Digital technology and healthcare delivery in insulin-treated adults with diabetes: a proposal for analysis of self-monitoring blood glucose patterns using a dedicated platform.

PURPOSE: A remote platform for diabetes care (Roche Diabetes® Care Platform, RDCP) has been developed that allows combined face-to-face consultations and remote patient monitoring (RPM). METHODS: A dedicated flowchart is proposed as a clinical approach to help healthcare professionals in the appropriate interpretation of structured self-monitoring blood glucose data, as visualized on the RDCP during the visits, and in the optimal management of patients using the integrated RDCP-RPM tools. RESULTS: The platform organizes patterns in different blocks: (i) hypoglycemia; (ii) hyperglycemia; (iii) blood glucose variability; (iv) treatment adherence, which identifies a possible individual pattern according to glycemic control challenges, potential causal factors, and behavioral type patterns. The flowchart proposed for use of the RDCP-RPM is self-explanatory and entails 3 steps: (1) evaluation of quality and quantity of self-monitoring blood glucose data; (2) pattern analysis; (3) personalized suggestions and therapy changes. CONCLUSION: The main aim of the remote treatment flowchart proposed is to support healthcare professionals in the identification of hypoglycemic and hyperglycemic patterns using the RDCP regardless of the HbA1c value and ongoing treatment, which however, become crucial in combination with pattern analysis in the therapeutical choice.

Achieving Good Metabolic Control Without Weight Gain with the Systematic Use of GLP-1-RAs and SGLT-2 Inhibitors in Type 2 Diabetes: A Machine-learning Projection Using Data from Clinical Practice.

PURPOSE: Recently, the 2022 American Diabetes Association and European Association for the Study of Diabetes (ADA-EASD) consensus report stressed the importance of weight control in the management of patients with type 2 diabetes; weight control should be a primary target of therapy. This retrospective analysis evaluated, through an artificial-intelligence (AI) projection of data from the AMD Annals database-a huge collection of most Italian diabetology medical records covering 15 years (2005-2019)-the potential effects of the extended use of sodium-glucose co-transporter 2 inhibitors (SGLT-2is) and of glucose-like peptide 1 receptor antagonists (GLP-1-RAs) on HbA1c and weight. METHODS: Data from 4,927,548 visits in 558,097 patients were retrospectively extracted using these exclusion criteria: type 1 diabetes, pregnancy, age >75 years, dialysis, and lack of data on HbA1c or weight. The analysis revealed late prescribing of SGLT-2is and GLP-1-RAs (innovative drugs), and considering a time frame of 4 years (2014-2017), a paradoxic greater percentage of combined-goal (HbA1c <7% and weight gain <2%) achievement was found with older drugs than with innovative drugs, demonstrating aspects of therapeutic inertia. Through a machine-learning AI technique, a "what-if" analysis was performed, using query models of two outcomes: (1) achievement of the combined goal at the visit subsequent to a hypothetical initial prescribing of an SGLT-2i or a GLP-1-RA, with and without insulin, selected according to the 2018 ADA-EASD diabetes recommendations; and (2) persistence of the combined goal for 18 months. The precision values of the two models were, respectively, sensitivity, 71.1 % and 69.8%, and specificity, 67% and 76%. FINDINGS: The first query of the AI analysis showed a great improvement in achievement of the combined goal: 38.8% with prescribing in clinical practice versus 66.5% with prescribing in the "what-if" simulation. Addressing persistence at 18 months after the initial achievement of the combined goal, the simulation showed a potential better performance of SGLT-2is and GLP-1-RAs with respect to each antidiabetic pharmacologic class or combination considered. IMPLICATIONS: AI appears potentially useful in the analysis of a great amount of data, such as that derived from the AMD Annals. In the present study, an LLM analysis revealed a great potential improvement in achieving metabolic targets with SGLT-2i and GLP-1-RA utilization. These results underscore the importance of early, timely, and extended use of these new drugs.

