Adaptive threshold algorithm for detecting EEG-interburst intervals in extremely preterm neonates.

An adaptive confidence algorithm for vehicle detection is proposed. Shortcomings of traditional vehicle detection method of deep learning with fixed confidence threshold are analyzed. To deal with false alarms and false negatives brought by these shortcomings, an adaptive confidence threshold algorithm for vehicle detection is raised. Two datasets are set up to test and compare the detection performance of the adaptive confidence algorithm with fixed confidence on MS-CNN. The experimental results show that the proposed algorithm could effectively reduce the false alarm rate and improve the detection performance of MS-CNN. It is of certain significance for the application of deep learning technology to vehicle detection.

EEG as a possible prognostic tool in phenylketonuria

Context. Electroencephalography (EEG) signals are contaminated with diverse types of noises and artifacts, which greatly distort EEG recording and increase the difficulty in obtaining accurate diagnosis. Objective. This paper investigates, for the first time, multi-kernel normalized least mean square with coherence-based sparsification (MKNLMS-CS) algorithm for suppressing different artifact components, and the 1D patch-based non-local means (NLM) algorithm for eliminating white and colored noises. Approach. A novel multi-stage system based on combining the NLM algorithm with the MKNLMS-CS algorithm is proposed for eliminating different noise and artifact sources by targeting each noise or artifact component in a single stage. Main Results. The proposed approach is applied to clinical real EEG data, and the results reveal the superior performance of the proposed system in removing white and colored noises, suppressing different artifact components, preserving the important and tiny features of the original EEG signal, and keeping the morphology of EEG frequency components. Significance. The proposed multi-stage design succeeds not only to suppress different artifact components and noise sources under low and high noise conditions, but also to achieve accurate sleep spindle detection from the filtered high-quality EEG signals. This demonstrates the usefulness of the proposed approach for obtaining high-resolution EEG signal from noisy and contaminated EEG recordings.

Epilepsy is a neurological condition of human being, mostly treated based on the patients’ seizure symptoms, often recorded over multiple visits to a health-care facility. The lengthy time-consuming process of obtaining multiple recordings creates an obstacle in detecting epileptic patients in real time. An epileptic signature validated over EEG data of multiple similar kinds of epilepsy cases will haste the decision-making process of clinicians. In this paper, we have identified EEG data derived signatures for differentiating epileptic patients from normal individuals. Here we define the signatures with the help of various machine learning techniques, viz., feature selection and classification, pattern mining, and fuzzy rule mining. These signatures will add confidence to the decision-making process for detecting epileptic patients. Moreover, we define separate signatures by incorporating few demographic features like gender and age. Such signatures may aid the clinicians with the generalized epileptic signature in case of complex decisions.

West syndrome in tuberous sclerosis complex

Women with breast cancer are prone to moderate to severe preoperative anxiety. Effective measures for preventing and managing preoperative anxiety include drug therapy and non-drug intervention. The main evaluation method is scale assessment, which has certain limitations and may involve human concealment or evaluation errors. In this study, resting-state electroencephalography (EEG) was used to explore changes in power spectrum during the alleviation of preoperative anxiety in breast cancer patients, which is of great significance for objectively identifying and evaluating preoperative anxiety in patients. 40 breast cancer patients were randomly divided into two groups (20 patients per group), receiving either psychological intervention (PI) or intravenous midazolam (MID) before surgery. Visual Analog Scale for Anxiety (VAS-A) and Observer's assessment alert/Sedation (OAA/S) scores, clinical monitoring indexes and EEG data were measured before and after intervention. VAS-A scores significantly decreased in both groups (p < 0.05), the power in the theta band of the frontal parietal regions decreased (p < 0.05) and was positively correlated with VAS-A scores (p < 0.001). Network analysis revealed that the three highest centrality measures in the PI group were located in the alpha band frontal parietal region, frontal central region, and gamma band parietal region, while the OAA/S scores showed the highest centrality for all three measures in the MID group. Both PI and intravenous MID can effectively alleviate preoperative anxiety in breast cancer patients, but their neuroelectrophysiological mechanisms were not entirely the same. Regarding the relationship between brain region power and monitoring indexes, the power of three specific regions in certain frequency bands was the primary factor in the PI group, while the level of sedation was the determining factor in the MID group.

