A Decision Support System Based on Classification Algorithms for the Diagnosis of Periodontal Disease

The study purposes For periodontal applications, such as diagnosing gingivitis and periodontal disease, artificial intelligence (AI) models have been developed; however, their accuracy and technological maturity are to be evolved. The applications of such technologies in the field of periodontics are walking baby steps worldwide. The Kingdom of Saudi Arabia is moving fast in technology adoption and implementation in different sectors. However, the healthcare sector, especially clinical-related, needs original research applied to Saudi subjects. The literature in the field of machine learning applications in dentistry is limited. Although AI models for periodontology applications are still being developed, they could serve as potent diagnostic instruments. The current study was planned to add to the current gap in the literature.

Study Overview

• Status: Not yet recruiting
• Conditions: Periodontal Diseases
• Intervention / Treatment: Diagnostic test: Clinical Periodontal Examination

Detailed Description

A cross-sectional study design will be applied. Two hundred fifty patients will be evaluated by an experienced periodontist and used as input variables. The final diagnosis output will be generated by considering relevant information from the patient's medical history, clinical dental examination, and radiographic exam. Of the sample of 250 patients, 20% of the participants will be assigned randomly to the test group, while the rest will be assigned to the training group before feeding it to the algorithms.

The study purposes For periodontal applications, such as diagnosing gingivitis and periodontal disease, artificial intelligence (AI) models have been developed; however, their accuracy and technological maturity are to be evolved. The applications of such technologies in the field of periodontics are walking baby steps worldwide. The Kingdom of Saudi Arabia is moving fast in technology adoption and implementation in different sectors. However, the healthcare sector, especially clinical-related, needs original research applied to Saudi subjects. The literature in the field of machine learning applications in dentistry is limited. Although AI models for periodontology applications are still being developed, they could serve as potent diagnostic instruments. The current study was planned to add to the current gap in the literature.

• Study Type: Observational
• Enrollment (Estimated): 250

Contacts and Locations

• Study Contact: Name: Abdulrahman Al Shehri, BSD, MS; Phone Number: +966507090251; Email: alshehriabdulrahman3@gmail.com
• Study Contact Backup: Name: Abdulrahman Al Shehri, BDS, MS; Phone Number: +966507090251; Email: alshehriabdulrahman3@gmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Data will be collected randomly during the study period planned to end by the end of the year 2023. Data will be collected from participants attending the periodontal department at Abha Specialized Dental Center seeking periodontal treatment.

Description

Inclusion Criteria:

• age 18 or more
• no periodontal treatment has been done at least 6 months prior to the enrollment
• seeking periodontal treatment

Exclusion Criteria:

• refuse to volunteer in the study

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Age	<30, 30-34, 35-39, 40-44, 45-49, 50-54, 55-59, 60-64, 65-69, 70-74, 75-79, >80	One time measure; baseline during periodontal clinical examination.
Gender	Male; Female.	One time measure; baseline during periodontal clinical examination.
Marital statue	Married, widowed, divorced, never married	One time measure; baseline during periodontal clinical examination.
Education	< secondary school, secondary school, graduate or equivalent, some college or associates degree, College graduate or higher	One time measure; baseline during periodontal clinical examination.
Physical Activities	Light, Moderate, Heavy	One time measure; baseline during periodontal clinical examination.
Bleeding on Probing	Yes; No	One time measure; baseline during periodontal clinical examination.
Gingival Index	Percentage	One time measure; baseline during periodontal clinical examination.
Plaque Index	Percentage	One time measure; baseline during periodontal clinical examination.
Periodontal Probing Depth	PPD at the site of greatest loss (number)	One time measure; baseline during periodontal clinical examination.
Recession Type	Yes; No	One time measure; baseline during periodontal clinical examination.
Clinical Attachment Loss	CAL at the site of greatest loss (number)	One time measure; baseline during periodontal clinical examination.
Radiographic Bone Loss	RBL at the site of greatest loss (percentage)	One time measure; baseline during periodontal clinical examination.
Tooth Mobility	Yes; No	One time measure; baseline during periodontal clinical examination.
Missing Teeth	Yes; No	One time measure; baseline during periodontal clinical examination.
Furcation Involvement	Yes; No	One time measure; baseline during periodontal clinical examination.
Diabetes	Healthy, <7% HbA1c, ≥7% HbA1c	One time measure; baseline during periodontal clinical examination.
Smoking	None, <10 cig/day, ≥10cig/day	One time measure; baseline during periodontal clinical examination.
Body Mass Index	Underweight, Healthy, Overweight, Obese	One time measure; baseline during periodontal clinical examination.
Cardiovascular Disease	Yes; No	One time measure; baseline during periodontal clinical examination.

Collaborators and Investigators

• Sponsor: Ministry of Health, Saudi Arabia
• Investigators: Principal Investigator: Abdulrahman Al Shehri, BDS, MS, General Directorate of Health Affairs, Aseer Region, KSA.

Publications and helpful links

General Publications

• Ozden FO, Ozgonenel O, Ozden B, Aydogdu A. Diagnosis of periodontal diseases using different classification algorithms: a preliminary study. Niger J Clin Pract. 2015 May-Jun;18(3):416-21. doi: 10.4103/1119-3077.151785.
• Alqahtani HM, Koroukian SM, Stange K, Schiltz NK, Bissada NF. Identifying Factors Associated with Periodontal Disease Using Machine Learning. J Int Soc Prev Community Dent. 2022 Dec 30;12(6):612-622. doi: 10.4103/jispcd.JISPCD_188_22. eCollection 2022 Nov-Dec.

Study record dates

Study Major Dates

• Study Start (Estimated): October 1, 2023
• Primary Completion (Estimated): December 30, 2024
• Study Completion (Estimated): December 30, 2024

Study Registration Dates

• First Submitted: September 22, 2023
• First Submitted That Met QC Criteria: October 4, 2023
• First Posted (Actual): October 6, 2023

Study Record Updates

• Last Update Posted (Actual): October 6, 2023
• Last Update Submitted That Met QC Criteria: October 4, 2023
• Last Verified: October 1, 2023

More Information

Terms related to this study

• Keywords: learning; diagnosis; disease; periodontal; Saudi; machine
• Additional Relevant MeSH Terms: Stomatognathic Diseases; Mouth Diseases; Periodontal Diseases
• Other Study ID Numbers: H-06-B-091

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: No intention and no need to share individual patient data with research community.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No