Haoer Shi

One-third of the world’s 70 million people with epilepsy have seizures uncontrolled by medication, and implantable devices are a promising treatment. These devices can detect impending seizures, missed medication and impaired cognition, but, like most medical devices, they cannot share this information with patients in real time. This is a missed opportunity for devices to learn from clinical events and teach patients how their behaviors affect their health. Here we present a device platform that converses with patients to help them manage their epilepsy. The inpatient prototype links scalp and intracranial electroencephalography (EEG) to a secure, large language model-based artificial intelligence (AI) that communicates bidirectionally through a smartphone app. The AI processes biomarkers of sleep, medication, cognition and seizure probability, notifies patients of clinical events and trends, records symptoms and responses, and uses their feedback to retrain its seizure detector, reducing false alarms. We validated this platform in 13 patients who are undergoing video-EEG monitoring for epilepsy (scalp, n = 11; intracranial, n = 2). In a pseudoprospective simulation, seizure detectors improved precision from patient feedback alone, without expert intervention. We propose this system as a scalable, safeguarded platform for medical devices that can rapidly adapt to patient and provider needs across epilepsy and other medical conditions.

Objective: Subscalp electroencephalographic ( EEG) systems with few channels have emerged as promising solutions for ultra‐long‐term seizure monitoring, but the impact of montage configuration on automated seizure detection is unclear. We compared automated detection performance between full‐scalp and simulated reduced montages approximating published subscalp devices, and assessed variation by epilepsy type, lateralization, and localization. Methods: We conducted a retrospective cross‐sectional study of consecutive epilepsy monitoring unit (EMU) admissions from January 2017 to December 2024 at the Hospital of the University of Pennsylvania. Admissions with at least one clinician‐annotated seizure and at least one interictal segment of ≥20 min from any seizure were included. We simulated reduced bipolar montages from standard 10–20 scalp EEG. Three validated detectors, a one‐class support vector machine (SVM), a convolutional neural network (SPaRCNet), and a long short‐term memory autoregressive model with neural dynamic divergence method (NDD), were applied to montages and evaluated using event‐level F1 scores. We additionally evaluated the contributions of patient, detector, and montage to performance variance and associations between performance and epilepsy characteristics using linear mixed‐effects models. Results: A total of 466 admissions from 436 patients (mean [SD] age = 39.0 [14.4] years; 54.4% female) met inclusion criteria, comprising 1683 seizures and 1527 interictal clips. SPaRCNet achieved the highest performance (mean [SD] F1 = .61 [.30]), followed by NDD (.56 [.28]) and SVM (.39 [.25]). Absolute decreases in F1 score with reduced montages were modest (≤.09). Patient admission accounted for the most of performance variance (29.2%), followed by detector (10.3%), whereas montage contributed minimally (.4%). Performance between full and reduced montages was correlated ( ρ = .29–.73). Significance: Automated seizure detection performance was primarily driven by patient and algorithm factors rather than montage. Findings support the feasibility of seizure monitoring with reduced montages approximating chronic subscalp device geometries, despite the need for improved detection algorithms, and suggest that EMU‐based full‐montage performance could help identify candidates for these devices.

Importance: Implantable sub-scalp EEG systems with a small number of channels have emerged as promising solutions for long-term seizure monitoring in patients with epilepsy. How seizure detection performance varies by montage configuration is unknown. Objective: To quantify how automated seizure detection performance differs between full and reduced montages, and how these differences vary by epilepsy characteristics. Design: Retrospective cross-sectional study. Setting: Single-center at the Hospital of the University of Pennsylvania Epilepsy Monitoring Unit (EMU). Participants: EEG data from 2281 consecutive EMU admissions between January 2017 and December 2024 were screened. Admissions with at least one annotated seizure and one interictal clip ≥20 minutes from any seizure were included. Exposure: Computational simulation of published sub-scalp device montages using standard 10-20 EEG channels. Main Outcomes and Measures: The primary outcome was event-based F1 scores evaluated for three published seizure detectors—a one-class support vector machine (SVM), a convolutional neural network (SPaRCNet), and a long short-term memory autoregressive model (NDD)—across montages. Results: A total of 466 admissions from 436 patients (mean [SD] age, 39.0 [14.4] years; 54.4% female) met inclusion criteria, comprising 1683 seizures and 1527 interictal clips. SPaRCNet achieved the highest performance (mean [SD] F1, 0.61 [0.30]), followed by NDD (0.56 [0.28]) and SVM (0.39 [0.25]). Performance decreased by at most 0.09 with reduced montages, depending on detectors. Patient factors accounted for the largest proportion of performance variance (29.2%), followed by detector choice (10.3%). Montage effects were minimal (0.4%), despite variation in optimal montage across detectors. Reduced-montage performance correlated moderately to highly with full-montage performance (ρ=0.29–0.73), suggesting full-montage performance could help identify patients suitable for sub-scalp devices. Missed seizures were associated with lower amplitude and bandpowers than detected seizures, though they remained distinguishable from interictal data. Conclusions and Relevance: Automated seizure detection achieved comparable accuracy, with only modest reductions, under simulated reduced montages. Performance differences were driven primarily by detector- and patient-level factors rather than montage. These findings support the feasibility of accurately detecting seizures with published sub-scalp devices and highlight the need for improved algorithms to optimize performance. Key Findings: Question: How do automated seizure detection algorithms perform with reduced-channel montages simulating published sub-scalp devices? Findings: In this retrospective cross-sectional study, seizure detection performance decreased only modestly on reduced montages relative to the full montage (absolute F1 change −0.09 to 0.014), whereas patient- and algorithm-level factors accounted for most of performance variance (29.2% and 10.3%, respectively). Algorithm performance on full montage recordings was moderately correlated with performance on reduced channel montages (ρ=0.29–0.73). Meaning: Reduced-montage sub-scalp devices are promising for ultra-long-term monitoring, but best performance requires selecting the right patients. Patient-specific seizure detectors will likely be required to optimize long-term performance.

