Competencies for Repetitive Transcranial Magnetic Stimulation in Postgraduate Medical Education: Expert Consensus Using a Modified Delphi Process.

BACKGROUND: Repetitive transcranial magnetic stimulation (rTMS) is recommended in Canadian guidelines as a first-line treatment for major depressive disorder. With the shift towards competency-based medical education, it remains unclear how to determine when a resident is considered competent in applying knowledge of rTMS to patient care. Given inconsistencies between postgraduate training programmes with regards to training requirements, defining competencies will improve the standard of care in rTMS delivery. OBJECTIVE: The goal of this study was to develop competencies for rTMS that can be implemented into a competency-based training curriculum in postgraduate training programmes. METHODS: A working group drafted competencies for postgraduate psychiatry trainees. Fourteen rTMS experts from across Canada were invited to participate in the modified Delphi process. RESULTS: Ten experts participated in all three rounds of the modified Delphi process. A total of 20 items reached a consensus. There was improvement in the Cronbach's alpha over the rounds of modified Delphi process (Cronbach's alpha increased from 0.554 to 0.824) suggesting improvement in internal consistency. The intraclass correlation coefficient (ICC) increased from 0.543 to 0.805 suggesting improved interrater agreement. CONCLUSIONS: This modified Delphi process resulted in expert consensus on competencies to be acquired during postgraduate medical education programmes where a learner is training to become competent as a consultant and/or practitioner in rTMS treatment. This is a field that still requires development, and it is expected that as more evidence emerges the competencies will be further refined. These results will help the development of other curricula in interventional psychiatry.

Naturalistic Study on the Effects of Electroconvulsive Therapy (ECT) on Depressive Symptoms.

OBJECTIVE: The effectiveness of ECT under naturalistic conditions has not been well-studied. The current study aimed to 1) characterize a naturalistic sample of ECT patients; and 2) examine the long-term outcomes of ECT on depressive symptoms (Beck Depression Inventory-II; BDI-II) and functional disability symptoms (WHO Disability Assessment Schedule 2.0) in this sample. METHODS: Participants were adults who received ECT for a major depressive episode at an ambulatory ECT clinic between September 2010 and November 2020. Clinical and cognitive assessments were completed at baseline (n = 100), mid-ECT (n = 94), 2-4 weeks post-ECT (n = 64), 6-months post-ECT (n = 34), and 12-months post-ECT (n = 19). RESULTS: At baseline, participants had severe levels of depressive symptoms (BDI-II: M = 41.0, SD = 9.4), and 62.9% screened positive for multiple psychiatric diagnoses on the MINI International Neuropsychiatric Interview. Depressive symptoms (F(4,49.1) = 49.92, P < 0.001) and disability symptoms (F(3,40.72) = 12.30, P < 0.001) improved significantly following ECT, and this was maintained at 12-months follow-up. Improvement in depressive symptoms trended towards significantly predicting reduction in disability symptoms from baseline to post-ECT, (F(1,56) = 3.67, P = 0.061). Although our clinical remission rate of 27% (BDI-II score ≤ 13 and ≥ 50% improvement) and overall response rate of 41.3% (≥50% improvement in BDI-II score) were lower than the rates reported in the extant RCT and community ECT literature, 36% of those treated with ECT were lost to follow-up and did not complete post-ECT rating scales. At baseline, remitters had significantly fewer psychiatric comorbidities, lower BDI-II scores, and lower disability symptoms than non-responders (P < 0.05). CONCLUSIONS: Participants were severely symptomatic and clinically complex. ECT was effective at reducing depressive symptoms and functional disability in this heterogeneous sample. Although a large amount of missing data may have distorted our calculated response/remission rates, it is also likely that clinical heterogeneity and severity contribute to lower-than-expected remission and response rates to ECT.

Using deep learning and pretreatment EEG to predict response to sertraline, bupropion, and placebo.

