A sensitive and repeatable digital tool for cognitive performance tracking

A sensitive and repeatable digital tool for cognitive performance tracking


Background Science

OptiMind is based on the Integrated Cognitive Assessment (ICA) which is a patented test[1] based on humans’ strong reaction to animal stimuli, and the ability of a healthy brain to process images of animals in less than 200ms[2-4]. The test has been validated as a tool for use in cognitive assessments[2,5,6].

The ICA is a rapid animal/non-animal visual categorization test, which assesses information processing speed while engaging large volumes of the brain. This enables detection of subtle cognitive changes and high-resolution longitudinal monitoring of cognitive function.

ICA task engages large areas of the brain

Performance of a rapid categorisation task such as the ICA provides an objective measure of a number of critical cognitive functions, including executive decision making (identification of animal vs. non-animal), visual processing (processing of images observed) and motor coordination (to select left vs. right on the touchscreen interface), therefore engaging a large volume of cortex. This involves the engagement of the retina, the visual cortex and the motor cortex.

How is the OptiMind score calculated?

The OptiMind score is based on the user’s speed and accuracy during the ICA test. Accuracy is the proportion of images which were categorised correctly during the test.

Speed is defined based on the user’s response reaction time (RT) to the images they categorised correctly. Speed is inversely related to reaction time. The higher the speed, the lower the reaction time. The overall speed and accuracy are combined to calculate the OptiMind Score.

The OptiMind Score is a value between 0 and 1000, with a higher score indicating better performance.

For further details please see the published paper on the ICA[2].

OptiMind for cognitive performance tracking

The use of OptiMind as a cognitive performance tool has been explored in longitudinal studies on healthy participants of age 26 to 72 years, with a sample of the data shown in the graph below.

Variation of OptiMind score within participant (each participant is shown by a distinct colour), and across participants of different ages

Monitoring of OptiMind scores over numerous tests allows the cognitive stability of participants to be measured and compared. Daily lifestyle factors can have varying effects on cognitive stability, with some participants more significantly affected by factors such as sleep or exercise than others.

As an adjunct to other platforms and technologies such as wearables, OptiMind allows optimisation of cognitive performance based on daily lifestyle factors.

The scatterplot shows the variation in OptiMind score for a participant relative to number of exercise hours. The scatterplot shows a Spearman correlation of 0.41 (p<0.001) with a positive correlation between exercise and OptiMind score.

For this participant the number of hours sleep is correlated with their OptiMind score. The scatterplot shows a Spearman correlation of 0.25 (p=0.04); with a positive correlation between sleep and OptiMind score.

OptiMind Intended use

OptiMind is a wellness application that provides objective measures of mental acuity and cognitive performance in adults. OptiMind is intended for use only for general wellbeing purposes or to encourage or maintain a healthy lifestyle, and is not intended to be used for any medical purpose (such as the detection, diagnosis, monitoring, management or treatment of any medical condition or disease). Any health-related information provided by this device or software should not be treated as medical advice.

Please consult a doctor for any medical advice required.


1. Khaligh-Razavi S-M, Habibi S. System for assessing a mental health disorder. 9 2016. https://patents.google.com/patent/US20160278682A1/en.

2. Khaligh-Razavi, S.M. et al. Integrated Cognitive Assessment: Speed and Accuracy of Visual Processing as a Reliable Proxy to Cognitive Performance. Sci. Rep. 9, 1102 (2019). https://www.nature.com/articles/s41598-018-37709-x

3. Khaligh-Razavi, S.M., Cichy, R.M., Pantazis, D., & Oliva, A. (2018). Tracking the spatiotemporal neural dynamics of object properties in the human brain. Journal of Cognitive Neuroscience, 30(11), 1559-1576. https://pubmed.ncbi.nlm.nih.gov/29877767/

4. Mirzaei, A., Khaligh-Razavi, S.M., Ghodrati, M., Zabbah, S., & Ebrahimpour, R. (2013). Predicting the human reaction time based on natural image statistics in a rapid categorization task. Vision research, 81, 36-44. https://www.sciencedirect.com/science/article/pii/S0042698913000230

5. Khaligh-Razavi, S.M., Sadeghi, M., Khanbagi, M., Kalafatis, C., & Nabavi, S. M. (2019). A self-administered, artificial intelligence (AI) platform for cognitive assessment in multiple sclerosis (MS). BMC Neurology 20 (1) 193 https://bmcneurol.biomedcentral.com/articles/10.1186/s12883-020-01736-x

6. Kalafatis, C., Modarres, M. H., Apostolou, P., Marefat, H., Khanbagi, M., Karimi, H., Vahabi, Z., Aarsland, D., & Khaligh-Razavi, S.-M. (2021). Validity and Cultural Generalisability of a 5-Minute AI-Based, Computerised Cognitive Assessment in Mild Cognitive Impairment and Alzheimer’s Dementia. Frontiers in Psychiatry, 12. 

For more information, see https://cognetivity.com/optimind/