Annotating seizure onset and spread in intracranial EEG is essential for epilepsy surgical planning, yet manual annotation is unreliable and cannot scale to large datasets. We introduce Neural Dynamic Divergence (NDD), an unsupervised framework that detects seizure activity by measuring deviation from patient-specific baseline neural dynamics using autoregressive models. NDD requires no labeled training data and adapts to individual patients, channels, and brain states. Validating against expert consensus annotations from 46 seizures, NDD achieves human-level agreement ( ϕ = 0.58 vs. inter-rater ϕ = 0.64) and outperforms existing algorithms on 1,019 seizures with soft labels (AUROC = 0.87). We demonstrate clinical utility by automatically annotating 2,017 seizures, revealing that seizure spread patterns distinguish epilepsy subtypes and predict surgical outcomes. NDD also generalizes to continuous ICU scalp EEG monitoring (AUROC = 0.77). We provide NDD as an open-source Python package to enable scalable seizure annotation across research centers.

IMPORTANCE: Intracranial hypertension (IH) is a life-threatening condition requiring timely intervention. Morphology of the intracranial pressure (ICP) waveform, especially the ratio of the second to the first ICP waveform peaks (P2/P1 ratio), may serve as a biomarker for IH. OBJECTIVES: This study evaluates the potential of the P2/P1 ratio and other morphological features to detect and predict IH and their utility in clinical practice. Design, Setting, and Participants: Retrospective data from 121 patients with brain injury who underwent both ICP and electrocardiographic monitoring across two neurointensive care units at the University of Pennsylvania were collected between July 1, 2015, and October 31, 2024. MAIN OUTCOMES AND MEASURES: Seven ICP morphological features reflecting peak, amplitude, frequency, and shape domains were calculated every minute. IH events were defined as mean ICP greater than or equal to 20 mm Hg for at least 30 minutes. RESULTS: Features effectively detected or predicted IH in only a subset of patients, ranging from 20% to 75% for detection and 13% to 53% for prediction. Amplitude-based features outperformed features in other domains, with mean pulse amplitude (AMP) achieving the highest average area under the receiver operating characteristic curve of 0.83 (95% CI, [0.77–0.88]), compared with 0.71 (95% CI [0.67–0.76]) for the P2/P1 ratio. Better amplitude-based feature performance was associated with female sex and traumatic brain injury diagnoses. Optimal classification thresholds varied across individuals. Applying predicted thresholds in real-time monitoring simulations led to reduced performance. AMP achieved the best, albeit suboptimal, performance, with a false-positive rate of 1.77/hr, and IH detection rates of 36%, 54%, and 65% within 30 minutes before onset, 15 minutes after onset, and over the full event duration, respectively. CONCLUSIONS AND RELEVANCE: The ICP morphological features examined demonstrated limited utility in detecting or predicting IH and, in their current form, may not be suitable for routine clinical use.

One-third of the world’s 70 million people with epilepsy have seizures that are not controlled by medication; and implantable devices are an exciting option for treatment. These devices improve seizure control and can detect impending attacks, missed medication, and impaired cognition. Unfortunately, they have no way to share this information with their hosts in real-time – a limitation common to most medical devices. This is a missed opportunity for implants and wearables to learn from patients, focus on what matters most to them, and teach them how their behavior affects their health. Here, we present a device platform that converses with patients and learns to co-manage epilepsy. The inpatient pro-totype links scalp and intracranial EEG (electroencephalograms) to secure large language models that communicate freely and bidirectionally with their hosts through a smartphone app. An AI agent ingests biomarkers of sleep, medication level, cognition, and seizure risk extracted from brain activity. It con-verses with patients to inform them of clinical events and physiological trends, records their symptoms, responses, and behaviors, and automatically retrains itself to improve performance. Both patients and the AI agent can initiate conversations to teach each other and personalize interactions. We demon-strate this platform in 13 patients undergoing inpatient video-EEG monitoring for epilepsy and validate its performance. Algorithms for detecting seizures optimized their precision over several days without expert intervention – in contrast to the months of iterative, in-person physician programming currently required. Patients responded positively to messages regarding sleep, cognition, and seizure risk while rating the system as highly usable. The platform includes several safeguards, including a system for further algorithm fine-tuning using efficient expert review, and features that ensure data security and regulate communication content. Further work will link other biosensors to measure behavior, improve performance, and optimize therapeutic stimulation. We propose this system as a scalable platform for medical devices that can rapidly adapt to patient and provider needs; one that is broadly adaptable to improving care for many medical conditions.