OBJECTIVE: Predicting an individual's response to antidepressant medication remains one of the most challenging tasks in the treatment of major depressive disorder (MDD). Our objective was to use the large EMBARC study database to develop an electroencephalography (EEG)-based method to predict response to antidepressant treatment. METHODS: Pre-treatment EEG data were collected from study participants treated with either sertraline (N = 105), placebo (N = 119), or bupropion (N = 35). After preprocessing, the robust exact low-resolution electromagnetic tomography (ReLORETA) brain source localization method was used to reconstruct the source signals in 54 brain regions. Connectivity between regions was determined using symbolic transfer entropy (STE). A convolutional neural network (CNN) classified participants as responders or non-responders to each treatment. RESULTS: Classification accuracy was 91.0%, 95.4%, and 86.8% for sertraline, placebo, and bupropion, respectively. The most highly predictive features were connectivity between i) the anterior cingulate cortex and superior parietal lobule (alpha frequency), ii) the anterior cingulate cortex and orbitofrontal area (beta frequency), and iii) the orbitofrontal area and anterior cingulate cortex (gamma frequency). CONCLUSION: CNN analysis of EEG connectivity may accurately predict response to sertraline, bupropion, and placebo. SIGNIFICANCE: The suggested method may offer clinicians an accessible and cost-effective tool for speedy treatment and helps pharmaceutical firms to test new antidepressants efficiently.

Diagnostic deep learning algorithms that use resting EEG to distinguish major depressive disorder, bipolar disorder, and schizophrenia from each other and from healthy volunteers.

BACKGROUND: Mood disorders and schizophrenia affect millions worldwide. Currently, diagnosis is primarily determined by reported symptomatology. As symptoms may overlap, misdiagnosis is common, potentially leading to ineffective or destabilizing treatment. Diagnostic biomarkers could significantly improve clinical care by reducing dependence on symptomatic presentation. METHODS: We used deep learning analysis (DLA) of resting electroencephalograph (EEG) to differentiate healthy control (HC) subjects (N = 239), from those with major depressive disorder (MDD) (N = 105), MDD-atypical (MDD-A) (N = 27), MDD-psychotic (MDD-P) (N = 35), bipolar disorder-depressed episode (BD-DE) (N = 71), BD-manic episode (BD-ME) (N = 49), and schizophrenia (SCZ) (N = 122) and also differentiate subjects with mental disorders on a pair-wise basis. DSM-III-R diagnoses were determined and supplemented by computerized Quick Diagnostic Interview Schedule. After EEG preprocessing, robust exact low-resolution electromagnetic tomography (ReLORETA) computed EEG sources for 82 brain regions. 20 % of all subjects were then set aside for independent testing. Feature selection methods were then used for the remaining subjects to identify brain source regions that are discriminating between diagnostic categories. RESULTS: Pair-wise classification accuracies between 90 % and 100 % were obtained using independent test subjects whose data were not used for training purposes. The most frequently selected features across various pairs are in the postcentral, supramarginal, and fusiform gyri, the hypothalamus, and the left cuneus. Brain sites discriminating SCZ from HC were mainly in the left hemisphere while those separating BD-ME from HC were on the right. LIMITATIONS: The use of superseded DSM-III-R diagnostic system and relatively small sample size in some disorder categories that may increase the risk of overestimation. CONCLUSIONS: DLA of EEG could be trained to autonomously classify psychiatric disorders with over 90 % accuracy compared to an expert clinical team using standardized operational methods.

A review of recent literature employing electroencephalographic techniques to study the pathophysiology, phenomenology, and treatment response of schizophrenia.

