Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery.
Ontology highlight
ABSTRACT:
SUBMITTER: Armananzas R
PROVIDER: S-EPMC3640010 | biostudies-literature | 2013
REPOSITORIES: biostudies-literature
Publications
Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery.
Armañanzas Rubén R Alonso-Nanclares Lidia L Defelipe-Oroquieta Jesús J Kastanauskaite Asta A de Sola Rafael G RG Defelipe Javier J Bielza Concha C Larrañaga Pedro P
PloS one 20130430 4
Epilepsy surgery is effective in reducing both the number and frequency of seizures, particularly in temporal lobe epilepsy (TLE). Nevertheless, a significant proportion of these patients continue suffering seizures after surgery. Here we used a machine learning approach to predict the outcome of epilepsy surgery based on supervised classification data mining taking into account not only the common clinical variables, but also pathological and neuropsychological evaluations. We have generated mo ...[more]
Similar Datasets
Project description:There is controversy about relative contributions of ictal scalp video EEG recording (vEEG), routine scalp outpatient interictal EEG (rEEG), intracranial EEG (iEEG) and MRI for predicting seizure-free outcomes after temporal lobectomy. We reviewed NIH experience to determine contributions at specific time points as well as long-term predictive value of standard pre-surgical investigations.Raw data was obtained via retrospective chart review of 151 patients. After exclusions, 118 remained (median 5 years follow-up). MRI-proven mesial temporal sclerosis (MTSr) was considered a separate category for analysis. Logistic regression estimated odds ratios at 6-months, 1-year, and 2 years; proportional hazard models estimated long-term comparisons. Subset analysis of the proportional hazard model was performed including only patients with commonly encountered situations in each of the modalities, to maximize statistical inference.Any MRI finding, MRI proven MTS, rEEG, vEEG and iEEG did not predict two-year seizure-free outcome. MTSr was predictive at six months (OR=2.894, p=0. 0466), as were MRI and MTSr at one year (OR=10.4231, p=0. 0144 and OR=3.576, p=0. 0091). Correcting for rEEG and MRI, vEEG failed to predict outcome at 6 months, 1year and 2 years. Proportional hazard analysis including all available follow-up failed to achieve significance for any modality. In the subset analysis of 83 patients with commonly encountered results, vEEG modestly predicted long-term seizure-free outcomes with a proportional hazard ratio of 1.936 (p=0.0304).In this study, presurgical tools did not provide unambiguous long-term outcome predictions. Multicenter prospective studies are needed to determine optimal presurgical epilepsy evaluation.
| S-EPMC5086266 | biostudies-other
Project description:ObjectiveWe sought to augment the presurgical workup of medically refractory temporal lobe epilepsy by creating a supervised machine learning technique that uses diffusion-weighted imaging to classify patient-specific seizure onset laterality and surgical outcome.Methods151 subjects were included in this analysis: 62 patients (aged 18-68 years, 36 women) and 89 healthy controls (aged 18-71 years, 47 women). We created a supervised machine learning technique that uses diffusion-weighted metrics to classify subject groups. Specifically, we sought to classify patients versus healthy controls, unilateral versus bilateral temporal lobe epilepsy, left versus right temporal lobe epilepsy and seizure-free versus not seizure-free surgical outcome. We then reduced the dimensionality of derived features with community detection for ease of interpretation.ResultsWe classified the subject groups in withheld testing data sets with a cross-fold average testing areas under the receiver operating characteristic curve of 0.745 for patients versus healthy controls, 1.000 for unilateral versus bilateral seizure onset, 0.662 for left versus right seizure onset, 0.800 for left-sided seizure-free vsersu not seizure-free surgical outcome and 0.775 for right-sided seizure-free versus not seizure-free surgical outcome.ConclusionsThis technique classifies important clinical decisions in the presurgical workup of temporal lobe epilepsy by generating discerning white-matter features. We believe that this work augments existing network connectivity findings in the field by further elucidating important white-matter pathology in temporal lobe epilepsy. We hope that this work contributes to recent efforts aimed at using diffusion imaging as an augmentation to the presurgical workup of this devastating neurological disorder.
