Long-term detection of Parkinsonian tremor activity from subthalamic nucleus local field potentials

Improved detection of Parkinsonian resting tremor with feature engineering and Kalman filtering

OBJECTIVE

Accurate and reliable detection of tremor onset in Parkinson's disease (PD) is critical to the success of adaptive deep brain stimulation (aDBS) therapy. Here, we investigated the potential use of feature engineering and machine learning methods for more accurate detection of rest tremor in PD.

METHODS

We analyzed the local field potential (LFP) recordings from the subthalamic nucleus region in 12 patients with PD (16 recordings). To explore the optimal biomarkers and the best performing classifier, the performance of state-of-the-art machine learning (ML) algorithms and various features of the subthalamic LFPs were compared. We further used a Kalman filtering technique in feature domain to reduce the false positive rate.

RESULTS

The Hjorth complexity showed a higher correlation with tremor, compared to other features in our study. In addition, by optimal selection of a maximum of five features with a sequential feature selection method and using the gradient boosted decision trees as the classifier, the system could achieve an average F1 score of up to 88.7% and a detection lead of 0.52 s. The use of Kalman filtering in feature space significantly improved the specificity by 17.0% (p = 0.002), thereby potentially reducing the unnecessary power dissipation of the conventional DBS system.

CONCLUSION

The use of relevant features combined with Kalman filtering and machine learning improves the accuracy of tremor detection during rest.

SIGNIFICANCE

The proposed method offers a potential solution for efficient on-demand stimulation for PD tremor.

Parkinsonian Tremor Detection from Subthalamic Nucleus Local Field Potentials for Closed-Loop Deep Brain Stimulation

Deep Brain Stimulation (DBS) is a widely used therapy to ameliorate symptoms experienced by patients with Parkinson's Disease (PD). Conventional DBS is continuously ON even though PD symptoms fluctuate over time leading to undesirable side-effects and high energy requirements. This study investigates the use of a Iogistic regression-based classifier to identify periods when PD patients have rest tremor exploiting Local Field Potentials (LFPs) recorded with DBS electrodes implanted in the Subthalamic Nucleus in 7 PD patients (8 hemispheres). Analyzing 36.1 minutes of data with a 512 milliseconds non-overlapping window, the classification accuracy was well above chance-level for all patients, with Area Under the Curve (AUC) ranging from 0.67 to 0.93. The features with the most discriminative ability were, in descending order, power in the 31-45 Hz, 5-7 Hz, 21-30 Hz, 46-55 Hz, and 56-95 Hz frequency bands. These results suggest that using a machine learning-based classifier, such as the one proposed in this study, can form the basis for on-demand DBS therapy for PD tremor, with the potential to reduce side-effects and lower battery consumption.

Clinical neuroprosthetics: Today and tomorrow

Implantable neurostimulation devices provide a direct therapeutic link to the nervous system and can be considered brain-computer interfaces (BCI). Under this definition, BCI are not simply science fiction, they are part of existing neurosurgical practice. Clinical BCI are standard of care for historically difficult to treat neurological disorders. These systems target the central and peripheral nervous system and include Vagus Nerve Stimulation, Responsive Neurostimulation, and Deep Brain Stimulation. Recent advances in clinical BCI have focused on creating "closed-loop" systems. These systems rely on biomarker feedback and promise individualized therapy with optimal stimulation delivery and minimal side effects. Success of clinical BCI has paralleled research efforts to create BCI that restore upper extremity motor and sensory function to patients. Efforts to develop closed loop motor/sensory BCI is linked to the successes of today's clinical BCI.

A machine-learning approach to volitional control of a closed-loop deep brain stimulation system

OBJECTIVE

Deep brain stimulation (DBS) is a well-established treatment for essential tremor, but may not be an optimal therapy, as it is always on, regardless of symptoms. A closed-loop (CL) DBS, which uses a biosignal to determine when stimulation should be given, may be better. Cortical activity is a promising biosignal for use in a closed-loop system because it contains features that are correlated with pathological and normal movements. However, neural signals are different across individuals, making it difficult to create a 'one size fits all' closed-loop system.

APPROACH

We used machine learning to create a patient-specific, CL DBS system. In this system, binary classifiers are used to extract patient-specific features from cortical signals and determine when volitional, tremor-evoking movement is occurring to alter stimulation voltage in real time.

MAIN RESULTS

This system is able to deliver stimulation up to 87%-100% of the time that subjects are moving. Additionally, we show that the therapeutic effect of the system is at least as good as that of current, continuous-stimulation paradigms.

SIGNIFICANCE

These findings demonstrate the promise of CL DBS therapy and highlight the importance of using subject-specific models in these systems.

