1.Pullout Strength Predictor: A Machine Learning Approach
Ravi KHATRI ; Vicky VARGHESE ; Sunil SHARMA ; Gurunathan Saravana KUMAR ; Harvinder Singh CHHABRA
Asian Spine Journal 2019;13(5):842-848
STUDY DESIGN: A biomechanical study. PURPOSE: To develop a predictive model for pullout strength. OVERVIEW OF LITERATURE: Spine fusion surgeries are performed to correct joint deformities by restricting motion between two or more unstable vertebrae. The pedicle screw provides a corrective force to the unstable spinal segment and arrests motions at the unit that are being fused. To determine the hold of a screw, surgeons depend on a subjective perioperative feeling of insertion torque. The objective of the paper was to develop a machine learning based model using density of foam, insertion angle, insertion depth, and reinsertion to predict the pullout strength of pedicle screw. METHODS: To predict the pullout strength of pedicle screw, an experimental dataset of 48 data points was used as training data to construct a model based on different machine learning algorithms. A total of five algorithms were tested in the Weka environment and the performance was evaluated based on correlation coefficient and error matrix. A sensitive study of various parameters for obtaining the best combination of parameters for predicting the pullout strength was also preformed using the L9 orthogonal array of Taguchi Design of Experiments. RESULTS: Random forest performed the best with a correlation coefficient of 0.96, relative absolute error of 0.28, and root relative squared error of 0.29. The difference between the experimental and predicted value for the six test cases was not significant (p >0.05). CONCLUSIONS: This model can be used clinically for understanding the failure of pedicle screw pullout and pre-surgical planning for spine surgeon.
2.Utilisation patterns of helpline and Web chat services among gamblers in Singapore.
Pezhummoottil Vasudevan Nair ASHARANI ; Syidda AMRON ; Raymond Swee Khoon NG ; Sunil VARGHESE ; Christopher Cheng Soon CHEOK
Singapore medical journal 2019;60(4):164-167
We evaluated the utilisation of a helpline and Web chat system by the public for gambling-related services in Singapore over a period of 12 months. The profile of callers, call characteristics and actions taken were descriptively analysed using aggregate data. The majority of helpline calls and Web chats were from gamblers aged 40-49 years (23.3%, n = 644). Gamblers made 85.4% (n = 8,010) of the calls to the helpline and 73.3% (n = 546) of the Web chats. About four-fifths of the gamblers were Chinese (79.5%, n = 6,381) and employed full time (79.9%, n = 4,125). Table games (67.6%, n = 2,605) were the most popular gambling activity reported by callers, 55.8% of which involved local casinos. Enquiries were mostly casino related (92.4%, n = 5,739). Approximately 1,827 calls were received per month during the study period and 185 referrals were made to the clinic, 80.5% of whom sought treatment.