Faculty Bibliography

INTRODUCTION/BACKGROUND:This study aimed to explore the experience of living with amyotrophic lateral sclerosis (ALS) and to develop a conceptual model for this rare disease. METHODS:Concept elicitation interviews were conducted (January-September 2024) with people living with ALS (PLwALS; n = 31), caregivers (n = 20), and clinicians (n = 10). Qualitative data were analyzed separately to develop a conceptualization of the experience of living with ALS. Concept saturation was assessed every 5-6 interviews, and a conceptual model was developed. RESULTS:The mean age of PLwALS was 42.4 years (standard deviation [SD] 11.5), 81% were female, 84% were white, and 23% had SOD1-ALS. The mean time since diagnosis was 4.6 years (SD 4.2); mean normed Rasch Overall ALS Disability Scale score was 76 (SD 17.16). Signs, symptoms, and functions reported during PLwALS interviews included neuromuscular, bulbar, speech, neurocognitive (e.g., memory issues), and a range of physical functioning issues (e.g., motor coordination). PLwALS also reported impacts on a range of activities and psychosocial interactions (e.g., eating, depressed mood, and relationships), alongside management strategies they employed. Interviews with caregivers and clinicians supported findings from the PLwALS interviews. Caregivers also identified signs such as drooling/excess salivation, and impacts related to ALS management (e.g., need for writing aids). Clinicians additionally considered loss of speech and neurocognitive signs (e.g., behavior/personality change) as ALS clinical manifestations. Concept saturation was reached, and a consolidated, comprehensive conceptual model was developed. CONCLUSION/CONCLUSIONS:This research provides a holistic understanding of the experience of living with ALS and is the first conceptual model based on in-depth concept elicitation interviews. The findings highlight the range of signs, symptoms, and impacts that PLwALS experience, emphasizing its serious humanistic impact and high unmet need, and will help to guide patient-centric evaluation of clinical outcome assessments in future ALS studies.

Stroke recovery outcomes vary across individuals, motivating the search for biomarkers that can improve prediction. White matter hyperintensities (WMH) volume is a leading biomarker candidate, with FLAIR MRI typically used for WMH segmentation; however, T1-weighted (T1) MRI is often more available. Therefore, we evaluated the performance of two automated WMH segmentation methods (WMH-SynthSeg, SAMSEG) to determine whether WMH volume can be reliably estimated using T1 alone. We analyzed imaging data from 227 stroke patients across three datasets spanning early subacute to chronic recovery, with gold-standard WMH masks and stroke lesion masks manually traced on available T1 and FLAIR scans. WMH was segmented using T1 only as input to WMH-SynthSeg and SAMSEG, as well as using both T1 and FLAIR as input to SAMSEG, as previously implemented in stroke recovery research. Automated WMH segmentations were compared to the gold-standard WMH mask: spatial accuracy was assessed using Dice similarity index (SI) and cluster-level false negative ratio, while volumetric agreement was assessed using intraclass correlation, Pearson's correlation, and volume ratio. We used linear mixed-effects models to evaluate whether SI was influenced by factors such as WMH volume, stroke lesion volume, WMH contrast, age, sex, and days since stroke, with dataset as a random effect. WMH-SynthSeg using T1-only input produced more accurate and reliable WMH segmentations compared to SAMSEG with T1-only input and performed comparably to SAMSEG using both T1 and FLAIR input. WMH-SynthSeg using T1-only input may be used for WMH volume estimation in stroke recovery research in the absence of multimodal imaging.

BACKGROUND AND OBJECTIVES/OBJECTIVE:Traditional medical board examinations present clinical information in static vignettes with multiple-choices (MC), fundamentally different from how physicians gather and integrate data in practice. Recent advances in large language models (LLMs) offer promising approaches to creating more realistic clinical interactive conversations. However, these approaches are limited in neurosurgery, where patient communication capacity varies significantly and diagnosis heavily relies on objective data such as imaging and neurological examinations. We aimed to develop and evaluate a multi-artificial intelligence (AI) agent conversation framework for neurosurgical case assessment that enables realistic clinical interactions through simulated patients and structured access to objective clinical data. METHODS:We developed a framework to convert 608 Self-Assessment in Neurological Surgery first-order diagnosis questions into conversation sessions using 3 specialized AI agents: patient AI for subjective information, system AI for objective data, and clinical AI for diagnostic reasoning. We evaluated generative pretrained transformer 4o's (GPT-4o's) diagnostic accuracy across traditional vignettes, patient-only conversations, and patient + system AI interactions, with human benchmark testing from 10 neurosurgery residents. RESULTS:= .0030) using fewer interactions and reported high educational value of the interactive format. CONCLUSION/CONCLUSIONS:This multi-AI agent framework provides both a more challenging evaluation method for LLMs and an engaging educational tool for neurosurgical training. The significant performance drops in conversational formats suggest that traditional MC testing may overestimate LLMs' clinical reasoning capabilities, while the framework's interactive nature offers promising applications for enhancing medical education.