Clinical experience and research findings suggest that schizophrenia is a disorder comprised of multiple genetic and neurophysiological subtypes with differential response to treatment. Electroencephalography (EEG) is a non-invasive, inexpensive and useful tool for investigating the neurobiology of schizophrenia and its subtypes. EEG studies elucidate the neurophysiological mechanisms potentially underlying clinical symptomatology. In this review article recent advances in applying EEG to study pathophysiology, phenomenology, and treatment response in schizophrenia are discussed. Investigative strategies employed include: analyzing quantitative EEG (QEEG) spectral power during the resting state and cognitive tasks; applying machine learning methods to identify QEEG indicators of diagnosis and treatment response; and using the event-related brain potential (ERP) technique to characterize the neurocognitive processes underlying clinical symptoms. Studies attempting to validate potential EEG biomarkers of schizophrenia and its symptoms, which could be useful in assessing familial risk and treatment response, are also reviewed.

EEG Biomarkers to Predict Response to Sertraline and Placebo Treatment in Major Depressive Disorder.

OBJECTIVE: Major depressive disorder (MDD) is a persistent psychiatric condition, and the leading cause of disability, affecting up to 5% of the population worldwide. Antidepressant medications (ADMs) are often the first-line treatment for MDD, but it may take the clinician months of "trial and error" to find an effective ADM for a particular patient. Therefore, identification of predictive biomarkers that can be used to accurately determine the effectiveness of a specific treatment for an individual patient is extremely valuable. METHOD: Using resting EEG data, we develop a machine learning algorithm (MLA) that searches for connectivity patterns within an individual's EEG signal that are predictive of the probability of responding to the antidepressant Sertraline or Placebo. The MLA has two steps: 1) Directed phase lag index (DPLI), a measure of phase synchronization between brain regions, that is not sensitive to volume conduction is applied to resting-state EEG data, 2) the resulting DPLI matrix is searched for a pattern set of features that can be used to successfully predict the response to Sertraline or Placebo. RESULTS: Our MLA predicted response to Sertraline (N = 105) or Placebo (N = 119) with more than 80% accuracy. CONCLUSION: Our findings suggest that feature patterns selected from a DPLI matrix may be predictive of response to Sertraline and to Placebo. SIGNIFICANCE: The proposed MLA may provide an inexpensive, non-invasive, and readily available tool that clinicians may use to enhance treatment effectiveness, accelerate time to recovery, reduce personal suffering, and decrease treatment costs.

Repetitive transcranial magnetic stimulation for treatment of medication-resistant depression in older adults: a case series.

UNLABELLED: The antidepressant effects of repetitive transcranial magnetic stimulation (rTMS) are well documented, but studies to date have produced heterogeneous results in late-life depression. OBJECTIVE: To address this matter, we evaluated the efficacy of both high- and low-frequency rTMS delivered to the prefrontal cortex of older adults with treatment-resistant major depression. METHODS: Forty-nine older adults (69 +/- 6.7 years) with treatment-refractory major depressive disorders underwent a series of rTMS treatments as an adjuvant to pharmacotherapy. Patients received high-frequency rTMS delivered to the left dorsolateral prefrontal cortex, low-frequency stimulation to the right dorsolateral prefrontal cortex, or a combination thereof, at 80-110% of the motor threshold. RESULTS: There was a modest, but statistically significant, mean reduction (24.7%) in Hamilton Depression Rating Scale (HDRS) scores from baseline to the end of treatment. Nine patients were classified as responders (50% HDRS reduction), and 4 patients reached remission status (final HDRS score <8). Similar improvements in HDRS scores were observed for high- and low-frequency rTMS. Treatment was generally well tolerated, and no serious adverse effects were reported. CONCLUSIONS: The findings support the contention that in older adults with treatment-refractory depression, rTMS can be an effective treatment alternative for some patients.

Wavelet-Based Muscle Artefact Noise Reduction for Short Latency rTMS Evoked Potentials.

