Predicting Emergency Department Visits for Non‐Traumatic Dental‐Related Conditions Among Medicaid Beneficiaries
Open accessAbstract
Patients who use the emergency department (ED) for non-traumatic dental-related conditions are likely to return for multiple visits, accounting for a disproportionate share of healthcare cost. Reliance on the ED for receiving dental care continues to rise, particularly among Medicaid beneficiaries. We sought to predict future "ED users" for non-traumatic dental-related conditions using machine learning algorithms and identify associated risk factors to help Medicaid outreach programs better target populations in most need of improvement in access to dental care. Among 6.4 million Medicaid beneficiaries aged 19-64 years, the state-specific ensemble prediction models demonstrated high performance across four states, with C-statistics ranging from 0.70 to 0.73, accuracy from 0.90 to 0.95, specificity from 0.93 to 0.97, and sensitivity from 0.17 to 0.23, consistently outperformingtraditional logistic regression models. Individual-level variables, such as age, race/ethnicity, and musculoskeletal complications, and area-level variables, such as racial/ethnic composition, indices of food access, and proportion of US-citizenship, explained a significant proportion of the variation in dental-related ED use. Using a machine learning-based risk model to monitor for risk factors of dental-related ED use can assist in developing more targeted care management interventions, addressing unmet dental care and social needs while reducing unnecessary dental-related ED visits.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Methods included gradient boosting, random forest, ensemble models, XGBoost, and logistic regression-based ML pipelines with fairness optimization.
“Methods included gradient boosting [32], random forest [26, 34], ensemble models [26], XGBoost [27], and logistic regression‐based ML pipelines with fairness optimization [21].”
From Artificial Intelligence and Machine Learning for Identifying Social Determinants of Health in Low‐Income Populations Within United States Health Systems: A Scoping Review (2026) · cites this paper as [26]
The Statistical analysis section describes logistic regression with elastic-net regularization as part of a machine-learning ensemble and a separate logistic-regression comparator. It does not describe fairness optimization, so the qualifier attached to citation [21] is unsupported. (LLM, conf=0.87)
Experimental — accuracy not yet measuredML consistently outperformed logistic regression.
“C‐statistics 0.70–0.73; accuracy 0.90–0.95; specificity 0.93–0.97; ML consistently outperformed logistic regression; sociodemographic risk factors identified”
From Artificial Intelligence and Machine Learning for Identifying Social Determinants of Health in Low‐Income Populations Within United States Health Systems: A Scoping Review (2026) · cites this paper as [26]
The Discussion says the machine-learning ensemble outperformed traditional logistic regression in discrimination and calibration, particularly among high-risk patients. But “consistently outperformed” is too broad without specifying the metrics: the Results table shows logistic regression had higher sensitivity in all four states and a higher F1 score in two. (LLM, conf=0.85)
Experimental — accuracy not yet measuredAccuracy was 0.90-0.95 and specificity 0.93-0.97.
“C‐statistics 0.70–0.73; accuracy 0.90–0.95; specificity 0.93–0.97; ML consistently outperformed logistic regression; sociodemographic risk factors identified”
Sociodemographic risk factors were identified.
“C‐statistics 0.70–0.73; accuracy 0.90–0.95; specificity 0.93–0.97; ML consistently outperformed logistic regression; sociodemographic risk factors identified”
The ML ensemble models predicting ED visits for non-traumatic dental conditions had C-statistics of 0.70-0.73.
“C‐statistics 0.70–0.73; accuracy 0.90–0.95; specificity 0.93–0.97; ML consistently outperformed logistic regression; sociodemographic risk factors identified”
Choi et al. [26] reported C-statistics of 0.70-0.73 for Medicaid dental emergency department visit prediction.
