Improved positional accuracy of dental implant placement using a haptic and machine-vision-controlled collaborative surgery robot: A pilot randomized controlled trial

AIM

To compare the implant accuracy, safety and morbidity between robot-assisted and freehand dental implant placement.

MATERIALS AND METHODS

Subjects requiring single-site dental implant placement were recruited. Patients were randomly allocated to freehand implant placement and robot-assisted implant placement. Differences in positional accuracy of the implant, surgical morbidity and complications were assessed. The significance of intergroup differences was tested with an intention-to-treat analysis and a per-protocol (PP) analysis (excluding one patient due to calibration error).

RESULTS

Twenty patients (with a median age of 37, 13 female) were included. One subject assigned to the robotic arm was excluded from the PP analysis because of a large calibration error due to the dislodgement of the index. For robot-assisted and freehand implant placement, with the PP analysis, the median (25th-75th percentile) platform global deviation, apex global deviation and angular deviation were 1.23 (0.9-1.4) mm/1.9 (1.2-2.3) mm (p = .03, the Mann-Whitney U-test), 1.40 (1.1-1.6) mm/2.1 (1.7-3.9) mm (p < .01) and 3.0 (0.9-6.0)°/6.7 (2.2-13.9)° (p = .08), respectively. Both methods showed limited damage to the alveolar ridge and had similar peri- and post-operative morbidity and safety.

CONCLUSIONS

Robot-assisted implant placement enabled greater positional accuracy of the implant compared to freehand placement in this pilot trial. The robotic system should be further developed to simplify surgical procedures and improve accuracy and be validated in properly sized trials assessing the full spectrum of relevant outcomes.

Development of a machine learning multiclass screening tool for periodontal health status based on non-clinical parameters and salivary biomarkers

AIM

To develop a multiclass non-clinical screening tool for periodontal disease and assess its accuracy for differentiating periodontal health, gingivitis and different stages of periodontitis.

MATERIALS AND METHODS

A cross-sectional diagnostic study on a convenience sample of 408 consecutive subjects was conducted by applying three non-clinical index tests estimating different features of the periodontal health-disease spectrum: a self-administered questionnaire, an oral rinse activated matrix metalloproteinase-8 (aMMP-8) point-of-care test (POCT) and determination of gingival bleeding on brushing (GBoB). Full-mouth periodontal examination was the reference standard. The periodontal diagnosis was made on the basis of the 2017 classification of periodontal diseases and conditions. Logistic regression and random forest (RF) analyses were performed to predict various periodontal diagnoses, and the accuracy measures were assessed.

RESULTS

Four-hundred and eight subjects were enrolled in this study, including those with periodontal health (16.2%), gingivitis (15.2%) and stage I (15.9%), stage II (15.9%), stage III (29.7%) and stage IV (7.1%) periodontitis. Nine predictors, namely 'gum disease' (Q1), 'a rating of gum/teeth health' (Q2), 'tooth cleaning' (Q3a), the symptom of 'loose teeth' (Q4), 'use of floss' (Q7), aMMP-8 POCT, self-reported GBoB, haemoglobin and age, resulted in high levels of accuracy in the RF classifier. High accuracy (area under the ROC curve > 0.94) was observed for the discrimination of three (health, gingivitis and periodontitis) and six classes (health, gingivitis, stages I, II, III and IV periodontitis). Confusion matrices showed that the misclassification of a periodontitis case as health or gingivitis was less than 1%-2%.

CONCLUSIONS

Machine learning-based classifiers, such as RF analyses, are promising tools for multiclass assessment of periodontal health and disease in a non-clinical setting. Results need to be externally validated in appropriately sized independent samples (ClinicalTrials.gov NCT03928080).