Scope of Research
The integration of Artificial Intelligence (AI) and Informatics into the field of dentistry represents a paradigm shift in dental practice and oral & craniofacial research. Our newly established center is at the forefront of this transformative movement, dedicated to advancing the boundaries of dental care through innovative applications of AI, big data analysis, image processing/computer vision, machine learning, and deep learning. In this center, we integrate domain expertise from various areas of healthcare such as medical, dental, nutrition, behavioral, and such as with computer science and AI to improve the decision-making, problem-solving, and treatment planning, improving oral and overall health of the patient. One of the major goals of this center is to integrate oral health with other overall health to provide holistic and interdisciplinary patient care through the power of practice-based evidence and AI. Another major goal of this center is to study oral health disparities using diverse datasets generated from our diverse patient population from the great Philadelphia area. Some research approaches are mentioned below.
Big Data Analysis in Dentistry
One of the cornerstones of our research approach is the utilization of big data analysis techniques to extract valuable insights from vast and heterogeneous datasets. Due to the wide adoption of electronic dental records (EDRs) and digital imaging modalities, we have a unique opportunity to leverage data-driven approaches to inform evidence-based practices in dentistry. By aggregating and analyzing large-scale datasets encompassing diverse patient populations and clinical scenarios, we aim to identify patterns, trends, and associations that hold significant implications for clinical decision-making and treatment outcomes. Through advanced statistical modeling and predictive analytics, we seek to uncover hidden correlations and risk factors, ultimately paving the way for more personalized and precise approaches to dental care delivery.
Practice-Based Evidence Generation
Central to our research agenda is the generation of practice-based evidence, which bridges the gap between research findings and real-world clinical applications. Unlike traditional randomized controlled trials (RCTs), practice-based evidence relies on observational data obtained from routine clinical practice, offering insights into the effectiveness and outcomes of interventions in diverse patient populations and clinical settings. By harnessing the wealth of data available in EDR, patient registries, and clinical databases, we endeavor to generate robust evidence that informs clinical decision-making and enhances the quality of patient care. Through rigorous data analysis and validation methodologies, we aim to establish evidence-based guidelines and protocols that are grounded in the realities of everyday clinical practice, thereby facilitating the translation of research findings into actionable strategies for improving patient outcomes and enhancing the efficiency of dental care delivery.
Image Processing and Diagnostic Precision
In addition to big data analysis, our center specializes in the application of advanced image processing techniques to enhance diagnostic accuracy and treatment planning in dentistry. Digital imaging modalities, such as intraoral radiography, cone-beam computed tomography (CBCT), and optical coherence tomography (OCT), have revolutionized the way dental professionals visualize and interpret anatomical structures, pathologies, and treatment outcomes. Leveraging state-of-the-art image processing algorithms, we aim to develop automated tools and software platforms for image analysis, segmentation, and feature extraction, enabling clinicians to obtain quantitative measurements and objective assessments of dental conditions with high precision and reproducibility. From caries detection and periodontal assessment to orthodontic treatment planning and implant placement, our image-processing initiatives empower clinicians with the tools and technologies they need to deliver optimal care and achieve superior clinical outcomes.
Integrate oral health with overall health
Linking oral health and overall health is crucial due to their bidirectional relationship. Poor oral health can contribute to systemic conditions like cardiovascular disease, diabetes, and respiratory infections, while systemic health issues can also impact oral health. Recognizing this connection is essential for implementing comprehensive healthcare strategies, as addressing oral health can help prevent and manage a range of systemic diseases, ultimately improving overall health outcomes and quality of life. Patients' electronic dental and health records are powerful sources to integrate oral health with overall health, however, due to interoperability and data standard issues, in most cases, patients' EDR and HER remain unlinked. Our center also aims to develop cutting-edge linking algorithms and data science pipelines to link these two critical sources of datasets to obtain patients' complete information which will allow us to study connections between oral and overall health more closely and enhance health information exchange between medical and dental providers in real-time.
Machine Learning & Deep Learning for Oral Health Disparities
Oral health disparities, defined as differences in oral health status and access to care across demographic, socioeconomic, and geographic lines, remain a persistent challenge in public health. Through the application of machine learning methods, we aim to identify predictive models and risk stratification algorithms that shed light on the underlying determinants of oral health disparities and inform targeted interventions and preventive strategies. By analyzing multidimensional datasets including clinical, socioeconomic, and environmental factors, we seek to determine complex interplay of social determinants of health, behavioral risk factors, and biological markers that contribute to oral disease burden and disparities. By harnessing the power of machine learning and big data analytics, we aim to develop evidence-based interventions and policy recommendations that promote oral health equity and reduce disparities in access to quality dental care.
Please join us on this journey towards a future where AI-powered dentistry transforms lives and communities, one smile at a time.
Dr. Jay S. Patel
Recent Funding
National Institute of Dental and Craniofacial Research NIDCR
"ICPSR Sequential Modeling for Prediction of Periodontal Diseases: an intra-Collaborative Practice-based Research Study".
