Methods: The study was conducted at University Dental Hospital Sharjah, UAE. Patients undergoing tooth extraction at the oral surgery clinic were advised to return immediately if they suffer from pain. Over the following first week after tooth extraction, patients who reported pain symptoms were recalled and all dry sockets were identified. The patients were divided into two groups. Group I patients received conventional treatment with socket curettage and saline irrigation only, while in group II CGF was inserted into the socket. Both groups were observed for pain score and quantification of granulation tissue formation.
Results: A total of 40 dry socket patients, aged between 18 and 60 years, from a total of 1,250 patients, were included in the study. 30 patients were given conventional treatment while another 10 patients were given CGF. Patients who received CGF had a pain score of 7-10 at presentation, and the pain score dropped to 0-3 on day 4 and further improved to 0-1 on day 7 (p = 0.001). Granulation tissue formation appeared in the conventional group I on day 7 while the CGF group II showed earlier granulation tissue formation by day 4 (p = 0.001). The posttreatment pain score is inversely proportional to the amount and rate of granulation tissue formation in the socket.
Conclusion: The study suggests that delivery of CGF into a dry socket helps relieve pain and expedite the wound healing process as shown by a statistically much lower pain score and earlier and more rapid formation of granulation tissue when compared to the conventional alveolar osteitis therapy.
Aim: To produce an accurate model of BCVA changes of postpterygium surgery according to its morphological characteristics by using the machine learning technique. Methodology. A retrospective of the secondary dataset of 93 samples of pterygium patients with different pterygium attributes was used and imported into four different machine learning algorithms in RapidMiner software to predict the improvement of BCVA after pterygium surgery.
Results: The performance of four machine learning techniques were evaluated, and it showed the support vector machine (SVM) model had the highest average accuracy (94.44% ± 5.86%), specificity (100%), and sensitivity (92.14% ± 8.33%).
Conclusion: Machine learning algorithms can produce a highly accurate postsurgery classification model of BCVA changes using pterygium characteristics.