Value-based neural representations predict social decision preferences.

Social decision-making is omnipresent in everyday life, carrying the potential for both positive and negative consequences for the decision-maker and those closest to them. While evidence suggests that decision-makers use value-based heuristics to guide choice behavior, very little is known about how decision-makers' representations of other agents influence social choice behavior. We used multivariate pattern expression analyses on fMRI data to understand how value-based processes shape neural representations of those affected by one's social decisions and whether value-based encoding is associated with social decision preferences. We found that stronger value-based encoding of a given close other (e.g. parent) relative to a second close other (e.g. friend) was associated with a greater propensity to favor the former during subsequent social decision-making. These results are the first to our knowledge to explicitly show that value-based processes affect decision behavior via representations of close others.

Maternal early life stress is associated with pro-inflammatory processes during pregnancy.

Early life stress (ELS) is common in the United States and worldwide, and contributes to the development of psychopathology in individuals with these experiences and their offspring. A growing body of research suggests that early life stress may contribute to adverse health partly through modulation of immune (and particularly inflammatory) responses. Therefore, increased maternal prenatal inflammation has been proposed as a mechanistic pathway by which the observed cross-generational effects of parental early life stress on child neuropsychiatric outcomes may be exerted. We examined associations between early life stress and molecular markers of inflammation (specifically pro-inflammatory gene expression and receptor-mediated transcription factor activity) and a commonly studied circulating marker of inflammation (C-Reactive Protein) in a diverse group of women in or near their third trimester of pregnancy, covarying for age, race/ethnicity, BMI, concurrent infection, concurrent perceived stress, and per capita household income. Mothers who experienced higher levels of early life stress had significantly increased pro-inflammatory (NF-κB) and decreased anti-viral (IRF) transcription factor activity. Transcripts that were up or down regulated in mothers with high ELS were preferentially derived from both CD16+ and CD16- monocytes. Early life stress was not associated with elevated CRP. Taken together, these findings provide preliminary evidence for an association between ELS and a pro-inflammatory transcriptional phenotype during pregnancy that may serve as a mechanistic pathway for cross-generational transmission of the effects of early life stress on mental and physical health.

Sensory processing challenges as a novel link between early caregiving experiences and mental health.

Early caregiving adversity (ECA) is associated with elevated psychological symptomatology. While neurobehavioral ECA research has focused on socioemotional and cognitive development, ECA may also increase risk for "low-level" sensory processing challenges. However, no prior work has compared how diverse ECA exposures differentially relate to sensory processing, or, critically, how this might influence psychological outcomes. We examined sensory processing challenges in 183 8-17-year-old youth with and without histories of institutional (orphanage) or foster caregiving, with a particular focus on sensory over-responsivity (SOR), a pattern of intensified responses to sensory stimuli that may negatively impact mental health. We further tested whether sensory processing challenges are linked to elevated internalizing and externalizing symptoms common in ECA-exposed youth. Relative to nonadopted comparison youth, both groups of ECA-exposed youth had elevated sensory processing challenges, including SOR, and also had heightened internalizing and externalizing symptoms. Additionally, we found significant indirect effects of ECA on internalizing and externalizing symptoms through both general sensory processing challenges and SOR, covarying for age and sex assigned at birth. These findings suggest multiple forms of ECA confer risk for sensory processing challenges that may contribute to mental health outcomes, and motivate continuing examination of these symptoms, with possible long-term implications for screening and treatment following ECA.

Revisiting the Neural Architecture of Adolescent Decision-Making: Univariate and Multivariate Evidence for System-Based Models.

Understanding adolescent decision-making is significant for informing basic models of neurodevelopment as well as for the domains of public health and criminal justice. System-based theories posit that adolescent decision-making is guided by activity amongst reward and control processes. While successful at explaining behavior, system-based theories have received inconsistent support at the neural level, perhaps because of methodological limitations. Here, we used two complementary approaches to overcome said limitations and rigorously evaluate system-based models. Using decision-level modeling of fMRI data from a risk-taking task in a sample of 2000+ decisions across 51 human adolescents (25 females, mean age = 15.00 years), we find support for system-based theories of decision-making. Neural activity in lateral prefrontal cortex and a multivariate pattern of cognitive control both predicted a reduced likelihood of risk-taking, whereas increased activity in the nucleus accumbens predicted a greater likelihood of risk-taking. Interactions between decision-level brain activity and age were not observed. These results garner support for system-based accounts of adolescent decision-making behavior.SIGNIFICANCE STATEMENT:Adolescent decision-making behavior is of great import for basic science, and carries equally consequential implications for public health and criminal justice. While dominant psychological theories seeking to explain adolescent decision-making have found empirical support, their neuroscientific implementations have received inconsistent support. This may be partly due to statistical approaches employed by prior neuroimaging studies of system-based theories. We used brain modeling-an approach that predicts behavior from brain activity-of univariate and multivariate neural activity metrics to better understand how neural components of psychological systems guide decision behavior in adolescents. We found broad support for system-based theories such that neural systems involved in cognitive control predicted a reduced likelihood to make risky decisions, whereas value-based systems predicted greater risk-taking propensity.

