Skip to navigation Skip to main content Skip to footer

Approved Research

Using Artificial Intelligence (AI) methods with multi-dimensional data to improve clinical care outcomes for individuals with ADHD.

Principal Investigator: Dr Sarojini Sengupta
Approved Research ID: 93777
Approval date: December 6th 2022

Lay summary

At Artificial Intelligence for Mental Health (AIMH), we have developed a tool to streamline the treatment of ADHD. Our prototype transforms different kinds of data into models that can predict different outcomes, so an individual can have a treatment plan that is tailored to her/his needs.

The approach currently used in clinical care for ADHD is based on trial-and-error (or prescribe-and-wait), for lack of a better choice. This can be especially difficult if the individual has side effects to the prescribed medication. Every individual is a complex interaction of many aspects including the underlying biology and external environment.

Our aim is the research and development of a decision support tool to streamline the treatment of ADHD. This innovation allows clinicians to capitalize on their own vast medical records, in addition to all other sources of multi-dimensional data available for the child. A combination of AI methods transforms this data into prediction models of short and long-term outcomes.

These predictions will be an aide in a collaborative decision-making process between the clinician and the family, so the individual can have a treatment plan that is tailored to their needs.

We are currently in the pre-clinical, pre-revenue, validation phase where we are working in close collaboration with clinicians to validate the clinical utility of the prediction models and the platform across multiple, real-world clinical datasets. We have already started working in collaboration with family physicians at the University of Toronto. Here in this project proposed with the UKbiobank dataset, we aim to: (1) validate the models in a second large, longitudinal dataset and, (2) expand the models and platform to genetic, environmental, assay, and imaging data. 

Globally, ADHD has a significant public health impact. A systematic review of seven European studies estimated that the total ADHD-related costs in the Netherlands range from !9,860 to !14,483 per patient per year, with annual national costs of more than !1 billion. A systematic review of 19 U.S. studies noted that the overall national annual costs range from $143 to $266 billion.

The streamlining and optimization of treatment is likely to reduce costs for health care delivery systems. But above all, this tailored approach will reduce the difficulties for the individual!