Prediction of antiepileptic drug treatment outcomes using machine learning

EEG Beta-Band Spectral Entropy Can Predict the Effect of Drug Treatment on Pain in Patients With Herpes Zoster

BACKGROUND

Medication is the main approach for early treatment of herpes zoster, but it could be ineffective in some patients. It is highly desired to predict the medication responses to control the degree of pain for herpes zoster patients. The present study is aimed to elucidate the relationship between medication outcome and neural activity using EEG and to establish a machine learning model for early prediction of the medication responses from EEG.

METHODS

The authors acquired and analyzed eye-closed resting-state EEG data 1 to 2 days after medication from 70 herpes zoster patients with different drug treatment outcomes (measured 5-6 days after medication): 45 medication-sensitive pain patients and 25 medication-resistant pain patients. EEG power spectral entropy of each frequency band was compared at each channel between medication-sensitive pain and medication-resistant pain patients, and those features showing significant difference between two groups were used to predict medication outcome with different machine learning methods.

RESULTS

Medication-sensitive pain patients showed significantly weaker beta-band power spectral entropy in the central-parietal regions than medication-resistant pain patients. Based on these EEG power spectral entropy features and a k-nearest neighbors classifier, the medication outcome can be predicted with 80% ± 11.7% accuracy, 82.5% ± 14.7% sensitivity, 77.7% ± 27.3% specificity, and an area under the receiver operating characteristic curve of 0.85.

CONCLUSIONS

EEG beta-band power spectral entropy in the central-parietal region is predictive of the effectiveness of drug treatment on herpes zoster patients, and it could potentially be used for early pain management and therapeutic prognosis.

EEG-Driven Prediction Model of Oxcarbazepine Treatment Outcomes in Patients With Newly-Diagnosed Focal Epilepsy

Objective: Antiseizure medicine (ASM) is the first choice for patients with epilepsy. The choice of ASM is determined by the type of epilepsy or epileptic syndrome, which may not be suitable for certain patients. This initial choice of a particular drug affects the long-term prognosis of patients, so it is critical to select the appropriate ASMs based on the individual characteristics of a patient at the early stage of the disease. The purpose of this study is to develop a personalized prediction model to predict the probability of achieving seizure control in patients with focal epilepsy, which will help in providing a more precise initial medication to patients.

Methods: Based on response to oxcarbazepine (OXC), enrolled patients were divided into two groups: seizure-free (52 patients), not seizure-free (NSF) (22 patients). We created models to predict patients' response to OXC monotherapy by combining Electroencephalogram (EEG) complexities and 15 clinical features. The prediction models were gradient boosting decision tree-Kolmogorov complexity (GBDT-KC) and gradient boosting decision tree-Lempel-Ziv complexity (GBDT-LZC). We also constructed two additional prediction models, support vector machine-Kolmogorov complexity (SVM-KC) and SVM-LZC, and these two models were compared with the GBDT models. The performance of the models was evaluated by calculating the accuracy, precision, recall, F1-score, sensitivity, specificity, and area under the curve (AUC) of these models.

Results: The mean accuracy, precision, recall, F1-score, sensitivity, specificity, AUC of GBDT-LZC model after five-fold cross-validation were 81%, 84%, 91%, 87%, 91%, 64%, 81%, respectively. The average accuracy, precision, recall, F1-score, sensitivity, specificity, AUC of GBDT-KC model with five-fold cross-validation were 82%, 84%, 92%, 88%, 83%, 92%, 83%, respectively. We used the rank of absolute weights to separately calculate the features that have the most significant impact on the classification of the two models.

Conclusion: (1) The GBDT-KC model has the potential to be used in the clinic to predict seizure-free with OXC monotherapy. (2). Electroencephalogram complexity, especially Kolmogorov complexity (KC) may be a potential biomarker in predicting the treatment efficacy of OXC in newly diagnosed patients with focal epilepsy.

