Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning

Abstract Objective To evaluate factors influencing the response to periodontal therapy in patients with periodontitis and type 2 diabetes mellitus (DM) using machine learning (ML) techniques, considering periodontal parameters, metabolic status, and demographic characteristics. Methodology We ap...

Full description

Saved in:
Bibliographic Details
Main Authors: Nidia CASTRO DOS SANTOS, Arthur MANGUSSI, Tiago RIBEIRO, Rafael Nascimento de Brito SILVA, Mauro Pedrine SANTAMARIA, Magda FERES, Thomas VAN DYKE, Ana Carolina LORENA
Format: Article
Language:English
Published: University of São Paulo 2025-07-01
Series:Journal of Applied Oral Science
Subjects:
Online Access:http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1678-77572025000100436&lng=en&tlng=en
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730604515459072
author Nidia CASTRO DOS SANTOS
Arthur MANGUSSI
Tiago RIBEIRO
Rafael Nascimento de Brito SILVA
Mauro Pedrine SANTAMARIA
Magda FERES
Thomas VAN DYKE
Ana Carolina LORENA
author_facet Nidia CASTRO DOS SANTOS
Arthur MANGUSSI
Tiago RIBEIRO
Rafael Nascimento de Brito SILVA
Mauro Pedrine SANTAMARIA
Magda FERES
Thomas VAN DYKE
Ana Carolina LORENA
author_sort Nidia CASTRO DOS SANTOS
collection DOAJ
description Abstract Objective To evaluate factors influencing the response to periodontal therapy in patients with periodontitis and type 2 diabetes mellitus (DM) using machine learning (ML) techniques, considering periodontal parameters, metabolic status, and demographic characteristics. Methodology We applied machine learning techniques to perform a post hoc analysis of data collected at baseline and a 6-month follow-up from a randomized clinical trial (RCT). A leave-one-out cross-validation strategy was used for model training and evaluation. We tested seven different algorithms: K-Nearest Neighbors, Decision Tree, Support Vector Machine, Random Forest, Extreme Gradient Boosting, and Logistic Regression. Model performance was assessed using accuracy, specificity, recall, and the area under the Receiver Operating Characteristic (ROC) curve (AUC). Results a total of 75 patients were included. Using the first exploratory data analysis, we observed three clusters of patients who achieved the clinical endpoint related to HbA1c values. HbA1c ≤ 9.4% was correlated with lower PD (r=0.2), CAL (r=0.1), and the number of sites with PD ≥5 mm (r=0.1) at baseline. This study induced AI classification models with different biases. The model with the best fit was Random Forest with a 0.83 AUC. The Random Forest AI model has an accuracy of 80%, a sensitivity of 64%, and a specificity of 87%. Our findings demonstrate that PD and CAL were the most important variables contributing to the predictive performance of the Random Forest model. Conclusion The combination of nine baseline periodontal, metabolic, and demographic factors from patients with periodontitis and type 2 DM may indicate the response to periodontal therapy. Lower levels of full mouth PD, CAL, plaque index, and HbA1c at baseline increased the chances of achieving the endpoint for treatment at 6-month follow-up. However, all nine features included in the model should be considered for treatment outcome predictability. Clinicians may consider the characterization of periodontal therapy response to implement personalized care and treatment decision-making. Clinical trial registration ID: NCT02800252
format Article
id doaj-art-f5eced91b5e644348dddc80a2de641c6
institution DOAJ
issn 1678-7765
language English
publishDate 2025-07-01
publisher University of São Paulo
record_format Article
series Journal of Applied Oral Science
spelling doaj-art-f5eced91b5e644348dddc80a2de641c62025-08-20T03:08:48ZengUniversity of São PauloJournal of Applied Oral Science1678-77652025-07-013310.1590/1678-7757-2025-0211Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learningNidia CASTRO DOS SANTOShttps://orcid.org/0000-0003-2041-9426Arthur MANGUSSIhttps://orcid.org/0000-0003-2086-532XTiago RIBEIROhttps://orcid.org/0009-0003-3841-4663Rafael Nascimento de Brito SILVAhttps://orcid.org/0000-0002-3863-7790Mauro Pedrine SANTAMARIAhttps://orcid.org/0000-0001-9468-0729Magda FEREShttps://orcid.org/0000-0002-2293-3392Thomas VAN DYKEhttps://orcid.org/0000-0003-0568-124XAna Carolina LORENAhttps://orcid.org/0000-0002-6140-571XAbstract Objective To evaluate factors influencing the response to periodontal therapy in patients with periodontitis and type 2 diabetes mellitus (DM) using machine learning (ML) techniques, considering periodontal parameters, metabolic status, and demographic characteristics. Methodology We applied machine learning techniques to perform a post hoc analysis of data collected at baseline and a 6-month follow-up from a randomized clinical trial (RCT). A leave-one-out cross-validation strategy was used for model training and evaluation. We tested seven different algorithms: K-Nearest Neighbors, Decision Tree, Support Vector Machine, Random Forest, Extreme Gradient Boosting, and Logistic Regression. Model performance was assessed using accuracy, specificity, recall, and the area under the Receiver Operating Characteristic (ROC) curve (AUC). Results a total of 75 patients were included. Using the first exploratory data analysis, we observed three clusters of patients who achieved the clinical endpoint related to HbA1c values. HbA1c ≤ 9.4% was correlated with lower PD (r=0.2), CAL (r=0.1), and the number of sites with PD ≥5 mm (r=0.1) at baseline. This study induced AI classification models with different biases. The model with the best fit was Random Forest with a 0.83 AUC. The Random Forest AI model has an accuracy of 80%, a sensitivity of 64%, and a specificity of 87%. Our findings demonstrate that PD and CAL were the most important variables contributing to the predictive performance of the Random Forest model. Conclusion The combination of nine baseline periodontal, metabolic, and demographic factors from patients with periodontitis and type 2 DM may indicate the response to periodontal therapy. Lower levels of full mouth PD, CAL, plaque index, and HbA1c at baseline increased the chances of achieving the endpoint for treatment at 6-month follow-up. However, all nine features included in the model should be considered for treatment outcome predictability. Clinicians may consider the characterization of periodontal therapy response to implement personalized care and treatment decision-making. Clinical trial registration ID: NCT02800252http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1678-77572025000100436&lng=en&tlng=enArtificial intelligenceClinical trialDiabetes mellitusNon-surgical periodontal debridementPeriodontitis
spellingShingle Nidia CASTRO DOS SANTOS
Arthur MANGUSSI
Tiago RIBEIRO
Rafael Nascimento de Brito SILVA
Mauro Pedrine SANTAMARIA
Magda FERES
Thomas VAN DYKE
Ana Carolina LORENA
Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
Journal of Applied Oral Science
Artificial intelligence
Clinical trial
Diabetes mellitus
Non-surgical periodontal debridement
Periodontitis
title Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
title_full Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
title_fullStr Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
title_full_unstemmed Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
title_short Factors influencing the response to periodontal therapy in patients with diabetes: post hoc analysis of a randomized clinical trial using machine learning
title_sort factors influencing the response to periodontal therapy in patients with diabetes post hoc analysis of a randomized clinical trial using machine learning
topic Artificial intelligence
Clinical trial
Diabetes mellitus
Non-surgical periodontal debridement
Periodontitis
url http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1678-77572025000100436&lng=en&tlng=en
work_keys_str_mv AT nidiacastrodossantos factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT arthurmangussi factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT tiagoribeiro factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT rafaelnascimentodebritosilva factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT mauropedrinesantamaria factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT magdaferes factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT thomasvandyke factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning
AT anacarolinalorena factorsinfluencingtheresponsetoperiodontaltherapyinpatientswithdiabetesposthocanalysisofarandomizedclinicaltrialusingmachinelearning