Basal ganglia, movement disorders and deep brain stimulation: advances made through non-human primate research

Studies in non-human primates (NHPs) have led to major advances in our understanding of the function of the basal ganglia and of the pathophysiologic mechanisms of hypokinetic movement disorders such as Parkinson's disease and hyperkinetic disorders such as chorea and dystonia. Since the brains of NHPs are anatomically very close to those of humans, disease states and the effects of medical and surgical approaches, such as deep brain stimulation (DBS), can be more faithfully modeled in NHPs than in other species. According to the current model of the basal ganglia circuitry, which was strongly influenced by studies in NHPs, the basal ganglia are viewed as components of segregated networks that emanate from specific cortical areas, traverse the basal ganglia, and ventral thalamus, and return to the frontal cortex. Based on the presumed functional domains of the different cortical areas involved, these networks are designated as 'motor', 'oculomotor', 'associative' and 'limbic' circuits. The functions of these networks are strongly modulated by the release of dopamine in the striatum. Striatal dopamine release alters the activity of striatal projection neurons which, in turn, influences the (inhibitory) basal ganglia output. In parkinsonism, the loss of striatal dopamine results in the emergence of oscillatory burst patterns of firing of basal ganglia output neurons, increased synchrony of the discharge of neighboring basal ganglia neurons, and an overall increase in basal ganglia output. The relevance of these findings is supported by the demonstration, in NHP models of parkinsonism, of the antiparkinsonian effects of inactivation of the motor circuit at the level of the subthalamic nucleus, one of the major components of the basal ganglia. This finding also contributed strongly to the revival of the use of surgical interventions to treat patients with Parkinson's disease. While ablative procedures were first used for this purpose, they have now been largely replaced by DBS of the subthalamic nucleus or internal pallidal segment. These procedures are not only effective in the treatment of parkinsonism, but also in the treatment of hyperkinetic conditions (such as chorea or dystonia) which result from pathophysiologic changes different from those underlying Parkinson's disease. Thus, these interventions probably do not counteract specific aspects of the pathophysiology of movement disorders, but non-specifically remove the influence of the different types of disruptive basal ganglia output from the relatively intact portions of the motor circuitry downstream from the basal ganglia. Knowledge gained from studies in NHPs remains critical for our understanding of the pathophysiology of movement disorders, of the effects of DBS on brain network activity, and the development of better treatments for patients with movement disorders and other neurologic or psychiatric conditions.

Closed-loop neuromodulation systems: next-generation treatments for psychiatric illness

Despite deep brain stimulation's positive early results in psychiatric disorders, well-designed clinical trials have yielded inconsistent clinical outcomes. One path to more reliable benefit is closed-loop therapy: stimulation that is automatically adjusted by a device or algorithm in response to changes in the patient's electrical brain activity. These interventions may provide more precise and patient-specific treatments. This article first introduces the available closed-loop neuromodulation platforms, which have shown clinical efficacy in epilepsy and strong early results in movement disorders. It discusses the strengths and limitations of these devices in the context of psychiatric illness. It then describes emerging technologies to address these limitations, including pre-clinical developments such as wireless deep neurostimulation and genetically targeted neuromodulation. Finally, ongoing challenges and limitations for closed-loop psychiatric brain stimulation development, most notably the difficulty of identifying meaningful biomarkers for titration, are discussed. This is considered in the recently-released Research Domain Criteria (RDoC) framework, and how neuromodulation and RDoC are jointly very well suited to address the problem of treatment-resistant illness is described.

Proceedings of the Fourth Annual Deep Brain Stimulation Think Tank: A Review of Emerging Issues and Technologies

This paper provides an overview of current progress in the technological advances and the use of deep brain stimulation (DBS) to treat neurological and neuropsychiatric disorders, as presented by participants of the Fourth Annual DBS Think Tank, which was convened in March 2016 in conjunction with the Center for Movement Disorders and Neurorestoration at the University of Florida, Gainesveille FL, USA. The Think Tank discussions first focused on policy and advocacy in DBS research and clinical practice, formation of registries, and issues involving the use of DBS in the treatment of Tourette Syndrome. Next, advances in the use of neuroimaging and electrochemical markers to enhance DBS specificity were addressed. Updates on ongoing use and developments of DBS for the treatment of Parkinson's disease, essential tremor, Alzheimer's disease, depression, post-traumatic stress disorder, obesity, addiction were presented, and progress toward innovation(s) in closed-loop applications were discussed. Each section of these proceedings provides updates and highlights of new information as presented at this year's international Think Tank, with a view toward current and near future advancement of the field.

Tremor Detection Using Parametric and Non-Parametric Spectral Estimation Methods: A Comparison with Clinical Assessment

In the clinic, tremor is diagnosed during a time-limited process in which patients are observed and the characteristics of tremor are visually assessed. For some tremor disorders, a more detailed analysis of these characteristics is needed. Accelerometry and electromyography can be used to obtain a better insight into tremor. Typically, routine clinical assessment of accelerometry and electromyography data involves visual inspection by clinicians and occasionally computational analysis to obtain objective characteristics of tremor. However, for some tremor disorders these characteristics may be different during daily activity. This variability in presentation between the clinic and daily life makes a differential diagnosis more difficult. A long-term recording of tremor by accelerometry and/or electromyography in the home environment could help to give a better insight into the tremor disorder. However, an evaluation of such recordings using routine clinical standards would take too much time. We evaluated a range of techniques that automatically detect tremor segments in accelerometer data, as accelerometer data is more easily obtained in the home environment than electromyography data. Time can be saved if clinicians only have to evaluate the tremor characteristics of segments that have been automatically detected in longer daily activity recordings. We tested four non-parametric methods and five parametric methods on clinical accelerometer data from 14 patients with different tremor disorders. The consensus between two clinicians regarding the presence or absence of tremor on 3943 segments of accelerometer data was employed as reference. The nine methods were tested against this reference to identify their optimal parameters. Non-parametric methods generally performed better than parametric methods on our dataset when optimal parameters were used. However, one parametric method, employing the high frequency content of the tremor bandwidth under consideration (High Freq) performed similarly to non-parametric methods, but had the highest recall values, suggesting that this method could be employed for automatic tremor detection.