Predicting cognitive impairment in outpatients with epilepsy using machine learning techniques

Many studies report predictions for cognitive function but there are few predictions in epileptic patients; therefore, we established a workflow to efficiently predict outcomes of both the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) in outpatients with epilepsy. Data from 441 outpatients with epilepsy were included; of these, 433 patients met the 12 clinical characteristic criteria and were divided into training (n = 304) and experimental (n = 129) groups. After descriptive statistics were analyzed, cross-validation was used to select the optimal model. The random forest (RF) algorithm was combined with the redundancy analysis (RDA) algorithm; then, optimal feature selection and resampling were carried out after removing linear redundancy information. The features that contributed more to multiple outcomes were selected. Finally, the external traceability of the model was evaluated using the follow-up data. The RF algorithm was the best prediction model for both MMSE and MoCA outcomes. Finally, seven markers were screened by overlapping the top ten important features for MMSE ranked by RF modeling, those ranked for MoCA ranked by RF modeling, and those for both assessments ranked by RDA. The optimal combination of features were namely, sex, age, age of onset, seizure frequency, brain MRI abnormalities, epileptiform discharge in EEG and usage of drugs. which was the most efficient in predicting outcomes of MMSE, MoCA, and both assessments.

Delta-gamma phase-amplitude coupling as a biomarker of postictal generalized EEG suppression

Postictal generalized EEG suppression is the state of suppression of electrical activity at the end of a seizure. Prolongation of this state has been associated with increased risk of sudden unexpected death in epilepsy, making characterization of underlying electrical rhythmic activity during postictal suppression an important step in improving epilepsy treatment. Phase-amplitude coupling in EEG reflects cognitive coding within brain networks and some of those codes highlight epileptic activity; therefore, we hypothesized that there are distinct phase-amplitude coupling features in the postictal suppression state that can provide an improved estimate of this state in the context of patient risk for sudden unexpected death in epilepsy. We used both intracranial and scalp EEG data from eleven patients (six male, five female; age range 21–41 years) containing 25 seizures, to identify frequency dynamics, both in the ictal and postictal EEG suppression states. Cross-frequency coupling analysis identified that during seizures there was a gradual decrease of phase frequency in the coupling between delta (0.5–4 Hz) and gamma (30+ Hz), which was followed by an increased coupling between the phase of 0.5–1.5 Hz signal and amplitude of 30–50 Hz signal in the postictal state as compared to the pre-seizure baseline. This marker was consistent across patients. Then, using these postictal-specific features, an unsupervised state classifier—a hidden Markov model—was able to reliably classify four distinct states of seizure episodes, including a postictal suppression state. Furthermore, a connectome analysis of the postictal suppression states showed increased information flow within the network during postictal suppression states as compared to the pre-seizure baseline, suggesting enhanced network communication. When the same tools were applied to the EEG of an epilepsy patient who died unexpectedly, ictal coupling dynamics disappeared and postictal phase-amplitude coupling remained constant throughout. Overall, our findings suggest that there are active postictal networks, as defined through coupling dynamics that can be used to objectively classify the postictal suppression state; furthermore, in a case study of sudden unexpected death in epilepsy, the network does not show ictal-like phase-amplitude coupling features despite the presence of convulsive seizures, and instead demonstrates activity similar to postictal. The postictal suppression state is a period of elevated network activity as compared to the baseline activity which can provide key insights into the epileptic pathology.

Cross-Frequency Coupling Features of Postictal Generalized EEG Suppression State

In patients with epilepsy, convulsive seizures are often followed by a postictal generalized EEG suppression (PGES) state characterized by reduced background activity. Recent studies found a correlation between seizure termination state and PGES duration, and suggested that PGES is the result of the cessation of neuronal activity. To test that assertion, we investigated ten seizure records obtained from intracranial EEG (iEEG) from six patients, four of which had Engel Class 1 surgical outcome. In each case expert neurologists identified the most likely seizure onset electrode. We found the iEEG equivalent of PGES and an artifact-free preictal quiescent state of the same window size. Using index of cross-frequency coupling (ICFC) we identified the degree of coupling and dominant frequency bands involved in PGES and preictal quiescent states, and quantified the areas of high ICFC. We found that there was an increase in the degree of coupling between the 0.5-1.5Hz with high gamma frequency bands in the PGES states. We found that among all of the patients, as well as in Engel Class 1 patients specifically, the change in the quantified area of high ICFC was significant (p <; 0.05) between PGES and preictal quiescent states. Furthermore, we were able to identify whether a recording was from a depth or subdural electrode, or whether it was from seizure onset zone or not using ICFC markers in PGES. This suggests that there are frequency coupling markers that successfully identify PGES and that there are underlying dynamics that occur in this seemingly quiet postictal state.