| S-EPMC9149039 | biostudies-literature
Project description:Mesial temporal lobe epilepsy is the most common type of focal epilepsy and in its course often becomes refractory to anticonvulsant pharmacotherapy. A resection of the mesial temporal lobe structures is a promising option in these cases. However, approximately 30% of all patients remain with persistent seizures after surgery. In other words, reliable criteria for patients' outcome prediction are absent. To address this limitation, we investigated pre-surgical brain morphology of patients with unilateral left mesial temporal lobe epilepsy who underwent a selective amygdalohippocampectomy. Using support vector classification, we aimed to predict the post-surgical seizure outcome of each patient based on the pre-surgical T1-weighted structural brain images. Due to morphological gender differences and the evidence that men and women differ in onset, prevalence and symptomology in most neurological diseases, we investigated male and female patients separately. Thus, we benefitted from the capability to validate the reliability of our method in two independent samples. Notably, we were able to accurately predict the individual patients' outcome in the male (94% balanced accuracy) as well as in the female (96% balanced accuracy) group. In the male cohort relatively larger white matter volumes in the favorable as compared to the non-favorable outcome group were identified bilaterally in the cingulum bundle, fronto-occipital fasciculus and both caudate nuclei, whereas the left inferior longitudinal fasciculus showed relatively larger white matter volume in the non-favorable group. While relatively larger white matter volumes in the female cohort in the left inferior and right middle longitudinal fasciculus were associated with the favorable outcome, relatively larger white matter volumes in the non-favorable outcome group were identified bilaterally in the superior longitudinal fasciculi I and II. Here, we observed a clear lateralization and distinction of structures involved in the classification in men as compared to women with men exhibiting more alterations in the hemisphere contralateral to the seizure focus. In conclusion, individual post-surgical outcome predictions based on a single T1-weighted magnetic resonance image seem plausible and may thus support the routine pre-surgical workup of epilepsy patients.
| S-EPMC3778257 | biostudies-literature
Project description:BackgroundIt is common for patients diagnosed with medial temporal lobe epilepsy (TLE) to have extrahippocampal damage. However, it is unclear whether microstructural extrahippocampal abnormalities are consistent enough to enable classification using diffusion MRI imaging. Therefore, we implemented a support vector machine (SVM)-based method to predict TLE from three different imaging modalities: mean kurtosis (MK), mean diffusivity (MD), and fractional anisotropy (FA). While MD and FA can be calculated from traditional diffusion tensor imaging (DTI), MK requires diffusion kurtosis imaging (DKI).MethodsThirty-two TLE patients and 36 healthy controls underwent DKI imaging. To measure predictive capability, a fivefold cross-validation (CV) was repeated for 1000 iterations. An ensemble of SVM models, each with a different regularization value, was trained with the subject images in the training set, and had performance assessed on the test set. The different regularization values were determined using a Bayesian-based method.ResultsMean kurtosis achieved higher accuracy than both FA and MD on every iteration, and had far superior average accuracy: 0.82 (MK), 0.68 (FA), and 0.51 (MD). Finally, the MK voxels with the highest coefficients in the predictive models were distributed within the inferior medial aspect of the temporal lobes.ConclusionThese results corroborate our earlier publications which indicated that DKI shows more promise in identifying TLE-associated pathological features than DTI. Also, the locations of the contributory MK voxels were in areas with high fiber crossing and complex fiber anatomy. These traits result in non-Gaussian water diffusion, and hence render DTI less likely to detect abnormalities. If the location of consistent microstructural abnormalities can be better understood, then it may be possible in the future to identify the various phenotypes of TLE. This is important since treatment outcome varies dependent on type of TLE.
| S-EPMC5651385 | biostudies-literature
Project description:The National Institutes of Health-sponsored Epilepsy Connectome Project aims to characterize connectivity changes in temporal lobe epilepsy (TLE) patients. The magnetic resonance imaging protocol follows that used in the Human Connectome Project, and includes 20 min of resting-state functional magnetic resonance imaging acquired at 3T using 8-band multiband imaging. Glasser parcellation atlas was combined with the FreeSurfer subcortical regions to generate resting-state functional connectivity (RSFC), amplitude of low-frequency fluctuations (ALFFs), and fractional ALFF measures. Seven different frequency ranges such as Slow-5 (0.01-0.027 Hz) and Slow-4 (0.027-0.073 Hz) were selected to compute these measures. The goal was to train machine learning classification models to discriminate TLE patients from healthy controls, and to determine which combination of the resting state measure and frequency range produced the best classification model. The samples included age- and gender-matched groups of 60 TLE patients and 59 healthy controls. Three traditional machine learning models were trained: support vector machine, linear discriminant analysis, and naive Bayes classifier. The highest classification accuracy was obtained using RSFC measures in the Slow-4 + 5 band (0.01-0.073 Hz) as features. Leave-one-out cross-validation accuracies were ∼83%, with receiver operating characteristic area-under-the-curve reaching close to 90%. Increased connectivity from right area posterior 9-46v in TLE patients contributed to the high accuracies. With increased sample sizes in the near future, better machine learning models will be trained not only to aid the diagnosis of TLE, but also as a tool to understand this brain disorder.
