Abstract
BACKGROUND:
Artificial intelligence is a relatively newer technology in the field of medical world. This science uses the machine – learning algorithm and computer software to aid in the diagnostics in medical and dental fields. It is a huge talking point in the field of technology which is spreading it’s wings in all possible sectors at a great speed. This field covers solutions from coaching solutions to diagnostics in medical field covering under the umbrella of all what can be achieved by machine and deep learning.
CONTENT:
In dentistry, artificial intelligence is creating a revolution in all sections from collection of data, creating algorithms for orthodontic procedures, diagnostic records in the aspect of radiographic data, three dimensional scans and cone beam computed tomography, CAD CAM systems for restorative and prosthetic purposes. Similarly continuous research is being done in the field of periodontics in terms of measuring bone loss, amount of plaque present and much more.
CONCLUSION:
The field of artificial technology with its varied applications will change the face of dentistry in the upcoming times. Artificial intelligence with its application of machine learning will change the face of dentistry in future.
Introduction
Artificial intelligence is a new-fangled science which bequeath the machine science to impersonate the intelligent human behaviour. It is a wide-ranging branch which is concerned with building smart machines capable of performing tasks that typically require human intelligence. It is an interdisciplinary science with multiple approaches, but advancements in machine learning and deep learning are creating a paradigm shift in virtually every sector of the technical and health industry. In the modern day world, artificial intelligence refers to any machine or technology that is able to mimic human cognitive skills like problem solving. The pandemic has affected the workstyle of the dentists’ and is compelling us to accept new ways of operating and technological change. The experience of the pandemic year has made us necessary to accept a pathway through which other novel technology-driven processes will gain entry, including computer vision, data mining, and predictive analytics, AI solutions for diagnosis, treatment planning, and business intelligence. The greatest advantage of such technology is that they can solve problems too complex for conventional methods. In dentistry, this technology was primely introduced with the digitization of dental records. Using these records, this novel setup has enabled automated localization of anatomical landmarks, recognition of diseases and classification of tumors. The prospects of artificial intelligence in the dental field are infinite and its use is rapidlyadvancing.
Artificial intelligence and computerized support, have lately received a lot of attention within the domain of dental health care. The potential dental applications reviewed were [1], success in detecting precancerous lesions and metastases [2], effectiveness in improving the quality of maxillofacial radiology [3], success in orthodontic treatment [4], and orthopedic rehabilitation [5], as well as concurrent application with virtual reality to decrease anxiety in young patients [6]. However, the aforementioned reviews did not systematically explore the current diagnostic capabilities of AI in identifying common orofacial diseases and disorders and/or the subsequently elicited pain [7].
Along with the dental health care, artificial science is setting foot in modern health science applications. In detection of COVID-19, for speeding up the identification process using deep learning from chest radiographic images [8]. Researchers have found the use of artificial intelligence (AI) to differentiate the subtypes of intracranial hemorrhage with higher accuracy which will help professionals to improve diagnostic accuracy [9] and in the detection of liver tumors [10].
The essential terminologies to understand the paradigm of artificial intelligence are: Artificial intelligence is termed as a capability of machines that exhibits a form of its own intelligence. The aim here was to develop machines which will learn through data in order to solve the problems. Machine learning is part of AI, which depends on algorithms to predict outcomes based on a dataset. The purpose of machine learning is to facilitate machines to learn from data so they can resolve issues without human input. Representation learning is a subtype of ML in which the computer algorithm learns the features required to classify the provided data. Neural networks are a set of algorithms that compute signals via artificial neurons. The purpose of neural networks is to form neural networks that function just like the human brain. Deep learning is a component of machine learning that utilizes the network with different computational layers in a deep neural network to analyse the input data. The purpose of deep learning is to construct a neural network that automatically identifies patterns to improve feature detection [11]. Clinical decision support system CDSS is a system between a broad dynamic (medical) knowledge database and an inferencing output mechanism that are a set of algorithms derived from evidence-based medical practice executed through medical logic modules. Currently, the intuitive interphase with voice controls are designed to assist the health care professional to work more efficiently with time saving and cost effective clinical dental practice. Augmented reality is a defined as “a technology that superimposes a computer-generated image on a user’s perspective of the real world, accordingly giving a composite view”. Virtual reality is a computer-generated reenactment of a three-dimensional image or environment that can be communicated with, in an apparently real or physical path by an individual utilizing unique electronic equipment [12].
Machine learning systems’ perceptive abilities grow in proportion to the amount and array of data available to them. The more data that is available—from patients, imaging devices, material applications, treatment plans, and other factors influencing dental care outcomes—the more perceptive AI will become. The more perceptive dental AI becomes, the more profoundly dentists and patients will benefit.
