Flexoelectric Engineering of Bulk Photovoltaic Photodetector.

The bulk photovoltaic effect (BPVE) offers an interesting approach to generate a steady photocurrent in a single-phase material under homogeneous illumination, and it has been extensively investigated in ferroelectrics exhibiting spontaneous polarization that breaks inversion symmetry. Flexoelectricity breaks inversion symmetry via a strain gradient in the otherwise nonpolar materials, enabling manipulation of ferroelectric order without an electric field. Combining these two effects, we demonstrate active mechanical control of BPVE in suspended 2-dimensional CuInP2S6 (CIPS) that is ferroelectric yet sensitive to electric field, which enables practical photodetection with an order of magnitude enhancement in performance. The suspended CIPS exhibits a 20-fold increase in photocurrent, which can be continuously modulated by either mechanical force or light polarization. The flexoelectrically engineered photodetection device, activated by air pressure and without any optimization, possesses a responsivity of 2.45 × 10-2 A/W and a detectivity of 1.73 × 1011 jones, which are superior to those of ferroelectric-based photodetection and comparable to those of the commercial Si photodiode.

Widespread slow oscillations support interictal epileptiform discharge networks in focal epilepsy.

Interictal epileptiform discharges (IEDs) often co-occur across spatially-separated cortical regions, forming IED networks. However, the factors prompting IED propagation remain unelucidated. We hypothesized that slow oscillations (SOs) might facilitate IED propagation. Here, the amplitude and phase synchronization of SOs preceding propagating and non-propagating IEDs were compared in 22 patients with focal epilepsy undergoing intracranial electroencephalography (EEG) evaluation. Intracranial channels were categorized into the irritative zone (IZ) and normal zone (NOZ) regarding the presence of IEDs. During wakefulness, we found that pre-IED SOs within the IZ exhibited higher amplitudes for propagating IEDs than non-propagating IEDs (delta band: p = 0.001, theta band: p < 0.001). This increase in SOs was also concurrently observed in the NOZ (delta band: p = 0.04). Similarly, the inter-channel phase synchronization of SOs prior to propagating IEDs was higher than those preceding non-propagating IEDs in the IZ (delta band: p = 0.04). Through sliding window analysis, we observed that SOs preceding propagating IEDs progressively increased in amplitude and phase synchronization, while those preceding non-propagating IEDs remained relatively stable. Significant differences in amplitude occurred approximately 1150 ms before IEDs. During non-rapid eye movement (NREM) sleep, SOs on scalp recordings also showed higher amplitudes before intracranial propagating IEDs than before non-propagating IEDs (delta band: p = 0.006). Furthermore, the analysis of IED density around sleep SOs revealed that only high-amplitude sleep SOs demonstrated correlation with IED propagation. Overall, our study highlights that transient but widely distributed SOs are associated with IED propagation as well as generation in focal epilepsy during sleep and wakefulness, providing new insight into the EEG substrate supporting IED networks.

Correction: Ionic migration induced loss analysis of perovskite solar cells: a poling study.

Correction for 'Ionic migration induced loss analysis of perovskite solar cells: a poling study' by Xue Zheng et al., Phys. Chem. Chem. Phys., 2022, 24, 7805-7814, https://doi.org/10.1039/D1CP05450C.

A region-specific modulation of sleep slow waves on interictal epilepsy markers in focal epilepsy.

OBJECTIVE: Sleep strongly activates interictal epileptic activity through an unclear mechanism. We investigated how scalp sleep slow waves (SSWs), whose positive and negative half-waves reflect the fluctuation of neuronal excitability between the up and down states, respectively, modulate interictal epileptic events in focal epilepsy. METHODS: Simultaneous polysomnography was performed in 45 patients with drug-resistant focal epilepsy during intracranial electroencephalographic recording. Scalp SSWs and intracranial spikes and ripples (80-250 Hz) were detected; ripples were classified as type I (co-occurring with spikes) or type II (occurring alone). The Hilbert transform was used to analyze the distributions of spikes and ripples in the phases of SSWs. RESULTS: Thirty patients with discrete seizure-onset zone (SOZ) and discernable sleep architecture were included. Intracranial spikes and ripples accumulated around the negative peaks of SSWs and increased with SSW amplitude. Phase analysis revealed that spikes and both ripple subtypes in SOZ were similarly facilitated by SSWs exclusively during down state. In exclusively irritative zones outside SOZ (EIZ), SSWs facilitated spikes and type I ripples across a wider range of phases and to a greater extent than those in SOZ. The type II and type I ripples in EIZ were modulated by SSWs in different patterns. Ripples in normal zones decreased specifically during the up-to-down transition and then increased after the negative peak of SSW, with a characteristically high post-/pre-negative peak ratio. SIGNIFICANCE: SSWs modulate interictal events in an amplitude-dependent and region-specific pattern. Pathological ripples and spikes were facilitated predominantly during the cortical down state. Coupling analysis of SSWs could improve the discrimination of pathological and physiological ripples and facilitate seizure localization.

