Methods: Data from 160 hypertensive patients from a tertiary hospital in Kuala Lumpur, Malaysia, were used in this study. Variables were ranked based on their significance to adherence levels using the RF variable importance method. The backward elimination method was then performed using RF to obtain the variables significantly associated with the patients' adherence levels. RF, SVR and ANN models were developed to predict adherence using the identified significant variables. Visualizations of the relationships between hypertensive patients' adherence levels and variables were generated using SOM.

Result: Machine learning models constructed using the selected variables reported RMSE values of 1.42 for ANN, 1.53 for RF, and 1.55 for SVR. The accuracy of the dichotomised scores, calculated based on a percentage of correctly identified adherence values, was used as an additional model performance measure, resulting in accuracies of 65% (ANN), 78% (RF) and 79% (SVR), respectively. The Wilcoxon signed ranked test reported that there was no significant difference between the predictions of the machine learning models and the actual scores. The significant variables identified from the RF variable importance method were educational level, marital status, General Overuse, monthly income, and Specific Concern.

METHODOLOGY: This cross-sectional study was conducted from October 2017 to December 2017 and involved female patients with breast cancer. The QoL scores and domains were determined using the EuroQol EQ-5D-5L, and were presented as the utility value and visual analog scores, respectively.

RESULTS: We recruited a total of 173 women, aged 33-87 years. The median VA score was 80.00 (interquartile range [IQR] 70.00-90.00); the median utility value was 0.78 (interquartile range [IQR] 0.65-1.00. Women who did not take traditional medicine had a higher utility index score of 0.092 (95% CI 0.014-0.171), and women with household income of RM3000-5000 had a higher utility index score of 0.096 (95% CI 0.011-0.180).

PATIENTS AND METHODS: A retrospective review study involving 20 eyes that underwent primary augmented trabeculectomy with mitomycin (MMC) and 10 eyes GDD implantation in 3 tertiary centres in Malaysia between 1 January 2013 and 31 December 2019. They were followed up for at least 12 months postsurgical intervention. Intraocular pressure (IOP), number of topical IOP lowering medication and complications were evaluated at 1, 3, 6 and 12 months post-intervention. Based on the IOP, the success was divided into complete and partial success, and failure. IOP and postsurgical complications were compared using the Repetitive Measure Analysis of Variance (RM ANOVA) and the Pearson chi-square test.

RESULTS: Both methods were effective in lowering the IOP. Eyes with primary augmented trabeculectomy have significant lower IOP compared to GDD implantation (p = 0.037). There was a higher incidence of postoperative hypotony (30%) in the trabeculectomy group. There was also a significant reduction of mean number of topical pressure-lowering drugs required postoperatively (p = 0.015). Complete success was achieved in 100% of eyes with trabeculectomy and 67% in GDD implantation (p = 0.047).

STUDY DESIGN: Case-control study.

SETTING: Spinal Rehabilitation outpatient clinic in a tertiary hospital in Kuala Lumpur, Malaysia.

PARTICIPANTS: Thirty-one sports participants (SP) and thirty-four non-sports participants (NSP) (N = 65) met the following inclusion criteria; chronic SCI more than one year, age between 18 and 50 years, both traumatic and non-traumatic SCI at C5 level and below, complete or incomplete SCI (AIS A-D) and mobilizing with either manual or motorized wheelchair independently.

METHODS: Face-to-face interviews were performed with a 22-item self-constructed questionnaire which contained four domains of variables; socio-demographic, SCI-related, environmental and sports-related factors. Data collection was done between June 2017 and May 2018.