ARTIFICIAL

INTELLIGENCE IN
PROSTHODONTIC
S
DR. S ANANTHA NARAYANAN
DEPT. OF PROSTHODONTICS
SHDCH,HASSAN
 WHAT IS ARTIFICIAL INTELLIGENCE??
DONEC QUIS NUNC

• To work smarter, not harder is the

deepest assimilation of every
human being.
• Artificial intelligence offers
advanced decision supporting
tools.
• Machine learning does not intend
to replace the dental health care
worker, but can be a method to
create a second informed opinion
based on mathematical decision
making and prediction.
KEY ASPECTS OF AI
DONEC QUIS NUNC
 MACHINE LEARNING
DONEC QUIS NUNC

With machine learning, computers

are able to infer their own rules by
using advanced algorithms.
Machine learning is subdivided into
four categories of learning
• Supervised Learning
• Unsupervised Learning
• Semi-Supervised Learning
• Reinforced Learning
 DONEC QUIS NUNC

NEURAL NETWORK
As the name suggests, it uses artificial neurons to set the algorithm .it works almost
similar to the human brain.

DEEP LEARNING
It is a type of machine learning that utilizes the network
with different computational layers to analyse the input
data.
Deep learning is also known as conventional neural
network.
 ARTIFICIAL INTELLIGENCE IN DECISION
DONEC QUIS NUNC
SUPPORT SYSTEMS

• Clinical decision support can

improve the diagnostic accuracy
• It is also used for reducing the
feudal claims in the field of dental
insurance
• It has potential application in the
field of orthodontics, periodontics
and oral surgery for analysing the
condition and treatment planning.
• Periodontics
• Prosthodontics
• Oral Surgery
 PROSTHODONTICS AND AI
DONEC QUIS NUNC

• CAD/CAM

• Implant Therapy

• Maxillofacial Prosthetics

• Clinical Environment and AI

• Tongue Controlled devices

• Digital Smile Designing

ARTIFICIA
L
INTELLIG
ENCE FOR
TOOTH
SUPPORTE
MARTA REVILLA
D
ET FIXED
AL &
REMOVAB
JPD 2021

LE
 PURPOSE
DONEC QUIS NUNC

The purpose of this systematic review was to assess the performance of the artificial
intelligence models in prosthodontics for
• tooth shade selection,
• automation of restoration design,
• mapping the tooth preparation finishing line,
• optimizing the manufacturing casting,
• predicting facial changes in patients with removable prostheses, and
• designing removable partial dentures.
 MATERIALS AND METHODS
DONEC QUIS NUNC

• An electronic systematic review was performed in MEDLINE/PubMed, EMBASE, Web

of Science, Cochrane, and Scopus.
• A manual search was also conducted. Studies with artificial intelligence models were
selected based on 6 criteria: tooth shade selection, automated fabrication of dental
restorations, mapping the finishing line of tooth preparations, optimizing the
manufacturing casting process, predicting facial changes in patients with removable
prostheses, and designing removable partial dentures.
• Two investigators independently evaluated the quality assessment of the studies by
applying the Joanna Briggs Institute Critical Appraisal Checklist for Quasi-
Experimental Studies (nonrandomized experimental studies). A third investigator was
consulted to resolve lack of consensus.
 RESULTS
DONEC QUIS NUNC

A total of 36 articles were reviewed and classified into 6 groups based on the application of the artificial
intelligence model.
• One article reported on the development of an artificial intelligence model for tooth shade selection,
reporting better shade matching than with conventional visual selection;
• 14 articles reported on the feasibility of automated design of dental restorations using different artificial
intelligence models;
• 1 artificial intelligence model was able to mark the margin line without manual interaction with an average
accuracy ranging from 90.6% to 97.4%;
• 2 investigations developed artificial intelligence algorithms for optimizing the manufacturing casting
process, reporting an improvement of the design process, minimizing the porosity on the cast metal, and
reducing the overall manufacturing time;
• 1 study proposed an artificial intelligence model that was able to predict facial changes in patients using
removable prostheses; and
• 17 investigations that developed clinical decision support, expert systems for designing removable partial
dentures for clinicians and educational purposes, computer-aided learning with video interactive programs
for student learning, and automated removable partial denture design.
ARTIFICIA
L
INTELLIG
ENCE FOR
IMPLANT
DENTISTR
MARTA REVILLA
Y
ET -
AL A
SYSTEMA
JPD 2021

TIC
 PURPOSE
DONEC QUIS NUNC

The purpose of this systematic review was to assess the performance of AI models in implant dentistry
for
• implant type recognition,
• implant success prediction by using patient risk factors and ontology criteria, and
• implant design optimization combining finite element analysis (FEA) calculations and AI models.
 MATERIALS & METHODS
DONEC QUIS NUNC

An electronic systematic review was completed in 5 databases: MEDLINE/ PubMed, EMBASE, World
of Science, Cochrane, and Scopus.
A manual search was also conducted. Peer- reviewed studies that developed AI models for implant type
recognition, implant success prediction, and implant design optimization were included.
The search strategy included articles published until February 21, 2021.
Two investigators independently evaluated the quality of the studies by applying the Joanna Briggs
Institute (JBI) Critical Appraisal Checklist for Quasi-Experimental Studies (nonrandomized
experimental studies). A third investigator was consulted to resolve lack of consensus.
 RESULTS
DONEC QUIS NUNC

