AI: Analysis of Outcomes of Oral Healthcare at a US Dental School

Monday, 9th September 2024 - 11:30 to 13:00

Add to Calendar

Timezone:

CEST (Brussels time)

Duration:

90 minutes

Venue:

HP8

Session synopsis:

Utilizing AI to develop a prediction model for Patient Wellness Report at Temple University School of Dentistry.

Background

Temple University School of Dentistry has developed and implemented a Patient Wellness Report (PWR) for assessing oral, dental, quality of life, health literacy, and general health outcomes as part of comprehensive oral health care . The PWR measures 14 wellness dimensions (scale: good-fair-poor) to monitor improvements in all outcomes. Determining its effectiveness in improving dental and oral disease outcomes is critical, especially in identifying factors responsible for disease improvement versus disease progression (DIVP).

Objectives

Using Artificial Intelligence (AI) prediction methods, this analysis evaluates the effectiveness of oral and dental care on four measures of dental caries and periodontal diseases.

Materials and methods

PWR datasets of 7,344 patients (caries and periodontal disease) between Jan-2022 – Dec-2023 were obtained. Three outcome categories and a rank-based system were created (see Abstract 1 for more information) for binary classification to determine DIVP. AI models (Random Forest, Decision Tree, Naïve Bayes, XGBoost) and de-biasing methods (cross-validations, sampling) were utilized for testing and training the prediction model. The performance of the models was evaluated using sensitivity, specificity, precision, recall, and f-1 measures.

Results

The XGBoost model performed best with a 75% f-1 score, 83% precision, and 72% recall. For caries measures, age, fluoride, recall exams, dietary advice, number of bitewing radiographs exposed, and number of periodontal treatments were strong predictors of disease improvement. For disease progression, the number of restorations and higher number of treatment codes were major predictors. For periodontal disease, the number of periodontal treatment codes, dietary counselling, prosthetic prostheses , and recall examples were associated with disease improvement, and older age, poor oral hygiene, and higher number of restorations were associated with disease progression.

Discussion and conclusion

This study demonstrated the successful application of AI to build the prediction model using PWRs in a dental school setting. We found fluoride, recall exams, periodontal treatments, and dietary advice were helpful in disease outcomes. This study provides recommendations for other schools to utilize such tools to improve the outcomes of dental diseases.

Programme:

11:30	Welcome and introduction
11:35	Artificial Intelligence (AI): Analysis of Outcomes of Oral Healthcare at a US Dental School Part I: Descriptive Analysis
11:45	Artificial Intelligence (AI): Analysis of Outcomes of Oral Healthcare at a US Dental School Part II: AI methods and their potential application in dental education and patient care
12:55	Artificial Intelligence (AI): Analysis of Outcomes of Oral Healthcare at a US Dental School Part III: Utilizing AI to develop a prediction model
12:05	Artificial Intelligence (AI): Analysis of Outcomes of Oral Healthcare at a US Dental School: Part IV: Comparative analysis of outcomes using the generalized linear models
12:15	Artificial Intelligence (AI): Analysis of Outcomes of Oral Healthcare at a US Dental School Part V: Discussion of results from AI and GLM analyses
12:30	Discussion, Q&A and take away message
13:00	End

Chair:

Amid I. Ismail

Dean

Temple University Kornberg School of Dentistry, Philadelphia, Pennsylvania, USA

Dr. Amid I. Ismail, BDS, MPH, DrPH, MBA, is the Laura H. Carnell Professor and Dean of Temple University Kornberg School of Dentistry, Philadelphia, Pennsylvania, USA. He is an epidemiologist and has expertise in public health, systems, dental care, learn management, and cariology degree from the Ross School of Business at the University of Michigan. He is a Diplomate of the American Board of Dental Public Health. He has published over 130 referred papers and several book chapters. He has received over $16 Million in research funding throughout his career. Dr. Ismail H index is 75.

