Can we predict which patients are likely to develop severe complications following reconstruction for osteoradionecrosis?

High morbidity has been reported for free vascularised reconstruction for osteoradionecrosis (ORN) and there are no apparent risk factors. A single nucleotide polymorphism in the transforming growth factor beta 1 gene (TGF-β1) has been implicated in the cause of ORN and may also predict these complications. We studied a series of 30 consecutive patients who had had reconstruction for severe ORN with free tissue transfer in relation to their outcomes and complications for a number of risk factors including TFG-β1 genotype, age, sex, comorbidities, site and stage of tumour, type of initial operation, and dose of radiotherapy or chemoradiotherapy. Two patients died and 2 flaps failed. Using the Clavien–Dindo classification, 16 patients developed grade III complications and 6 grade II. Median (IQR) duration of inpatient stay was 19.5 (12–25) days and the median (IQR) duration of outpatient treatment was 6 (4–11) weeks. No specific risk factors for postoperative complications were identified. In view of the severity and unpredictability of the complications, careful preoperative counselling of patients is essential.     

What should we do about patients who smoke?

The adverse consequences of smoking on both general and oral health are well recognized. It is now accepted that brief advice from a healthcare professional is an effective aid to stopping smoking and recently interest has focused on the role of the dental team in this area. This paper provides an update on current concepts of how smokers give up and makes practical suggestions as to how smoking may be discussed in the dental clinic.     

Can text messages encourage flossing among orthodontic patients?

ObjectivesTo assess the extent to which text messages on WhatsApp play a role in patient awareness of the importance of proper oral hygiene and flossing on a daily basis and to test the null hypothesis that daily text messages do not influence the flossing habits of orthodontics patients.Materials and MethodsForty-four patients wearing fixed orthodontic appliances with a mean age of 14.3 years participated in the study. Patients (male and female) were randomly assigned to two groups (n = 22): group 1, text messages sent via WhatsApp daily during the study period, and group 2 (control), no text messages received. Plaque index, gingival bleeding index, and halitosis were assessed at baseline and after 30 days. The results were analyzed and subjected to normality test, McNemar test, Fisher exact test, Mann-Whitney test, and Wilcoxon signed-rank test.ResultsThere was a significant influence on flossing habits (P < .05) and a significant reduction in plaque and gingival bleeding indices in group 1 (P < .05). Group 1 had a significant reduction in halitosis (P < .05).ConclusionsDaily text messages seem to influence patient awareness of the importance of proper oral hygiene and flossing. The null hypothesis was rejected because those patients who received text messages every day changed their flossing habits.     

What information should we give to our orthognathic patients?

In 2002, whilst the author was an orthodontic registrar, she underwent a bimaxillary osteotomy to correct her class III malocclusion. This therefore gives her a unique perspective into the information she believes prospective patients undergoing similar procedures would find helpful and the choices of format to deliver that advice.     

Can we predict orthodontic extraction patterns by using machine learning?

Objective

To investigate the utility of machine learning (ML) in accurately predicting orthodontic extraction patterns in a heterogeneous population.

Materials and Methods

The material of this retrospective study consisted of records of 366 patients treated with orthodontic extractions. The dataset was randomly split into training (70%) and test sets (30%) and was stratified according to race/ethnicity and gender. Fifty-five cephalometric and demographic input data were used to train and test multiple ML algorithms. The extraction patterns were labelled according to the previous treatment plan. Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM) algorithms were used to predict the patient's extraction patterns.

Results

The highest class accuracy percentages were obtained for the upper and lower 1st premolars (U/L4s) (RF: 81.63%, LR: 63.27%, SVM: 63.27%) and upper 1st premolars only (U4s) extraction patterns (RF: 61.11%, LR: 72.22%, SVM: 72.22%). However, all methods revealed low class accuracy rates (<50%) for the upper 1st and lower 2nd premolars (U4/L5s), upper 2nd and lower 1st premolars (U5/L4s), and upper and lower 2nd premolars (U/L5s) extraction patterns. For the overall accuracy, RF yielded the highest percentage with 54.55%, followed by SVM with 52.73% and LR with 49.09%.

Conclusion

All tested supervised ML techniques yielded good accuracy in predicting U/L4s and U4s extraction patterns. However, they predicted poorly for the U4/L5s, U5/L4s, and U/L5s extraction patterns. Molar relationship, mandibular crowding, and overjet were found to be the most predictive indicators for determining extraction patterns.