BackgroundElectroencephalography at hospital presentation may offer important insights regarding prognosis that can inform understanding of cerebral malaria (CM) pathophysiology and potentially guide patient selection and risk stratification for future clinical trials. Electroencephalogram (EEG) findings in children with CM in Uganda and Malawi were compared and associations between admission EEG findings and outcome across this diverse population were assessed. Demographic, clinical and admission EEG data from Ugandan and Malawian children admitted from 2009 to 2012 with CM were gathered, and survivors assessed for neurological abnormalities at discharge.Results281 children were enrolled (Uganda n = 122, Malawi n = 159). The Malawian population was comprised only of retinopathy positive children (versus 72.5% retinopathy positive in Uganda) and were older (4.2 versus 3.7 years; p = 0.046), had a higher HIV prevalence (9.0 versus 2.8%; p = 0.042), and worse hyperlactataemia (7.4 versus 5.2 mmol/L; p < 0.001) on admission compared to the Ugandan children. EEG findings differed between the two groups in terms of average voltage and frequencies, reactivity, asymmetry, and the presence/absence of sleep architecture. In univariate analyses pooling EEG and outcomes data for both sites, higher average and maximum voltages, faster dominant frequencies, and retained reactivity were associated with survival (all p < 0.05). Focal slowing was associated with death (OR 2.93; 95% CI 1.77–7.30) and a lower average voltage was associated with neurological morbidity in survivors (p = 0.0032).ConclusionsDespite substantial demographic and clinical heterogeneity between subjects in Malawi and Uganda as well as different EEG readers at each site, EEG findings on admission predicted mortality and morbidity. For CM clinical trials aimed at decreasing mortality or morbidity, EEG may be valuable for risk stratification and/or subject selection.

Rasmussens encephalitis (RE) is a rare inflammatory brain disease characterized by severe intractable epilepsy and unilateral progressive motor defect associated with contralateral hemispheric atrophy. The authors present clinical features, EEG and MRI data and results of effective treatment of patient withadult onset RE. Despite the predominance of RE in children, stressed is the necessity of taking into consideration this condition in adults as well in differential diagnostics of intractable epilepsies.

In this paper a new non-predictive wavelet based video coding scheme is presented. The scheme omits motion estimation/compensation process (prediction step) in the temporal axis. The video sequence is grouped into a number of frames. An adaptive thresholding algorithm is used to optimize the subband threshold settings, and use to identify the significance of the subband coefficients. The significant vectors of the same subband within the group frames are joined together in order to exploit their spatial-temporal redundancies. The significant vectors are quantized using a novel multistage lattice vector quantization (MLVQ). This process reduces quantization errors and enhances the reconstructed frame quality. Incremental results of the new non-predictive video coding scheme with adaptive thresholding algorithm are obtained with more than 1 dB. Also it is significantly better and than MPEG-2 with I frames only for several test sequences.

Anti-N-methyl-D-aspartate receptor encephalitis is produced by an autoimmune reaction against macromolecular structures that form ionotropic receptors for glutamic acid NR2A and NR2B subunits. Other important findings are the multiple clinical and paraclinical manifestations, among which the EEG stands out. We characterized EEG patterns and their association with functional disability and hospitalization time in patients with anti-N-methyl-D-aspartate receptor encephalitis admitted in our center. We performed a retrospective cohort study that included patients with anti-N-methyl-D-aspartate receptor encephalitis. We recorded the clinical and sociodemographic characteristics and initial scalp EEG data. Functional disability was evaluated at admission and follow-up using the modified Rankin scale. Forty-five patients aged 15 to 80 years were included. An abnormal EEG was reported in 92.5% of patients. We identified six EEG patterns. The mean hospitalization time was 3.2 (±2.4) months. The higher modified Rankin scale at admission and the absence of parietal or temporal epileptiform activity were associated with more prolonged hospitalization, hazard ratio of 0.338 for each modified Rankin scale level (95% confidence interval 0.174-0.658, P = 0.001), 14.5, P = 0.017, and hazard ratio of 5.6, P = 0.009, respectively. EEGs are frequently abnormal in patients with anti-N-methyl-D-aspartate receptor encephalitis. The lower modified Rankin scale at admission and the absence of some focal epileptiform activity may be associated with shorter hospitalizations.