BACKGROUND AND OBJECTIVES/OBJECTIVE:Implementation of telemedicine expanded options for outpatient neurology care. It remains uncertain which new neurology patients can be appropriately evaluated virtually. We compared subsequent health care utilization after virtual vs in-person new patient neurology visits across 3 academic medical centers. METHODS:We conducted a retrospective multicenter cohort study of adults with a new outpatient neurology visit from September 2020 through December 2021 using the Vizient Clinical Data Base and Clinical Practice Solutions Center databases. Virtual and in-person patients were matched 1:1 using propensity scores incorporating demographics, clinical characteristics, time period, and previous health care utilization. Outcomes were analyzed overall and stratified by neurologic chief complaint category and institution. We compared rates of subsequent neurologic clinic follow-up, emergency department (ED) visits, and hospitalizations after virtual and in-person encounters. Testing and all-cause ED visits/hospitalizations were also assessed. RESULTS:= 0.13, respectively). Analyses by chief complaint found that 90-day follow-up was higher after in-person visits for dementia, whereas 30- and 90-day follow-up was higher after virtual visits for Parkinson disease and multiple sclerosis, and 90-day follow-up was higher after virtual visits for headache. Testing was more frequent after in-person visits for certain chief complaints. DISCUSSION/CONCLUSIONS:In this propensity score-matched multicenter cohort, new neurology patients seen virtually had similar downstream utilization as those seen in-person, including comparable 90-day follow-up and similar neurologic and all-cause ED visits and hospitalizations. Although follow-up varied modestly by chief complaint and testing was more frequent after some in-person visits, no major differences emerged overall.

Deep venous drainage (DVD) is considered a negative prognostic factor in AVM surgery, yet its effect on postoperative functional decline remains incompletely defined. This study evaluates whether DVD predicts worsened functional status after surgical resection of Spetzler-Martin Grade II-III AVMs. This retrospective multicenter study analyzed 129 patients with Spetzler-Martin Grade II-III AVMs across nine centers in North America and Europe who underwent primary surgical resection. We excluded cases with prior endovascular or stereotactic interventions. The primary outcome measured was poor functional status, defined as modified Rankin Scale (mRS) score 3-6 at last follow up. Among 129 patients with Spetzler-Martin Grade II-III AVMs, 38 (29.5%) exhibited deep venous drainage (DVD). Poor functional outcome (mRS ≥ 3) at last follow-up occurred in 14 patients (10.9%). This occurred in 6 of 38 patients with DVD (15.8%) compared with 8 of 91 without DVD (8.8%; Fisher's exact p = 0.244). On univariate Firth-penalized logistic regression, DVD was not significantly associated with poor outcome (OR 1.96, 95% CI 0.65-5.89; p = 0.228). In the primary reduced Firth model adjusting for age and pre-existing functional disability, DVD was independently associated with poor outcome (OR 6.87, 95% CI 1.07-44.20; p = 0.042). Increasing age (OR 1.08 per year, 95% CI 1.02-1.13; p = 0.004) and pre-existing functional disability (OR 6.53, 95% CI 1.63-26.22; p = 0.008) were also independently associated with poor outcome. DVD is associated with functional decline following surgical resection of Spetzler-Martin Grade II-III AVMs after adjustment for age and pre-existing functional disability.

BACKGROUND/UNASSIGNED:Attention impairment is common in post-traumatic brain injury. We synthesized evidence on pharmacological treatments for adults with attention deficits in the acute-to-chronic phases. METHODS/UNASSIGNED:We searched Ovid MEDLINE and Cochrane Library (1946-December 2024). Two reviewers screened studies, extracted data, and assessed study quality. Risk of bias was assessed using the Cochrane Risk of Bias tool and the PEDro scale for RCTs. Levels of evidence (LoE) were determined by the Sackett framework. RESULTS/UNASSIGNED:Twenty-nine studies met inclusion criteria across five drug classes and 14 medications. Results of LoE 1 were mixed: Methylphenidate improved classroom attention/processing speed, and exhibited neutral outcome; amantadine showed no improvement (LoE 1, 4, 5). MLC901 (a multi-herb antioxidant) improved complex attention (LoE 1). Donepezil improved sustained (LoE 1) and divided attention (LoE 4). Physostigmine/lecithin (LoE 1) and antidepressants (LoE 1, 3, 5) had mixed effects; growth hormone (LoE 4), and L-carnitine (LoE 1) showed no effect. Anticonvulsants impaired cognition (LoE 1). CONCLUSION/UNASSIGNED:Methylphenidate showed the strongest evidence at lower doses. Donepezil and MLC901 showed potential benefits. Phenytoin and carbamazepine showed adverse effects on cognition. Standardized attention outcome measures and other high-quality alternative clinical trials with larger study samples are recommended to overcome the current limitations.