Summary: In various metazoans, including Drosophila and humans, neural progenitors exit the cell cycle and are eliminated by the end of development, limiting adult neurogenesis. We demonstrate that in Drosophila, the conserved transcription factor Krüppel ( Kr ) controls neurogenic capacity of a specific subset of neuroblasts that forms the mushroom body (MBNBs), analogous to the mammalian hippocampus. The Irregular facet mutation, which alters Kr expression, and neuroblast-specific Kr depletion allow MBNBs, but not other neuroblasts, to persist beyond development and generate neurons in adult brains. Persisting MBNBs express Imp, an RNA-binding protein that promotes neuroblast proliferation and survival. Our results underscore a critical role for Kr in the developmental control of a specific progenitor population, uncovering a novel mechanism controlling adult neurogenesis.

Background. Culturally relevant exercises may help improve health and address disparities faced by older immigrants due to language and cultural barriers. Few studies have focused on such exercise interventions among older Chinese immigrants at US daycare centers. Methods. We conducted a 10-week nonrandomized controlled trial in older Chinese immigrants in Philadelphia, US. The intervention group practiced Chinese Qigong (Baduanjin) 5 days a week guided by trained research assistants and video instructions. The control group maintained their usual daily activities. We collected self-report assessments on overall health, sleep, and fatigue and implemented two computerized cognitive tests measuring psychomotor vigilance task (PVT) and memory twice, preintervention and postintervention. Repeated measures general linear model (GLM) and paired samples t-tests were used for data analyses. Results. Eighty-eight older adults (Qigong, n = 53; control, n = 35) with an average age of 78.13 (SD = 5.05) were included. Groups showed no significant differences at baseline evaluation. After the 10-week exercise, the intervention group showed significant improvements in overall health ( ), fatigue ( ), and cognitive functions including memory ( ), response speed ( ), and response time ( ) on the PVT, as well as marginally significant benefits in sleep ( ). Between-group comparisons identified significant group-by-time interactions in health ( ), sleep ( ), fatigue ( ), and memory ( ). Conclusion. We revealed significant positive effects of Qigong in older Chinese immigrants across multiple health domains. Findings highlight the potential of a culturally relevant exercise in addressing health disparities.

We aim to assess the relationship between nutrition status, physical exercise, and cognitive function and particularly examine how happiness modifies and mediates the relationship, among 699 seniors aged 60 and above in Shanghai, China. Linear regression models were used to validate the effects of nutrition and exercise on cognitive function and to test their interaction effects with happiness. When the interactions were significant, stratified analyses in sub-groups were conducted. Mediation effects of happiness were examined using two-step causal mediation models. We confirmed that better nutrition (p < 0.001) and exercise (p = 0.009) were significantly associated with less cognitive decline. Furthermore, the effects of nutrition and exercise on cognitive decline were significant in the unhappy (happiness < 20) (p < 0.001) and younger (age < 74) sub-groups (p = 0.015). Happiness partially mediated 11.5% of the negative association of cognitive decline with nutrition (p = 0.015) and 23.0% of that with exercise (p = 0.017). This study suggests that happiness moderates and partially mediates the effects of exercise and nutrition on cognitive status. The beneficial effects of exercise and nutrition were stronger in less happy or younger seniors. Future intervention studies are required to confirm this path relationship.

We aim to examine how happiness modifies and mediates the impact of physical activity and nu-trition on cognitive function among 699 seniors aged 60 and above in Shanghai, China. Linear regression models were used to validate the effects of nutrition and exercise on cognitive function, and to test their interaction effects with happiness. When the interactions were significant, strati-fied analyses in sub-groups were conducted. Mediation effects of happiness were examined using two-step causal mediation models. We confirmed that better nutrition (p < 0.001) and exercise (p = 0.009) were significantly associated with less cognitive decline. Furthermore, the effects of nu-trition and exercise on cognitive decline were significant in the unhappy (happiness < 20) (p <0.001) and younger (age < 74) sub-groups (p = 0.015). Happiness partially mediated 11.5% of the negative association of cognitive decline with nutrition (p = 0.015) and 23.0% of that with exercise (p = 0.017). This study suggests that happiness moderates and also partially mediates the effects of exercise and nutrition on cognitive status. The beneficial effects of exercise and nutrition were stronger in less happy or younger seniors. Future intervention studies are required to confirm this path relationship.