| S-EPMC6484357 | biostudies-literature
Project description:Epilepsy is a neurological disorder in which the brain is transiently altered. Predicting outcomes in epilepsy is essential for providing feedback that can foster improved outcomes in the future. This study aimed to investigate whether applying spectral and temporal filters to resting-state electroencephalography (EEG) signals could improve the prediction of outcomes for patients taking antiseizure medication to treat temporal lobe epilepsy (TLE). We collected EEG data from a total of 46 patients (divided into a seizure-free group (SF, n = 22) and a non-seizure-free group (NSF, n = 24)) with TLE and retrospectively reviewed their clinical data. We segmented spectral and temporal ranges with various time-domain features (Hjorth parameters, statistical parameters, energy, zero-crossing rate, inter-channel correlation, inter-channel phase locking value and spectral information derived from Fourier transform, Stockwell transform, and wavelet transform) and compared their performance by applying an optimal frequency strategy, an optimal duration strategy, and a combination strategy. For all time-domain features, the optimal frequency and time combination strategy showed the highest performance in distinguishing SF patients from NSF patients (area under the curve (AUC) = 0.790 ± 0.159). Furthermore, optimal performance was achieved by utilizing a feature vector derived from statistical parameters within the 39- to 41-Hz frequency band with a window length of 210 s, as evidenced by an AUC of 0.748. By identifying the optimal parameters, we improved the performance of the prediction model. These parameters can serve as standard parameters for predicting outcomes based on resting-state EEG signals.
| S-EPMC10728218 | biostudies-literature
Project description:ObjectiveWe aimed to predict language deficits after epilepsy surgery. In addition to evaluating surgical factors examined previously, we determined the impact of the extent of functional magnetic resonance imaging (fMRI) activation that was resected on naming ability.MethodThirty-five adults (mean age 37.5 ± 10.9 years, 13 male) with temporal lobe epilepsy completed a preoperative fMRI auditory description decision task, which reliably activates frontal and temporal language networks. Patients underwent temporal lobe resections (20 left resection). The Boston Naming Test (BNT) was used to determine language functioning before and after surgery. Language dominance was determined for Broca and Wernicke area (WA) by calculating a laterality index following statistical parametric mapping processing. We used an innovative method to generate anatomic resection masks automatically from pre- and postoperative MRI tissue map comparison. This mask provided the following: (a) resection volume; (b) overlap between resection and preoperative activation; and (c) overlap between resection and WA. We examined postoperative language change predictors using stepwise linear regression. Predictors included parameters described above as well as age at seizure onset (ASO), preoperative BNT score, and resection side and its relationship to language dominance.ResultsSeven of 35 adults had significant naming decline (6 dominant-side resections). The final regression model predicted 38% of the naming score change variance (adjusted r2 = 0.28, P = 0.012). The percentage of top 10% fMRI activation resected (P = 0.017) was the most significant contributor. Other factors in the model included WA LI, ASO, volume of WA resected, and WA LI absolute value (extent of laterality).SignificanceResection of fMRI activation during a word-definition decision task is an important factor for postoperative change in naming ability, along with other previously reported predictors. Currently, many centers establish language dominance using fMRI. Our results suggest that the amount of the top 10% of language fMRI activation in the intended resection area provides additional predictive power and should be considered when planning surgical resection.
| S-EPMC6401285 | biostudies-literature
Project description:ObjectivesThe objective of this cohort study was to compare neuropsychological outcomes following left temporal lobe resection (TLR) in patients with epilepsy who had or had not undergone prior invasive monitoring.MethodsData were obtained from an institutional review board-approved, neuropsychology registry for patients who underwent epilepsy surgery at Cleveland Clinic between 1997 and 2013. A total of 176 patients (45 with and 131 without invasive EEG) met inclusion criteria. Primary outcome measures were verbal memory and language scores. Other cognitive outcomes were also examined. Outcomes were assessed using difference in scores from before to after surgery and by presence/absence of clinically meaningful decline using reliable change indices (RCIs). Effect of invasive EEG on cognitive outcomes was estimated using weighting and propensity score adjustment to account for differences in baseline characteristics. Linear and logistic regression models compared surgical groups on all cognitive outcomes.ResultsPatients with invasive monitoring showed greater declines in confrontation naming; however, when RCIs were used to assess clinically meaningful change, there was no significant treatment effect on naming performance. No difference in verbal memory was observed, regardless of how the outcome was measured. In secondary outcomes, patients with invasive monitoring showed greater declines in working memory, which were no longer apparent using RCIs to define change. There were no outcome differences on other cognitive measures.ConclusionsResults suggest that invasive EEG monitoring conducted prior to left TLR is not associated with greater cognitive morbidity than left TLR alone. This information is important when counseling patients regarding cognitive risks associated with this elective surgery.
