{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T17:39:28Z","timestamp":1787593168184,"version":"build-2736575974"},"reference-count":25,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aap.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Periodontology"],"published-print":{"date-parts":[[2026,8]]},"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n To identify novel periodontal phenotypes using unsupervised machine learning on a large\u2010scale, multicenter cohort, specifically characterizing disease patterns based on the \u201cperiodontal architecture\u201d of localized structural failures (tooth mobility and molar furcation defects) rather than global severity averages alone.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n This cross\u2010sectional study analyzed electronic health records from 15,723 adult patients with periodontitis. A high\u2010dimensional feature vector (\n D<\/jats:italic>\n \u00a0=\u00a072) was constructed for each patient, integrating tooth\u2010specific ordinal grades for mobility and furcation, mean probing depths (PPD), clinical attachment loss (CAL), and systemic health variables. Unsupervised phenotyping was performed using principal component analysis (PCA), t\u2010SNE visualization, and\n K<\/jats:italic>\n \u2010means clustering. Cluster validity was assessed via Silhouette Analysis, and phenotypes were compared using ANOVA and Chi\u2010square (\n X<\/jats:italic>\n 2<\/jats:sup>\n ) tests.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Four distinct architectural phenotypes were identified: (1) Maintenance\/Healthy, representing stability; (2) Anterior\u2013Mobility dominant, defined by high\u2010grade anterior mobility (52.4% prevalence), and the highest diabetes prevalence (12.2%); (3)\u00a0Molar\u2010Furcation Dominant, a male\u2010dominated group (61%) characterized by advanced posterior furcation defects (93.8%\u00a0prevalence) despite lower anterior mobility; and (4)\u00a0Generalized severe, exhibiting global architectural collapse. The phenotypes demonstrated statistically significant separation across all clinical metrics (\n p<\/jats:italic>\n \u00a0<\u00a00.001).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n Periodontitis manifests as distinct architectural archetypes\u2014specifically \u201cAnterior\u2013Mobility\u201d and \u201cMolar\u2010Furcation\u201d phenotypes\u2014that are often aggregated into a single severity category by traditional staging. These data\u2010driven clusters have unique systemic risk profiles, suggesting that diagnosis and treatment planning should incorporate the specific localization of structural failure.<\/jats:p>\n <\/jats:sec>\n \n Plain language summary<\/jats:title>\n Severe gum disease (periodontitis) is traditionally classified by overall severity, often grouping different types of tooth damage into the same broad category. To uncover hidden patterns, we used an artificial intelligence technique to analyze the detailed dental and medical records of more than 15,000 patients. Instead of simply grouping patients by how advanced their disease was, the computer identified four distinct patient profiles based on specific patterns of tooth damage and overall health. Interestingly, two of the most severe profiles were fundamentally different. One featured loose front teeth and was strongly linked to diabetes and systemic health issues. The other featured damage between the roots of back teeth (molars) and was primarily driven by local anatomical problems rather than general health. These findings demonstrate that severe gum disease is not a single condition, but rather develops through completely distinct biological pathways. Recognizing these unique patterns allows dental professionals to move beyond a \u201cone\u2010size\u2010fits\u2010all\u201d approach, paving the way for personalized treatments\u2014such as medical screening for patients with loose front teeth and targeted surgical repairs for molar damage.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/jper.70123","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T14:24:51Z","timestamp":1776090291000},"page":"1746-1757","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised phenotyping of the periodontal architecture through high\u2010dimensional clustering of electronic health records: A multicenter study"],"prefix":"10.1002","volume":"97","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6951-8794","authenticated-orcid":false,"given":"Georgios S.","family":"Chatzopoulos","sequence":"first","affiliation":[{"name":"Division of Periodontology School of Dentistry University of Minnesota Minneapolis Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Larry F.","family":"Wolff","sequence":"additional","affiliation":[{"name":"Division of Periodontology School of Dentistry University of Minnesota Minneapolis Minnesota USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrdp.2017.38"},{"issue":"1","key":"e_1_2_8_3_1","first-page":"89","article-title":"Biological definition of periodontal diseases: