JMIR Publications

ABSTRACT

Background:

Although evidence indicates that T2D prognosis is influenced by individual factors and supports the need for personalized care, practical guidance on implementing such strategies remains limited.

Objective:

This study aimed to develop and validate a personalized follow-up model to improve clinical outcomes and optimize healthcare resource utilization.

Methods:

We conducted a retrospective analysis of a 10-year prospective real-world cohort of 41,398 T2D patients from ten community health centers in China. Patients were categorized into a standardized follow-up group (four annual in-person visits as per guidelines) and a non-standardized group (which received care deviating from this schedule). We developed a risk prediction model for the purpose of establishing personalized follow-up strategies in patients with T2D.

Results:

Compared to standardized follow-up strategy, the personalized strategy reduced the probability of complications by 4.4% and increased QALDs by 13.3 days per patient per year, and the incremental cost-effectiveness ratio (ICER) was −258.41 CNY/QALD at individual level; It reduced the probability of complications by 3.53% and increased QALDs by 31.4 days per year, and the ICER was −238.86 CNY/QALD at group level. External validation confirmed its incremental benefits and generalizability.

Conclusions:

Compared with the standardized strategy, the personalized model—developed from real-world data and externally validated—offers more effective and cost-efficient care for type 2 diabetes patients. This study provides a novel framework for optimizing follow-up frequency and modality in personalized diabetes management. Clinical Trial: The Ethics Board of Nanjing University (Nanjing, China) reviewed and approved the protocol for the present study (ID No. OAP20240930001)