scholarly journals Deep anomaly detection of seizures with paired stereoelectroencephalography and video recordings

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Michael L. Martini ◽  
Aly A. Valliani ◽  
Claire Sun ◽  
Anthony B. Costa ◽  
Shan Zhao ◽  
...  
Keyword(s):  
Real Time ◽  
Seizure Detection ◽  
Patient Specific ◽  
Training Time ◽  
Robust Detection ◽  
Whitney Test ◽  
Video Recordings ◽  
Mann Whitney Test ◽  
Drug Resistant Epilepsy ◽  
Epilepsy Monitoring

AbstractReal-time seizure detection is a resource intensive process as it requires continuous monitoring of patients on stereoelectroencephalography. This study improves real-time seizure detection in drug resistant epilepsy (DRE) patients by developing patient-specific deep learning models that utilize a novel self-supervised dynamic thresholding approach. Deep neural networks were constructed on over 2000 h of high-resolution, multichannel SEEG and video recordings from 14 DRE patients. Consensus labels from a panel of epileptologists were used to evaluate model efficacy. Self-supervised dynamic thresholding exhibited improvements in positive predictive value (PPV; difference: 39.0%; 95% CI 4.5–73.5%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.03) with similar sensitivity (difference: 14.3%; 95% CI − 21.7 to 50.3%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.42) compared to static thresholds. In some models, training on as little as 10 min of SEEG data yielded robust detection. Cross-testing experiments reduced PPV (difference: 56.5%; 95% CI 25.8–87.3%; Wilcoxon–Mann–Whitney test; N = 14; p = 0.002), while multimodal detection significantly improved sensitivity (difference: 25.0%; 95% CI 0.2–49.9%; Wilcoxon–Mann–Whitney test; N = 14; p < 0.05). Self-supervised dynamic thresholding improved the efficacy of real-time seizure predictions. Multimodal models demonstrated potential to improve detection. These findings are promising for future deployment in epilepsy monitoring units to enable real-time seizure detection without annotated data and only minimal training time in individual patients.

Intracellular Levels of Oblimersen Sodium and Target Downregulation Correlates to Clinical Activity of bcl-2 Antisense in Acute Myeoid Leukemia (AML).

Blood ◽  
2004 ◽  
Vol 104 (11) ◽  
pp. 1170-1170
Author(s):  
Guido Marcucci ◽  
W. Stock ◽  
G. Dai ◽  
S. Liu ◽  
R. Klisovic ◽  
...  
Keyword(s):  
Real Time ◽  
Cross Reactivity ◽  
Phase Iii ◽  
Clinical Activity ◽  
Rt Pcr ◽  
Limit Of Quantification ◽  
Whitney Test ◽  
Mann Whitney Test

