Welcome to Brainless Intelligence’s first blog post! Over the course of our blog journey, we will be discussing all thing AI. This week we will be discussing the implementation of Artificial Intelligence in health care, beginning with dentistry. Odontophobia is the fear of going to the dentists and is a common fear among all ages. Whether this is due to a fear of needles or because of a past traumatic experience, it’s enough to make people dread their yearly check-up. So, what if there was a way of not going to the dentist for check-ups while also avoiding bad dental health? Image source: https://www.evansondds.com/dont-let-fear-of-the-dentist-keep-you-from-having-routine-dental-care/ (Evanson, A) Artificial Intelligence (AI) is evolving in the dental field constantly. By doing tasks usually completed by humans, AI can provide accurate information regarding a patient’s teeth without them needing to take that dreaded visit to the dentist. Deep learning is an advanced form of machine learning where the machine trains itself and performs complicated tasks by processing multi-layered networks of data. Deep convolutional networks have revolutionized image, video, speech, and audio processing. (LeCun, Bengio, and Hinton, 2015). The Dental Monitoring (DM) ScanBox uses deep learning technology to drastically improve a dental patient’s experience. The patient is given a DM ScanBox and a DM cheek retractor and then must download the DM mobile app. The patient scans their teeth from their home at certain intervals requested by the online dentist so that they can monitor the treatment. As the patient scans their teeth with their smart phone, the system takes 20 to 30 pictures and processes them by cropping the images and labelling them. Firstly, the system will automatically crop out any unnecessary aspects of the image, for example, the patients’ cheeks and nose. It will then detect the teeth and label them one by one with prediction scores. The prediction score indicates how certain the machine is of its accuracy. Following the AI’s analysis, depending on what is found in the scans, if a problem is detected, an automatic message with advice from the dentist on what to do will be sent to the patient through their DM application (Dental Monitoring, 2021). Rather than using the DM ScanBox, some people may believe that the same results can be achieved for free through self-assessed photographs. It is evident through comparing the DM ScanBox to self-assessing photographs that AI provides a much more accurate evaluation of the patient’s teeth. Self-assessing photographs is labour intensive and inefficient while requiring attentiveness and dental knowledge which most patient’s lack. Whereas the DM ScanBox is consistent, efficient and continues to get smarter with deep machine learning. Image source: https://dentistry.co.uk/2020/09/04/accurate-artificial-intelligence-tooth-decay/ (Bissett, B. 2020)
Of course, there are many other ways in which Artificial Intelligence can benefit the dental industry. Popular smart home device, Amazon Alexa uses Natural Language Processing (NLP) which is a computerised method of text analysis based on a collection of theories and technologies to create human-like language processing. Oral or written texts are both acceptable (Liddy, 2001). This technology could be used in the future for the world of dentistry. As the patient is talking and explaining their problems and concerns, the NLP machine will take notes which eliminates human error when entering information into a database. As I previously stated, AI is constantly evolving and will continue to have an impact on the dental industry as we know it. I have only mentioned a couple of ways in which AI has and will continue to influence the world we live in but stay tuned with our blog to learn more about the effects of Artificial Intelligence in various aspects of our lives. Bibliography Dental Monitoring. (2021) How Artificial Intelligence is Reshaping Dentistry, by Dr. Rayan Skafi. 28 April. Available at: https://youtu.be/rgLoT0Lw7E0 LeCun, Y., Bengio, Y. & Hinton, G. (2015) Deep learning. Nature 521, 436–444. https://doi.org/10.1038/nature14539 Liddy, E.D. (2001) Natural Language Processing. In Encyclopedia of Library and Information Science, 2nd Ed. NY. Marcel Decker, Inc.
5 Comments
|
Author Ciara O'Brien Archives
|