Uncovering Predictors of Lipid Goal Attainment in Type 2 Diabetes Outpatients Using Logic Learning Machine: Insights from the AMD Annals and AMD Artificial Intelligence Study Group.

Identifying and treating lipid abnormalities is crucial for preventing cardiovascular disease in diabetic patients, yet only two-thirds of patients reach recommended cholesterol levels. Elucidating the factors associated with lipid goal attainment represents an unmet clinical need. To address this knowledge gap, we conducted a real-world analysis of the lipid profiles of 11.252 patients from the Annals of the Italian Association of Medical Diabetologists (AMD) database from 2005 to 2019. We used a Logic Learning Machine (LLM) to extract and classify the most relevant variables predicting the achievement of a low-density lipoprotein cholesterol (LDL-C) value lower than 100 mg/dL (2.60 mmol/L) within two years of the start of lipid-lowering therapy. Our analysis showed that 61.4% of the patients achieved the treatment goal. The LLM model demonstrated good predictive performance, with a precision of 0.78, accuracy of 0.69, recall of 0.70, F1 Score of 0.74, and ROC-AUC of 0.79. The most significant predictors of achieving the treatment goal were LDL-C values at the start of lipid-lowering therapy and their reduction after six months. Other predictors of a greater likelihood of reaching the target included high-density lipoprotein cholesterol, albuminuria, and body mass index at baseline, as well as younger age, male sex, more follow-up visits, no therapy discontinuation, higher Q-score, lower blood glucose and HbA1c levels, and the use of anti-hypertensive medication. At baseline, for each LDL-C range analysed, the LLM model also provided the minimum reduction that needs to be achieved by the next six-month visit to increase the likelihood of reaching the therapeutic goal within two years. These findings could serve as a useful tool to inform therapeutic decisions and to encourage further in-depth analysis and testing.

Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes.

AIMS: The objective of this study is to establish a predictive model using transparent machine learning (ML) to identify any drivers that characterize therapeutic inertia. METHODS: Data in the form of both descriptive and dynamic variables collected from electronic records of 1.5 million patients seen at clinics within the Italian Association of Medical Diabetologists between 2005-2019 were analyzed using logic learning machine (LLM), a "clear box" ML technique. Data were subjected to a first stage of modeling to allow ML to automatically select the most relevant factors related to inertia, and then four further modeling steps individuated key variables that discriminated the presence or absence of inertia. RESULTS: The LLM model revealed a key role for average glycated hemoglobin (HbA1c) threshold values correlated with the presence or absence of insulin therapeutic inertia with an accuracy of 0.79. The model indicated that a patient's dynamic rather than static glycemic profile has a greater effect on therapeutic inertia. Specifically, the difference in HbA1c between two consecutive visits, what we call the HbA1c gap, plays a crucial role. Namely, insulin therapeutic inertia is correlated with an HbA1c gap of <6.6 mmol/mol (0.6%), but not with an HbA1c gap of >11 mmol/mol (1.0%). CONCLUSIONS: The results reveal, for the first time, the interrelationship between a patient's glycemic trend defined by sequential HbA1c measurements and timely or delayed initiation of insulin therapy. The results further demonstrate that LLM can provide insight in support of evidence-based medicine using real world data.

Determinants of good metabolic control without weight gain in type 2 diabetes management: a machine learning analysis.