Abstract Oblimersen sodium (Ob, Genasense™) is an 18 mer phosphorothioate antisense directed against bcl-2, an antiapoptotic protein that mediates chemoresistance in malignant cells. In order to assess whether detectable intracellular concentrations (ICs) of Ob are achievable in vivo, we have developed a sensitive and specific ELISA-based assay. This assay involves Ob hybridization to a 5′-end overhang of a 3′-biotinylated capture probe ligated to a digoxigenin (Dig)-labeled probe, and detection by an anti-Dig-alkaline phosphatase system. In K562 cell extract, the assay was linear within 50–2000 pM range with a limit of quantification (LOQ) of 50 pM (equivalent to 5.0 fmol/100 μL). The withtin-run coefficients of variation (CVs) in 4 spiked concentrations were between 3–7% in 6 replicates with accuracy values between 93–109%. The between-run CVs were between 6–12% and accuracy values between 97–102%. The specificity of the assay was demonstrated by low cross reactivity with mismatched oligonucleotides and putative 3′-end metabolites shortened by 1, 2 or 3 nucleotides. Validation of IC measurement was performed in vitro in K562 cells treated with fluorescent labeled Ob conjugated to oligofectamine. At Ob concentrations between 0.1 – 10 μM, Bcl-2 mRNA downregulation measured by real-time RT-PCR occurred efficiently. Nonlinear regression analysis of a dose-response curve showed that 50% Bcl-2 downregulation (IC50) occurred at approximately 0.29 μM, corresponding to an Ob IC concentration of 37 pmole/mg protein. Cellular uptake was confirmed by microscopy and flow cytometry. To validate these results in vivo, we measured Ob IC in bone marrow samples from untreated AML pts aged &gt; 60 yrs enrolled on the phase I study OSU 0164. These pts were induced with Ob 7 mg/kg/d CIVI on days 1–10, cytarabine 100 mg/m2/d CIVI on days 4–10 and daunorubicin administered iv at two dose levels (45 mg/m2/d IV and 60 mg/m2/d) on days 4–6. Among 21 pts assessable for clinical response and Bcl-2 levels, at pretreatment, Bcl-2 copy numbers (normalized to ABL) were higher among 12 pts who achieved a CR (median 85,325; range 19,120–149,100) than among 9 non-responsive (NR) pts (32,100 bcl-2 /abl copies; range 1,488–163,500) (P=.04; Mann-Whitney test). Following 72 hr Ob infusion, a decrease (−38%) in median Bcl-2/ABL mRNA copies in CR patients and an increase (+115%) in Bcl-2/ABL copies in NR pts (P=.002; Mann-Whitney test) were observed by real time RT-PCR. A trend in higher median IC of Ob was observed in CR pts (17.0 pmole/mg protein; range 1.5–30.0) as compared to NR pts (4.4 pmole/mg protein; range 0.33–28.0) (P=.06; Mann-Whitney test). Six of 7 pts with IC above the median obtained a CR. No differences were observed in the Ob plasma PKs between the CR pts [median steady state concentration (Css) 2.8 μg/mL, area-under-the-curve (AUC) 772 μg*hr/mL and clearance (Cl) 9.6 L/hr) and the NR pts (median Css 3.4 μg/mL, AUC 752 μg*hr/mL, Cl 6.4 L/hr). Although the number of samples analyzed was small, our data suggest that, despite interpatient variability of both Bcl-2 mRNA expression and Ob uptake, this antisense can be successfully delivered to pts and result in clinically relevant target downregulation. A Cancer and Leukemia Group B phase III AML study to characterize prospectively the interplay of IC levels of the Ob and Bcl-2 downregulation is in progress.

scholarly journals CLoSES: A platform for closed-loop intracranial stimulation in humans

2020 ◽  
Author(s):  
Rina Zelmann ◽  
Angelique C. Paulk ◽  
Ishita Basu ◽  
Anish Sarma ◽  
Ali Yousefi ◽  
...  
Keyword(s):  
Real Time ◽  
Closed Loop ◽  
Therapeutic Modality ◽  
Patient Specific ◽  
Cognitive State ◽  
Intracranial Stimulation ◽  
Decision Algorithm ◽  
Depth Electrodes ◽  
Neuropsychiatric Diseases ◽  
Epilepsy Monitoring

AbstractTargeted interrogation of brain networks through invasive brain stimulation has become an increasingly important research tool as well as a therapeutic modality. The majority of work with this emerging capability has been focused on open-loop approaches. Closed-loop techniques, however, could improve neuromodulatory therapies and research investigations by optimizing stimulation approaches using neurally informed, personalized targets. Specifically, closed-loop direct electrical stimulation tests in humans performed during semi-chronic electrode implantation in patients with refractory epilepsy could help deepen our understanding of basic research questions as well as the mechanisms and treatment solutions for many neuropsychiatric diseases.However, implementing closed-loop systems is challenging. In particular, during intracranial epilepsy monitoring, electrodes are implanted exclusively for clinical reasons. Thus, detection and stimulation sites must be participant- and task-specific. In addition, the system must run in parallel with clinical systems, integrate seamlessly with existing setups, and ensure safety features. A robust, yet flexible platform is required to perform different tests in a single participant and to comply with clinical settings.In order to investigate closed-loop stimulation for research and therapeutic use, we developed a Closed-Loop System for Electrical Stimulation (CLoSES) that computes neural features which are then used in a decision algorithm to trigger stimulation in near real-time. To summarize CLoSES, intracranial EEG signals are acquired, band-pass filtered, and local and network features are continuously computed. If target features are detected (e.g. above a preset threshold for certain duration), stimulation is triggered. An added benefit is the flexibility of CLoSES. Not only could the system trigger stimulation while detecting real-time neural features, but we incorporated a pipeline wherein we used an encoder/decoder model to estimate a hidden cognitive state from the neural features. Other features include randomly timed stimulation, which percentage of biomarker detections produce stimulation, and safety refractory periods.CLoSES has been successfully used in twelve patients with implanted depth electrodes in the epilepsy monitoring unit during cognitive tasks, spindle detection during sleep, and epileptic activity detection. CLoSES provides a flexible platform to implement a variety of closed-loop experimental paradigms in humans. We anticipate that probing neural dynamics and interaction between brain states and stimulation responses with CLoSES will lead to novel insights into the mechanism of normal and pathological brain activity, the discovery and evaluation of potential electrographic biomarkers of neurological and psychiatric disorders, and the development and testing of patient-specific stimulation targets and control signals before implanting a therapeutic device.