Role: Co-Investigator
Total Costs: $3,568,695
National Institute of Dental and Craniofacial Research NIDCR
"Early Bone Loss Pattern Detection from Periapical Radiographs Using Deep Learning and Artificial Intelligence”
Role: Principal Investigator
Total Costs: $804,395
CareQuest Institute of Oral Health
"Determining the Ideal PM Frequency Using Longitudinal Medical & Dental Claims Data and Dental Electronic Health Records"
Role: Principal Investigator
Total Costs: $10,000
CareQuest Institute of Oral Health
"Trajectories and Predictors of Caries Using Longitudinal Medical & Dental Claims Data"
Role: Co-Investigator
Total Costs: $10,000
Robert Wood Johnson Foundation's Health Data for Action Program
"Predictive Modeling of Primary Care Visit Adherence and Emergency Department Use for Patients with Hypertension and Diabetes"
Role: Co-Investigator
Data Access Award
Philadelphia Department of Public Health
"Community Vaccine Distribution"
Role: Data Scientist
Total Costs: $1,252,219
New Jersey Health Foundation
"Investigating Oral Health Disparities Between Dental Patients with and without Mental Health Conditions Using Machine Learning"
Role: Co-Principal Investigator
Total Costs: $30,000
News
Leverett Graduate Student Merit Award
Congratulations to Dr. Jay Patel for receiving the prestigious AADOCR William Butler Fellowship Award at the 2024 annual conference in New Orleans. Click here to read more information about this award.
Selected Publications
Wiener RC, Patel JS. Oral and oropharyngeal cancer screening and tobacco cessation discussions, NHANES 2011–2018. Community Dentistry and Oral Epidemiology. 2024 Apr;52(2):248-54.
Ogwo C, Osisioma W, Okoye DI, Patel JS. Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach. BMC Oral Health. 2024 Mar 9;24(1):313.
Patel JS, Shin D, Willis L, Zai A, Thyvalikakath T. Feasibility of Utilizing Electronic Dental Record Data and Periodontitis Case Definition to Automate Diagnosis. Studies in Health Technology and Informatics. 2024 Jan 1;310:214-8.
Patel JS, Wu H. Utilizing Electronic Dental Records to Predict Neuro-Degenerative Diseases in a Dental Setting: A Pilot Study. Studies in Health Technology and Informatics. 2024 Jan 1;310:1322-6.
Patel JS, Yao L, Vina E, Fleece D, Arundathi J, Caricchio R, Wu H. Phenotype Systemic Lupus Erythematosus Patients from EPIC Cosmos. Studies in Health Technology and Informatics. 2024 Jan 1;310:159-63.
Patel JS, Shin D, Willis L, Zai A, Kumar K, Thyvalikakath TP. Comparing gingivitis diagnoses by bleeding on probing (BOP) exclusively versus BOP combined with visual signs using large electronic dental records. Scientific Reports. 2023 Oct 10;13(1):17065.
Felix Gomez GG, Hugenberg ST, Zunt S, Patel JS, Wang M, Rajapuri AS, Lembcke LR, Rajendran D, Smith JC, Cheriyan B, Boyd LJ. Characterizing clinical findings of Sjögren’s Disease patients in community practices using matched electronic dental-health record data. PloS one. 2023 Jul 31;18(7):e0289335.
Patel JS, Oaikhena O, Phan TT, Vo H, Alizadeh JM, Wu H. The Landscape of Health Informatics Education in Low-or Middle-Income Countries. In2023 IEEE 11th International Conference on Healthcare Informatics (ICHI) 2023 Jun 26 (pp. 652-656). IEEE.
Patel JS, Zhan S, Siddiqui Z, Dzomba B, Wu H. Automatic identification of self-reported COVID-19 vaccine information from vaccine adverse events reporting system. Methods of Information in Medicine. 2023 May;62(01/02):049-59.
Patel JS, Kumar K, Zai A, Shin D, Willis L, Thyvalikakath TP. Developing Automated Computer Algorithms to Track Periodontal Disease Change from Longitudinal Electronic Dental Records. Diagnostics. 2023 Mar 8;13(6):1028.
Patel JS, Mital D, Singhal V, Srinivasan S, Wu H, Mehta S. Feasibility of automatic differential diagnosis of endodontic origin periapical lesions-a pilot study. International Journal of Medical Engineering and Informatics. 2023;15(5):430-41.
Patel JS, Ogwo C, Schueck M, Ginu N, Wu H, Yucel R, et al. Machine Learning Based Dental Caries Prediction Model Using Matched Electronic Dental Records and Social Determinants of Health Data. . AMIA . 2023
Patel JS et al., Wu H, Alizadeh JM. Prediction of Emergency Visits of Diabetic Patients Using Integrated Social Determinants of Health with Electronic Medical Records. 2023;
Patel JS, Brandon R, Tellez M, Albandar JM, Rao R, Krois J, Wu H. Developing automated computer algorithms to phenotype periodontal disease diagnoses in electronic dental records. Methods of Information in Medicine. 2022 Dec;61(S 02):e125-33
Patel JS, Shin D, Willis L, Zai A, Kumar K, Thyvalikakath TP. Gingivitis diagnoses using 2017 classification versus pre-2017 criteria: a retrospective study using electronic dental record data.