Focal cortical dysplasia links to sleep-related epilepsy in symptomatic focal epilepsy.

OBJECTIVE: In sleep-related epilepsy (SRE), epileptic seizures predominantly occur during sleep, but the clinical characteristics of SRE remain elusive. We aimed to identify the clinical features associated with the occurrence of SRE in a large cohort of symptomatic focal epilepsy. METHODS: We retrospectively included patients with four etiologies, including focal cortical dysplasia (FCD), low-grade tumors (LGT), temporal lobe epilepsy with hippocampal sclerosis (TLE-HS), and encephalomalacia. SRE was defined as more than 70% of seizures occurring during sleep according to the seizure diary. The correlation between SRE and other clinical variables, such as etiology of epilepsy, pharmacoresistance, seizure frequency, history of bilateral tonic-clonic seizures, and seizure localization was analyzed. RESULTS: A total of 376 patients were included. Among them 95 (25.3%) were classified as SRE and the other 281(74.7%) as non-SRE. The incidence of SRE was 53.5% in the FCD group, which was significantly higher than the other three groups (LGT: 19.0%; TLE-HS: 9.9%; encephalomalacia: 16.7%; P < 0.001). The etiology of FCD (p < 0.001) was significantly associated with SRE (OR: 9.71, 95% CI: 3.35-28.14) as an independent risk factor. In addition, small lesion size (p = 0.009) of FCD further increased the risk of SRE (OR: 3.18, 95% CI: 1.33-7.62) in the FCD group. SIGNIFICANCE: Our data highlight that FCD markedly increased the risk of sleep-related epilepsy independently of seizure localization. A small lesion of FCD further increased the risk of sleep-related epilepsy by 2.18 times in the FCD group.

Ionic migration induced loss analysis of perovskite solar cells: a poling study.

Understanding the interplay between ionic migration and defect trapping in photovoltaic perovskites is critical to develop targeted passivation techniques for performance enhancement. In this study, systematic poling experiments on Cs0.05(FA0.85MA0.15)0.95Pb(I0.85Br0.15)3 perovskite solar cells (PSCs) were conducted to resolve the principal effects of bias dependent pretreatment effects due to dynamic ionic migration. We find that under negative polarizations, iodine ion accumulation at perovskite/electron transport layer (ETL) interfaces causes enhanced global non-radiative recombination in PSCs and significant open-circuit voltage (Voc) losses. On the other hand, dramatic short-circuit current (Jsc) reduction occurs in positively polarized devices, which is ascribed to ineffective charge collection due to modified band-bending towards both charge transport materials. Spatiotemporally scanning probe microscopy on the surface of polarized perovskites provides an in situ estimation of iodine diffusion mobility and visualization of reorganizations under an external bias. Moreover, our findings suggest that the precondition effect of PSCs under operation due to defect ions is recoverable, therefore achieving a respectable lifetime of PSCs for commercialization is promising.

Epilepsy surgery for low-grade epilepsy-associated neuroepithelial tumor of temporal lobe: a single-institution experience of 61 patients.

BACKGROUND: Low-grade epilepsy-associated neuroepithelial tumor (LEAT) is highly responsive to surgery in general. The appropriate surgical strategy remains controversial in temporal LEAT. The aim of this study is to analyze the surgical seizure outcome of temporal LEAT, focusing on the aspects of surgical strategy. METHODS: Sixty-one patients from a single epilepsy center with temporal LEAT underwent surgery. The surgical strategy was according to the multidisciplinary presurgical evaluation. Electrocorticogram (ECoG)-assisted resection was utilized. Surgical extent including lesionectomy and extended resection was described in detail. Seizure outcome was classified as satisfactory (Engel class I) and unsatisfactory (Engel classes II-IV). RESULTS: After a median follow-up of 36.0 (30.0) months, 83.6% of patients achieved satisfactory outcome, including 72.1% with Engel class Ia. There was 39.3% (24/61) of patients with antiepileptic drug (AED) withdrawal. Use of ECoG (χ2 = 0.000, P > 0.1), preresection spike (χ2 = 0.000, P = 0.763), or spike residue (P = 0.545) was not correlated with the seizure outcome. For lateral temporal LEAT, outcome from lesionectomy was comparable to extended resection (χ2 = 0.499, P > 0.1). For mesial temporal LEAT, 94.7% (18/19) of patients who underwent additional hippocampectomy were satisfactory, whereas only 25% (1/4) of patients who underwent lesionectomy were satisfactory (P = 0.009). CONCLUSION: Surgical treatment was highly effective for temporal LEAT. ECoG may not influence the seizure outcome. For lateral temporal LEAT, lesionectomy with or without cortectomy was sufficient in most patients. For mesial temporal LEAT, extended resection was recommended.

