Strzelczyk, D. | Search bioRxiv

bioRxiv2022

Neurophysiological markers of successful learning in healthy aging

The capacity to learn and memorize is a key determinant for the quality of life, but is known to decline to varying degrees with age. Previous ERP research methods had the limitation that their design did not allow to track the gradual memory formation process. Thus, the neural mechanisms underlying memory formation and the critical features that determine the extent to which aging affects learning are still unknown. By using a visual sequence learning task, which consists of the repeated presentation of a simple sequence of tokens, we are able to track the progress of gradual memory formation through both neurophysiological and behavioral markers. On a neurophysiological level, we focused on two learning related centroparietal ERP components: the P300 and broad positivity. Our results revealed that although both age groups showed significant learning progress, young individuals learned faster and remembered more stimuli than older participants. Successful learning was directly linked to a decrease of P300 amplitude. However, young participants showed larger P300 amplitude with a sharper decrease during the memory formation process. The P300 amplitude predicted learning success in both age groups, was associated with increased fronto-parietal brain network activation and showed good test-retest reliability. Highly, similar results were found for the broad positivity component, which raises the questions if the BP is a distinct component or just a prolonged P300. In a series of analyses, including topographic analysis of variance (TANOVA), equivalence testing and source reconstruction analysis, we addressed the unresolved questions. These analyses revealed concordant distributed brain activation patterns within parietal circuits. Thus, there is no evidence (rather evidence for equivalence) for distinct underlying neural generators for the two components. Taken together, the results highlight the importance of the P300 as a neurophysiological marker of learning and may enable the development of preventive measures for age-related impeded learning.

neuroscience↗

bioRxiv2022

The AI Neuropsychologist: Automatic scoring of memory deficits with deep learning

BackgroundMemory deficits are a hallmark of many different neurological and psychiatric conditions. The Rey-Osterrieth complex figure (ROCF) is the state-of-the-art assessment tool for neuropsychologists across the globe to assess the degree of non-verbal visual memory deterioration. To obtain a score, a trained clinician inspects a patients ROCF drawing and quantifies deviations from the original figure. This manual procedure is time-consuming, slow and scores vary depending on the clinicians experience, motivation and tiredness. MethodsHere, we leverage novel deep learning architectures to automatize the rating of memory deficits. For this, we collected more than 20k hand-drawn ROCF drawings from patients with various neurological and psychiatric disorders as well as healthy participants. Unbiased ground truth ROCF scores were obtained from crowdsourced human intelligence. This dataset was used to train and evaluate a multi-head convolutional neural network. ResultsThe model performs highly unbiased as it yielded predictions very close to the ground truth and the error was similarly distributed around zero. The neural network outperforms both online raters and clinicians. The scoring system can reliably identify and accurately score individual figure elements in previously unseen ROCF drawings, which facilitates explainability of the AI-scoring system. To ensure generalizability and clinical utility, the model performance was successfully replicated in a large independent prospective validation study that was pre-registered prior to data collection. ConclusionsOur AI-powered scoring system provides healthcare institutions worldwide with a digital tool to assess objectively, reliably and time-efficiently the performance in the ROCF test from hand-drawn images.

neuroscience↗