OBJECTIVES: The present study was conducted to determine the reproducibility of peri-implant tissue assessment using the new implant success index (ISI) in comparison with the Misch classification. MATERIALS AND METHODS: In this descriptive study, 22 cases of peri-implant soft tissue with different conditions were selected, and color slides were prepared from them. The slides were shown to periodontists, maxillofacial surgeons, prosthodontists and general dentists, and these professionals were asked to score the images according to the Misch classification and ISI. The intra- and inter-observer reproducibility scores of the viewers were assessed and reported using kappa and weighted kappa (WK) tests. RESULTS: Inter-observer reproducibility of the ISI technique between the prosthodontists-periodontists (WK=0.85), prosthodontists-maxillofacial surgeons (WK=0.86) and periodontists-maxillofacial surgeons (WK=0.9) was better than that between general dentists and other specialists. In the two groups of general dentists and maxillofacial surgeons, ISI was more reproducible than the Misch classification system (WK=0.99 versus WK non-calculable, WK=1 and WK=0.86). The intra-observer reproducibility of both methods was equally excellent among periodontists (WK=1). For prosthodontists, the WK was not calculable via any of the methods. CONCLUSION: The intra-observer reproducibility of both the ISI and Misch classification techniques depends on the specialty and expertise of the clinician. Although ISI has more classes, it also has higher reproducibility than simpler classifications due to its ability to provide more detail.
Classification* ; Dentists ; Humans ; Peri-Implantitis* ; Reproducibility of Results* ; Specialization

Objectives: Machine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset. Methods: Our study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18. Results: We studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively. Conclusions Our findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.