Wu H, Patel JS. Challenges in artificial intelligence development of radiotherapy. InArtificial Intelligence in Radiation Therapy 2022 Dec 1 (pp. 11-1). Bristol, UK: IOP Publishing.
Siddiqui ZA, Dhumal T, Patel JS, LeMasters T, Almony A, Kamal KM. Cost impact of different treatment regimens of brolucizumab in neovascular age-related macular degeneration: A budget impact analysis. Journal of Managed Care & Specialty Pharmacy. 2022 Dec;28(12):1350-64.
Patel JS, Su C, Tellez M, Albandar JM, Rao R, Iyer V, Shi E, Wu H. Developing and testing a prediction model for periodontal disease using machine learning and big electronic dental record data. Frontiers in Artificial Intelligence. 2022 Oct 13;5:979525.
Cejudo Grano de Oro JE, Koch PJ, Krois J, Garcia Cantu Ros A, Patel JS, Meyer-Lueckel H, Schwendicke F. Hyperparameter Tuning and Automatic Image Augmentation for Deep Learning-Based Angle Classification on Intraoral Photographs—A Retrospective Study. Diagnostics. 2022 Jun 23;12(7):1526.
Patel JS, Dzomba B, Wu H. “Think Outside of Box”-Ten Commandments in Providing Optimal Health Informatics Education. In2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) 2022 Jun 11 (pp. 585-590). IEEE.
Li S, Williams KS, Medam JK, Patel JS, Gonzalez T, Thyvalikakath TP. Retrospective study of the reasons and time involved for dental providers' medical consults. Frontiers in Digital Health. 2022 May 12;4:838538.
Rohrer C, Krois J, Patel JS, Meyer-Lueckel H, Rodrigues JA, Schwendicke F. Segmentation of dental restorations on panoramic radiographs using deep learning. Diagnostics. 2022 May 25;12(6):1316.
Patel JS, Rao R, Brandon R, Iyer V, Albandar JM, Tellez M, Krois J, Wu H. Develop a natural language processing pipeline to automate extraction of periodontal disease information from electronic dental clinical notes. InProceedings of the 6th International Conference on Medical and Health Informatics 2022 May 13 (pp. 61-68).
Patel JS, Patel K, Vo H, Jiannan L, Tellez MM, Albandar J, Wu H. Enhancing an AI-Empowered Periodontal CDSS and Comparing with Traditional Perio-risk Assessment Tools. InAMIA Annual Symposium Proceedings 2022 (Vol. 2022, p. 846). American Medical Informatics Association.
Patel JS, Vo H, Nguyen A, Dzomba B, Wu H. A data-driven assessment of the US Health Informatics Programs and job market. Applied Clinical Informatics. 2022 Mar;13(02):327-38.
Patel JS, Dzomba B, Vo H, Von Nessen-Scanlin S, Siminoff LA, Wu H. A Health IT-Empowered Integrated Platform for Secure Vaccine Data Management and Intelligent Visual Analytics and Reporting. InHEALTHINF 2022 (pp. 522-531).
Patel JS, Voytek J, Maltepes M, Lengner A. An Integrated Interactive COVID-19 Dashboard for Individual Risk Analysis. BMC Medical Informatics and Decision Making. 2022;
Dzomba B, Patel JS, Pratico D, Shi X, Wu H. Challenges of exploring social factors associated to Alzheimer’s Disease patients and comparing AD patient cohorts using Epic Cosmos. International Conference on Intelligent Biology and Medicine. 2022;
Jones J, Patel JS. Health Informatics Education: from Content-Based Courses to Competency- Driven Curricula. American Medical Informatics Association Conference Proceedings. 2022; https://amia.org/education-events/linking-informatics-and-education-academic-forum-lieaf/afs07-health-informatics
Watson JI, Patel JS, Ramya MB, Capin O, Diefenderfer KE, Thyvalikakath TP, Cook NB. Longevity of crown margin repairs using glass ionomer cement: a retrospective study. Operative Dentistry. 2021 May 1;46(3):263-70.
Siddiqui Z, Wang Y, Patel JS, Thyvalikakath T. Differences in medication usage of dental patients by age, gender, race/ethnicity and insurance status. Technology and Health Care. 2021 Jan 1;29(6):1099-108.
Patel JS, Lai P, Dormer D, Gullapelli R, Wu H, Jones JJ. Comparison of Ease of Use and Comfort in Fitness Trackers for Participants Impaired by Parkinson's Disease: An exploratory study. AMIA Summits on Translational Science Proceedings. 2021;2021:505.
Alzeer A, Jones JF, Bair MJ, Liu X, Alfantoukh LA, Patel JS, Dixon BE. A Comparison Of Text Mining Versus Diagnostic Codes To Identify Opioid Use Problem: A Retrospective Study .