This paper presents a new method of reducing the noise in the EEG response signal recorded during repetitive transcranial magnetic stimulation (rTMS). This noise is principally composed of the residual stimulus artefact and millivolt amplitude compound muscle action potentials (CMAP) recorded from the scalp muscles and precludes analysis of the cortical evoked potentials, especially during the first 20-ms post stimulus. The proposed method uses the wavelet transform with a fourth-order Daubechies mother wavelet and a novel coefficient reduction algorithm based on cortical amplitude thresholds. Four other mother wavelets as well as digital filtering have been tested, and the Coiflets 2 and 3 also found to be effective with Coiflet 3 results marginally better than Daubechies 4. The approach has been tested using data recorded from 16 normal subjects during a study of cortical sensitivity to rTMS at different cortical locations using stimulation amplitudes, frequencies, and sites typically used in clinical practice to treat major depressive disorder.

A machine learning approach using auditory odd-ball responses to investigate the effect of Clozapine therapy.

OBJECTIVE: To develop a machine learning (ML) methodology based on features extracted from odd-ball auditory evoked potentials to identify neurophysiologic changes induced by Clozapine (CLZ) treatment in responding schizophrenic (SCZ) subjects. This objective is of particular interest because CLZ, though a potentially dangerous drug, can be uniquely effective for otherwise medication-resistant SCZ subjects. We wish to determine whether ML methods can be used to identify a set of EEG-based discriminating features that can simultaneously (1) distinguish all the SCZ subjects before treatment (BT) from healthy volunteer (HV) subjects, (2) distinguish EEGs collected before CLZ treatment (BT) vs. those collected after treatment (AT) for those subjects most responsive to CLZ, (3) discriminate least responsive subjects from HV AT, and (4) no longer discriminate most responsive subjects from HVs AT. If a set of EEG-derived features satisfy these four conditions, then it may be concluded that these features normalize in responsive subjects as a result of CLZ treatment, and therefore potentially provide insight into the functioning of the drug on the SCZ brain. METHODS: Odd-ball auditory evoked potentials of 66 HVs and 47 SCZ adults both BT and AT with CLZ were derived from EEG recordings. Treatment outcome, after at least one year follow-up, was assessed through clinical rating scores assigned by an experienced clinician, blind to EEG results. Using a criterion of at least 35% improvement after CLZ treatment, subjects were divided into "most-responsive" (MR) and "least-responsive" (LR) groups. As a first step, a brain source localization (BSL) procedure was employed on the EEG signals to extract source waveforms from specified brain regions. ML methods were then applied to these source waveform signals to determine whether a set of features satisfying the four conditions outlined above could be discovered. RESULTS: A set of cross-power spectral density (CPSD) features meeting these criteria was identified. These CPSD features, consisting of a combination of brain regional source activity and connectivity measures, significantly overlap with the default mode network (DMN). All decrease with CLZ treatment in responding SCZs. CONCLUSIONS: A set of EEG-derived discriminating features which normalize as a result of CLZ treatment was identified. These discriminating features define a network that shares significant commonality with the DMN. Our findings are consistent with those of previous literature, which suggest that regions of the DMN are hyperactive and hyperconnected in SCZ subjects. Our study shows that these discriminating features decrease after treatment, consistent with portions of the DMN normalizing with CLZ therapy in responsive subjects. SIGNIFICANCE: Machine learning is proposed as a potentially powerful tool for analysis of the effect of medication on psychiatric illness. If replicated, the proposed approach could be used to gain some improved understanding of the effect of neuroleptic medications in treating psychotic illness. These results may also be useful in the development of new pharmaceuticals, since a new drug which induces changes in brain electrophysiology similar to those seen after CLZ could also have powerful antipsychotic properties.

Effects of electroconvulsive therapy on cognitive functioning in patients with depression: protocol for a systematic review and meta-analysis.

