Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring.

Background: CTG remains the only non-invasive tool available to the maternity team for continuous monitoring of fetal well-being during labour. Despite widespread use and investment in staff training, difficulty with CTG interpretation continues to be identified as a problem in cases of fetal hypoxia, which often results in permanent brain injury. Given the recent advances in AI, it is hoped that its application to CTG will offer a better, less subjective and more reliable method of CTG interpretation. Objectives: This mini-review examines the literature and discusses the impediments to the success of AI application to CTG thus far. Prior randomised control trials (RCTs) of CTG decision support systems are reviewed from technical and clinical perspectives. A selection of novel engineering approaches, not yet validated in RCTs, are also reviewed. The review presents the key challenges that need to be addressed in order to develop a robust AI tool to identify fetal distress in a timely manner so that appropriate intervention can be made. Results: The decision support systems used in three RCTs were reviewed, summarising the algorithms, the outcomes of the trials and the limitations. Preliminary work suggests that the inclusion of clinical data can improve the performance of AI-assisted CTG. Combined with newer approaches to the classification of traces, this offers promise for rewarding future development.

Bag of Patterns for Nearest Neighbour Neonatal EEG Recall.

Clinical neurophysiologists often find it difficult to recall rare EEG patterns despite the fact that this information could be diagnostic and help with treatment intervention. Traditional search methods may take time to retrieve the archived EEGs that could provide the meaning or cause of the specific pattern, which is undesirable as time can be critical for sick neonates. If neurophysiologists had the ability to quickly recall similar patterns, the prior occurrence of the pattern may help make an earlier diagnosis. This paper presents a system that may be used to assist a clinical neurophysiologist in the recall of neonatal EEG patterns. This paper compares two brute force approaches for the task of neonatal EEG recall and looks at the performance accuracy, speed and memory requirements. This system was tested on six different neonatal EEG pattern types with 430 events in total and the results are presented in this paper.

A comparison of quantitative EEG features for neonatal seizure detection.

OBJECTIVE: This study was undertaken to identify the best performing quantitative EEG features for neonatal seizures detection from a test set of 21. METHODS: Each feature was evaluated on 1-min, artefact-free segments of seizure and non-seizure neonatal EEG recordings. The potential utility of each feature for neonatal seizure detection was determined using receiver operating characteristic analysis and repeated measures t-tests. A performance estimate of the feature set was obtained using a cross-fold validation and combining all features together into a linear discriminant classifier model. RESULTS: Significant differences between seizure and non-seizure segments were found in 19 features for 17 patients. The best performing features for this application were the RMS amplitude, the line length and the number of local maxima and minima. An estimate of the patient independent classifier performance yielded a sensitivity of 81.08% and specificity of 82.23%. CONCLUSIONS: The individual performances of 21 quantitative EEG features in detecting electrographic seizure in the neonate were compared and numerically quantified. Combining all features together into a classifier model led to superior performance than that provided by any individual feature taken alone. SIGNIFICANCE: The results documented in this study may provide a reference for the optimum quantitative EEG features to use in developing and enhancing neonatal seizure detection algorithms.

Classifier models and architectures for EEG-based neonatal seizure detection.

Neonatal seizures are the most common neurological emergency in the neonatal period and are associated with a poor long-term outcome. Early detection and treatment may improve prognosis. This paper aims to develop an optimal set of parameters and a comprehensive scheme for patient-independent multi-channel EEG-based neonatal seizure detection. We employed a dataset containing 411 neonatal seizures. The dataset consists of multi-channel EEG recordings with a mean duration of 14.8 h from 17 neonatal patients. Early-integration and late-integration classifier architectures were considered for the combination of information across EEG channels. Three classifier models based on linear discriminants, quadratic discriminants and regularized discriminants were employed. Furthermore, the effect of electrode montage was considered. The best performing seizure detection system was found to be an early integration configuration employing a regularized discriminant classifier model. A referential EEG montage was found to outperform the more standard bipolar electrode montage for automated neonatal seizure detection. A cross-fold validation estimate of the classifier performance for the best performing system yielded 81.03% of seizures correctly detected with a false detection rate of 3.82%. With post-processing, the false detection rate was reduced to 1.30% with 59.49% of seizures correctly detected. These results represent a comprehensive illustration that robust reliable patient-independent neonatal seizure detection is possible using multi-channel EEG.