Excitation and Inhibition Balance Underlying Epileptiform Activity

OBJECTIVE

The phenomenon of postictal generalized EEG suppression state (PGES) - a period with suppressed activity following seizure termination and has been found to be associated with sudden unexpected death in epilepsy - remains poorly understood. This article aims to examine the how the balance of excitation and inhibition (E/I balance) affect the dynamics of seizure and PGES.

METHODS

A network of 1000 Izhikevich model neurons was developed and only the strengths of synaptic connections were adjusted to recreate the dynamics observed in recordings of seizure and PGES from human patients.

RESULTS

A rapid rise followed by a slow decay of dominant frequency was observed in iEEG recordings of ictal periods and reproduced in the simulated local field potential by changing the E/I balance of the model network. The rate of this dominant frequency evolution was quantified by a single measure, β, which was found to have a significant rank correlation with the duration of PGES in iEEG data and the rate of E/I balance shift in the model. Significance and Conclusion: (i) highlighting the importance of E/I balance in the dynamics of seizure and PGES; (ii) suggesting the measure, β, as a marker for PGES and the shift in E/I balance as a neural correlate for this marker.

Classification of Scalp EEG States Prior to Clinical Seizure Onset

OBJECTIVE

To investigate the feasibility of improving the performance of an EEG-based multistate classifier (MSC) previously proposed by our group.

RESULTS

Using the random forest (RF) classifiers on the previously reported dataset of patients, but with three improvements to classification logic, the specificity of our alarm algorithm improves from 82.4% to 92.0%, and sensitivity from 87.9% to 95.2%.

DISCUSSION

The MSC could be a useful approach for seizure-monitoring both in the clinic and at home.

METHODS

Three improvements to the MSC are described. Firstly, an additional check using RF outputs is made prior to alarm to confirm increasing probability of a seizure onset state. Secondly, a post-alarm detection horizon that accounts for the seizure state duration is implemented. Thirdly, the alarm decision window is kept constant.

The Application of Machine Learning Techniques in Clinical Drug Therapy

INTRODUCTION

The development of a novel drug is an extremely complicated process that includes the target identification, design and manufacture, and proper therapy of the novel drug, as well as drug dose selection, drug efficacy evaluation, and adverse drug reaction control. Due to the limited resources, high costs, long duration, and low hit-to-lead ratio in the development of pharmacogenetics and computer technology, machine learning techniques have assisted novel drug development and have gradually received more attention by researchers.

METHODS

According to current research, machine learning techniques are widely applied in the process of the discovery of new drugs and novel drug targets, the decision surrounding proper therapy and drug dose, and the prediction of drug efficacy and adverse drug reactions.

RESULTS AND CONCLUSION

In this article, we discussed the history, workflow, and advantages and disadvantages of machine learning techniques in the processes mentioned above. Although the advantages of machine learning techniques are fairly obvious, the application of machine learning techniques is currently limited. With further research, the application of machine techniques in drug development could be much more widespread and could potentially be one of the major methods used in drug development.

Prediction of antiepileptic drug treatment outcomes of patients with newly diagnosed epilepsy by machine learning

OBJECTIVE

The objective of this study was to build a supervised machine learning-based classifier, which can accurately predict the outcomes of antiepileptic drug (AED) treatment of patients with newly diagnosed epilepsy.