[Monitoring time of interictal epileptiform discharges by long-term video EEG in patients with epilepsy].

Objective: To optimize the monitoring time of interictal epileptiform discharges (IED) in patients with epilepsy by long-term video electroencephalogram (VEEG). Methods: The cumulative percentages of IED detected by VEEG in 346 epilepsy patients (349 times) with different purposes, different waking sleep states and different MRI findings were retrospectively analyzed. According to the purposes, there were 164 patients (165 times) for clarifying diagnosis, 124 patients (124 times) for preoperative evaluation and 58 patients (60 times) for adjustment of medications. According to MRI results, there were responsible lesions in 98 patients (98 times) and no responsible lesions in 173 patients (174 times). Results: Among 346 patients (349 times), IED was detected within 24 h in 231 patients (times). The percentage of detection in patients with purpose of preoperative evaluation was higher than those with purpose of diagnosis and medication adjustment. The detection of LED was gradually increased in first 8 h with 59.0%, then stably in 24 h. 46.8% IED was recorded during sleep time, particularly in the second stage of sleep. The cumulative percentage of IED in patients with abnormal MRI findings was higher in all periods. It reached 83.7% within 8 h, and then tended to be stable. Conclusion: The study shows that LED should be monitored by VEEG at least 8 hours and should include the second stage of sleep in patients with epilepsy. Patients with refractory epilepsy and with abnormal lesions on MRI should record IED more frequently.

Increased Deep Trap Density in Interfacial Engineered Nanocomposite Revealed by Sequential Kelvin Probe Force Microscopy for High Dielectric Energy Storage.

Nanocomposites combining inorganic nanoparticles with high dielectric constant and polymers with high breakdown strength are promising for the high energy density storage of electricity, and carrier traps can significantly affect the dielectric breakdown process. Nevertheless, there still lacks direct experimental evidence on how nanoparticles affect the trap characteristics of nanocomposites, especially in a spatially resolved manner. Here, a technique is developed to image the trap distribution based on sequential Kelvin probe force microscopy (KPFM) in combination with the isothermal surface potential decay (ISPD) technique, wherein both shallow and deep trap densities and the corresponding energy levels can be mapped with nanoscale resolution. The technique is first validated using the widely-used commercial biaxially oriented polypropylene, yielding consistent results with macroscopic ISPD. The technique is then applied to investigate polyvinylidene fluoride-based nanocomposites filled with barium titanate nanoparticles, revealing higher deep trap density around surface-modified nanoparticles, which correlates well with its increased breakdown strength. This technique thus provides a powerful spatially resolved tool for understanding the microscopic mechanism of dielectric breakdown of nanocomposites.

Anomalous reverse mechanical polarization switching in negative piezoelectric CuInP2S6.

van der Waals ferroelectric CuInP2S6 (CIPS) has drawn significant attention not only because of its unique properties but also owing to its technological potential for nanoelectronics. Mechanical polarization switching provides a new approach to modulating polarization states through flexoelectricity. This approach is particularly favourable for CIPS to avoid surface damage under an electric field due to the coupling between polarization switching and ionic motion. Here, we report anomalous downward-to-upward polarization switching under tip force in CIPS nanoflakes, which is believed to stem from the competition between piezoelectric and flexoelectric fields induced by tip pressure, together with the unique quadruple-well state present in CIPS. This work provides novel insights into the polarization switching mechanism of CIPS, elucidating the interplay between competing piezoelectric and flexoelectric fields, and it may pave the way for the design of electromechanical devices based on flexoelectric engineering.

Speech decoding using cortical and subcortical electrophysiological signals.

