A transparent machine learning algorithm uncovers HbA1c patterns associated with therapeutic inertia in patients with type 2 diabetes and failure of metformin monotherapy.

AIMS: This study aimed to identify and categorize the determinants influencing the intensification of therapy in Type 2 Diabetes (T2D) patients with suboptimal blood glucose control despite metformin monotherapy. METHODS: Employing the Logic Learning Machine (LLM), an advanced artificial intelligence system, we scrutinized electronic health records of 1.5 million patients treated in 271 diabetes clinics affiliated with the Italian Association of Medical Diabetologists from 2005 to 2019. Inclusion criteria comprised patients on metformin monotherapy with two consecutive mean HbA1c levels exceeding 7.0%. The cohort was divided into "inertia-NO" (20,067 patients with prompt intensification) and "inertia-YES" (13,029 patients without timely intensification). RESULTS: The LLM model demonstrated robust discriminatory ability among the two groups (ROC-AUC = 0.81, accuracy = 0.71, precision = 0.80, recall = 0.71, F1 score = 0.75). The main novelty of our results is indeed the identification of two main distinct subtypes of therapeutic inertia. The first exhibited a gradual but steady HbA1c increase, while the second featured a moderate, non-uniform rise with substantial fluctuations. CONCLUSIONS: Our analysis sheds light on the significant impact of HbA1c levels over time on therapeutic inertia in patients with T2D, emphasizing the importance of early intervention in the presence of specific HbA1c patterns.

Role of telemedicine during COVID-19 pandemic in type 2 diabetes outpatients: The AMD annals initiative.

AIMS: Telemedicine is advocated as a fundamental tool in modern clinical management. However, data on the effects of telemedicine vs face-to-face consultation on clinical outcomes in type 2 diabetes (T2DM) are still uncertain. This paper describes the use of telemedicine during the 2020 COVID-19 emergency and compares volume activity and quality indicators of diabetes care between face-to-face vs telemedicine counseling in the large cohort of T2DM patients from the AMD Annals Initiative. METHODS: Demographic and clinical characteristics, including laboratory parameters, rate of the screening of long-term complications, current therapies and the Q-score, a validated score that measures the overall quality of care, were compared between 364,898 patients attending face-to-face consultation and 46,424 on telemedicine, during the COVID-19 pandemic. RESULTS: Patients on telemedicine showed lower HbA1c levels (7.1 ± 1.2 % vs 7.3 ± 1.3 %, p < 0.0001), and they were less frequently treated with metformin, GLP1-RAs and SGLT2i and more frequently with DPP4i. The telemedicine group showed reduced monitoring of the various parameters considered as process indicators, especially, eye and foot examination. The proportion of patients with a good quality of care (Q score > 25) was higher among those receiving face-to-face consultation. Moreover, in the telemedicine group, all major clinical outcomes remained stable when further compared to those collected in the year 2019, when the same patients underwent a regular face-to-face consultation, suggesting that the care provided through telemedicine did not negatively affect the most important parameters. CONCLUSIONS: During the COVID-19 pandemic, telemedicine provided an acceptable quality of diabetes care, comparable to that of patients attending face-to-face consultation, although a less frequent screening of complications seems to have occurred in subjects consulted by telemedicine.