METHODS: This is a prospective, single-centre, single-blind, randomised controlled pilot feasibility study: The Kegel Exercise Pregnancy Training app (KEPT-app) Trial. Sixty-four incontinent pregnant women who attended one primary care clinic for the antenatal follow-up will be recruited and randomly assigned to either intervention or waitlist control group. The intervention group will receive the intervention, the KEPT-app developed from the Capability, Opportunity, Motivation-Behaviour (COM-B) theory with Persuasive Technology and Technology Acceptance Model.
DISCUSSION: This study will provide a fine-tuning for our future randomised control study on the recruitment feasibility methods, acceptability, feasibility, and usability of the KEPT-app, and the methods to reduce the retention rates among pregnant women with UI.
TRIAL REGISTRATION: This study was registered on ClinicalTrials.gov on 19 February 2021 (NCT04762433) and is not yet recruiting.
METHODS: A gender-matched case-control study was conducted in the largest public sector cardiac hospital of Pakistan, and the data of 460 subjects were collected. The dataset comprised of eight nonclinical features. Four supervised ML algorithms were used to train and test the models to predict the CVDs status by considering traditional logistic regression (LR) as the baseline model. The models were validated through the train-test split (70:30) and tenfold cross-validation approaches.
RESULTS: Random forest (RF), a nonlinear ML algorithm, performed better than other ML algorithms and LR. The area under the curve (AUC) of RF was 0.851 and 0.853 in the train-test split and tenfold cross-validation approach, respectively. The nonclinical features yielded an admissible accuracy (minimum 71%) through the LR and ML models, exhibiting its predictive capability in risk estimation.
CONCLUSION: The satisfactory performance of nonclinical features reveals that these features and flexible computational methodologies can reinforce the existing risk prediction models for better healthcare services.
BACKGROUND: The burden of noncommunicable diseases has increased globally, and it has negatively affected the QoL of diabetic patients.
METHODS: A quasi-experimental study was conducted by including 77 T2DM patients selected from 2 public health centers in Thailand. The respondents were randomly selected 38 in control group and 39 in intervention group. Pretested, piloted, and validated tool were used during this study. Knowledge on blood glucose level, stress, and QoL was measured at baseline and then compared to end line after 3 months of the intervention. The effects of intervention were estimated by regression coefficient of intervention on blood glucose level and QoL. The study was ethically approved by the Chulalongkorn University, Thailand.
FINDINGS: Baseline characteristics of both the groups were similar before the start of the intervention and there were no significant differences observed in age, education, blood sugar monitoring behavior, medical checkup, knowledge, self-care, stress, and hemoglobin HbA1c (>0.05). However, blood HbA1c, stress level, and QoL among the T2DM patients had significant changes (<0.05) after the intervention. The control group was remained same and there was no statistically significant difference reported (>0.05).
CONCLUSIONS: The study concluded that the designed intervention of DSME has proved effective in lowering the blood sugar level, HbA1c level, stress level, and improved QoL among T2DM patients during this limited period of time. Hence, policy-makers can replicate this intervention for diabetic patients in a similar context.