Dental radiographic examinations in the United States generate approximately 320 million images annually that routinely capture markers of systemic disease, yet traditional workflows do not routinely translate these findings into actionable medical referrals. This represents a significant missed opportunity for early disease detection and intervention. The scientific evidence linking periodontal disease with cardiovascular disease and diabetes is substantial, and recent policy expansions in Medicare coverage for dental services related to medical conditions underscore growing recognition of oral-systemic connections. However, data fragmentation between medical and dental systems creates blind spots resulting in missed opportunities to optimize patient care. Artificial and augmented intelligence offers a practical mechanism to bridge this gap. FDA-cleared dental AI systems demonstrate high diagnostic accuracy for detecting both oral pathology and systemic disease markers, such as carotid artery calcifications associated with stroke risk. AI-assisted decision support tools could be used to increase appropriate cross-referrals between medical and dental practitioners while improving collection of relevant clinical data. Realizing this potential requires not only technological advancement but also electronic health record interoperability, clinician trust in explainable AI systems, and educational reform that incorporates oral-systemic health principles across both dental and medical curricula.
Dental visits generate an estimated 320 million radiographic examinations annually in the United States.1 These images routinely capture markers of low-grade chronic inflammation and systemic disease, including carotid artery calcifications associated with stroke risk. A recent systematic review and meta-analysis confirmed that artificial intelligence (AI) models achieve high sensitivity and specificity for detecting these calcifications on standard panoramic radiographs,2 yet traditional workflows rarely translate such findings into actionable dental-to-medical referrals. This represents a missed opportunity of considerable scale.
The Scientific Foundation
The evidence supporting oral-systemic health connections is substantial. Periodontitis is independently associated with cardiovascular disease3,4 and diabetes,5,6 relationships that extend beyond shared risk factors. The 2021 Surgeon General’s report emphasized that “the mouth is the gateway to the rest of the body.”7 This framing carries particular weight in an era when AI can operationalize that connection of various patient data at the point of care.
The quantitative case for integration is compelling. A model-based cost-effectiveness analysis found that expanding coverage for nonsurgical periodontal treatment among patients with type 2 diabetes would avert tooth loss by 34%, reduce microvascular complications by 18% to 21%, and generate net savings of $5,904 per patient with a gain of 0.6 quality-adjusted life years.8 These are not marginal improvements.
Healthcare Delivery Gaps
Current healthcare delivery models perpetuate disparities. In 2018, 64.7 million Americans received neither medical nor dental care9—a population for whom any healthcare encounter represents a valuable screening opportunity. Recent policy shifts have expanded payment policy under traditional Medicare for services that are inextricably linked to covered medical services such as organ transplant, cardiac valve replacements, valvuloplasty procedures, chemotherapy services, chimeric antigen receptor (CAR) T-cell therapy, use of high-dose bone modifying agents (antiresorptive therapy), head and neck cancer, and end-stage renal disease. These policy shifts highlight the need for evidence-based integration models that can survive policy scrutiny and volatility and support the adoption of changes that improve the health and well-being of patients and populations.
A fundamental barrier to healthcare integration is data fragmentation. A patient’s dental records and medical records almost never interact. Medical and dental systems use different coding languages, and this separation creates blind spots for the medical and dental clinical teams as well as health systems. A physician treating a diabetic patient may be unaware of severe periodontal disease hindering glycemic control; a dentist may not know the patient has cardiac conditions requiring precautions. Recent advances in computer vision and natural language processing demonstrate that AI can help bridge these gaps (Figure 1). For example, one study achieved 97% to 98% accuracy in extracting periodontal diagnoses from unstructured clinical notes across institutions.10 Ready access to periodontal health data can empower prediabetic and diabetic patients as well as their medical care team.
AI as a Bridge to Integration
AI offers a mechanism to address these challenges. Food and Drug Administration (FDA)–cleared dental AI systems have demonstrated measurable improvements in diagnostic accuracy. In a cross-sectional study using an algorithm trained on more than 250,000 panoramic radiographs, AI detected caries, periodontal bone loss, and other pathologies with accuracy ranging from 90% to 99% depending on the condition.11 More significantly for integration, digital decision support tools have been shown to increase appropriate cross-referral between general practitioners and dental practitioners by 4.3 to 8.3 times and improve collection of relevant clinical data such as glycated hemoglobin values in patients with periodontitis and diabetes by more than threefold.12
These findings matter because time constraints demonstrably compromise diagnostic performance. Studies show that workflow pressure reduces diagnostic sensitivity by 40% for caries and 67% for periodontal destruction.13 AI-assisted analysis can help mitigate these limitations through consistent, objective evaluation regardless of clinical tempo.