OBJECTIVE:This study was undertaken to evaluate whether seizure freedom in pregnancy predicts seizure freedom in the postpartum period in women with epilepsy (WWE). Prior studies have shown that seizure freedom prior to conception strongly predicts seizure freedom during pregnancy. The postpartum period is considered especially vulnerable to recurrent seizures given rapid hormonal changes, shifting antiseizure medication pharmacokinetics, and disrupted sleep. There is a lack of sufficient data on whether seizure freedom during pregnancy predicts postpartum outcomes. METHODS:Pregnant WWE (aged 14-45 years) were enrolled at <20 weeks gestation in the prospective Maternal Outcomes and Neurodevelopmental Effects of Antiepileptic Drugs study. Participants completed electronic daily seizure and medication diaries with study visits each trimester, and at 6-12 weeks and 6 and 9 months postpartum. Participants also reported retrospective seizure frequency for the 9 months preconception. We used logistic regression to assess whether seizure freedom during pregnancy predicted seizure freedom postpartum, with additional analyses by seizure types. In participants with seizures during pregnancy, we evaluated median percent change in seizure frequency. RESULTS:This analysis included 331 pregnant WWE. Overall, 60.7% were seizure-free during pregnancy and 61.0% postpartum. Seizure freedom during pregnancy strongly predicted seizure freedom postpartum (odds ratio [OR] = 6.78, 95% confidence interval [CI] = 4.15-11.1, p < .0001), with a predictive value of 78% (95% CI = 72%-84%). Retrospectively reported preconception seizure freedom was also independently associated with postpartum seizure freedom (OR = 5.84, 95% CI = 3.57-9.58, p < .0001). Long-term seizure freedom during pregnancy and preconception was associated with 85% postpartum seizure freedom, whereas long-term presence of seizures was associated with only 36% postpartum seizure freedom. There were no significant differences by seizure type. Among participants with seizures during pregnancy, median postpartum seizure frequency declined by 77% (interquartile range = seizure-free to 31% reduced). SIGNIFICANCE/CONCLUSIONS:Our data demonstrated that seizure freedom during pregnancy was a robust predictor of seizure freedom during the postpartum period. These data can be used to counsel patients about seizure risk in the postpartum period.

PURPOSE/UNASSIGNED:Optical character recognition (OCR), a process that converts printed or handwritten text into machine-readable form, is widely used in assistive technology for people with blindness and low vision. Yet most evaluations rely on static datasets that do not reflect the challenges of mobile use. This study evaluated how OCR performance changes under static and walking conditions relevant to real-world navigation. METHODS/UNASSIGNED:Static tests varied distance from 1-7 metres and viewing angle from 0°-75°. Dynamic tests examined the impact of motion by varying walking speed from 0.8 m/s to 1.8 m/s and compared head-mounted, shoulder-mounted, and handheld positions. We evaluated a smartphone and smart glasses, including the phone's main and ultra-wide cameras, across four OCR engines: Google Vision, PaddleOCR 3.0, EasyOCR, and Tesseract. Dynamic tests used PaddleOCR 3.0. Accuracy was computed at the character level using the Levenshtein ratio against manually defined ground truth. RESULTS/UNASSIGNED:Recognition accuracy declined with increased walking speed and wider viewing angles. Google Vision achieved the highest overall accuracy, with PaddleOCR close behind as the strongest open-source alternative. Across devices, the phone's main camera achieved the highest accuracy, and a shoulder-mounted placement yielded the highest average among body positions; however, differences among shoulder, head, and hand were not statistically significant. CONCLUSION/UNASSIGNED:OCR performance depends on the recognition engine, camera hardware, field of view, device placement, and user motion. OCR systems for navigation should be evaluated under dynamic, mobility-relevant conditions rather than static images alone and designed to balance coverage, recognition accuracy, and practical deployment.