This study reveals an unexpected parallel between instructible vision-language models (VLMs) and human cognitive disorders, specifically constructive apraxia. We tested 25 state-of-the-art VLMs, including GPT-4 Vision, DALL-E 3, and Midjourney v5, on their ability to generate images of the Ponzo illusion, a task that requires basic spatial reasoning and is often used in clinical assessments of constructive apraxia. Remarkably, 24 out of 25 models failed to correctly render two horizontal lines against a perspective background, mirroring the deficits seen in patients with parietal lobe damage. The models consistently misinterpreted spatial instructions, producing tilted or misaligned lines that followed the perspective of the background rather than remaining horizontal. This behavior is strikingly similar to how apraxia patients struggle to copy or construct simple figures despite intact visual perception and motor skills. Our findings suggest that current VLMs, despite their advanced capabilities in other domains, lack fundamental spatial reasoning abilities akin to those impaired in constructive apraxia. This limitation in AI systems provides a novel computational model for studying spatial cognition deficits and highlights a critical area for improvement in VLM architecture and training methodologies.

The prevalence of dementia has increased over time as global life expectancy improves and populations age. An individual's risk of developing dementia is influenced by various genetic, lifestyle, and environmental factors, among others. Predicting dementia risk may enable individuals to employ mitigation strategies or lifestyle changes to delay dementia onset. Current computational approaches to dementia prediction only return risk upon narrow categories of variables and do not account for interactions between different risk variables. The proposed framework utilizes a novel holistic approach to dementia risk prediction and is the first to incorporate various sources of tabular environmental pollution and lifestyle factor data with network systems biology-based genetic data. LightGBM gradient boosting was employed to ensure validity of included factors. This approach successfully models interactions between variables through an original weighted integration method coined Sysable. Multiple machine learning models trained the algorithm to reduce reliance on a single model. The developed approach surpassed all existing dementia risk prediction approaches, with a sensitivity of 85%, specificity of 99%, geometric accuracy of 92%, and AUROC of 91.7%. A transfer learning model was implemented as well. De-biasing algorithms were run on the model via the AI Fairness 360 Library. Effects of demographic disparities on dementia prevalence were analyzed to potentially highlight areas in need and promote equitable and accessible care. The resulting model was additionally integrated into a user-friendly app providing holistic predictions and personalized risk mitigation strategies. The developed model successfully employs holistic computational dementia risk prediction for clinical use.

Researchers are turning to a unexpected treatment for cognitive disorders: video games.

A screenshot of Neurogrow, which tests a patient's memory and reaction time as an experimental treatment for cognitive decline. A screenshot of Neurogrow, which tests a patient's memory and reaction time as an experimental treatment for cognitive decline. The neurologist said Pam Stevens' cognitive impairment couldn't be treated. She and her husband, Pete Stevens, were told to give up hope. "On two separate occasions, over a two-year period, the neurologist said there was nothing we could do," said Pete Stevens.

California based company Cognoa is using machine learning to detect cognitive disorders in children up to 13 months earlier than traditional diagnosis methods. The company's VP of data science, Halim Abbas, told Which-50 a machine learning approach is ideal for detecting developmental delays. "Machine learning algorithms can ingest very large numbers of historical patient records, and use them to capture incredibly subtle patterns that might indicate the presence of cognitive disorders." "Highly resilient to noise and subjectivity" the process ultimately produces models that can approximate the understanding of what constitutes autism from the many different doctors who contributed to the dataset, Abbas said. "This allows Machine Learning screeners to succeed when applied at complex assessments like autism spectrum disorder, which can present a wide and highly variant set of behavioural phenotypes." The Cognoa method is much more accessible, according to Abbas.