Background: Neuropsychological tests (NPTs) are important tools for informing diagnoses of cognitive impairment (CI). However, interpreting NPTs requires specialists and is thus time-consuming. To streamline the application of NPTs in clinical settings, we developed and evaluated the accuracy of a machine learning algorithm using multi-center NPT data. Methods: Multi-center data were obtained from 14,926 formal neuropsychological assessments (Seoul Neuropsychological Screening Battery), which were classified into normal cognition (NC), mild cognitive impairment (MCI) and Alzheimer’s disease dementia (ADD). We trained a machine learning model with artificial neural network algorithm using TensorFlow (https://www.tensorflow.org) to distinguish cognitive state with the 46-variable data and measured prediction accuracies from 10 randomly selected datasets. The features of the NPT were listed in order of their contribution to the outcome using Recursive Feature Elimination. Results: The ten times mean accuracies of identifying CI (MCI and ADD) achieved by 96.66 ± 0.52% of the balanced dataset and 97.23 ± 0.32% of the clinic-based dataset, and the accuracies for predicting cognitive states (NC, MCI or ADD) were 95.49 ± 0.53 and 96.34 ± 1.03%. The sensitivity to the detection CI and MCI in the balanced dataset were 96.0 and 96.0%, and the specificity were 96.8 and 97.4%, respectively. The ‘time orientation’ and ‘3-word recall’ score of MMSE were highly ranked features in predicting CI and cognitive state. The twelve features reduced from 46 variable of NPTs with age and education had contributed to more than 90% accuracy in predicting cognitive impairment. Conclusions: The machine learning algorithm for NPTs has suggested potential use as a reference in differentiating cognitive impairment in the clinical setting.

Park SA, et al. J Clin Neurol. 2022 Jul;18(4):401-409. https://doi.org/10.3988/jcn.2022.18.4.401

Park HK, et al. J Clin Neurol. 2020 Apr;16(2):292-303. https://doi.org/10.3988/jcn.2020.16.2.292

We investigated levels of the β-amyloid 1–42 (Aβ42), total tau protein (T-tau) and tau phosphorylated at position threonine 181 (P-tau) in cerebrospinal fluid (CSF) of idiopathic normal pressure hydrocephalus (iNPH) patients and tried to find their clinical implications in the evaluation and treatment of iNPH. Twenty-five possible iNPH patients were prospectively enrolled and their CSF was collected to analyze levels of Aβ42, T-tau and P-tau using ELISA method. Gait disturbance, urinary incontinence, and cognitive impairment were semi-quantified and detailed neuropsychological (NP) test was performed. Eight iNPH patients were classified into the lower CSF Aβ42 group and 17 patients were classified into the higher CSF Aβ42 group. There was no difference in the iNPH grading score and its improvement after LP between the two groups. The lower CSF Aβ42 group showed more deficits in attention, visuospatial function and verbal memory in the baseline NP test and less improvement in phonemic categorical naming and frontal inhibitory function after LP. Our study suggested that concomitant AD in iNPH patients might contribute to lumbar puncture or shunt unresponsiveness, especially in the field of cognitive dysfunction.

Background: Type 2 diabetes is related to an increased risk of dementia. Preclinical studies of dipeptidyl peptidase-IV inhibitors (DPP-4i) for dementia have yielded promising results. Therefore, we investigated the risk of dementia in elderly patients with type 2 diabetes on DPP-4is and sulfonylureas (SU). Methods: Using a claims database called the Korean National Health Insurance Service Senior cohort, new users of DPP-4is and SUs were matched by 1:1 propensity score matching using 49 confounding variables (7552 new DPP-4is users and 7552 new SU users were matched by 1:1 propensity score matching; average age 75.4; mean follow-up period: 1361.9 days). Survival analysis was performed to estimate the risk of dementia. Results: The risk of all-cause dementia was lower in the DPP-4i group compared to the SU group (hazard ratio (HR) 0.66; 95% confidence interval (CI) 0.56–0.78; p < 0.001). Particularly, DPP-4i use showed a significantly lower risk of Alzheimer’s disease (HR 0.64; 95% CI 0.52–0.79; p < 0.001) and a lower risk, albeit non-significant, of vascular dementia compared to SU use (HR 0.66; 95% CI 0.38–1.14; p = 0.139). Conclusion: Our findings suggest that DPP-4i use decreases the risk of dementia compared to SU use in elderly patients with type 2 diabetes in a real-world clinical setting.

Park KH, et al. Dement Neurocogn Disord. 2024 Oct;23(4):165-187. https://doi.org/10.12779/dnd.2024.23.4.165