INTRODUCTION: Depression is the leading cause of disability worldwide, affecting approximately 350 million people. Evidence indicates that only 60-70% of persons with major depressive disorder who tolerate antidepressants respond to first-line drug treatment; the remainder become treatment resistant. Electroconvulsive therapy (ECT) is considered an effective therapy in persons with treatment-resistant depression. The use of ECT is controversial due to concerns about temporary cognitive impairment in the acute post-treatment period. We will conduct a meta-analysis to examine the effects of ECT on cognition in persons with depression. METHODS: This systematic review and meta-analysis has been registered with PROSPERO (registration number: CRD42014009100). We developed our methods following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. We are searching MEDLINE, PsychINFO, EMBASE, CINAHL and Cochrane from the date of database inception to the end of October 2014. We are also searching the reference lists of published reviews and evidence reports for additional citations. Comparative studies (randomised controlled trials, cohort and case-control) published in English will be included in the meta-analysis. Three clinical neuropsychologists will group the cognitive tests in each included article into a set of mutually exclusive cognitive subdomains. The risk of bias of randomised controlled trials will be assessed using the Jadad scale. We will supplement the Jadad scale with additional questions based on the Cochrane risk of bias tool. The risk of bias of cohort and case-control studies will be assessed using the Newcastle-Ottawa Scale. We will employ the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) to assess the strength of evidence. STATISTICAL ANALYSIS: Separate meta-analyses will be conducted for each ECT treatment modality and cognitive subdomain using Comprehensive Meta-Analysis V.2.0.

The effects of pulse configuration on magnetic stimulation.

A study is presented in which the authors have examined the effects of pulse configuration, stimulation intensity, and coil current direction during magnetic stimulation. Using figure-8 and circular coils, the median nerve was stimulated at the cubital fossa and at the wrist of 10 healthy volunteers, and the response amplitude and site of stimulation were determined. The key findings of this study are in agreement with other researchers' findings and confirm that biphasic stimulating pulses produce significantly higher M-wave amplitudes than monophasic stimulating pulses for the same stimulus intensity. Mean response amplitudes for biphasic stimuli applied by both coils at the elbow and wrist are consistently higher for the normal current direction. Mean response amplitudes for monophasic pulses are almost always higher for reversed currents. The site for effective stimulation (the position of the virtual cathode) cannot be defined within a fixed distance from the center of the coil (3 to 4 cm), as has been suggested by other researchers, but was found to vary depending on the coil current amplitude and direction as well as the degree of inhomogeneity of the tissues surrounding the nerve. There is a statistically significant relationship between virtual cathode shift and stimulus intensity for biphasic and monophasic pulses. Reversing the coil current direction has no statistically significant effect on the virtual cathode position. Virtual cathode shifts can be measured for biphasic and monophasic stimulations using a figure-8 coil at the wrist and the elbow. However, such a shift is difficult to determine with a circular coil.

Minimum variance brain source localization for short data sequences.

In the electroencephalogram (EEG) or magnetoencephalogram (MEG) context, brain source localization methods that rely on estimating second-order statistics often fail when the number of samples of the recorded data sequences is small in comparison to the number of electrodes. This condition is particularly relevant when measuring evoked potentials. Due to the correlated background EEG/MEG signal, an adaptive approach to localization is desirable. Previous work has addressed these issues by reducing the adaptive degrees of freedom (DoFs). This reduction results in decreased resolution and accuracy of the estimated source configuration. This paper develops and tests a new multistage adaptive processing technique based on the minimum variance beamformer for brain source localization that has been previously used in the radar statistical signal processing context. This processing, referred to as the fast fully adaptive (FFA) approach, can significantly reduce the required sample support, while still preserving all available DoFs. To demonstrate the performance of the FFA approach in the limited data scenario, simulation and experimental results are compared with two previous beamforming approaches; i.e., the fully adaptive minimum variance beamforming method and the beamspace beamforming method. Both simulation and experimental results demonstrate that the FFA method can localize all types of brain activity more accurately than the other approaches with limited data.

A machine learning approach using EEG data to predict response to SSRI treatment for major depressive disorder.