Dr. Ismail has led the transformation of Temple University Kornberg School of Dentistry to become a vital player in the university’s community engagement, research, and graduating clinical competent dentists. He has experience working with faculty, several of the schools and colleges, and in working with all the service units. His quest for excellence with compassion and kindness has created an engaging and happy environment at the dental school among most students, faculty, and staff.

Dr. Ismail has built a new research program at Temple Dental focusing on the oral microbiome, smart biomaterials, behavioral sciences, and community health. Last year he assisted Dr. Jay Patel in opening a new center for research on artificial intelligence. Temple Dental secured a large grant from NIH to evaluate the predictors of periodontal disease using AI including predictors as medical health, oral microbiome, and other risk factors. Part of the activities in AI include using software to evaluate detection of enamel and dental radiofluorines and alveolar bone loss and evaluation of generative AI to manage patient scheduling.

Speakers:

Sungwoo Lim

Associate professor at Oral health Science

Kornberg School of Dentistry, Temple University

Dr. Sungwoo Lim, DrPH, MA, MS, is an adjunct associate professor at Oral health Science, Kornberg School of Dentistry, Temple University. Trained as a statistician/epidemiologist, in the past 18 years he has been working with dentists and oral epidemiologists to better understand risk factors of early childhood caries and caries progression among vulnerable populations. He has also strived to introduce and apply advanced statistical methods (e.g., targeted maximum likelihood method, sequence analysis) to oral epidemiology research to identify patterns and make causal inference. Specifically, his research interest in causal mechanism of early childhood dental caries has led to several research projects where he has tested social and behavioral determinants for caries progression among African American children. He has further contributed to developing an evaluation and educational tool for data collection and data analysis experiences for dental students.

These inter-disciplinary collaborations have successfully resulted in major scientific publications where causal relationships between social, behavioral, and dietary factors and early childhood caries were identified and innovative methods to analyze complex caries progression data and dietary data were demonstrated. He has published 108 scientific papers.

Jay Patel

Director of the Center for Dental Informatics and AI

Temple University Kornberg School of Dentistry

Dr. Jay Patel (BDS, MS, PhD in informatics) is an Assistant Professor and the Director of the Center for Dental Informatics and AI at the Temple University Kornberg School of Dentistry. Dr. Patel is one of the very few across the US who have pursued training in both clinical dentistry and a doctorate in informatics and computer science. This diverse training and experience provide unique opportunities for Dr. Patel to conduct cutting-edge AI transitional dental research. Dr. Patel’s research focuses on developing AI models and software applications using large electronic health record data to predict disease initiation and progression to enhance prevention. His research also focuses on the integration of oral and systemic health by linking electronic medical and dental records by developing AI-based linking algorithms. He has also developed over 40 natural language processing pipelines and electronic dental records data quality measures to extract information from free-text and clinical notes. Dr. Patel has been invited as an honored speaker and a panelist to present his pioneering work in dental AI at various universities and at the National Institute of Dental Oral and Craniofacial Research and the National Institute of Health.

Dr. Patel has been a recipient of several NIH-NIDCR funded awards as a PI and Co-Is, including K08, U01, William Buttler, Robert Wood Johnson Foundations, New Jersey Health Foundations, and CareQuest Award. His K08 will create three software applications to improve the quality of dental radiographs and extract bone loss features from the radiographs to predict future bone loss. His CareQuest award provided him with over 40M patients' dental claims datasets to be linked with their medical claim datasets. This dataset will become a vital resource for his Center to conduct AI and data science-related studies to answer many clinical research questions. He has published 38 papers and 31 abstracts related to dental AI research and is a recipient of a US patent as a principal investigator. Dr. Patel has taught AI and data sciences-related courses in a health informatics program consisting of a majority of dentists, physicians, and public health students. With the Dean, Dr. Patel is also working on creating one of the very few certificate programs in dental informatics and AI that will be offered by Temple University Kornberg School of Dentistry in the near future.