| S-EPMC4631071 | biostudies-literature
Project description:Currently, approximately 60-70% of patients with unilateral temporal lobe epilepsy (TLE) remain seizure-free 3 years after surgery. The goal of this work was to develop a presurgical connectivity-based biomarker to identify those patients who will have an unfavorable seizure outcome 1-year postsurgery.Resting-state functional and diffusion-weighted 3T magnetic resonance imaging (MRI) was acquired from 22 unilateral (15 right, 7 left) patients with TLE and 35 healthy controls. A seizure propagation network was identified including ipsilateral (to seizure focus) and contralateral hippocampus, thalamus, and insula, with bilateral midcingulate and precuneus. Between each pair of regions, functional connectivity based on correlations of low frequency functional MRI signals, and structural connectivity based on streamline density of diffusion MRI data were computed and transformed to metrics related to healthy controls of the same age.A consistent connectivity pattern representing the network expected in patients with seizure-free outcome was identified using eight patients who were seizure-free at 1-year postsurgery. The hypothesis that increased similarity to the model would be associated with better seizure outcome was tested in 14 other patients (Engel class IA, seizure-free: n = 5; Engel class IB-II, favorable: n = 4; Engel class III-IV, unfavorable: n = 5) using two similarity metrics: Pearson correlation and Euclidean distance. The seizure-free connectivity model successfully separated all the patients with unfavorable outcome from the seizure-free and favorable outcome patients (p = 0.0005, two-tailed Fisher's exact test) through the combination of the two similarity metrics with 100% accuracy. No other clinical and demographic predictors were successful in this regard.This work introduces a methodologic framework to assess individual patients, and demonstrates the ability to use network connectivity as a potential clinical tool for epilepsy surgery outcome prediction after more comprehensive validation.
| S-EPMC5498250 | biostudies-literature
Project description:Brain age prediction based on machine learning has been applied to various neurological diseases to discover its clinical values. By this innovative approach, it has been reported that the patients with refractory epilepsy had premature brain aging. Of refractory epilepsy, right and left subtypes of mesial temporal lobe epilepsy (MTLE) are the most common forms and exhibit distinct patterns in white matter alterations. So far, it is unclear whether these two subtypes of MTLE would have difference in white matter aging due to distinct white matter alterations. To address this issue, a machine learning based brain age model using diffusion MRI data was established to investigate biological age of white matter tracts. All diffusion MRI datasets were obtained from the same 3-Tesla MRI scanner. To build the brain age prediction model, diffusion MRI datasets of 300 healthy participants were processed to extract age-relevant diffusion indices from 76 major white matter tracts. The extracted diffusion indices underwent Gaussian process regression to build the prediction model for white matter brain age. The model was validated in an independent testing set (N = 40) to ensure no overfitting of the model. The model was then applied to patients with right and left MTLE and matched controls (right MTLE: N = 17, left MTLE: N = 18, controls: N = 37), and predicted age difference (PAD) was obtained by calculating the difference between each individual's predicted brain age and chronological age. The higher PAD score indicated older brain age. The results showed that right MTLE exhibited older predicted brain age than the other two groups (PAD of right MTLE = 10.9 years [p < 0.05 against left MTLE; p < 0.001 against control]; PAD of left MTLE = 2.2 years [p > 0.1 against control]; PAD of controls = 0.82 years). Patients with right and left MTLE showed strong correlations of the PAD scores with age of onset and duration of illness, but both groups showed opposite directions of correlations. In right MTLE, positive correlation of PAD with seizure frequency was found, and the right uncinate fasciculus was the most attributable tract to the increase in PAD. In conclusion, the present study found that patients with right MTLE exhibited premature white matter brain aging and their PAD scores were correlated with seizure frequency. Therefore, PAD is a potentially useful indicator of white matter impairment and disease severity in patients with right MTLE.
| S-EPMC6978225 | biostudies-literature