including signal acquisition, pre-processing, feature extraction, and classification. Most previous and current research efforts have used traditional features and decomposing techniques. Therefore, in this paper, we introduced an enhanced and efficient epileptic seizure technique using EEG signals, for which we also developed a mobile application for monitoring the classification of EEG signals. The application triggers notifications to all associated users and sends a visual notification should an EEG signal be classified as epileptic. In this research, we have used publicly available EEG data from the University of Bonn. Our proposed method achieved an average accuracy of 98% by utilizing different machine-learning algorithms for classification, and it has outperformed recently published studies. Though there have been other mobile applications for epileptic seizure detection, they have been based on motion and falling detection, as opposed to ours, which was developed based on EEG classification. Our proposed method will have an impact in the medical field, particularly for epilepsy seizure monitoring as well as in the Human–Computer Interaction fields, majorly in the Brain–Computer Interaction (BCI) applications.

Early Vitrectomy with Silicone Oil Tamponade in the Management of Postoperative Endophthalmitis.

Background: Early vitrectomy for postsurgical endophthalmitis may improve visual acuity outcomes. Silicone oil as a tamponade has some potential benefits in the management of endophthalmitis. This study aims to evaluate the use of a silicone oil tamponade in the surgical management of endophthalmitis. Material and Methods: All patients with a pars plana vitrectomy with silicone oil tamponade for postsurgical endophthalmitis at the Department of Ophthalmology, University of Bonn, Germany, between 2017 and 2021 were retrospectively reviewed. We included all preoperative data, including BCVA at diagnosis, clinical findings, and symptoms. For every follow-up visit, we looked at BCVA and complications. Results: In total, 82 patients were included in this study. The mean follow-up was 13.1 months (range 1-58 months). An intravitreal injection was the cause in 42 patients (51.2%) and cataract surgery in 29 patients (35.4%). The mean interval between the causing event and the date of onset was 8.8 days (range, 1-59 days). The most prevalent pathogen was Staphylococcus epidermidis in 16 patients (19.5%). In 47 patients (57.3%), no pathogen was found. The initial best-corrected visual acuity was 2.1 logMAR and improved significantly to 1.0 logMAR after six months (p < 0.001) and 1.1 logMAR after 1 year (p < 0.001). In a multivariate analysis, a low BCVA at diagnosis (p = 0.041) was a significant predictor for poor visual acuity outcomes. A total of 17 patients (20.1%) developed postoperative complications. Five patients (6.1%) needed an anterior chamber washout with repeated injections of antibiotics. Two patients (2.4%) had persistent fibrin and were treated with YAG-laser treatment. Three patients (6.7%) developed a retinal detachment. Two patients (2.4%) had persistent corneal decompensation with endothelial cell loss and received perforating keratoplasty. We performed a matched-pair analysis (n = 30, each group n = 15) to compare a silicone oil tamponade with BSS at the end of surgery. The visual acuity outcome showed no significant differences (BCVA after one year: 1.17 logMAR in eyes with silicone oil and 0.90 logMAR in eyes with BSS; p = 0.684). Conclusions: In our study, a vitrectomy with silicone oil tamponade in the surgical management of postoperative endophthalmitis led to a significant improvement in visual acuity and had a low complication rate. Low BCVA at diagnosis was significantly associated with poor visual acuity outcomes. A comparison of silicone oil and BSS at the end of surgery showed similar results.