Seventeen articles were included:

• 7 investigations analyzed AI models for implant type recognition,
• 7 studies included AI prediction models for implant success forecast, and
• 3 studies evaluated AI models for optimization of implant designs.
• The AI models developed to recognize implant type by using periapical and panoramic
images obtained an overall accuracy outcome ranging from 93.8% to 98%.
• The models to predict osteointegration success or implant success by using different
input data varied among the studies, ranging from 62.4% to 80.5%.
• Finally, the studies that developed AI models to optimize implant designs seem to agree
on the applicability of AI models to improve the design of dental implants.
• This improvement includes minimizing the stress at the implant-bone interface by
36.6% compared with the finite element model; optimizing the implant design porosity,
length, and diameter to improve the finite element calculations; or accurately
determining the elastic modulus of the implant-bone interface.
 CONCLUSION FROM THIS STUDY
DONEC QUIS NUNC

Based on the findings of this systematic review, the subsequent conclusions were drawn:
1. AI models have the potential to recognize implant type, predict implant success by using
patient risk factors and ontology criteria, and optimize implant designs, but they are still
being developed. With its application in implant dentistry rapidly expanding, the
effectiveness and reliability of AI models should be evaluated before recommending
them for clinical practice.
2. Based on the reviewed studies, the AI models developed to recognize implant type by
using radiographical images were the more developed application of AI in implant
dentistry, obtaining an overall accuracy ranging from 93.8% to 98%.
3. The AI models to predict osteointegration or implant success varied from 62.4% to
80.5% among the studies.
 DISCUSSION
DONEC QUIS NUNC

• AI based software will help lab technicians design prostheses with hygienic contours,
ideal esthetics, and minimal failure expectations.
• For fixed dental prostheses, it will be possible to scan the existing tooth structure with an
optical intraoral scanner, and then use the software to analyze and propose therapeutic
options.
• For partial edentulism, the program will be able to utilize the algorithm to propose the
possible design of removable partial dental prostheses.
• Dental implant therapy will be standardized using research- based, clinically proven
techniques and technology.
• Once a CBCT scan and intraoral scan are taken, the AI will automatically merge the two
together, design the future restoration, and then place the correct implant with the proper
design in the ideal position based on tissue thickness, emergence profile, bone
type/thickness, and the patient’s specific medical history. From there the surgical guide
can be generated and the surgery can be scheduled.
 INTRA-ORAL SCAN
DONEC QUIS NUNC
• The intraoral scans can be analyzed by dental
inspection software (Smart Margin and Scan
Clarity Score, Pearl).
• Dental clinicians can use this software to
analyze their own scans to verify preparations
with instant feedback.
• Laboratories can analyze these scans at high
volume to then score the dental practitioners or
categorize their preparations based on the
difficulty of the case to make sure it ends up in
the hands of a skilled technician.
• In addition, business entities such as dental
service organization managers can use this
technology to score their dental practitioners, to
make decisions on who needs further training
and who is excelling clinically.
• If the margin is visible and the scan is accurate,
the software can then automatically mark the
margins on tooth preparations with high
precision
 DIGITAL SMILE DESIGNING
DONEC QUIS NUNC

• Smile design has been a useful tool for team communication and patient motivation.
• Currently, there are around 15 smile design softwares available for clinicians.
• All of these software rely on the input and preference of the clinician to design the shape
and alignment of the future smile.
• A new interactive cloud-based platform (Smilecloud, ADN3D Biotech) incorporating
digital smile design, the treatment plan, and the communication tool among clinicians,
technicians, and patients was introduced. Once the required patient data (photos) are
uploaded, the AI engine searches and proposes natural shapes of teeth and alignment.
• The proposed smile design can be versatilely modified by the clinician and then used to
create an STL file for creation of a mock-up model, preparation guide, or surgical guide.
FUTURE OF AI
DONEC QUIS NUNC
 LIMITATIONS OF AI
DONEC QUIS NUNC

• Using AI to solve problems requires the algorithm to be comprehensive with multiple

applications to solve a single question.
• Like the nature of data mining, AI might only reflect the results subjectively with
associations, not with causality.
• Direct interpretation will not be provided with AI; a misinterpretation might occur with
the misconduct of the algorithms.
• AI programs still need to be developed in collaborations that involve experienced
clinicians and expert computer engineers to minimize potential risks of AI.
 CONCLUSION
DONEC QUIS NUNC

• The field of artificial intelligence has altered medicine and dentistry in

numerous ways.
•

• Though Artificial Intelligence systems are a great strength in dentistry and

dental training, the human biological system is composite and it is to be noted
that these technological progressions are still the brain child of novelties and
discoveries by mankind.
•

• Moreover, AI can only support the clinician in performing the tasks

professionally, but in no way swaps the intellect of the human knowledge,
skill and treatment planning.