Emotion regulation strategy usage explains links between institutional caregiving and elevated internalizing symptoms.

Early adversity, including institutional orphanage care, is associated with the development of internalizing disorders. Previous research suggests that institutionalization can disrupt emotion regulation processes, which contribute to internalizing symptoms. However, no prior work has investigated how early orphanage care shapes emotion regulation strategy usage (e.g., cognitive reappraisal, expressive suppression) and whether the said strategy usage contributes to internalizing symptoms. This study probed emotion regulation strategy usage and internalizing symptoms in a sample of 36 previously institutionalized and 58 comparison youth. As hypothesized, previously institutionalized youth exhibited higher rates of internalizing symptoms than comparison youth, and more frequent use of suppression partially accounted for the relationship between early institutional care and elevated internalizing symptoms. Contrary to our initial hypotheses, reappraisal use did not buffer previously institutionalized or comparison youth against internalizing symptoms. Our findings highlight the potential utility of targeting emotion regulation strategy usage in adversity-exposed youth in future intervention work.

Assessing hidden parentage and genetic integrity of the "United Fruit Clones" of cacao (Theobroma cacao) from Costa Rica using SNP markers.

The international cacao collection in CATIE, Costa Rica contains nearly 1200 accessions of cacao, mainly from the center of genetic diversity of this species. Among these accessions, the United Fruit clones (UF clones) were developed by the United Fruit Company in Costa Rica, and they represent one of the earliest groups of improved cacao germplasm in the world. Some of these UF clones have been used as key progenitors for breeding resistance/tolerance to Frosty Pod and Black Pod diseases in the Americas. Accurate information on the identity and background of these clones is important for their effective use in breeding. Using Single Nucleotide Polymorphism (SNP) markers, we genotyped 273 cacao germplasm accessions including 44 UF clones and 229 reference accessions. We verified the true-to-type identity of UF clones in the CATIE cacao collection and analyzed their population memberships using maximum-likelihood-based approaches. Three duplicate groups, representing approximately 30% of the UF clones, were identified. Both distance- and model-based clustering methods showed that the UF clones were mainly composed of Trinitario, ancient Nacional and hybrids between ancient Nacional and Amelonado. This result filled the information gap about the UF clones thus will improve their utilization for cacao breeding.

Classifier Combination Supported by the Sleep-Wake Cycle Improves EEG Seizure Prediction Performance.

OBJECTIVE: Seizure prediction is a promising solution to improve the quality of life for drug-resistant patients, which concerns nearly 30% of patients with epilepsy. The present study aimed to ascertain the impact of incorporating sleep-wake information in seizure prediction. METHODS: We developed five patient-specific prediction approaches that use vigilance state information differently: i) using it as an input feature, ii) building a pool of two classifiers, each with different weights to sleep/wake training samples, iii) building a pool of two classifiers, each with only sleep/wake samples, iv) changing the alarm-threshold concerning each sleep/wake state, and v) adjusting the alarm-threshold after a sleep-wake transition. We compared these approaches with a control method that did not integrate sleep-wake information. Our models were tested with data (43 seizures and 482 hours) acquired during presurgical monitoring of 17 patients from the EPILEPSIAE database. As EPILEPSIAE does not contain vigilance state annotations, we developed a sleep-wake classifier using 33 patients diagnosed with nocturnal frontal lobe epilepsy from the CAP Sleep database. RESULTS: Although different patients may require different strategies, our best approach, the pool of weighted predictors, obtained 65% of patients performing above chance level with a surrogate analysis (against 41% in the control method). CONCLUSION: The inclusion of vigilance state information improves seizure prediction. Higher results and testing with long-term recordings from daily-life conditions are necessary to ensure clinical acceptance. SIGNIFICANCE: As automated sleep-wake detection is possible, it would be feasible to incorporate these algorithms into future devices for seizure prediction.

