DESIGN: In-depth and focus group interviews were conducted with participants who have engaged in telemedicine. Questions included were participants' perception on the programme being used, satisfaction as well as engagement with the telemedicine programme. All interviews and focus groups were audio-recorded and transcribed verbatim. Data were analysed using a thematic approach.

PARTICIPANTS AND SETTING: People with type 2 diabetes (n=48) who participated in a randomised controlled study which examined the use of telemedicine for diabetes management were recruited from 11 primary care clinics located within the Klang Valley.

RESULTS: Twelve focus groups and two in-depth interviews were conducted. Four themes emerged from the analysis: (1) generational difference; (2) independence and convenience, (3) sharing of health data and privacy and (4) concerns and challenges. The main obstacles found in patients using the telemedicine systems were related to internet connectivity and difficulties experienced with system interface. Cost was also another significant concern raised by participants. Participants in this study were primarily positive about the benefits of telemedicine, including its ability to provide real-time data and disease monitoring and the reduction in clinic visits.

METHODS: To predict CD while prioritizing patient privacy, our study employed data anonymization involved adding Laplace noise to sensitive features like age and gender. The anonymized dataset underwent analysis using a differential privacy (DP) framework to preserve data privacy. DP ensured confidentiality while extracting insights. Compared with Logistic Regression (LR), Gaussian Naïve Bayes (GNB), and Random Forest (RF), the methodology integrated feature selection, statistical analysis, and SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) for interpretability. This approach facilitates transparent and interpretable AI decision-making, aligning with responsible AI development principles. Overall, it combines privacy preservation, interpretability, and ethical considerations for accurate CD predictions.

RESULTS: Our investigations from the DP framework with LR were promising, with an area under curve (AUC) of 0.848 ± 0.03, an accuracy of 0.797 ± 0.02, precision at 0.789 ± 0.02, recall at 0.797 ± 0.02, and an F1 score of 0.787 ± 0.02, with a comparable performance with the non-privacy framework. The SHAP and LIME based results support clinical findings, show a commitment to transparent and interpretable AI decision-making, and aligns with the principles of responsible AI development.