Accurately Identifying Cerebroarterial Stenosis from Angiography Reports Using Natural Language Processing Approaches.

Patients with intracranial artery stenosis show high incidence of stroke. Angiography reports contain rich but underutilized information that can enable the detection of cerebrovascular diseases. This study evaluated various natural language processing (NLP) techniques to accurately identify eleven intracranial artery stenosis from angiography reports. Three NLP models, including a rule-based model, a recurrent neural network (RNN), and a contextualized language model, XLNet, were developed and evaluated by internal-external cross-validation. In this study, angiography reports from two independent medical centers (9614 for training and internal validation testing and 315 as external validation) were assessed. The internal testing results showed that XLNet had the best performance, with a receiver operating characteristic curve (AUROC) ranging from 0.97 to 0.99 using eleven targeted arteries. The rule-based model attained an AUROC from 0.92 to 0.96, and the RNN long short-term memory model attained an AUROC from 0.95 to 0.97. The study showed the potential application of NLP techniques such as the XLNet model for the routine and automatic screening of patients with high risk of intracranial artery stenosis using angiography reports. However, the NLP models were investigated based on relatively small sample sizes with very different report writing styles and a prevalence of stenosis case distributions, revealing challenges for model generalization.

A disease-specific language representation model for cerebrovascular disease research.

BACKGROUND: Effectively utilizing disease-relevant text information from unstructured clinical notes for medical research presents many challenges. BERT (Bidirectional Encoder Representation from Transformers) related models such as BioBERT and ClinicalBERT, pre-trained on biomedical corpora and general clinical information, have shown promising performance in various biomedical language processing tasks. OBJECTIVES: This study aims to explore whether a BERT-based model pre-trained on disease-related clinical information can be more effective for cerebrovascular disease-relevant research. METHODS: This study proposed the StrokeBERT which was initialized from BioBERT and pre-trained on large-scale cerebrovascular disease related clinical text information. The pre-trained corpora contained 113,590 discharge notes, 105,743 radiology reports, and 38,199 neurological reports. Two real-world empirical clinical tasks were conducted to validate StrokeBERT's performance. The first task identified extracranial and intracranial artery stenosis from two independent sets of radiology angiography reports. The second task predicted the risk of recurrent ischemic stroke based on patients' first discharge information. RESULTS: In stenosis detection, StrokeBERT showed improved performance on targeted carotid arteries, with an average AUC compared to that of ClinicalBERT of 0.968 ± 0.021 and 0.956 ± 0.018, respectively. In recurrent ischemic stroke prediction, after 10-fold cross-validation on 1,700 discharge information, StrokeBERT presented better prediction ability (AUC±SD = 0.838 ± 0.017) than ClinicalBERT (AUC±SD = 0.808 ± 0.045). The attention scores of StrokeBERT showed better ability to detect and associate cerebrovascular disease related terms than current BERT based models. CONCLUSIONS: This study shows that a disease-specific BERT model improved the performance and accuracy of various disease-specific language processing tasks and can readily be fine-tuned to advance cerebrovascular disease research and further developed for clinical applications.

Age-related changes of task-specific brain activity in normal aging.

An important question in healthcare for older patients is whether age-related changes in cortical reorganization can be measured with advancing age. This study investigated the factors behind such age-related changes, using time-frequency analysis of event-related potentials (ERPs). We hypothesized that brain rhythms was affected by age-related changes, which could be reflected in the ERP indices. An oddball task was conducted in two experimental groups, namely young participants (N=15; mean age 23.7±2.8 years) and older participants (N=15; mean age 70.1±7.9 years). Two types of stimuli were used: the target (1 kHz frequency) and standard (2 kHz frequency). We scrutinized three ERP indices: event-related spectral power (ERPSP), inter-trial phase-locking (ITPL), and event-related cross-phase coherence (ERPCOH). Both groups performed equally well for correct response rate. However, the results revealed a statistically significant age difference for inter-trial comparison. Compared with the young, the older participants showed the following age-related changes: (a) power activity decreased; however, an increase was found only in the late (P3, 280-450 ms) theta (4-7 Hz) component over the bilateral frontal and temporo-frontal areas; (b) low phase-locking in the early (N1, 80-140 ms) theta band over the parietal/frontal (right) regions appeared; (c) the functional connections decreased in the alpha (7-13 Hz) and beta (13-30 Hz) bands, but no difference emerged in the theta band between the two groups. These results indicate that age-related changes in task-specific brain activity for a normal aging population can be depicted using the three ERP indices.

Psychiatric morbidity in dementia patients in a neurology-based memory clinic.

The behavioral and psychological symptoms of dementia (BPSD) often present major problems for patients and their caregivers. In the past, neurologists paid less attention to such symptoms than to the cognitive symptoms of dementia. This prospective study investigated the prevalence of psychiatric morbidity in a neurology-based memory clinic and the stress of caregivers. Our patients with dementia were found to have a high prevalence of BPSD. The most frequent were anxiety, apathy, and delusion; the most distressing to caregivers were agitation, anxiety, delusion, and sleep disturbance. Using Clinical Dementia Rating (CDR), we compared BPSD between patients with mild dementia and those with moderate dementia. Only hallucinations and agitation were different significantly. Moderate dementia patients experienced these symptoms more frequently. The high prevalence of these symptoms might be explained by the fact that the cognitive symptoms were neglected or no enough information were received by many family members of patients with dementia until their own life quality was interfered and then they began to seek medical help. These symptoms and their effect of caregiver distress can be effectively reduced by pharmacologic and nonpharmacoloic managements, caregiver-focused training and education. They can be better approached by assessing neuropsychiatric symptoms regularly, educating the general population better, and treating these patients earlier.