Root Canal Dentin Microhardness after Contact with Antibiotic Medications: An In Vitro Study.

Background: Antibiotic pastes used as intracanal medication in cases of revascularization therapy might cause negative effects on tooth properties, such as a reduction in dentin microhardness. This in vitro study investigated dentin microhardness in three different locations distancing from the canal lumen after 20 days of treatment with a tri-antibiotic paste (ciprofloxacin, metronidazole, and minocycline), and with a double-antibiotic paste (ciprofloxacin and metronidazole), with calcium hydroxide [Ca(OH)2] UltracalTM XS-treated dentin as comparison. Material and Methods: Human mandibular premolars (n = 48) had the root canals cleaned and shaped and were used to produce dentin slices. Dentin slices remained immersed in the medications for 20 days. The Knoop microhardness (KHN) test was performed before (baseline/Day-0) and after treatment (Day-20) with the medications. Indentations were made at 25 µm, 50 µm, and 100 µm distances from the root canal lumen. The KHN was compared intra-group using Wilcoxon's test. Independent groups were compared using Mann-Whitney's and Kruskal-Wallis' tests, at α = 5%. Results: The microhardness in all the tested groups was reduced at Day-20 in comparison with Day-0 (p < 0.001) (intra-group comparison/same distances). The Day-0 values were similar, and the Day-20 values were higher for the Ca(OH)2 group (p < 0.05) (comparison between groups/same distances). Conclusions: Calcium hydroxide for 20 days would be preferred rather than antibiotic pastes to minimize the expected reduction in dentin microhardness during regenerative procedures.

Disparities in Depression and Anxiety That Impact Self-Identified Sexual Minority People Affect a Broader Group of Same-Gender Attracted Young Adults.

PURPOSE: Prior work suggests sexual minority (e.g., gay, bisexual) young adults are at greater risk for depression and anxiety. However, the majority of said work focuses exclusively on self-reported sexual minority identity and neglects same-gender attraction. The current study aimed to characterize links between identity- and attraction-based indicators of sexual minority status and depression and anxiety in young adults, and to examine the ongoing significance of caregiver support in mental health during this key developmental period. METHODS: 386 youth (mean age = 19.92 years; SD = 1.39) reported their sexual orientation identity and experiences of attraction toward men and/or women. Participants also reported on anxiety, depression, and caregiver social support. RESULTS: While less than 16% of participants identified as sexual minority individuals, nearly half reported same-gender attraction. Self-identified sexual minority participants reported significantly higher depression and anxiety than self-identified heterosexual participants. Similarly, same-gender attracted individuals exhibited heightened depression and anxiety compared to exclusively different-gender attracted individuals. Greater caregiver social support predicted lower depression and anxiety. DISCUSSION: The present findings suggest that not only are self-identified sexual minority individuals at heightened risk for depression and anxiety symptoms, but also that this risk extends to a larger group of young people who experience same-gender attraction. These results demonstrate that better mental health supports may be needed for youth who identify as sexual minority individuals or report same-gender attraction. That higher caregiver social support was associated with lower mental illness risk suggests caregivers may be key to mental health promotion during young adulthood.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models.

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

Access to medicines among the Brazilian population based on the 2019 National Health Survey.

INTRODUCTION: Access to medicines is a challenge, especially in developing countries, highlighting the need of population-based research to evaluate access and related factors. OBJECTIVE: This study aimed to assess access to medicines and identify associated factors using data from the 2019 Brazilian National Health Survey (PNS). METHODS: This population-based cross-sectional study used data from the 2019 PNS and considered access to prescription medicines as the primary outcome. The sample included 24,753 individuals aged 15 years or older who looked for medical care in the last 15 days and received a medicine prescription. Andersen's behavioral model was used to select independent variables. After descriptive analysis, a multinomial logistic regression multilevel analysis was performed using the independent variables with a significance level lower than 0.20 in the bivariate analysis. RESULTS: The lowest chances of getting access to medicines were observed in individuals aged between 40 and 59 years, women, with complete middle and high school, with lower-income families, who attended public services, with worse self-assessed health, and those who looked for health care for disease prevention and health promotion. CONCLUSIONS: Access to medicines among the Brazilian population is associated with social, economic, and health perception factors. Our findings may update and guide the development of public policies on medication and pharmaceutical care, facilitating medication purchases by the care user and promoting health equity.

The goal of explaining black boxes in EEG seizure prediction is not to explain models' decisions.