scholarly journals Automated Epileptic Seizure Detection in Scalp EEG Based on Spatial-Temporal Complexity

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Xinzhong Zhu ◽  
Huiying Xu ◽  
Jianmin Zhao ◽  
Jie Tian
Keyword(s):  
Real Time ◽  
Epileptic Seizure ◽  
Complexity Analysis ◽  
Epileptic Seizures ◽  
Seizure Detection ◽  
Permutation Entropy ◽  
Patient Specific ◽  
Temporal Complexity ◽  
Long Time ◽  
Almost All

Epilepsy is a group of neurological disorders characterized by epileptic seizures, wherein electroencephalogram (EEG) is one of the most common technologies used to diagnose, monitor, and manage patients with epilepsy. A large number of EEGs have been recorded in clinical applications, which leads to visual inspection of huge volumes of EEG not routinely possible. Hence, automated detection of epileptic seizure has become a goal of many researchers for a long time. A novel method is therefore proposed to construct a patient-specific detector based on spatial-temporal complexity analysis, involving two commonly used entropy-based complexity analysis methods, which are permutation entropy (PE) and sample entropy (SE). The performance of spatial-temporal complexity method is evaluated on a shared dataset. Results suggest that the proposed epilepsy detectors achieve promising performance: the average sensitivities of PE and SE in 23 patients are 99% and 96.6%, respectively. Moreover, both methods can accurately recognize almost all the seizure-free EEG. The proposed method not only obtains a high accuracy rate but also meets the real-time requirements for its application on seizure detection, which suggests that the proposed method has the potential of detecting epileptic seizures in real time.

scholarly journals A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection

2019 ◽  
Author(s):  
Farnaz Forooghifar ◽  
Amir Aminifar ◽  
Leila Cammoun ◽  
Ilona Wisniewski ◽  
Carolina Ciumas ◽  
...  
Keyword(s):  
Real Time ◽  
Monitoring System ◽  
Epileptic Seizure ◽  
Seizure Detection ◽  
Epileptic Seizure Detection ◽  
Epilepsy Monitoring

Efektifitas Penggunaan Metode Pembelajaran Simulasi Dengan Latihan Terhadap Keterampilan Pengisian Partograf Pada Mahasiswa Semester II Di Prodi Kebidanan (D-III) Universitas Kadiri Tahun 2015

2017 ◽  
Vol 4 (1) ◽  
pp. 12
Author(s):  
Dessy Lutfiasari ◽  
Mahmudah Mahmudah
Keyword(s):  
Current Method ◽  
Skills Training ◽  
Health Sciences ◽  
Control Group ◽  
Learning Methods ◽  
Control Group Design ◽  
Significance Level ◽  
Whitney Test ◽  
Mann Whitney Test ◽  
Training Simulation

