Neurology News Network for the week ending August 7, 2021.
Welcome to this special edition of Neurology News Network. I’m Marco Meglio. Please excuse our appearance this week as a majority of the US workforce, including the NeurologyLive team, moves to working remote as we come together to help reduce the spread of the novel coronavirus.
Findings from a recent study indicate automatic seizure detection using machine learning (ML) from multimodal sensor data is feasible to detect a broad range of epileptic seizures. Pediatric participants wore sensors on wrists or ankles, with ML models trained to detect all seizure types performing better than models trained to detect specific types. Of the 94 patients included in the study, investigators reported a total of 548 epileptic seizures over the course of 11,066 hours of sensor data collection, resulting in 930 seizures in total and 9 seizure types. A combination of accelerometry (ACC) and blood volume post (BVP) data with convolutional neural network algorithms achieved the best overall area under the receiver operating characteristic curve. Algorithm 1, which was trained with seizure-type specific detection models of 9 seizure types, detected 8 out of 9 seizure types better than chance. Algorithm 2, which had a general type-agnostic seizure detection system for all seizure types, detected all 9 seizure types better than chance.
Despite observing a high SARS-CoV-2 seroconversion rate among patients with multiple sclerosis (MS) or neuromyelitis optica spectrum disorder (NMOSD), those treated with an anti-CD20 therapy had a seroconversion rate 2 times as low as untreated patients or patients receiving a non-anti-CD20 disease modifying therapy. ccording to the study authors, these findings, while heterogenous in nature, warrant monitoring the long-term risk of reinfection and specific vaccination strategies for patients within these populations.Overall, seroconversion rate was 80.6% (n = 96) within 5 months after infection. Specific subanalysis showed that those on anti-CD20 therapies had lower anti-S IgG positivity (P <.001), lower anti-S IgG titer (P <.001), lower anti-S IgA positivity (P = .05), and a lower anti-N IgG positivity (P <.001) in comparison to other DMT groups. Notably, there were no observed differences on such outcomes between the other DMT subgroups.
A longitudinal cohort study published in JAMA has identified a link between the age of onset of type 2 diabetes and the risk of dementia, concluding that patients diagnosed with type 2 diabetes at a younger age were consequently diagnosed with dementia at a younger age. A total of 10,095 participants were included in study analyses, with investigators reporting a total of 1710 (16.9%) cases of diabetes and 639 (6.3%) cases of dementia over the median follow-up period of 31.7 years (1985-2019). Investigators saw a higher increased hazard of dementia with every 5-year earlier onset of diabetes, with dementia rates per 1000 person-years at 8.9 in participants without diabetes at 70 years; 10.0 per 1000 person-years for participants with diabetes onset up to 5 years earlier; and 18.3 for over 10 years earlier.
For more direct access to expert insight, head to NeurologyLive.com. This has been Neurology News Network. Thanks for watching.