In a systematic review of 39 randomized controlled trials, AI-assisted interventions outperformed usual care in 77% of studies, with clinically relevant outcomes improved in 70% of cases.14 Patient acceptance appears favorable: multinational survey data indicate that 57.6% of patients hold positive views of AI in healthcare, and 71.4% prefer facilities that utilize AI-enabled technologies.15
The Path Forward
The potential of AI extends beyond diagnostic accuracy. AI systems can detect carotid artery calcifications on routine panoramic radiographs, enabling early intervention that may prevent strokes. They can identify obstructive sleep apnea risk factors and flag suspicious pathology requiring medical referral—transforming routine dental visits into comprehensive health screenings.
Realizing this potential requires more than technology—it demands workflow innovation and professional collaboration. In addition, AI-generated findings must translate into actionable referrals and coordinated care plans, which demand not only electronic health record interoperability but also clinician trust. For providers to act on AI-driven insights, they need to understand how the AI arrived at its conclusions—a challenge given that many deep learning models function as “black boxes.” The development of explainable AI that can highlight specific radiographic features driving a prediction will be essential for clinical adoption.
Educational reform is equally essential: dental curricula must incorporate oral-systemic health throughout, while medical programs should include oral health components. The scientific foundation exists; the technology is maturing; the economic case is favorable. What remains is the collective will to reimagine dental care as integral to whole-person health.
DISCLOSURE
Drs. Ghorbanifarajzadeh and Chalmers are full-time employees of Overjet. Dr. Dolan is a part-time consultant to Overjet.
About the Authors
Mina Ghorbanifarajzadeh, DMD
Senior Clinical Manager, Overjet; Courtesy Clinical Assistant Professor, University of Florida College of Dentistry
Teresa A. Dolan, DDS, MPH
Clinical Advisor, Overjet; Professor and Dean Emeritus, University of Florida College of Dentistry
Natalia I. Chalmers, DDS, MHSc, PhD
Chief Dental Officer, Overjet; Dean’s Faculty, University of Maryland School of Dentistry
References
1. Mettler FA Jr, Mahesh M, Bhargavan-Chatfield M, et al. Patient exposure from radiologic and nuclear medicine procedures in the United States: procedure volume and effective dose for the period 2006–2016. Radiology. 2020;295(2):418-427.
2. Arzani S, Soltani P, Karimi A, et al. Detection of carotid artery calcifications using artificial intelligence in dental radiographs: a systematic review and meta-analysis. BMC Med Imaging. 2025;25(1):174.
3. Sanz M, Marco Del Castillo A, Jepsen S, et al. Periodontitis and cardiovascular diseases: consensus report. J Clin Periodontol. 2020;47(3):268-288.
4. Genco RJ, Sanz M. Clinical and public health implications of periodontal and systemic diseases: an overview. Periodontol 2000. 2020;83(1):7-13.
5. Arbildo-Vega HI, Cruzado-Oliva FH, Infantes-Ruíz ED, et al. An umbrella review of the association between periodontal disease and diabetes mellitus. Healthcare (Basel). 2024;12(22):2311.
6. Nguyen ATM, Akhter R, Garde S, et al. The association of periodontal disease with the complications of diabetes mellitus. A systematic review. Diabetes Res Clin Pract. 2020;165:108244.
7. US Dept of Health and Human Services. Oral health in America: advances and challenges. NIDCR, NIH website. 2021. https://www.nidcr.nih.gov/research/oralhealthinamerica. Accessed February 4, 2026.
8. Choi SE, Sima C, Pandya A. Impact of treating oral disease on preventing vascular diseases: a model-based cost-effectiveness analysis of periodontal treatment among patients with type 2 diabetes. Diabetes Care. 2020;43(3):563-571.
9. Manski R, Rohde F, Ricks T. Trends in the number and percentage of the population with any dental or medical visits, 2003-2018. Statistical Brief #537. Agency for Healthcare Research and Quality (AHRQ) website. October 2021. https://meps.ahrq.gov/data_files/publications/st537/stat537.shtml. Accessed February 4, 2026.
10. Chuang YS, Lee CT, Lin GH, et al. Cross-institutional dental electronic health record entity extraction via generative artificial intelligence and synthetic notes. JAMIA Open. 2025;8(3):ooaf061.
11. Turosz N, Chęcińska K, Chęciński M, et al. Oral health status and treatment needs based on artificial intelligence (AI) dental panoramic radiograph (DPR) analysis: a cross-sectional study. J Clin Med. 2024;13(13):3686.
12. Kalmus O, Smits K, Seitz M, et al. Evaluation of a digital decision support system to integrate type 2 diabetes mellitus and periodontitis care: case-vignette study in simulated environments. J Med Internet Res. 2023;25:e46381.
13. Plessas A, Nasser M, Hanoch Y, et al. Impact of time pressure on dentists’ diagnostic performance. J Dent. 2019;82:38-44.
14. Lam TYT, Cheung MFK, Munro YL, et al. Randomized controlled trials of artificial intelligence in clinical practice: systematic review. J Med Internet Res. 2022;24(8):e37188.
15. Busch F, Hoffmann L, Xu L, et al. Multinational attitudes toward AI in health care and diagnostics among hospital patients. JAMA Netw Open. 2025;8(6):e2514452.
Figures and Images
Figure 1