METHODS

We collected information from 287 patients with newly diagnosed epilepsy between 2009 and 2017 at the Second Affiliated Hospital of Zhejiang University. Patients were prospectively followed up for at least 3 years. A number of features, including demographic features, medical history, and auxiliary examinations (electroencephalogram [EEG] and magnetic resonance imaging [MRI]) are selected to distinguish patients with different remission outcomes. Seizure outcomes classified as remission and never remission. In addition, remission is further divided into early remission and late remission. Five classical machine learning algorithms, i.e., Decision Tree, Random Forest, Support Vector Machine, XGBoost, and Logistic Regression, are selected and trained by our dataset to get classification models.

RESULTS

Our study shows that 1) compared with the other four algorithms, the XGBoost algorithm based machine learning model achieves the best prediction performance of the AED treatment outcomes between remission and never remission patients with an F1 score of 0.947 and an area under the curve (AUC) value of 0.979; 2) The best discriminative factor for remission and never remission patients is higher number of seizures before treatment (>3); 3) XGBoost-based machine learning model also offers the best prediction between early remission and later remission patients, with an F1 score of 0.836 and an AUC value of 0.918; 4) multiple seizure type has the highest dependence to the categories of early and late remission patients.

SIGNIFICANCES

Our XGBoost-based machine learning classifier accurately predicts the most probable AED treatment outcome of a patient after he/she finishes all the standard examinations for the epilepsy disease. The classifier's prediction result could help disease guide counseling and eventually improve treatment strategies.

Big Brain Data: On the Responsible Use of Brain Data from Clinical and Consumer-Directed Neurotechnological Devices

The focus of this paper are the ethical, legal and social challenges for ensuring the responsible use of “big brain data”—the recording, collection and analysis of individuals’ brain data on a large scale with clinical and consumer-directed neurotechnological devices. First, I highlight the benefits of big data and machine learning analytics in neuroscience for basic and translational research. Then, I describe some of the technological, social and psychological barriers for securing brain data from unwarranted access. In this context, I then examine ways in which safeguards at the hardware and software level, as well as increasing “data literacy” in society, may enhance the security of neurotechnological devices and protect the privacy of personal brain data. Regarding ethical and legal ramifications of big brain data, I first discuss effects on the autonomy, the sense of agency and authenticity, as well as the self that may result from the interaction between users and intelligent, particularly closed-loop, neurotechnological devices. I then discuss the impact of the “datafication” in basic and clinical neuroscience research on the just distribution of resources and access to these transformative technologies. In the legal realm, I examine possible legal consequences that arises from the increasing abilities to decode brain states and their corresponding subjective phenomenological experiences on the hitherto inaccessible privacy of these information. Finally, I discuss the implications of big brain data for national and international regulatory policies and models of good data governance.

Can a collaborative healthcare network improve the care of people with epilepsy?

New opportunities are now available to improve care in ways not possible previously. Information contained in electronic medical records can now be shared without identifying patients. With network collaboration, large numbers of medical records can be searched to identify patients most like the one whose complex medical situation challenges the physician. The clinical effectiveness of different treatment strategies can be assessed rapidly to help the clinician decide on the best treatment for this patient. Other capabilities from different components of the network can prompt the recognition of what is the best available option and encourage the sharing of information about programs and electronic tools. Difficulties related to privacy, harmonization, integration, and costs are expected, but these are currently being addressed successfully by groups of organizations led by those who recognize the benefits.

Predicting Presynaptic and Postsynaptic Neurotoxins by Developing Feature Selection Technique

Presynaptic and postsynaptic neurotoxins are proteins which act at the presynaptic and postsynaptic membrane. Correctly predicting presynaptic and postsynaptic neurotoxins will provide important clues for drug-target discovery and drug design. In this study, we developed a theoretical method to discriminate presynaptic neurotoxins from postsynaptic neurotoxins. A strict and objective benchmark dataset was constructed to train and test our proposed model. The dipeptide composition was used to formulate neurotoxin samples. The analysis of variance (ANOVA) was proposed to find out the optimal feature set which can produce the maximum accuracy. In the jackknife cross-validation test, the overall accuracy of 94.9% was achieved. We believe that the proposed model will provide important information to study neurotoxins.