Objective: To assess the impact of pharmacist-supervised intervention on HRQoL of newly diagnosed diabetics using an Audit of Diabetes-Dependent Quality of Life (ADDQoL) questionnaire.
Materials and Methods: A pre-post comparison study was conducted among the control group (CG), test 1 group (T1G) and test 2 group (T2G) patients with three treatment arms to explore the impact of pharmacist-supervised intervention on HRQoL of newly diagnosed diabetics for 18 months. Patients' HRQoL scores were determined using ADDQoL questionnaire at baseline, 3, 6, 9 and 12-months. T1G patients received pharmacist's intervention whereas T2G patients received diabetic kit demonstration in addition to pharmacist's intervention. CG patients were deprived of pharmacist intervention and diabetic kit demonstration, and only received care from attending physician/nurses. Non-parametric tests were used to find the differences in an average weighted impact scores (AWIS) among the groups before and after the intervention at P ≤ 0.05.
Results: Friedman test identified significant (P < 0.001) improvement in AWIS among the test groups' patients. Differences in scores were significant between T1G and T2G at 6-months (P = 0.033), 9-months (P < 0.001) and 12-months (P < 0.001); between CG and T1G at 12-months (P < 0.001) and between CG and T2G at 9-months (P < 0.001) and 12-months (P < 0.0010) on Mann.Whitney U test.
Conclusion: Pharmacist's intervention improved AWIS of test groups' diabetics. Diabetic kit demonstration strengthened the disease understanding and selfcare skills of T2G patients. Disease and self-care awareness among diabetics should be increased in Nepali healthcare system by involving pharmacists for better patient's related outcomes.
METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms.
RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs.
CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.