An Approximate Nearest Neighbour System For Neonatal EEG Recall.

Clinical neurophysiologists often find it difficult to recall rare EEG patterns despite the fact that this information could be diagnostic and help with treatment intervention. Traditional search methods may take time to retrieve the archived EEGs that could provide the meaning or cause of the specific pattern which is not acceptable as time can be critical for sick neonates. If neurophysiologists had the ability to quickly recall similar patterns, the prior occurrence of the pattern may help make an earlier diagnosis. This paper presents a system that may be used to assist a clinical neurophysiologist in the recall of neonatal EEG patterns. The proposed system consists of an alignment technique followed by an approximate nearest neighbour search algorithm called locality sensitive hashing. The system was tested on six different neonatal EEG pattern types with 430 events in total and the results are presented in this paper.

Application of audio fingerprinting to neonatal EEG.

A clinical neurophysiologist must recognize patterns in EEG signals to evaluate the health of a patient's brain activity. Rare or unusual patterns may take time to correctly identify. The ability to automatically assist this recall would be beneficial in ensuring that appropriate measures could be taken in a timely fashion. Audio fingerprinting is a method used to identify songs using only a snippet of the song. Fingerprints are extracted from a sub-section of the song and matched against a database of previously computed fingerprints. In this paper, a fingerprint quantization technique is implemented on neonatal EEG data to attempt to identify sections of EEG data when only seeing a sub-section of the data. The impact of signal distortions is investigated and results from a database of one hour recordings from 40 newborns are presented.

Stream computing for biomedical signal processing: A QRS complex detection case-study.

Recent developments in "Big Data" have brought significant gains in the ability to process large amounts of data on commodity server hardware. Stream computing is a relatively new paradigm in this area, addressing the need to process data in real time with very low latency. While this approach has been developed for dealing with large scale data from the world of business, security and finance, there is a natural overlap with clinical needs for physiological signal processing. In this work we present a case study of streams processing applied to a typical physiological signal processing problem: QRS detection from ECG data.

Automated detection of perturbed cardiac physiology during oral food allergen challenge in children.

This paper investigates the fully automated computer-based detection of allergic reaction in oral food challenges using pediatric ECG signals. Nonallergic background is modeled using a mixture of Gaussians during oral food challenges, and the model likelihoods are used to determine whether a subject is allergic to a food type. The system performance is assessed on the dataset of 24 children (15 allergic and 9 nonallergic) totaling 34 h of data. The proposed detector correctly classified all nonallergic subjects (100% specificity) and 12 allergic subjects (80% sensitivity) and is capable of detecting allergy on average 17 min earlier than trained clinicians during oral food challenges, the gold standard of allergy diagnosis. Inclusion of the developed allergy classification platform during oral food challenges recorded would result in a 30% reduction of doses administered to allergic subjects. The results of study introduce the possibility to halt challenges earlier which can safely advance the state of clinical art of allergy diagnosis by reducing the overall exposure to the allergens.

Robustness of time frequency distribution based features for automated neonatal EEG seizure detection.

In this paper we examined the robustness of a feature-set based on time-frequency distributions (TFDs) for neonatal EEG seizure detection. This feature-set was originally proposed in literature for neonatal seizure detection using a support vector machine (SVM). We tested the performance of this feature-set with a smoothed Wigner-Ville distribution and modified B distribution as the underlying TFDs. The seizure detection system using time-frequency signal and image processing features from the TFD of the EEG signal using modified B distribution was able to achieve a median receiver operator characteristic area of 0.96 (IQR 0.91-0.98) tested on a large clinical dataset of 826 h of EEG data from 18 full-term newborns with 1389 seizures. The mean AUC was 0.93.

An automated system for grading EEG abnormality in term neonates with hypoxic-ischaemic encephalopathy.

Automated analysis of the neonatal EEG has the potential to assist clinical decision making for neonates with hypoxic-ischaemic encephalopathy. This paper proposes a method of automatically grading the degree of abnormality in an hour long epoch of neonatal EEG. The automated grading system (AGS) was based on a multi-class linear classifier grading of short-term epochs of EEG which were converted into a long-term grading of EEG using a majority vote operation. The features used in the AGS were summary measurements of two sub-signals extracted from a quadratic time-frequency distribution: the amplitude modulation and instantaneous frequency. These sub-signals were based on a model of EEG as a multiplication of a coloured random process with a slowly varying pseudo-periodic waveform and may be related to macroscopic neurophysiological function. The 4 grade AGS had a classification accuracy of 83% compared to human annotation of the EEG (level of agreement, κ = 0.76). Features estimated on the developed sub-signals proved more effective at grading the EEG than measures based solely on the EEG and the incorporation of additional sub-grades based on EEG states into the AGS also improved performance.

