Boosting phase-contrast MRI performance in idiopathic normal pressure hydrocephalus diagnostics by means of machine learning approach.

OBJECTIVE: Phase-contrast MRI allows detailed measurements of various parameters of CSF motion. This examination is technically demanding and machine dependent. The literature on this topic is ambiguous. Machine learning (ML) approaches have already been successfully utilized in medical research, but none have yet been applied to enhance the results of CSF flowmetry. The aim of this study was to evaluate the possible contribution of ML algorithms in enhancing the utilization and results of MRI flowmetry in idiopathic normal pressure hydrocephalus (iNPH) diagnostics. METHODS: The study cohort consisted of 30 iNPH patients and 15 healthy controls examined on one MRI machine. All major phase-contrast parameters were inspected: peak positive, peak negative, and average velocities; peak amplitude; positive, negative, and average flow rates; and aqueductal area. The authors applied ML algorithms to 85 complex features calculated from a phase-contrast study. RESULTS: The most distinctive parameters with p < 0.005 were the peak negative velocity, peak amplitude, and negative flow. From the ML algorithms, the Adaptive Boosting classifier showed the highest specificity and best discrimination potential overall, with 80.4% ± 2.9% accuracy, 72.0% ± 5.6% sensitivity, 84.7% ± 3.8% specificity, and 0.812 ± 0.047 area under the receiver operating characteristic curve (AUC). The highest sensitivity was 85.7% ± 5.6%, reached by the Gaussian Naive Bayes model, and the best AUC was 0.854 ± 0.028 by the Extra Trees classifier. CONCLUSIONS: Feature extraction algorithms combined with ML approaches simplify the utilization of phase-contrast MRI. The highest-performing ML algorithm was Adaptive Boosting, which showed good calibration and discrimination on the testing data, with 80.4% accuracy, 72.0% sensitivity, 84.7% specificity, and 0.812 AUC. Phase-contrast MRI boosted by the ML approach can help to determine shunt-responsive iNPH patients.

Prediction of Shunt Responsiveness in Suspected Patients With Normal Pressure Hydrocephalus Using the Lumbar Infusion Test: A Machine Learning Approach.

BACKGROUND: Machine learning (ML) approaches can significantly improve the classical Rout-based evaluation of the lumbar infusion test (LIT) and the clinical management of the normal pressure hydrocephalus. OBJECTIVE: To develop a ML model that accurately identifies patients as candidates for permanent cerebral spinal fluid shunt implantation using only intracranial pressure and electrocardiogram signals recorded throughout LIT. METHODS: This was a single-center cohort study of prospectively collected data of 96 patients who underwent LIT and 5-day external lumbar cerebral spinal fluid drainage (external lumbar drainage) as a reference diagnostic method. A set of selected 48 intracranial pressure/electrocardiogram complex signal waveform features describing nonlinear behavior, wavelet transform spectral signatures, or recurrent map patterns were calculated for each patient. After applying a leave-one-out cross-validation training-testing split of the data set, we trained and evaluated the performance of various state-of-the-art ML algorithms. RESULTS: The highest performing ML algorithm was the eXtreme Gradient Boosting. This model showed a good calibration and discrimination on the testing data, with an area under the receiver operating characteristic curve of 0.891 (accuracy: 82.3%, sensitivity: 86.1%, and specificity: 73.9%) obtained for 8 selected features. Our ML model clearly outperforms the classical Rout-based manual classification commonly used in clinical practice with an accuracy of 62.5%. CONCLUSION: This study successfully used the ML approach to predict the outcome of a 5-day external lumbar drainage and hence which patients are likely to benefit from permanent shunt implantation. Our automated ML model thus enhances the diagnostic utility of LIT in management.

Seizure likelihood varies with day-to-day variations in sleep duration in patients with refractory focal epilepsy: A longitudinal electroencephalography investigation.