Many state-of-the-art methods for seizure prediction, using the electroencephalogram, are based on machine learning models that are black boxes, weakening the trust of clinicians in them for high-risk decisions. Seizure prediction concerns a multidimensional time-series problem that performs continuous sliding window analysis and classification. In this work, we make a critical review of which explanations increase trust in models' decisions for predicting seizures. We developed three machine learning methodologies to explore their explainability potential. These contain different levels of model transparency: a logistic regression, an ensemble of 15 support vector machines, and an ensemble of three convolutional neural networks. For each methodology, we evaluated quasi-prospectively the performance in 40 patients (testing data comprised 2055 hours and 104 seizures). We selected patients with good and poor performance to explain the models' decisions. Then, with grounded theory, we evaluated how these explanations helped specialists (data scientists and clinicians working in epilepsy) to understand the obtained model dynamics. We obtained four lessons for better communication between data scientists and clinicians. We found that the goal of explainability is not to explain the system's decisions but to improve the system itself. Model transparency is not the most significant factor in explaining a model decision for seizure prediction. Even when using intuitive and state-of-the-art features, it is hard to understand brain dynamics and their relationship with the developed models. We achieve an increase in understanding by developing, in parallel, several systems that explicitly deal with signal dynamics changes that help develop a complete problem formulation.

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy.

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

Interpretable EEG seizure prediction using a multiobjective evolutionary algorithm.

Seizure prediction might be the solution to tackle the apparent unpredictability of seizures in patients with drug-resistant epilepsy, which comprise about a third of all patients with epilepsy. Designing seizure prediction models involves defining the pre-ictal period, a transition stage between inter-ictal brain activity and the seizure discharge. This period is typically a fixed interval, with some recent studies reporting the evaluation of different patient-specific pre-ictal intervals. Recently, researchers have aimed to determine the pre-ictal period, a transition stage between regular brain activity and a seizure. Authors have been using deep learning models given the ability of such models to automatically perform pre-processing, feature extraction, classification, and handling temporal and spatial dependencies. As these approaches create black-box models, clinicians may not have sufficient trust to use them in high-stake decisions. By considering these problems, we developed an evolutionary seizure prediction model that identifies the best set of features while automatically searching for the pre-ictal period and accounting for patient comfort. This methodology provides patient-specific interpretable insights, which might contribute to a better understanding of seizure generation processes and explain the algorithm's decisions. We tested our methodology on 238 seizures and 3687 h of continuous data, recorded on scalp recordings from 93 patients with several types of focal and generalised epilepsies. We compared the results with a seizure surrogate predictor and obtained a performance above chance for 32% patients. We also compared our results with a control method based on the standard machine learning pipeline (pre-processing, feature extraction, classifier training, and post-processing), where the control marginally outperformed our approach by validating 35% of the patients. In total, 54 patients performed above chance for at least one method: our methodology or the control one. Of these 54 patients, 21 ([Formula: see text]38%) were solely validated by our methodology, while 24 ([Formula: see text]44%) were only validated by the control method. These findings may evidence the need for different methodologies concerning different patients.

EPIC: Annotated epileptic EEG independent components for artifact reduction.

Scalp electroencephalogram is a non-invasive multi-channel biosignal that records the brain's electrical activity. It is highly susceptible to noise that might overshadow important data. Independent component analysis is one of the most used artifact removal methods. Independent component analysis separates data into different components, although it can not automatically reject the noisy ones. Therefore, experts are needed to decide which components must be removed before reconstructing the data. To automate this method, researchers have developed classifiers to identify noisy components. However, to build these classifiers, they need annotated data. Manually classifying independent components is a time-consuming task. Furthermore, few labelled data are publicly available. This paper presents a source of annotated electroencephalogram independent components acquired from patients with epilepsy (EPIC Dataset). This dataset contains 77,426 independent components obtained from approximately 613 hours of electroencephalogram, visually inspected by two experts, which was already successfully utilised to develop independent component classifiers.

Ensemble Deep Neural Network for Automatic Classification of EEG Independent Components.