OBJECTIVE: The problem of identifying, in advance, the most effective treatment agent for various psychiatric conditions remains an elusive goal. To address this challenge, we investigate the performance of the proposed machine learning (ML) methodology (based on the pre-treatment electroencephalogram (EEG)) for prediction of response to treatment with a selective serotonin reuptake inhibitor (SSRI) medication in subjects suffering from major depressive disorder (MDD). METHODS: A relatively small number of most discriminating features are selected from a large group of candidate features extracted from the subject's pre-treatment EEG, using a machine learning procedure for feature selection. The selected features are fed into a classifier, which was realized as a mixture of factor analysis (MFA) model, whose output is the predicted response in the form of a likelihood value. This likelihood indicates the extent to which the subject belongs to the responder vs. non-responder classes. The overall method was evaluated using a "leave-n-out" randomized permutation cross-validation procedure. RESULTS: A list of discriminating EEG biomarkers (features) was found. The specificity of the proposed method is 80.9% while sensitivity is 94.9%, for an overall prediction accuracy of 87.9%. There is a 98.76% confidence that the estimated prediction rate is within the interval [75%, 100%]. CONCLUSIONS: These results indicate that the proposed ML method holds considerable promise in predicting the efficacy of SSRI antidepressant therapy for MDD, based on a simple and cost-effective pre-treatment EEG. SIGNIFICANCE: The proposed approach offers the potential to improve the treatment of major depression and to reduce health care costs.

Application of wavelet based denoising techniques to rTMS evoked potentials.

This paper presents a new method of removing noise from the EEG response signal recorded during repetitive transcranial magnetic stimulation (rTMS). This noise is principally composed of the residual stimulus artifact and mV amplitude compound muscle action potentials recorded from the scalp muscles and precludes analysis of the cortical evoked potentials, especially during the first 15 ms post stimulus. The method uses the wavelet transform with a fourth order Daubechies mother wavelet and a novel coefficient reduction algorithm based on cortical amplitude thresholds. The approach has been tested and two methods of coefficient reduction compared using data recorded during a study of cortical sensitivity to rTMS at different scalp locations.

A machine learning approach using P300 responses to investigate effect of clozapine therapy.

Clozapine (CLZ) is uniquely effective as a treatment for medication resistant schizophrenia. Information regarding its mechanism of action may offer clues to the pathophysiology of the disease and to improved treatment. In this study we employ a machine learning (ML) analysis of P300 evoked potentials obtained from quantitative electroencephalography (QEEG) data to identify changes in the brain induced by CLZ treatment. We employ brain source localization (BSL) on the EEG signals to extract source waveforms from specified regions of the brain. A subset of 8 features is selected from a large set of candidate features (consisting of spectral coherences between all identified source waveforms at multiple frequencies) that discriminate (by means of a classifier) between the pre- and post-treatment data for the schizophrenics (SCZ) most responsive to CLZ. We show these same selected features also discriminate between pre-treatment most responsive SCZ and healthy volunteers (HV), but not after treatment. Of note, these same features discriminate the least responsive SCZ from HV both pre- and post-treatment. This analysis suggests that the net beneficial effects of CLZ in SCZ are reflected in a normalization of P300 brain-source generators.

Dorsolateral prefrontal cortex sensitivity to rTMS.

This paper presents the preliminary results of a study to determine dorsolateral prefrontal cortex sensitivity to rTMS stimulation presented at clinically accepted amplitudes, frequencies and locations. A specially developed EEG system with 10-20 electrode locations was used to record the short latency magnetically evoked potentials. Sixteen normal subjects were stimulated using 10 Hz for the left hemisphere and 1 Hz for the right. The evoked potentials recorded for left sided stimulation were significantly larger than for the right sided stimulation. Further, the stimulation energies, though within the range used clinically for the treatment of depression were insufficient to excite evoked potentials in several subjects.

Using pre-treatment electroencephalography data to predict response to transcranial magnetic stimulation therapy for major depression.