BACKGROUND: While the effects of prolonged sleep deprivation (≥24 h) on seizure occurrence has been thoroughly explored, little is known about the effects of day-to-day variations in the duration and quality of sleep on seizure probability. A better understanding of the interaction between sleep and seizures may help to improve seizure management. METHODS: To explore how sleep and epileptic seizures are associated, we analysed continuous intracranial electroencephalography (EEG) recordings collected from 10 patients with refractory focal epilepsy undergoing ordinary life activities between 2010 and 2012 from three clinical centres (Austin Health, The Royal Melbourne Hospital, and St Vincent's Hospital of the Melbourne University Epilepsy Group). A total of 4340 days of sleep-wake data were analysed (average 434 days per patient). EEG data were sleep scored using a semi-automated machine learning approach into wake, stages one, two, and three non-rapid eye movement sleep, and rapid eye movement sleep categories. FINDINGS: Seizure probability changes with day-to-day variations in sleep duration. Logistic regression models revealed that an increase in sleep duration, by 1·66 ± 0·52 h, lowered the odds of seizure by 27% in the following 48 h. Following a seizure, patients slept for longer durations and if a seizure occurred during sleep, then sleep quality was also reduced with increased time spent aroused from sleep and reduced rapid eye movement sleep. INTERPRETATION: Our results suggest that day-to-day deviations from regular sleep duration correlates with changes in seizure probability. Sleeping longer, by 1·66 ± 0·52 h, may offer protective effects for patients with refractory focal epilepsy, reducing seizure risk. Furthermore, the occurrence of a seizure may disrupt sleep patterns by elongating sleep and, if the seizure occurs during sleep, reducing its quality.

From head micro-motions towards CSF dynamics and non-invasive intracranial pressure monitoring.

Continuous monitoring of the intracranial pressure (ICP) is essential in neurocritical care. There are a variety of ICP monitoring systems currently available, with the intraventricular fluid filled catheter transducer currently representing the "gold standard". As the placement of catheters is associated with the attendant risk of infection, hematoma formation, and seizures, there is a need for a reliable, non-invasive alternative. In the present study we suggest a unique theoretical framework based on differential geometry invariants of cranial micro-motions with the potential for continuous non-invasive ICP monitoring in conservative traumatic brain injury (TBI) treatment. As a proof of this concept, we have developed a pillow with embedded mechanical sensors and collected an extensive dataset (> 550 h on 24 TBI coma patients) of cranial micro-motions and the reference intraparenchymal ICP. From the multidimensional pulsatile curve we calculated the first Cartan curvature and constructed a "fingerprint" image (Cartan map) associated with the cerebrospinal fluid (CSF) dynamics. The Cartan map features maxima bands corresponding to a pressure wave reflection corresponding to a detectable skull tremble. We give evidence for a statistically significant and patient-independent correlation between skull micro-motions and ICP time derivative. Our unique differential geometry-based method yields a broader and global perspective on intracranial CSF dynamics compared to rather local catheter-based measurement and has the potential for wider applications.

Identifying seizure risk factors: A comparison of sleep, weather, and temporal features using a Bayesian forecast.

OBJECTIVE: Most seizure forecasting algorithms have relied on features specific to electroencephalographic recordings. Environmental and physiological factors, such as weather and sleep, have long been suspected to affect brain activity and seizure occurrence but have not been fully explored as prior information for seizure forecasts in a patient-specific analysis. The study aimed to quantify whether sleep, weather, and temporal factors (time of day, day of week, and lunar phase) can provide predictive prior probabilities that may be used to improve seizure forecasts. METHODS: This study performed post hoc analysis on data from eight patients with a total of 12.2 years of continuous intracranial electroencephalographic recordings (average = 1.5 years, range = 1.0-2.1 years), originally collected in a prospective trial. Patients also had sleep scoring and location-specific weather data. Histograms of future seizure likelihood were generated for each feature. The predictive utility of individual features was measured using a Bayesian approach to combine different features into an overall forecast of seizure likelihood. Performance of different feature combinations was compared using the area under the receiver operating curve. Performance evaluation was pseudoprospective. RESULTS: For the eight patients studied, seizures could be predicted above chance accuracy using sleep (five patients), weather (two patients), and temporal features (six patients). Forecasts using combined features performed significantly better than chance in six patients. For four of these patients, combined forecasts outperformed any individual feature. SIGNIFICANCE: Environmental and physiological data, including sleep, weather, and temporal features, provide significant predictive information on upcoming seizures. Although forecasts did not perform as well as algorithms that use invasive intracranial electroencephalography, the results were significantly above chance. Complementary signal features derived from an individual's historic seizure records may provide useful prior information to augment traditional seizure detection or forecasting algorithms. Importantly, many predictive features used in this study can be measured noninvasively.

An Unsupervised Multichannel Artifact Detection Method for Sleep EEG Based on Riemannian Geometry.

