BACKGROUND:Previous research has illustrated links between dental care and Alzheimer's disease, the aim of this study was to examine whether dental care variables can enhance Alzheimer's risk prediction using two models including Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) models with health and retirement study data. METHODS:9,979 HRS participants without cognitive impairment were analysed in this study (mean age 67 years; and 59.8% female, waves 11-15: 2006/2008-2016). Analysis included 52 predictors including demographic, genetic (APOE ε4), health (including dental visit frequency), and psychosocial domains. The outcomes as cognitive impairment and dementia were defined by Langa-Kabeto-Weir criteria. Class imbalance was addressed by SMOTE and missing data were mean imputed. We standardized and reshaped features into five-wave temporal sequences. Data were split into 3 sets: 70% training, 10% validation, and 20% test. LSTM (single layer, 64 units) and TCN (two dilated convolutional layers, 32 channels) models were trained for up to 50 epochs using binary cross-entropy loss with Adam optimizer, learning-rate reduction on plateau, and early stopping based on validation F1. The accuracy, precision, recall, F1, and AUC-ROC were evaluated via Five-fold stratified cross-validation; the optimization of classification thresholds was done by maximizing F1. McNemar's test compared final predictions. RESULTS:It was evident that LSTM consistently outperformed TCN as demonstrated by the following results: test accuracy 99.78% vs 79.01%; AUC-ROC 99.95% vs 92.74%; F1-score 99.67% vs 75.27%. Cross-validation consistency (LSTM F1 ~99.6%±0.1% vs TCN ~76.6%±1.5%) and stable validation-test metrics (final validation loss 0.0136 vs 0.3312) showed robust LSTM performance without overfitting. moreover, McNemar's test showed a significant difference (statistic = 2605.36; P<0.001). models with dental care variables showed high sensitivity (~99.8%). CONCLUSIONS:Enhancement in Alzheimer's disease risk prediction in older adults was evident when incorporating dental care variables in LSTM-based sequential modeling which suggest potential for early detection. However, further studies in diverse populations and assessment of feature importance is necessary because of reliance on self-reported dental care data and the study's HRS-specific sample.
BACKGROUND:This study aims to determine if self-reported issues with managing medication could be an early sign of cognitive decline, possibly pointing to a future diagnosis of Alzheimer's Disease and Related Dementias (ADRD). There is currently very little information available about the link between issues with medication management and the later diagnosis of an ADRD, despite the potential clinical importance of such a link. METHODS:We analyzed Health and Retirement Study participants present and interviewed at Wave 11 (2012) and followed them through Wave 16 (2020). Medication-taking difficulty (R11MEDS) was classified as no difficulty/don't do vs. difficulty/can't do. Separate cohorts excluded prevalent dementia (R11DEMENE) or AD (R11ALZHEE). Incident outcomes were first respondent-reported physician diagnoses (RwDEMENE, RwALZHEE). Kaplan-Meier curves and multivariable Cox models estimated associations. RESULTS:Of 18,878 dementia-free and 19,348 AD-free HRS respondents at Wave 11, 3.0-3.9% reported difficulty/could not take medications. Kaplan-Meier curves diverged early between exposure groups. In fully adjusted Cox models, medication-taking difficulty predicted higher hazards of incident all-cause dementia (HR 1.59, 95% CI 1.23-2.06) and AD (HR 1.57, 95% CI 1.09-2.27), with corroborating pooled logistic estimates. CONCLUSION:Difficulty in Managing Medications is considered to be a robust prodromal indicator of ADRD, regardless of demographic influences. Therefore, the evaluation of an individual's ability to manage medications within routine assessment may represent a practical, costeffective means to identify cognitive decline and develop appropriate management strategies.
Brucellosis is a prevalent zoonotic disease that is associated with consuming produce from animals infected with Brucella species, usually in the form of unpasteurized milk and milk products. The involvement of the central nervous system (CNS) is an uncommon but dangerous indication of neurobrucellosis. Neurobrucellosis can cause specific imaging findings on magnetic resonance imaging (MRI). In this study, we report a very rare case of neurobrucellosis presenting with stroke-like symptoms that were treated using antibiotics. A 38-year-old male was referred with a presenting complaint of headache, ataxia, and dysarthria. He was admitted one month prior for possible cerebral vascular accident (CVA), which was ruled out. On neurological examination, left-central facial paralysis and bilateral positive Babinski sign were observed. The brain magnetic resonance imaging (MRI) performed with and without contrast demonstrated an acute ischemic stroke in the right middle cerebral artery (MCA) territory and extra-axial heterogeneous ring-enhancing lesions, respectively. Brucellosis was confirmed on serological assessment. In rare instances, neurobrucellosis can cause stroke-like symptoms and brain abscesses. Neurobrucellosis should be considered in such patients when other neurological disorders cannot explain neuroimaging abnormalities.
BACKGROUND:Focal cortical dysplasia (FCD) is a congenital deformity caused by FCD maturation, differentiation, and neuronal migration. Magnetic resonance imaging (MRI) is one of the most popular and consistent procedures for diagnosing FCD. Limited research has evaluated the relationship between the FCD and thalamic volume. Therefore, we conducted the current study to compare thalamic volumes between patients with FCD and healthy individuals. METHODS:The current study was a cross-sectional study of patients with FCD referred to Kashani and Milad Hospitals in Isfahan City in 2019-2021. All patients who met the inclusion criteria were enrolled in the study using the census method. The study population was divided into two groups: patients with FCD and healthy controls. MRI was performed on patients with FCD using a Siemens 1.5 or 3 Tesla MRI device. The data were analyzed using SPSS Statistics for Windows (IBM SPSS Statistics for Windows, Version 18.0). RESULTS:Among the 60 patients, 30 had FCD with a mean age of 22.6 ± 9.3 years, and 30 were healthy with a mean age of 26.3 ± 3.6 years. The only significant difference observed was between the right and left thalamic volumes in the FCD group (P = 0.042). The thalamus on the involved side was significantly smaller than that on the non-involved side in patients (P-value < 0.001). However, no significant differences were observed in the absolute value of the difference between the left and right thalamic volumes when comparing all patients with FCD to those in the non-FCD group (P = 0.054). CONCLUSION:Our study showed that in patients with FCD, the thalamus on the involved side was significantly smaller than that on the noninvolved side.
BACKGROUND:Congenital myasthenic syndromes (CMS) are rare inherited disorders of neuromuscular transmission caused by mutations in presynaptic, synaptic, or postsynaptic components. They usually manifest in childhood with fatigability, ptosis, ophthalmoplegia, and generalized weakness, but late presentations also occur. CASE SUMMARY:We report a 20-year-old male presenting with heart failure and respiratory failure who was found to have a heterozygous AGRN gene mutation (c.4319>T; p. Pro1440Leu). Clinical features included muscle wasting, weakness, restricted gaze, and respiratory compromise requiring ICU care. Genetic sequencing confirmed AGRN-related CMS. Management included ICU support, pyridostigmine trial, heart failure therapy, salbutamol, and fluoxetine with improvement. DISCUSSION:Diagnosis of CMS requires clinical suspicion, characteristic electrophysiology, and genetic confirmation. Treatment varies with subtype; AGRN-related CMS responds variably to salbutamol and ephedrine, while cholinesterase inhibitors may be ineffective. Prognosis depends on timely diagnosis and management.
