Background Despite the fact that road traffic casualties presented a decreasing trend during the last years, the number of fatalities in road accidents is still unacceptable and illustrates the need for greater efforts with respect to better driving performance and increased road safety. The objective of this paper is to investigate the accident probability of drivers with cognitive impairments (Alzheimer’s Disease-AD, Parkinson’s disease-PD and Mild Cognitive Impairment-MCI) through a large driving simulator experiment.

Methods A full neurological and neuropsychological assessment was carried out and then a driving simulator experiment was applied. The driving tasks included driving in urban and rural road, at moderate and high traffic volumes, with and without distraction (conversation with passenger and conversation through mobile phone), while various unexpected incidents were scheduled to occur (sudden appearance of an animal on the roadway, or sudden appearance of a child chasing a ball or a car suddenly getting out of a parking position and getting in the road in urban area).

Results The sample scheme consisted of 140 participants of similar demographics: 31 healthy controls, 25 AD, 59 MCI, and 25 PD patients. The accident probability was analysed, by descriptive statistics at first and then appropriate mathematical models were developed. Results indicated that patients were more likely to crash the incident that unexpectedly happened. The accident risk of AD and MCI drivers was 30% higher than the control group. Finally, the negative impact of use of the mobile phone, regarding accident probability, was more significant on the patients.

Conclusions The patients had systematically higher accident probability than the cognitively intact individuals, in the majority of driving conditions. These results could have considerable practical importance as they provide useful information about the formulation of efficient countermeasures.