a historical review of host\u2010response diagnostics and their implications for disease classification","volume":"97","author":"Bostanci N","year":"2025","journal-title":"Periodontol 2000"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/JPER.18-0006"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/JPER.20-0096"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/JPER.17-0721"},{"issue":"10","key":"e_1_2_8_7_1","first-page":"1456","article-title":"Prognostic performance of the 2017 World Workshop classification on staging and grading of periodontitis compared with the British Society of Periodontology's implementation","volume":"93","author":"Dukka H","year":"2022","journal-title":"J Periodontol"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/prd.12314"},{"issue":"9","key":"e_1_2_8_9_1","first-page":"911","article-title":"At least three phenotypes exist among periodontitis patients","volume":"44","author":"Delatola C","year":"2017","journal-title":"J Clin Periodontol"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1902\/jop.2016.160379"},{"issue":"7","key":"e_1_2_8_11_1","first-page":"643","article-title":"Systematic comparison of machine learning algorithms to develop and validate predictive models for periodontitis","volume":"49","author":"Bashir NZ","year":"2022","journal-title":"J Clin Periodontol"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/JPER.17-0427"},{"issue":"1","key":"e_1_2_8_13_1","first-page":"1","article-title":"Developing predictive models for periodontitis progression using artificial intelligence: a longitudinal cohort study","volume":"52","author":"Furquim CP","year":"2025","journal-title":"J Clin Periodontol"},{"issue":"9","key":"e_1_2_8_14_1","first-page":"1044","article-title":"Examining bias and reporting in oral health prediction modeling studies","volume":"99","author":"Du M","year":"2020","journal-title":"J Dent Res"},{"issue":"1","key":"e_1_2_8_15_1","first-page":"56","article-title":"Application of the 2018 periodontal status classification to epidemiological survey data (ACES) framework to estimate the periodontitis prevalence in the United States","volume":"52","author":"Tay JRH","year":"2025","journal-title":"J Clin Periodontol"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcpe.13543"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcpe.13739"},{"issue":"1","key":"e_1_2_8_18_1","first-page":"12","article-title":"Epidemiology of molar furcation defects: a multi\u2010center study on prevalence, severity, and risk indicators","volume":"60","author":"Chatzopoulos GS","year":"2025","journal-title":"J Periodont Res"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2025.106024"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/jre.70049"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/prd.12344"},{"issue":"2","key":"e_1_2_8_22_1","first-page":"S1","article-title":"Consensus report of the 20th European Workshop on Periodontology: contemporary and emerging technologies in periodontal diagnosis","volume":"52","author":"Herrera D","year":"2025","journal-title":"J Clin Periodontol"},{"issue":"1","key":"e_1_2_8_23_1","first-page":"1234","article-title":"Exploring the role of lipid metabolism related genes and immune microenvironment in periodontitis by integrating machine learning and bioinformatics analysis","volume":"15","author":"Wei L","year":"2025","journal-title":"Sci Rep"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13061028"},{"issue":"1","key":"e_1_2_8_25_1","first-page":"e1","article-title":"A predictive model for significant periodontal disease progression: a large\u2010scale cohort study","volume":"30","author":"Chatzopoulos GS","year":"2025","journal-title":"Med Oral Patol Oral Cir Bucal"},{"issue":"11","key":"e_1_2_8_26_1","first-page":"1409","article-title":"Using periodontal staging and grading system as a prognostic factor for future tooth loss: a long\u2010term retrospective study","volume":"91","author":"Ravid\u00e0 A","year":"2020","journal-title":"J Periodontol"}],"container-title":["Journal of Periodontology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aap.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jper.70123","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aap.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jper.70123","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aap.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jper.70123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T17:16:44Z","timestamp":1787591804000},"score":1,"resource":{"primary":{"URL":"https:\/\/aap.onlinelibrary.wiley.com\/doi\/10.1002\/jper.70123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":25,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/jper.70123"],"URL":"https:\/\/doi.org\/10.1002\/jper.70123","archive":["Portico"],"relation":{},"ISSN":["0022-3492","1943-3670"],"issn-type":[{"value":"0022-3492","type":"print"},{"value":"1943-3670","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-01-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}