History
Alan Turing (British mathematician, 1936) was one of the most important visionary and theoretician, proved that a universal calculator—known as the Turing machine—is possible [13]. Turing’s central insight is that such a machine is capable of solving any problem as long as it may be represented and solved by an algorithm.
Newell and Simon (1955) designed “The Logic Theorist” which is considered to be the first AI program which marks the development of modern AI.
John McCarthy in 1965 coined the term ‘artificial intelligence’ [14].
Applications in the specialty of periodontics
Periodontal disease is a complex inflammatory disease contributed by multiple causal factors simultaneously and interactively. They are one of the most common oral diseases affecting the mankind. It is well reported by Lee et al. [15], that continuous progression of the disease will eventually lead to the loss of teeth in the adults. Various studies have been done to ascertain AI technology application to diagnose and predict periodontal diseases.
Lee et al. [16], reported use of CAD system, based on a deep convolutional neural network (CNN) algorithm for diagnosing and predicting the teeth that are compromised with periodontal health. Using the CNN algorithm, the accuracy of PCT diagnosis proved to be 76.7–81.0%, while the accuracy of predicting the need for extraction was 73.4–82.8%. The noted difference in accuracy seemed to occur between different types of teeth, with premolars more accurately diagnosed as PCTs than molars (accuracies were 82.8% and 73.4%, respectively). This could be explained by the fact that premolars normally have a single root, whereas molars have 2 or 3 roots, thus exhibiting a more complex anatomy for a CNN to interpret.
Yauney et al. [17], used an AI based system based on CNNs for correlating poor periodontal health with systemic health outcomes and reported that AI can be used for automated diagnoses and can also be useful for screenings for other diseases.
Papantanopoulos and colleagues [18] used an ANN to distinguish between aggressive periodontitis and chronic periodontitis in patients by using immunologic parameters, such as leukocytes, interleukins and IgG antibody titers. The one ANN was 90–98% accurate in classifying patients as aggressive periodontitis or chronic periodontitis. The best overall prediction was made by an ANN that included monocyte, eosinophil, neutrophil counts and CD4+/CD8+ T-cell ratio as inputs. The study concluded that ANNs can be employed for accurate diagnosis of between aggressive periodontitis or chronic periodontitis using relatively simple and conveniently obtained parameters, such as leukocyte counts in peripheral blood.
Wang et al. developed a Digital Convolution Neural Network based system that consists of 16 convolution layers and two fully connected layers for detecting periodontitis of premolars and molars [19].
Deep learning analysis using radiographs can help in diagnosing and treatment planning of periodontal diseases by the early detection of periodontal changes [20, 21]. This helps in early intervention in implantology. In addition to promoting our understanding of periodontitis, this technology serves as a bridge to incorporate conventional indicators and immunologic and microbiological parameters into periodontal diagnosis [22].
Discussion
While artificial intelligence’s value as a provider of second opinions and enforcer of consistency is evident, other applications—merging practice and patient data with diagnostic and treatment outcome data—will gradually establish new standards of care and operating efficiencies. Once AI is firmly established as a tool in care and practice management, new forms of data linkage—not only dental, but genetic, geographic, demographic, and medical—will allow AI to deliver truly revolutionary and potentially life-saving value by forging new links between systemic health and dental health.
Ozden et al. used an identification unit for classifying periodontal diseases using support vector machine (SVM), decision tree (DT), and artificial neural networks (ANNs). The performances of SVM and DT were found 98% with total computational time of 19.91 and 7.00 s, respectively [23].
Krois et al. [24] used CNNs to detect periodontal bone loss on panoramic dental radiographs. This system can still help in reducing the dentist’s diagnostic efforts.
The progressive technology should not harm the morale of the humankind or the machinery itself. It has various drawbacks such as collection of previous data, interpretability i.e. bridging the gap between the medical terms and mathematical algorithms, the need for complex and strong computing power, and ethical considerations in which the doctor will be liable and responsible for the patient and the use of his information.
AI solutions still are a faraway reach in routine dental practice, mainly because of: Limited data availability, accessibility, structure, and comprehensiveness Lacking methodological rigor and standards in their development Practical questions around the value and usefulness of these solutions, but also ethics and responsibility [25].
Conclusion
Artificial intelligence in the upcoming times will link dentistry, systemic medicine, and electronic record keeping into a continuum that will bring a new level of consistency, clarity, and convenience to patients, not to mention better outcomes, which is what we’re all trying to achieve. The dentist in obvious terms will not be replaced but will be aided to another level for smooth treatment plans in the long run. The near future will hold a lot of challenges, but will be worth for the to overcome in order to reduce the inaccuracies and thus surge the proficiency of dental practices for various conditions. With the speed of which artificial intelligence is booming in the sector of dentistry, the need of the hour is to have more systematic reviews and meta – analysis to enhance the knowledge and reach of applications.
Conflicts of interest
The authors have no conflict of interest to report.