In biomedical signal processing, we often face the problem of artifacts that distort the original signals. This concerns also sleep recordings, such as EEG. Artifacts may severely affect or even make impossible visual inspection, as well as automatic processing. Many proposed methods concentrate on certain artifact types. Therefore, artifact-free data are often obtained after sequential application of different methods. Moreover, single-channel approaches must be applied to all channels alternately. The aim of this study is to develop a multichannel artifact detection method for multichannel sleep EEG capable of rejecting different artifact types at once. The inspiration for the study is gained from recent advances in the field of Riemannian geometry. The method we propose is tested on real datasets. The performance of the proposed method is measured by comparing detection results with the expert labeling as a reference and evaluated against a simpler method based on Riemannian geometry that has previously been proposed, as well as against the state-of-the-art method FASTER. The obtained results prove the effectiveness of the proposed method.

Semi-automated Detection of Polysomnographic REM Sleep without Atonia (RSWA) in REM Sleep Behavioral Disorder.

We aimed at evaluating semi-automatic detection and quantification of polysomnographic REM sleep without atonia (RSWA). As basic requirements, we defined lower time demand, the possibility of comparison of several evaluations and ease of examination for neurologists. We focused on well-known primary processing of surface electromyographic signals and selected recordings that were free of technical artifacts that could compromise automated signal detection. Thus we created a comprehensive method consisting of several modules (data preprocessing, signal filtration, envelopes creation, detection of ECG QRS complexes, iterative RSWA detection, detection evaluation and interactive visualization). The original dataset consisted of 7 individual polysomnography (PSG) recordings of individual human adult subjects with REM sleep behavior disorder (RBD). RSWA detection was performed with three different methods for envelope creation (envelope by moving average filter, envelope by Savitzky-Golay filtration and peaks interpolation). Best RSWA detection was achieved using the envelope by moving average filter (average precision 64.24±12.34 % and recall 91.63±10.07 %). The lowest precision was 42.86 % with 100 % recall.

Noninvasive assessment of cardiac output by brachial occlusion-cuff technique: comparison with the open-circuit acetylene washin method.

Cardiac output (CO) assessment as a basic hemodynamic parameter has been of interest in exercise physiology, cardiology, and anesthesiology. Noninvasive techniques available are technically challenging, and thus difficult to use outside of a clinical or laboratory setting. We propose a novel method of noninvasive CO assessment using a single, upper-arm cuff. The method uses the arterial pressure pulse wave signal acquired from the brachial artery during 20-s intervals of suprasystolic occlusion. This method was evaluated in a cohort of 12 healthy individuals (age, 27.7 ± 5.4 yr, 50% men) and compared with an established method for noninvasive CO assessment, the open-circuit acetylene method (OpCirc) at rest, and during low- to moderate-intensity exercise. CO increased from rest to exercise (rest, 7.4 ± 0.8 vs. 7.2 ± 0.8; low, 9.8 ± 1.8 vs. 9.9 ± 2.0; moderate, 14.1 ± 2.8 vs. 14.8 ± 3.2 l/min) as assessed by the cuff-occlusion and OpCirc techniques, respectively. The average error of experimental technique compared with OpCirc was -0.25 ± 1.02 l/min, Pearson's correlation coefficient of 0.96 (rest + exercise), and 0.21 ± 0.42 l/min with Pearson's correlation coefficient of 0.87 (rest only). Bland-Altman analysis demonstrated good agreement between methods (within 95% boundaries); the reproducibility coefficient (RPC) = 0.84 l/min with R2 = 0.75 at rest and RPC = 2 l/min with R2 = 0.92 at rest and during exercise, respectively. In comparison with an established method to quantify CO, the cuff-occlusion method provides similar measures at rest and with light to moderate exercise. Thus, we believe this method has the potential to be used as a new, noninvasive method for assessing CO during exercise.

Frames of reference and their neural correlates within navigation in a 3D environment.

The goal of this study was an administration of the navigation task in a three-dimensional virtual environment to localize the electroencephalogram (EEG) features responsible for egocentric and allocentric reference frame processing in a horizontal and also in a vertical plane. We recorded the EEG signal of a traverse through a virtual tunnel to search for the best signal features that discriminate between specific strategies in particular plane. We identified intrahemispheric coherences in occipital-parietal and temporal-parietal areas as the most discriminative features. They have 10% lower error rate compared to single electrode features adopted in previous studies. The behavioral analysis revealed that 11% of participants switched from egocentric to allocentric strategy in a vertical plane, while 24% of participants consistently adopted egocentric strategy in both planes.