Introduction: Language impairments often result from severe neurological disorders, driving the development of neural prosthetics utilizing electrophysiological signals to restore comprehensible language. Previous decoding efforts primarily focused on signals from the cerebral cortex, neglecting subcortical brain structures' potential contributions to speech decoding in brain-computer interfaces. Methods: In this study, stereotactic electroencephalography (sEEG) was employed to investigate subcortical structures' role in speech decoding. Two native Mandarin Chinese speakers, undergoing sEEG implantation for epilepsy treatment, participated. Participants read Chinese text, with 1-30, 30-70, and 70-150 Hz frequency band powers of sEEG signals extracted as key features. A deep learning model based on long short-term memory assessed the contribution of different brain structures to speech decoding, predicting consonant articulatory place, manner, and tone within single syllable. Results: Cortical signals excelled in articulatory place prediction (86.5% accuracy), while cortical and subcortical signals performed similarly for articulatory manner (51.5% vs. 51.7% accuracy). Subcortical signals provided superior tone prediction (58.3% accuracy). The superior temporal gyrus was consistently relevant in speech decoding for consonants and tone. Combining cortical and subcortical inputs yielded the highest prediction accuracy, especially for tone. Discussion: This study underscores the essential roles of both cortical and subcortical structures in different aspects of speech decoding.

High Quality Epitaxial Piezoelectric and Ferroelectric Wurtzite Al1- xScxN Thin Films.

Piezoelectric and ferroelectric wurtzite are promising to reshape modern microelectronics because they can be easily integrated with mainstream semiconductor technology. Sc doped AlN (Al1- xScxN) has attracted much attention for its enhanced piezoelectric and emerging ferroelectric properties, yet the commonly used sputtering results in polycrystalline Al1- xScxN films with high leakage current. Here, the pulsed laser deposition of single crystalline epitaxial Al1- xScxN thin films on sapphire and 4H-SiC substrates is reported. Pure wurtzite phase is maintained up to x = 0.3 with ≤0.1 at% oxygen contamination. Polarization is estimated to be 140 µC cm-2 via atomic scale microscopy imaging and found to be switchable via a scanning probe. The piezoelectric coefficient is found to be five times of the undoped one when x = 0.3, making it desirable for high-frequency radiofrequency (RF) filters and 3D nonvolatile memories.

Seizures and electrophysiological features in familial cortical myoclonic tremor with epilepsy 1.

OBJECTIVES: To investigate and characterize epileptic seizures and electrophysiological features of familial cortical myoclonic tremor with epilepsy (FCMTE) type 1 patients in a large Chinese cohort. METHODS: We systematically evaluated 125 FCMTEtype 1 patients carrying the pentanucleotide (TTTCA) repeat expansion in the SAMD12 gene in China. RESULTS: Among the 28 probands, epileptic seizures (96.4%, 27/28) were the most common reason for an initial clinic visit. Ninety-seven (77.6%, 97/125) patients had experienced seizures. The seizures onset age was 36.5 ± 9.0 years, which was 6.9 years later than cortical tremors. The seizures were largely rare (<1/year, 58.8%) and occasional (1-6/year, 37.1%). Prolonged prodromes were reported in 57.7% (56/97). Thirty-one patients (24.8%, 31/125) reported photosensitivity history, and 79.5% (31/39) had a photoparoxysmal response. Interictal epileptiform discharges (IEDs) were recorded in 69.1% (56/81) of patients. Thirty-three patients showed generalized IEDs and 72.7% (24/33) were occipitally dominant, while 23 patients presented with focal IEDs with 65.2% (15/23) taking place over the occipital lobe. Overnight EEG of FCMTE patients displayed paradoxical sleep-wake fluctuation, with a higher average IED index of 0.82 ± 0.88/min during wakefulness and a lower IED index of 0.04 ± 0.06/min during non-rapid eye movement sleep stages I-II. INTERPRETATION: FCMTE type 1 has a benign course of epilepsy and distinct clinical and electrophysiological features. In addition to a positive family history and cortical myoclonus tremor, the seizure prodromes, specific seizure triggers, photosensitivity, distribution of IEDs, and unique fluctuations during sleep-wake cycle are cues for proper genetic testing and an early diagnosis of FCMTE.

Ictal EEG desynchronization during low-voltage fast activity for prediction of surgical outcomes in focal epilepsy.