Subcortical Neglect as a Consequence of a Remote Parieto-Temporal Dysfunction. A Quantitative Eeg Study

Antidepressive therapy with maprotiline was accompanied by blood level determinations psychological clinical and electroencephalographical assessments. It was the aim of the study to introduce objective methods in psychotropic drug therapy and to look for a relationship between blood level and clinical outcome, EEG and psychological data. We found a "therapeutical window" of blood levels between 300 to 600 ng/ml of maprotiline (oral dose of 75 or 150 mg per day). There is also a relationship between clinical outcome rated by the Hamilton-Depression-Scale and the d2-cancellation-test.

To assess the clinical implications and the pathophysiologic determinants of interictal bitemporal hypometabolism (BTH) in temporal lobe epilepsy (TLE) not associated with bilateral MRI abnormalities or intracranial space-occupying lesions. The authors compared the clinical, interictal, and ictal EEG, Wada test, and neuropsychology data of 15 patients with intractable complex partial seizures of temporal lobe origin and BTH with those of 13 consecutive patients with unilateral TLE associated with unilateral temporal hypometabolism (UTH) who remained seizure free for more than 3 years after anterior temporal lobectomy. 18F-fluorodeoxyglucose PET scans were analyzed visually and semiquantitatively, and ratios of counts in individual temporal areas to the rest of the cerebrum were compared with the corresponding values from 11 normal control subjects and with the nonepileptogenic hemisphere of the 13 patients with UTH. BTH was defined as more than 2.5 SDs below control values for two or more temporal areas on each side irrespective of any asymmetry. BTH reflected bilateral independent seizure onset in eight patients (53%). The topography of the metabolic depression was not a reliable predictor of epileptogenicity, but involvement of the inferior temporal gyrus was related specifically to ipsilateral seizure onset (70% sensitivity, 100% specificity). In patients with unilateral TLE, contralateral hypometabolism was associated with longer disease duration and worst memory performance during the Wada test, which amounted to global amnesia after ipsilateral injection in three patients, precluding surgical treatment. Contralateral seizure spread in the ictal EEG was significantly faster in patients with BTH. In TLE, symmetric or asymmetric BTH may signal bilateral independent seizure onset in approximately half the patients, especially when involving the inferior temporal gyrus. Alternatively, it may reflect an advanced stage of the disease process, characterized by a breakdown of the inhibitory mechanisms in the contralateral hemisphere, and secondary memory deficit associated with higher risk of postoperative memory decline. Patients with TLE and BTH but without bilateral MRI changes may still be operated on successfully, but surgical suitability should be proved by comprehensive intracranial EEG studies and Wada test.

Accurate disease prediction is essential for improving patient outcomes. Privacy regulations like GDPR and HIPAA limit data sharing, hindering the development of robust predictive models across institutions. FL and multi-modal fusion frameworks counter these problems but are restricted in scalability, inter-client communication, and heterogeneity of data modalities. Techniques which provide privacy on data have an issue whereby they cause a reduction in performance or are computationally costly. This paper presents Mamba-Fusion for Disease prediction, a privacy-preserving framework for multi-modal data. It uses a hierarchical FL architecture to minimize the communication costs and improve the architecture’s scalability solution and a Mixture of Experts (MoE) with LSTM based layers for dynamic temporal integration. The latest techniques like, differential privacy, secure aggregation protect both the data and its accuracy of the data as well. Experimental results on multi-modal clinical measurements, ECG, EEG, clinical notes, and demographic data support the applied framework. We have then used Mamba-Fusion to achieve 92:4% accuracy, 0:91 F-Score, and 0:96 AUC-ROC by keeping the privacy leakage at 0:02 and communication costs to 12:5 MB, which make it superior to conventional FL techniques. These results affirm Mamba-Fusion as an applications that are secure enough to support collaborative healthcare analytics on a large scale.

In this research article a dynamic estimation of neuronal activity and brain dynamics from electroencephalographic (EEG) signals is presented using a dual Kalman filter. The dynamic model for brain behavior is evaluated using physiological-based linear models. Filter performance is analyzed for simulated and clinical EEG data, over several noise conditions. As a result a better performance on the solution of the dynamic inverse problem is achieved, in case of time varying parameters compared with the system with fixed parameters and the static case. An evaluation of computational load is performed when predicted dynamic cases, estimated using the Kalman filter, are up to ten times faster than the static case.