We investigate the use of machine learning methods based on the pre-treatment electroencephalograph (EEG) to predict response to repetitive transcranial magnetic stimulation (rTMS), which is a non-pharmacological form of therapy for treating major depressive disorder (MDD). The learning procedure involves the extraction of a large number of candidate features from EEG data, from which a very small subset of most statistically relevant features is selected for further processing. A statistical prediction model based on mixture of factor analysis (MFA) model is constructed from a training set that classifies the respective subject into responder and non-responder classes. A leave-2-out (L2O) cross-validation procedure is used to evaluate the prediction performance. This pilot study involves 27 subjects who received either left high-frequency (HF) active rTMS therapy or simultaneous left HF and right low-frequency active rTMS therapy. Our results indicate that it is possible to predict rTMS treatment efficacy of either treatment modality with a specificity of 83% and a sensitivity of 78%, for a combined accuracy of 80%.

Using pre-treatment EEG data to predict response to SSRI treatment for MDD.

The problem of identifying in advance the most effective treatment agent for various psychiatric conditions remains an elusive goal. To address this challenge, we propose a machine learning (ML) methodology to predict the response to a selective serotonin reuptake inhibitor (SSRI) medication in subjects suffering from major depressive disorder (MDD), using pre-treatment electroencephalograph (EEG) measurements. The proposed feature selection technique is a modification of the method of Peng et al [10] that is based on a Kullback-Leibler (KL) distance measure. The classifier was realized as a kernelized partial least squares regression procedure, whose output is the predicted response. A low-dimensional kernelized principal component representation of the feature space was used for the purposes of visualization and clustering analysis. The overall method was evaluated using an 11-fold nested cross-validation procedure for which over 85% average prediction performance is obtained. The results indicate that ML methods hold considerable promise in predicting the efficacy of SSRI antidepressant therapy for major depression.

Diagnosis of psychiatric disorders using EEG data and employing a statistical decision model.

An automated diagnosis procedure based on a statistical machine learning methodology using electroencephalograph (EEG) data is proposed for diagnosis of psychiatric illness. First, a large collection of candidate features, mostly consisting of various statistical quantities, are calculated from the subject's EEG. This large set of candidate features is then reduced into a much smaller set of most relevant features using a feature selection procedure. The selected features are then used to evaluate the class likelihoods, through the use of a mixture of factor analysis (MFA) statistical model [7]. In a training set of 207 subjects, including 64 subjects with major depressive disorder (MDD), 40 subjects with chronic schizophrenia, 12 subjects with bipolar depression and 91 normal or healthy subjects, the average correct diagnosis rate attained using the proposed method is over 85%, as determined by various cross-validation experiments. The promise is that, with further development, the proposed methodology could serve as a valuable adjunctive tool for the medical practitioner.

A pilot study to determine whether machine learning methodologies using pre-treatment electroencephalography can predict the symptomatic response to clozapine therapy.

OBJECTIVE: To investigate whether applying advanced machine learning (ML) methodologies to pre-treatment electroencephalography (EEG) data can predict the response to clozapine therapy in adult subjects suffering from chronic schizophrenia. METHODS: Pre-treatment EEG data are collected in 23+14 schizophrenic adults. Treatment outcome, after at least one year follow-up, is determined using clinical ratings by a trained clinician blind to EEG results. First, a feature selection scheme is employed to select a reduced subset of features extracted from the subjects' EEG that is most statistically relevant to our treatment-response prediction. These features are then entered into a classifier, which is realized in the form of a kernel partial least squares regression method that performs response prediction. Various scales, including the positive and negative syndrome scale (PANSS) are used as treatment-response indicators. RESULTS: We determined that a set of discriminating EEG features do exist. A low-dimensional representation of the feature space showed significant clustering into clozapine responder and non-responder groups. The minimum level of performance of the proposed prediction methodology, tested over a range of conditions using the leave-one-out cross-validation method using the original 23 subjects, with further testing in an independent sample of 14 subjects, was 85%. CONCLUSIONS: These findings indicate that analysis of pre-treatment EEG data can predict the clinical response to clozapine in treatment resistant schizophrenia. SIGNIFICANCE: If replicated in a larger population, this novel approach to EEG analysis may assist the clinician in determining treatment-efficacy.