Kim DW, et al. J Korean Med Sci. 2019 Oct;34(43):e285. https://doi.org/10.3346/jkms.2019.34.e285

Objective The global impact of respiratory infectious diseases led to significant mental health challenges, highlighting the need for proactive psychological interventions to prepare for future pandemics. In response, virtual reality-based stabilization (VRS) was developed to mitigate posttraumatic stress symptoms (PTSS) and related comorbidities.Methods This study evaluated and predicted the effectiveness of VRS in 43 coronavirus disease-2019 (COVID-19) survivors and healthcare workers from COVID-19 treatment units. The effectiveness of VRS, conducted over five sessions, was measured using preand post-intervention psychological assessments for PTSS, depression, anxiety, COVID-related fear, posttraumatic growth, and quality of life. Additionally, a machine learning model was used to predict the impact of the intervention on PTSS and depression based on preintervention psychological assessments and heart rate variability tests.Results The post-intervention results showed significant improvements in all psychological outcomes. The machine learning-based model demonstrated good predictive accuracy for changes in PTSS and depression (R2=0.414–0.723). Notably, individuals with higher pre-intervention scores for PTSS and related comorbidities, as well as elevated heart rate variability and younger age, exhibited more significant improvements.Conclusion These findings suggest that VRS is effective in addressing PTSS and related conditions, and incorporating clinical and demographic data can enhance prediction models, enabling more personalized intervention strategies.

Background: It has been reported in many previous studies that the lack of auditory input due to hearing loss (HL) can induce changes in the brain. However, most of these studies have focused on individuals with pre-lingual HL and have predominantly compared the characteristics of those with normal hearing (NH) to cochlear implant (CI) users in children. This study examined the visual and auditory evoked potential characteristics in NH listeners, individuals with bilateral HL, and CI users, including those with single-sided deafness. Methods: A total of sixteen participants (seven NH listeners, four individuals with bilateral sensorineural HL, and five CI users) completed speech testing in quiet and noise and evoked potential testing. For speech testing, the Korean version of the Hearing in Noise Test was used to assess individuals’ speech understanding ability in quiet and in noise (noise from the front, +90 degrees, and −90 degrees). For evoked potential testing, visual and auditory (1000 Hz, /ba/, and /da/) evoked potentials were measured. Results: The results showed that CI users understood speech better than those with HL in all conditions except for the noise from +90 and −90 degrees. In the CI group, a decrease in P1 amplitudes was noted across all channels after implantation. The NH group exhibited the highest amplitudes, followed by the HL group, with the CI group (post-CI) showing the lowest amplitudes. In terms of auditory evoked potentials, the smallest amplitude was observed in the pre-CI condition regardless of the type of stimulus. Conclusions: To the best of our knowledge, this is the first study that examined visual and auditory evoked potentials based on various hearing profiles. The characteristics of evoked potentials varied across participant groups, and further studies with CI users are necessary, as there are significant challenges in collecting and analyzing evoked potentials due to artifact issues on the CI side.

Mild cognitive impairment (MCI) is an intermediary stage between typical cognitive aging and dementia. Identifying reliable biomarkers for early detection of MCI is crucial for slowing disease progression. This study explored multimodal biomarkers associated with amyloid-positive MCI and assessed wearable EEG/ERP and MRI features using machine learning. This study included 70 patients with MCI with amyloid-positive positron emission tomography (PET) scans and 140 cognitively normal (CN) individuals with negative PET scans. Data were collected using prefrontal wearable EEG/ERP and MRI devices. EEG data were obtained in three paradigms: resting-state, sensory-evoked potentials, and selective attention tasks. Machine learning techniques were applied to classify MCI and CN groups using these biomarkers. EEG/ERP analysis suggested differences in frontal alpha asymmetry, power ratio, and ERP components between the MCI and CN groups. MRI revealed atrophy of the hippocampus and accumbens along with cortical thinning in specific brain regions. Combining EEG/ERP and MRI features in a machine learning model yielded the highest classification accuracy of 80.90%. Prefrontal wearable EEG/ERP and MRI offered complementary candidate biomarkers of MCI in community-dwelling individuals using a machine learning approach. These findings support further validation of EEG/ERP and MRI biomarkers in larger and externally validated cohorts.

Background: Subjective cognitive decline (SCD) has been recognized as a preclinical stage of Alzheimer’s disease. However, the identification of early functional brain changes remains challenging. This study investigated the functional brain changes in SCD using longitudinal EEG and evaluate the feasibility of EEG features as scalable biomarkers for identifying amyloid burden and cognitive decline using an interpretable machine learning framework. Methods: We analyzed 120 individuals with SCD enrolled in a multicenter prospective cohort (the CoSCo study) at baseline and after a 2-year follow-up. Participants were classified as amyloid-positive (A + SCD) or amyloid-negative (A − SCD). Spectral power and graph theory-based network analyses were conducted. Also, we trained machine learning classifiers to distinguish between the groups and interpreted the predictions of classifiers using SHAP. Results: At both baseline and follow-up, the A + SCD group exhibited elevated low-frequency (delta and theta) activity and reduced alpha activity compared to the A − SCD group. The EEG-based classifiers distinguished A + SCD from A-SCD individuals with high performance, outperforming a classifier based on demographic data. The results of SHAP analysis confirmed the importance and relative contribution of selected EEG features. Conclusions: Longitudinal EEG, when combined with interpretable machine learning, can detect and track the functional alterations of brain related to amyloid pathology in preclinical AD. Our findings support the feasibility of EEG as a non-invasive, scalable, and sensitive biomarker for risk stratification, before overt cognitive impairment emerges. Trial registration: This study was registered at the Clinical Research Information Service (CRIS) (cris.nih.go.kr/cris; # KCT0003397, Registration Date: December 21, 2018).

Ryoo N, et al. J Cogn Interv Digit Health. 2024 Dec;3(1):1-11. https://doi.org/10.58558/jcd.2024.3.1.1