Research

The world's smartest toothbrush - powered AI.

Backed by Independent research, in the British Dental Journal

Toothfairy™ has developed its own proprietary AI that runs inside its award-winning app, helping detect dental disease and empower dentists alike. We never allow AI to make a decision alone; rather, each output is checked by a real human licensed dentist.

Our AI helps our dentists detect disease earlier and helps them make smarter decisions.

Real dentists, supercharged with AI.

British Dental Journal Open. Rathod, R., Dean, S. and Sproat, C. (2025) 'The effectiveness of a novel artificial intelligence (AI) model in detecting oral and dental diseases'

AI matches dental clinicians on diagnostic accuracy

Read study

Correct pathology diagnosis rate

Toothfairy AI

Dentists (n=51)

81%

Toothfairy AI

82%

Dentists

British Dental Journal Open. Rathod, R., Dean, S. and Sproat, C. (2025) 'The effectiveness of a novel artificial intelligence (AI) model in detecting oral and dental diseases'

Dentists agreed with the AI's calls 4 times out of 5

>80%

of dentist responses matched Toothfairy AI's diagnosis

British Dental Journal Open. Rathod, R., Dean, S. and Sproat, C. (2025) 'The effectiveness of a novel artificial intelligence (AI) model in detecting oral and dental diseases'

Near-identical at catching at least one real issue

Read study

Plaque removal effectiveness

Toothfairy AI

Dentists

Toothfairy AI

94%

Dentists

95%

When surveyed, dental professionals ranked the Toothfairy Wand™ as the #1 toothbrush they would choose for themselves.

Blind Survey Conducted with Dental Professionals (2026)

A blind survey of over a hundred dental professionals ranking four leading electric toothbrushes on features alone

Toothfairy Wand results

>90%

Dentists ranked the Wand™ as the #1 brush for their own patients

>90%

Dentists chose the Wand™ as the #1 brush to use themselves

The effectiveness of a novel artificial intelligence (AI) model in detecting oral and dental diseases

Ravi Rathod, Saffa Dean & Christopher Sproat
BDJ Open volume 11, Article number: 62 (2025)

A unique AI machine-learning model was built using a convolutional neural network (CNN) model and trained using a dataset of over five thousand images. Ninety different unseen images were selected and presented to the AI model to test the accuracy of disease detection. The AI model’s performance was compared with answers provided by fifty-one dentists who reviewed the same ninety images. Both groups identified plaque, calculus, gingivitis, and caries in the images.

Read the full article in the British Dental Journal.