The effects of lossy compression on diagnostically relevant seizure information in EEG signals.

This paper examines the effects of compression on EEG signals, in the context of automated detection of epileptic seizures. Specifically, it examines the use of lossy compression on EEG signals in order to reduce the amount of data which has to be transmitted or stored, while having as little impact as possible on the information in the signal relevant to diagnosing epileptic seizures. Two popular compression methods, JPEG2000 and SPIHT, were used. A range of compression levels was selected for both algorithms in order to compress the signals with varying degrees of loss. This compression was applied to the database of epileptiform data provided by the University of Freiburg, Germany. The real-time EEG analysis for event detection automated seizure detection system was used in place of a trained clinician for scoring the reconstructed data. Results demonstrate that compression by a factor of up to 120:1 can be achieved, with minimal loss in seizure detection performance as measured by the area under the receiver operating characteristic curve of the seizure detection system.

Parallel artefact rejection for epileptiform activity detection in routine EEG.

The EEG signal is very often contaminated by electrical activity external to the brain. These artefacts make the accurate detection of epileptiform activity more difficult. A scheme developed to improve the detection of these artefacts (and hence epileptiform event detection) is introduced. A structure of parallel Support Vector Machine classifiers is assembled, one classifier tuned to perform the identification of epileptiform activity, the remainder trained for the detection of ocular and movement-related artefacts. This strategy enables an absolute reduction in false detection rate of 21.6% with the constraint of ensuring all epileptic events are recognized. Such a scheme is desirable given that sections of data which are heavily contaminated with artefact need not be excluded from analysis.

Gaussian mixture models for classification of neonatal seizures using EEG.

A real-time neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. The system includes feature transformation techniques and classifier output postprocessing. The detector was evaluated on a database of 20 patients with 330 h of recordings. A detailed analysis of the choice of parameters for the detector is provided. A mean good detection rate of 79% was obtained with only 0.5 false detections per hour. A thorough review of all misclassified events was performed, from which a number of patterns causing false detections were identified.

The effect of lossy ECG compression on QRS and HRV feature extraction.

This paper describes the performance of beat detection and heart rate variability (HRV) feature extraction on electrocardiogram signals which have been compressed and reconstructed with a lossy compression algorithm. The set partitioning in hierarchical trees (SPIHT) compression algorithm was used with sixteen compression ratios (CR) between 2 and 50 over the records of the MIT/BIH arrhythmia database. Sensitivities and specificities between 99% and 85% were computed for each CR utilised. The extracted HRV features were between 99% and 82% similar to the features extracted from the annotated records. A notable accuracy drop over all features extracted was noted beyond a CR of 30, with falls of 10% accuracy beyond this compression ratio.

Seizure detection in neonates: Improved classification through supervised adaptation.

The goal of neonatal seizure detection is the development of a patient independent system to alert staff in the neonatal intensive care unit of ongoing seizures. This study demonstrates the potential in adapting a patient independent classifier using patient specific data. Supervised adaptation is investigated using the basic gradient descent algorithm and least mean squares procedures. An increase in mean ROC area of 3% is obtained for the best performing learning algorithm, yielding an increase in mean accuracy of 7.7% compared to the patient independent algorithm.

Automated single channel seizure detection in the neonate.

Neonatal seizures are the most common neurological emergency in the neonatal period and are associated with poor long-term outcome. EEG is considered the gold standard for identification of all neonatal seizures, reducing the number of EEG electrodes required would reduce patient handling and allow faster acquisition of data. A method for automated neonatal seizure detection based on two carefully chosen cerebral scalp electrodes but trained using multi-channel EEG is presented. The algorithm was developed and tested using a multi-channel EEG dataset containing 411 seizures from 251.9 hours of EEG recorded from 17 full-term neonates. Automated seizure detection using a variety of bipolar channel derivations was investigated. Channel C3-C4 yielded correct detection of 90.77% of seizures with a false detection rate of 9.43%. This compares favourably with a multi-channel seizure detection method which detected 81.03% of seizures with a false detection rate of 3.82%.