Stellenbosch University
Welcome to Stellenbosch University
Novel Screening Tool for ADHD
Author: Liesel Koch
Published: 21/02/2019

Members of the Biomedical Engineering Research Group at Stellenbosch University have developed a novel screening tool for ADHD amongst children. The project team comprises Prof Pieter Fourie, a paediatrician and engineer, and two of his master's students, Romano Swarts and Hervé Mwamba.

Attention-Deficit/Hyperactive Disorder (ADHD) is one of the most common neurodevelopmental disorders, distinctly characterised by a persistent pattern of inattentive, hyperactive or impulsive behaviour. Worldwide about 7,1% of children under 18 suffer from it. It is one of the most thoroughly researched conditions.

Prof Fourie says: "As a paediatrician I have always felt a great need for a quick, affordable method to diagnose ADHD. Currently, this is done by expensive clinical evaluations by psychologists. During the diagnostic process, psychologists also use questionnaires filled in by parents and teachers, but unfortunately these questionnaires are very subjective." 

ADHD is divided into three subtypes, namely Inattentive, Hyperactive/Impulsive, and a combination of the two. For his master's thesis Romano Swarts researched and developed a portable screening tool that incorporates machine learning to screen participants between the ages of six and twelve years for ADHD Inattentive subtype. His fellow student Hervé Mwamba tackled the Hyperactive/Impulsive subtype in his study.

The research project was dubbed The PANDA Project as the main character in the computer game is a panda bear that has to navigate through an underground mine whilst being presented with numerous challenges. (PANDA: Paediatric Attention-Deficit/Hyperactivity Disorder Application.)

Hervé says: "PANDA grabbed my attention immediately when I had to choose a topic for my research. I was fascinated by Prof Fourie's enthusiasm and vision for this topic." 

Romano explains why he chose this topic: "The profession I chose was not based on money, but the reward of the work I do. I want to better people's lives. 

"My ADHD screening tool is a testing interface in the form of a tablet-based game that uses machine learning to classify patients. The classifier I developed, together with algorithms used in my testing method, can discriminate between ADHD and non-ADHD patients with 97,4% accuracy. The device used for testing was a commercially available tablet with WiFi. No additional hardware is required."

Romano elaborates: "It is common knowledge that private medical services are costly. Given the current diagnostic process of ADHD mentioned above, it follows that early, accurate screening for ADHD could help to prevent unnecessary costs. It would also help to ensure that children identified by the tool could be referred for diagnosis and receive adequate treatment as early as possible. The ADHD screening tool could be used to ascertain the effectiveness of existing or new stimulant or non-stimulant type medication or treatment, to monitor the degree of severity of ADHD, as well as to help carers and parents to monitor dosage effects and enable strict control over ADHD medication. These benefits, in turn, decrease the need for the patient to frequently visit a mental healthcare professional. 

"Furthermore, this portable diagnostic tool could be utilised in rural and remote areas within South Africa, as well as abroad. The tool will serve as a method to aid proper diagnosis by providing quantitative output. In a school setting, the tool would remove the onus from teachers to convince parents of seeking professional diagnosis. The tool could also be used to conduct population studies in order to ascertain the incidence of ADHD for clinical or statistical research purposes."

Hervé adds: "The research was very rewarding, as I was able to contribute something new in this field. I do hope that the great work will not loose momentum and that a robust tool will be accessible to the whole of South Africa in the near future and that early screening will improve the quality of life and of education."

Prof Fourie notes: "Unfortunately, we lose many of our promising Biomedical Engineering graduates who seek career opportunities overseas. I have a great passion to create opportunities for them to stay in South Africa and have a prosperous career. To this end, I have been involved in establishing innovation4life, a company that will open the door to career opportunities for biomedical engineers in South Africa. I am sure that The PANDA Project will contribute greatly to the medical profession and will open up a host of opportunities for us as this tool has already been patented."

The team are now looking for investors to fund the next phase whilst moving ahead with the required planning.

Most of the Faculty of Engineering's research projects are driven and applicable to real-life engineering problems in the community. The Faculty has been successful in solving many of these problems in collaboration with industry and enjoys great support from industry. Shoprite supported The PANDA Project with R500 000. 

Photograph:

Left: A screenshot of the computer game where the panda bear is being navigated through an underground mine whilst being presented with numerous challenges.

Right: Romano Swarts.