“Choi et al. [26] reported C‐statistics of 0.70–0.73 for Medicaid dental emergency department visit prediction”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 19 · Cited by 2
Research works printed but not linked: 18
- [1]Bamezai, A., Melnick, G. & Nawathe, A. The cost of an emergency department visit and its relationship to emergency department volume. Ann. Emerg. Med.45 (5), 483–490. 10.1016/j.annemergmed.2004.08.029 (May 2005). 15855942 · DOI
- [3]Sun, B. C. et al. Emergency department visits for nontraumatic dental problems: a mixed-methods study. Am J. Public. Health May. 105 (5), 947–955. 10.2105/AJPH.2014.302398 (2015). PMC4386544 25790415 · DOI
- [4]Agency for Healthcare Research and Quality. Emergency Department Visits Involving Dental Conditions. Accessed Dec 15, 2021. (2018). https://hcup-us.ahrq.gov/reports/statbriefs/sb280-Dental-ED-Visits-2018.pdf 34662009
- [5]LaCalle, E. & Rabin, E. Frequent users of emergency departments: the myths, the data, and the policy implications. Ann. Emerg. Med.56 (1), 42–48. 10.1016/j.annemergmed.2010.01.032 (Jul 2010). 20346540 · DOI
- [6]Agency for Healthcare Research and Quality (AHRQ). Emergency Department Visits Involving Dental Conditions. Accessed May 3, 2023. (2018). https://hcup-us.ahrq.gov/reports/statbriefs/sb280-Dental-ED-Visits-2018.pdf 34662009
- [7]Kim, P. C. et al. Factors associated with preventable emergency department visits for nontraumatic dental conditions in the U.S. Int J. Environ. Res. Public. Health Sep.30 (19). 10.3390/ijerph16193671 (2019). PMC6801501 31574897 · DOI
- [8]Agarwal, P. et al. Factors associated with emergency department visits: A multistate analysis of adult Fee-for-Service medicaid beneficiaries. Health Serv. Res. Manag Epidemiol Apr. 27 (3)). 10.1177/2333392816648549 (2016). PMC4977022 27512721 · DOI
- [10]Ash, A. S. et al. Social determinants of health in managed care payment formulas. JAMA Intern. Med Oct. 1 (10), 1424–1430. 10.1001/jamainternmed.2017.3317 (2017). PMC5710209 28783811 · DOI · Paper page
- [11]Grinspan, Z. M., Patel, A. D., Hafeez, B., Abramson, E. L. & Kern, L. M. Predicting frequent emergency department use among children with epilepsy: A retrospective cohort study using electronic health data from 2 centers. Epilepsia Jan. 59 (1), 155–169. 10.1111/epi.13948 (2018). 29143960 · DOI
- [12]Ko, M., Lee, Y., Chen, C., Chou, P. & Chu, D. Prevalence of and predictors for frequent utilization of emergency department: A Population-Based study. Medicine (Baltimore) Jul. 94 (29), e1205. 10.1097/MD.0000000000001205 (2015). PMC4603019 26200638 · DOI
- [13]Walker, A., Probst, J. C., Martin, A. B., Bellinger, J. D. & Merchant, A. Analysis of hospital-based emergency department visits for dental caries in the united states in 2008. J Public. Health Dent Summer. 74 (3), 188–194. 10.1111/jphd.12045 (2014). 25215449 · DOI
- [14]Basu, S. & Narayanaswamy, R. A prediction model for uncontrolled type 2 diabetes mellitus incorporating Area-level social determinants of health. Med Care Aug. 57 (8), 592–600. 10.1097/MLR.0000000000001147 (2019). 31268954 · DOI · Paper page
- [19]Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33 (1), 1–22 (2010). 20808728 PMC2929880 · DOI · Paper page
- [20]Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001). · DOI · Paper page
- [21]Chen, T., Guestrin, C. & XGBoost: A Scalable Tree Boosting System. presented at: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining;; San Francisco, California, USA. (2016). 10.1145/2939672.2939785 · DOI · Paper page
- [22]Schmidhuber, J. Deep learning in neural networks: an overview. Neural Netw Jan. 61, 85–117. 10.1016/j.neunet.2014.09.003 (2015). 25462637 · DOI · Paper page
- [23]Scott, K. W. et al. Healthcare spending in U.S. Emergency departments by health condition, 2006–2016. PLoS One. 16 (10), e0258182. 10.1371/journal.pone.0258182 (2021). 34705854 PMC8550368 · DOI
- [24]Ranade, A. et al. Changes in dental benefits and use of emergency departments for nontraumatic dental conditions in massachusetts. Public Health Rep Sep/Oct. 135 (5), 571–577. 10.1177/0033354920946788 (2020). PMC7485060 32795220 · DOI
- Authors
- Choi, S. E., Fayyad, R., Nolte, D., Riedy, C., & Normand, S.-L.
- Affiliations
- Harvard University (US)
- Corresponding author
- Choi, Sung Eun
- Venue
- Scientific Reports
- Published
- 2025-06-06
- Volume
- 15
- Issue
- 1
- Pages
- 19872-19872
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC12144079
- OpenAlex
- W4411110687
- Cited by
- 2
- References
- 19
- Citations by year
- 2026: 2
- FWCI
- 1.86
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Scientific Reports (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Institutes of Health (R00MD016895)
- Topics
- Health Sciences › Dentistry › Periodontics › Dental Health and Care Utilization
- Health Sciences › Medicine › Emergency Medicine › Emergency and Acute Care Studies
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- emergency department visits, Medicaid beneficiaries, access to dental care, risk prediction model, ensemble prediction model, risk factors, food insecurity, musculoskeletal complications, racial and ethnic disparities, care management
- MeSH terms
- Machine Learning, Emergency Room Visits, Adult, Dental Care, Emergency Service, Hospital, Female, Humans, Male, Medicaid, Middle Aged, Stomatognathic Diseases, Risk Factors, United States, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