OBJECTIVE: The authors investigated alterations in functional connectivity (FC) and EEG power during ictal onset patterns of low-voltage fast activity (LVFA) in drug-resistant focal epilepsy. They hypothesized that such changes would be useful to classify epilepsy surgical outcomes. METHODS: In a cohort of 79 patients with drug-resistant focal epilepsy who underwent stereoelectroencephalography (SEEG) evaluation as well as resective surgery, FC changes during the peri-LVFA period were measured using nonlinear regression (h2) and power spectral properties within/between three regions: the seizure onset zone (SOZ), early propagation zone (PZ), and noninvolved zone (NIZ). Desynchronization and power desynchronization h2 indices were calculated to assess the degree of EEG desynchronization during LVFA. Multivariate logistic regression was employed to control for confounding factors. Finally, receiver operating characteristic curves were generated to evaluate the performance of desynchronization indices in predicting surgical outcome. RESULTS: Fifty-three patients showed ictal LVFA and distinct zones of the SOZ, PZ, and NIZ. Among them, 39 patients (73.6%) achieved seizure freedom by the final follow-up. EEG desynchronization, measured by h2 analysis, was found in the seizure-free group during LVFA: FC decreased within the SOZ and between regions compared with the pre-LVFA and post-LVFA periods. In contrast, the non-seizure-free group showed no prominent EEG desynchronization. The h2 desynchronization index, but not the power desynchronization index, enabled classification of seizure-free versus non-seizure-free patients after resective surgery. CONCLUSIONS: EEG desynchronization during the peri-LVFA period, measured by within-zone and between-zone h2 analysis, may be helpful for identifying patients with favorable postsurgical outcomes and also may potentially improve epileptogenic zone identification in the future.

Excitatory somatostatin interneurons in the dentate gyrus drive a widespread seizure network in cortical dysplasia.

Seizures due to cortical dysplasia are notorious for their poor prognosis even with medications and surgery, likely due to the widespread seizure network. Previous studies have primarily focused on the disruption of dysplastic lesions, rather than remote regions such as the hippocampus. Here, we first quantified the epileptogenicity of the hippocampus in patients with late-stage cortical dysplasia. We further investigated the cellular substrates leading to the epileptic hippocampus, using multiscale tools including calcium imaging, optogenetics, immunohistochemistry and electrophysiology. For the first time, we revealed the role of hippocampal somatostatin-positive interneurons in cortical dysplasia-related seizures. Somatostatin-positive were recruited during cortical dysplasia-related seizures. Interestingly, optogenetic studies suggested that somatostatin-positive interneurons paradoxically facilitated seizure generalization. By contrast, parvalbumin-positive interneurons retained an inhibitory role as in controls. Electrophysiological recordings and immunohistochemical studies revealed glutamate-mediated excitatory transmission from somatostatin-positive interneurons in the dentate gyrus. Taken together, our study reveals a novel role of excitatory somatostatin-positive neurons in the seizure network and brings new insights into the cellular basis of cortical dysplasia.

Flexoelectric engineering of van der Waals ferroelectric CuInP2S6.

Van der Waals layered CuInP2S6 (CIPS) is an ideal candidate for developing two-dimensional microelectronic heterostructures because of its room temperature ferroelectricity, although field-driven polarization reversal of CIPS is intimately coupled with ionic migration, often causing erratic and damaging switching that is highly undesirable for device applications. In this work, we develop an alternative switching mechanism for CIPS using flexoelectric effect, abandoning external electric fields altogether, and the method is motivated by strong correlation between polarization and topography variation of CIPS. Phase-field simulation identifies a critical radius of curvature around 5 µm for strain gradient to be effective, which is realized by engineered topographic surfaces using silver nanowires and optic grating upon which CIPS is transferred to. We also demonstrate mechanical modulation of CIPS on demand via strain gradient underneath a scanning probe, making it possible to engineer multiple polarization states of CIPS for device applications.

Clinical Characteristics and Prognostic Significance of Subclinical Seizures in Focal Epilepsy: A Retrospective Study.