The use of the current method of learning very big influence on the growth and development of students' creativity and interest for all subjects to be taught, especially in the use of partograf. From interviews to the 10 students of IV semester Prodi Midwifery (D-III) Kadiri University is known that 4 (40%) of students said it was understood, 4 (40%) of other students say they are confused and 2 (20%) of them said that he was a student not familiar with partograf. This shows the lack of understanding of students in filling partograph. The research objective is to determine the effectiveness of the use of learning methods for skills training simulation with filling partograph the second semester students in Midwifery (D-III) Kadiri University Faculty of Health Sciences in 2015. The research design used is pre experiment with design Static Group Comparison/Posttest Only Control Group Design. The population studied were all students of the second semester in Midwifery (D-III) Faculty of Health Sciences University of Kadiri numbered 50 students and sampling techniques Federer totaled 32 students. This is a research instrument partograph sheet. Results of the study were analyzed using the Mann Whitney test with a significance level of 0.05 were used.The results showed 7 respondents (46.7%) are adept at using partograf with simulation teaching methods and 6 respondents (40.0%) are adept at using partograph with practice learning methods. Data were analyzed by Mann Whitney test obtained ρ = 0.965; α = 0.05 means that H0 is accepted and H1 rejected. This means there is no difference in the effective use of learning methods for skills training simulation with partograph filling. Based on the results of this study are expected to choose the method of learning as a learning method in charging partograph because both methods equally effective.; Keywords: simulation methods, drilling methods, partograph filling

scholarly journals Pilot Study of Acupuncture’s Antispasmodic Effect on Upper Gastrointestinal Tract during Endoscopic Submucosal Dissection for Early Gastric Cancer: Controlled Clinical Trial

2021 ◽  
Vol 10 (14) ◽  
pp. 3050
Author(s):  
Masao Suzuki ◽  
Naoto Ishizaki ◽  
Takumi Kayo ◽  
Taiga Furuta ◽  
Ryo Igarashi ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Gastrointestinal Tract ◽  
Endoscopic Submucosal Dissection ◽  
Controlled Trial ◽  
Upper Gastrointestinal Tract ◽  
Controlled Clinical Trial ◽  
Whitney Test ◽  
Submucosal Dissection ◽  
Mann Whitney Test ◽  
Upper Gastrointestinal

A prospective study was conducted in patients with early-stage gastric cancer to determine the efficacy and safety of acupuncture stimulation as an antispasmodic compared with conventional medication during the procedure of endoscopic submucosal dissection (ESD) of the upper gastrointestinal tract. This study was a prospective single blinded quasi-randomized controlled trial. Seventy-three patients who were scheduled to undergo ESD for gastric cancer at Aizu Medical Center between 19 February 2016 and 30 June 2016 were assessed for eligibility for the study. Sixty out of 73 patients were included in the study and assigned into two intervention groups: medication group (MG) and acupuncture group (AG). Ease of the procedure was evaluated using modified NIWA classification (MNC) by endoscopist considering the frequency and amplitude of the upper gastrointestinal peristalsis. For the statistical analysis, Mann–Whitney test was used to compare the differences of MNC values (baseline and end of procedure) between two groups. The difference of MNC found in the AG (−2.00 (−3.0 to −2.0)) was significantly greater than that in the MG (−1.00 (−2.0 to −1.0), p < 0.0001, Mann–Whitney test). We consider that acupuncture to the abdomen could be an alternative antispasmodic method during upper gastrointestinal endoscopic procedure.

scholarly journals Probe-Based Real-Time qPCR Assays for a Reliable Differentiation of Capripox Virus Species

2021 ◽  
Vol 9 (4) ◽  
pp. 765
Author(s):  
Janika Wolff ◽  
Martin Beer ◽  
Bernd Hoffmann
Keyword(s):  
Real Time ◽  
Animal Health ◽  
Diagnostic Methods ◽  
Virus Species ◽  
Time Saving ◽  
Robust Detection ◽  
Highly Sensitive ◽  
Reliable Differentiation ◽  
World Organization ◽  
Real Time Qpcr

Outbreaks of the three capripox virus species, namely lumpy skin disease virus, sheeppox virus, and goatpox virus, severely affect animal health and both national and international economies. Therefore, the World Organization for Animal Health (OIE) classified them as notifiable diseases. Until now, discrimination of capripox virus species was possible by using different conventional PCR protocols. However, more sophisticated probe-based real-time qPCR systems addressing this issue are, to our knowledge, still missing. In the present study, we developed several duplex qPCR assays consisting of different types of fluorescence-labelled probes that are highly sensitive and show a high analytical specificity. Finally, our assays were combined with already published diagnostic methods to a diagnostic workflow that enables time-saving, reliable, and robust detection, differentiation, and characterization of capripox virus isolates.

Sign in / Sign up

Export Citation Format

Share Document