Related Experiment Video
Updated: Mar 5, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Development of a decision-making tool for reporting drivers with mild dementia and mild cognitive impairment to
Duncan H Cameron1, Carla Zucchero Sarracini2, Linda Rozmovits3
1McMaster University, Hamilton, Ontario, Canada.
Background:
Driving in persons with dementia poses risks that must be counterbalanced with the importance of the care for autonomy and mobility. Physicians often find substantial challenges in the assessment and reporting of driving safety for persons with dementia. This paper describes a driving in dementia decision tool (DD-DT) developed to aid physicians in deciding when to report older drivers with either mild dementia or mild cognitive impairment to local transportation administrators.
Methods:
A multi-faceted, computerized decision support tool was developed, using a systematic literature and guideline review, expert opinion from an earlier Delphi study, as well as qualitative interviews and focus groups with physicians, caregivers of former drivers with dementia, and transportation administrators. The tool integrates inputs from the physician-user about the patient's clinical and driving history as well as cognitive findings, and it produces a recommendation for reporting to transportation administrators. This recommendation is translated into a customized reporting form for the transportation authority, if applicable, and additional resources are provided for the patient and caregiver.
Conclusions:
An innovative approach was needed to develop the DD-DT. The literature and guideline review confirmed the algorithm derived from the earlier Delphi study, and barriers identified in the qualitative research were incorporated into the design of the tool.