INTRODUCTION: The aim was to evaluate the clinical characteristics and prognostic significance of subclinical seizures (SCSs) on scalp video-electroencephalogram (VEEG) monitoring with or without intracranial electroencephalogram (IEEG) monitoring in patients who had epilepsy surgery. METHODS: We reviewed 286 epileptic patients who underwent subsequent epilepsy surgery during scalp-VEEG evaluation with or without IEEG monitoring between 2013 and 2020, with a minimum follow-up of 1 year. The prevalence and clinical characteristics of SCSs, as well as their prognostic significance, were analyzed. RESULTS: A total of 286 patients were enrolled for analysis, and 80 patients had IEEG implanted. SCSs were recorded in 9.79% of the patients based on VEEG and 50% based on IEEG. In the VEEG group (n = 286), younger seizure onset (P = 0.004) was associated with the presence of s-SCSs (SCSs detected on scalp VEEG). In the IEEG group (n = 80), temporal lobe epilepsy (P = 0.015) was associated with the presence of i-SCSs (SCSs detected on IEEG). Of 286 patients, 208 (72.73%) were seizure-free in the VEEG group, and 56 0f 80 patients (70%) were seizure-free in the IEEG group through the last follow-up. In the VEEG group, the presence of s-SCSs did not affect seizure outcome; predictors of seizure recurrence were longer epilepsy duration (P = 0.003, OR 1.003, 95% CI 1.001-1.005), history of focal to bilateral tonic-clonic seizure (P = 0.027, OR 1.665, 95% CI 1.060-2.613), nonspecific pathology (P = 0.018, OR 2.184, 95% CI 1.145-4.163), and incomplete resection (P = 0.004, OR 2.705, 95% CI 1.372-5.332). In the IEEG group, i-SCSs were significantly associated with seizure outcome (P = 0.028, OR 0.371, 95% CI 0.153-0.898). CONCLUSION: The rate of SCSs captured on IEEG monitoring was higher than that on VEEG monitoring during presurgical evaluation. SCSs detected on VEEG monitoring were associated with younger seizure onset. SCSs detected on IEEG monitoring were associated with temporal lobe epilepsy and also predicted surgical outcomes in focal epilepsy.

Suppressing Defects-Induced Nonradiative Recombination for Efficient Perovskite Solar Cells through Green Antisolvent Engineering.

Organic-inorganic hybrid perovskites have attracted considerable attention due to their superior optoelectronic properties. Traditional one-step solution-processed perovskites often suffer from defects-induced nonradiative recombination, which significantly hinders the improvement of device performance. Herein, treatment with green antisolvents for achieving high-quality perovskite films is reported. Compared to defects-filled ones, perovskite films by antisolvent treatment using methylamine bromide (MABr) in ethanol (MABr-Eth) not only enhances the resultant perovskite crystallinity with large grain size, but also passivates the surface defects. In this case, the engineering of MABr-Eth-treated perovskites suppressing defects-induced nonradiative recombination in perovskite solar cells (PSCs) is demonstrated. As a result, the fabricated inverted planar heterojunction device of ITO/PTAA/Cs0.15 FA0.85 PbI3 /PC61 BM/Phen-NADPO/Ag exhibits the best power conversion efficiency of 21.53%. Furthermore, the corresponding PSCs possess a better storage and light-soaking stability.

Distinguishing Focal Cortical Dysplasia From Glioneuronal Tumors in Patients With Epilepsy by Machine Learning.

Purpose: We are aiming to build a supervised machine learning-based classifier, in order to preoperatively distinguish focal cortical dysplasia (FCD) from glioneuronal tumors (GNTs) in patients with epilepsy. Methods: This retrospective study was comprised of 96 patients who underwent epilepsy surgery, with the final neuropathologic diagnosis of either an FCD or GNTs. Seven classical machine learning algorithms (i.e., Random Forest, SVM, Decision Tree, Logistic Regression, XGBoost, LightGBM, and CatBoost) were employed and trained by our dataset to get the classification model. Ten features [i.e., Gender, Past history, Age at seizure onset, Course of disease, Seizure type, Seizure frequency, Scalp EEG biomarkers, MRI features, Lesion location, Number of antiepileptic drug (AEDs)] were analyzed in our study. Results: We enrolled 56 patients with FCD and 40 patients with GNTs, which included 29 with gangliogliomas (GGs) and 11 with dysembryoplasic neuroepithelial tumors (DNTs). Our study demonstrated that the Random Forest-based machine learning model offered the best predictive performance on distinguishing the diagnosis of FCD from GNTs, with an F1-score of 0.9180 and AUC value of 0.9340. Furthermore, the most discriminative factor between FCD and GNTs was the feature "age at seizure onset" with the Chi-square value of 1,213.0, suggesting that patients who had a younger age at seizure onset were more likely to be diagnosed as FCD. Conclusion: The Random Forest-based machine learning classifier can accurately differentiate FCD from GNTs in patients with epilepsy before surgery. This might lead to improved clinician confidence in appropriate surgical planning and treatment outcomes.