OBJECTIVE: Independent component analysis (ICA) is commonly used to remove noisy artifacts from multi-channel scalp electroencephalogram (EEG) signals. ICA decomposes EEG into different independent components (ICs) and then, experts remove the noisy ones. This process is highly time-consuming and experts are not always available. To surpass this drawback, research is going on to develop models to automatically conduct IC classification. Current state-of-the-art models use power spectrum densities (PSDs) and topoplots to classify ICs. The performance of these methods may be limited by disregarding the IC time-series that would contribute to fully simulate the visual inspection performed by experts. METHODS: We present a novel ensemble deep neural network that combines time-series, PSDs, and topoplots to classify ICs. Moreover, we study the ability to use our model in transfer learning approaches. RESULTS: Experimental results showed that using time-series improves IC classification. Results also indicated that transfer learning obtained higher performance than simply training a new model from scratch. CONCLUSION: Researchers should develop IC classifiers using the three sources of information. Moreover, transfer learning approaches should be considered when producing new deep learning models. SIGNIFICANCE: This work improves IC classification, enhancing the automatic removal of EEG artifacts. Additionally, since labelled ICs are generally not publicly available, the possibility of using our model in transfer learning studies may motivate other researchers to develop their own classifiers.

On the clinical acceptance of black-box systems for EEG seizure prediction.

Seizure prediction may be the solution for epileptic patients whose drugs and surgery do not control seizures. Despite 46 years of research, few devices/systems underwent clinical trials and/or are commercialized, where the most recent state-of-the-art approaches, as neural networks models, are not used to their full potential. The latter demonstrates the existence of social barriers to new methodologies due to data bias, patient safety, and legislation compliance. In the form of literature review, we performed a qualitative study to analyze the seizure prediction ecosystem to find these social barriers. With the Grounded Theory, we draw hypotheses from data, while with the Actor-Network Theory we considered that technology shapes social configurations and interests, being fundamental in healthcare. We obtained a social network that describes the ecosystem and propose research guidelines aiming at clinical acceptance. Our most relevant conclusion is the need for model explainability, but not necessarily intrinsically interpretable models, for the case of seizure prediction. Accordingly, we argue that it is possible to develop robust prediction models, including black-box systems to some extent, while avoiding data bias, ensuring patient safety, and still complying with legislation, if they can deliver human- comprehensible explanations. Due to skepticism and patient safety reasons, many authors advocate the use of transparent models which may limit their performance and potential. Our study highlights a possible path, by using model explainability, on how to overcome these barriers while allowing the use of more computationally robust models.

Early caregiving adversity differentially shapes behavioral sensitivity to reward and risk during decision-making.

Cognitive systems that track, update, and utilize information about reward (consequences) and risk (uncertainty) are critical for adaptive decision-making as well as everyday functioning and well-being. However, it remains unclear how individual differences in reward and risk sensitivity are independently shaped by environmental influences and give rise to decision-making. Here, we investigated the impact of early life experience-a potent sculptor of development-on behavioral sensitivity to reward and risk. We administered a widely used decision-making paradigm to 55 adolescents and young adults who were exposed to early deprivation in the form of early institutional (orphanage) care (a type of early life adversity) and 81 comparison individuals who were reared by their biological parents and did not experience institutional care. Leveraging random coefficient regression and computational models, we observed that previously institutionalized individuals displayed general reward hyposensitivity, contributing to a decreased propensity to make decisions that stood to earn relatively large rewards relative to comparison individuals. By contrast, group differences in risk sensitivity were selectively observed on loss, but not gain, trials. These results are the first to independently and explicitly link early experiences to reward and risk sensitivity during decision-making. As such, they lay the groundwork for therapeutic efforts to identify and treat adversity-exposed individuals at risk for psychiatric disorders characterized by aberrant decision-making processes. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Neurobiological Markers of Resilience to Early-Life Adversity During Adolescence.

Early-life adversity (ELA) exposure (e.g., trauma, abuse, neglect, or institutional care) is a precursor to poor physical and mental health outcomes and is implicated in 30% of adult mental illness. In recent decades, ELA research has increasingly focused on characterizing factors that confer resilience to ELA and on identifying opportunities for intervention. In this review, we describe recent behavioral and neurobiological resilience work that suggests that adolescence (a period marked by heightened plasticity, development of key neurobiological circuitry, and sensitivity to the social environment) may be a particularly opportune moment for ELA intervention. We review intrapersonal factors associated with resilience that become increasingly important during adolescence (specifically, reward processing, affective learning, and self-regulation) and describe the contextual factors (family, peers, and broader social environment) that modulate them. In addition, we describe how the onset of puberty interacts with each of these factors, and we explore recent findings that point to possible "pubertal recalibration" of ELA exposure as an opportunity for intervention. We conclude by describing considerations and future directions for resilience research in adolescents, with a focus on understanding developmental trajectories using dimensional and holistic models of resilience.

A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction.

Seizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms.