Predictive modeling for peri-implantitis by using machine learning techniques
Abstract The purpose of this retrospective cohort study was to create a model for predicting the onset of peri-implantitis by using machine learning methods and to clarify interactions between risk indicators. This study evaluated 254 implants, 127 with and 127 without peri-implantitis, from among 1...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-90642-4 |
| _version_ | 1818682581984477184 |
|---|---|
| author | Tomoaki Mameno Masahiro Wada Kazunori Nozaki Toshihito Takahashi Yoshitaka Tsujioka Suzuna Akema Daisuke Hasegawa Kazunori Ikebe |
| author_facet | Tomoaki Mameno Masahiro Wada Kazunori Nozaki Toshihito Takahashi Yoshitaka Tsujioka Suzuna Akema Daisuke Hasegawa Kazunori Ikebe |
| author_sort | Tomoaki Mameno |
| collection | DOAJ |
| description | Abstract The purpose of this retrospective cohort study was to create a model for predicting the onset of peri-implantitis by using machine learning methods and to clarify interactions between risk indicators. This study evaluated 254 implants, 127 with and 127 without peri-implantitis, from among 1408 implants with at least 4 years in function. Demographic data and parameters known to be risk factors for the development of peri-implantitis were analyzed with three models: logistic regression, support vector machines, and random forests (RF). As the results, RF had the highest performance in predicting the onset of peri-implantitis (AUC: 0.71, accuracy: 0.70, precision: 0.72, recall: 0.66, and f1-score: 0.69). The factor that had the most influence on prediction was implant functional time, followed by oral hygiene. In addition, PCR of more than 50% to 60%, smoking more than 3 cigarettes/day, KMW less than 2 mm, and the presence of less than two occlusal supports tended to be associated with an increased risk of peri-implantitis. Moreover, these risk indicators were not independent and had complex effects on each other. The results of this study suggest that peri-implantitis onset was predicted in 70% of cases, by RF which allows consideration of nonlinear relational data with complex interactions. |
| first_indexed | 2024-12-17T10:21:08Z |
| format | Article |
| id | doaj.art-d9b9b3695a65420184b374821fe3a48f |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-17T10:21:08Z |
| publishDate | 2021-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-d9b9b3695a65420184b374821fe3a48f2022-12-21T21:52:48ZengNature PortfolioScientific Reports2045-23222021-05-011111810.1038/s41598-021-90642-4Predictive modeling for peri-implantitis by using machine learning techniquesTomoaki Mameno0Masahiro Wada1Kazunori Nozaki2Toshihito Takahashi3Yoshitaka Tsujioka4Suzuna Akema5Daisuke Hasegawa6Kazunori Ikebe7Department of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDivision for Medical Information, Osaka University Dental HospitalDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryDepartment of Prosthodontics, Gerodontology and Oral Rehabilitation, Osaka University Graduate School of DentistryAbstract The purpose of this retrospective cohort study was to create a model for predicting the onset of peri-implantitis by using machine learning methods and to clarify interactions between risk indicators. This study evaluated 254 implants, 127 with and 127 without peri-implantitis, from among 1408 implants with at least 4 years in function. Demographic data and parameters known to be risk factors for the development of peri-implantitis were analyzed with three models: logistic regression, support vector machines, and random forests (RF). As the results, RF had the highest performance in predicting the onset of peri-implantitis (AUC: 0.71, accuracy: 0.70, precision: 0.72, recall: 0.66, and f1-score: 0.69). The factor that had the most influence on prediction was implant functional time, followed by oral hygiene. In addition, PCR of more than 50% to 60%, smoking more than 3 cigarettes/day, KMW less than 2 mm, and the presence of less than two occlusal supports tended to be associated with an increased risk of peri-implantitis. Moreover, these risk indicators were not independent and had complex effects on each other. The results of this study suggest that peri-implantitis onset was predicted in 70% of cases, by RF which allows consideration of nonlinear relational data with complex interactions.https://doi.org/10.1038/s41598-021-90642-4 |
| spellingShingle | Tomoaki Mameno Masahiro Wada Kazunori Nozaki Toshihito Takahashi Yoshitaka Tsujioka Suzuna Akema Daisuke Hasegawa Kazunori Ikebe Predictive modeling for peri-implantitis by using machine learning techniques Scientific Reports |
| title | Predictive modeling for peri-implantitis by using machine learning techniques |
| title_full | Predictive modeling for peri-implantitis by using machine learning techniques |
| title_fullStr | Predictive modeling for peri-implantitis by using machine learning techniques |
| title_full_unstemmed | Predictive modeling for peri-implantitis by using machine learning techniques |
| title_short | Predictive modeling for peri-implantitis by using machine learning techniques |
| title_sort | predictive modeling for peri implantitis by using machine learning techniques |
| url | https://doi.org/10.1038/s41598-021-90642-4 |
| work_keys_str_mv | AT tomoakimameno predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT masahirowada predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT kazunorinozaki predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT toshihitotakahashi predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT yoshitakatsujioka predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT suzunaakema predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT daisukehasegawa predictivemodelingforperiimplantitisbyusingmachinelearningtechniques AT kazunoriikebe predictivemodelingforperiimplantitisbyusingmachinelearningtechniques |