INTRODUCTION: The aim of this study was to investigate the factors (clinical, organizational or doctor-related) involved in a timely and effective achievement of metabolic control, with no weight gain, in type 2 diabetes. RESEARCH DESIGN AND METHODS: Overall, 5.5 million of Hab1c and corresponding weight were studied in the Associazione Medici Diabetologi Annals database (2005-2017 data from 1.5 million patients of the Italian diabetes clinics network). Logic learning machine, a specific type of machine learning technique, was used to extract and rank the most relevant variables and to create the best model underlying the achievement of HbA1c<7 and no weight gain. RESULTS: The combined goal was achieved in 37.5% of measurements. High HbA1c and fasting glucose values and slow drop of HbA1c have the greatest relevance and emerge as first, main, obstacles the doctor has to overcome. However, as a second line of negative factors, markers of insulin resistance, microvascular complications, years of observation and proxy of duration of disease appear to be important determinants. Quality of assistance provided by the clinic plays a positive role. Almost all the available oral agents are effective whereas insulin use shows positive impact on glucometabolism but negative on weight containment. We also tried to analyze the contribution of each component of the combined endpoint; we found that weight gain was less frequently the reason for not reaching the endpoint and that HbA1c and weight have different determinants. Of note, use of glucagon-like peptide-1 receptor agonists (GLP1-RA) and glifozins improves weight control. CONCLUSIONS: Treating diabetes as early as possible with the best quality of care, before beta-cell deterioration and microvascular complications occurrence, make it easier to compensate patients. This message is a warning against clinical inertia. All medications play a role in goal achievements but use of GLP1-RAs and glifozins contributes to overweight prevention.

Artificial Intelligence and Big Data in Diabetes Care: A Position Statement of the Italian Association of Medical Diabetologists.

Since the last decade, most of our daily activities have become digital. Digital health takes into account the ever-increasing synergy between advanced medical technologies, innovation, and digital communication. Thanks to machine learning, we are not limited anymore to a descriptive analysis of the data, as we can obtain greater value by identifying and predicting patterns resulting from inductive reasoning. Machine learning software programs that disclose the reasoning behind a prediction allow for "what-if" models by which it is possible to understand if and how, by changing certain factors, one may improve the outcomes, thereby identifying the optimal behavior. Currently, diabetes care is facing several challenges: the decreasing number of diabetologists, the increasing number of patients, the reduced time allowed for medical visits, the growing complexity of the disease both from the standpoints of clinical and patient care, the difficulty of achieving the relevant clinical targets, the growing burden of disease management for both the health care professional and the patient, and the health care accessibility and sustainability. In this context, new digital technologies and the use of artificial intelligence are certainly a great opportunity. Herein, we report the results of a careful analysis of the current literature and represent the vision of the Italian Association of Medical Diabetologists (AMD) on this controversial topic that, if well used, may be the key for a great scientific innovation. AMD believes that the use of artificial intelligence will enable the conversion of data (descriptive) into knowledge of the factors that "affect" the behavior and correlations (predictive), thereby identifying the key aspects that may establish an improvement of the expected results (prescriptive). Artificial intelligence can therefore become a tool of great technical support to help diabetologists become fully responsible of the individual patient, thereby assuring customized and precise medicine. This, in turn, will allow for comprehensive therapies to be built in accordance with the evidence criteria that should always be the ground for any therapeutic choice.

Switching Patients with Type 1 Diabetes to Insulin Degludec from Other Basal Insulins: Real-World Data of Effectiveness and Safety.

INTRODUCTION: Real-world evidence on the effectiveness and safety of insulin degludec (IDeg) in patients with diabetes is a priority. We have therefore evaluated the effectiveness and safety of IDeg, including impact on metabolic control, glycemic variability, weight gain and hypoglycemia, in patients with type 1 diabetes under routine clinical practice conditions. METHODS: This was an observational longitudinal multicenter study. A retrospective chart review of all patients with type 1 diabetes who were switched from basal insulin to IDeg was performed, and temporal trends in clinical outcomes were assessed. RESULTS: Data obtained from 195 patients, with a median age of 42.8 [interquartile range (IQR) 24.6-56.4] years and a median diabetes duration of 16 (IQR 10.0-28) years, were analyzed. Median follow-up was 9.5 (IQR 7.7-11.3) months. Improvements were found in glycated hemoglobin (- 0.34%; p < 0.0001), fasting blood glucose (- 24.82 mg/dL; p < 0.0001), post-prandial glucose (- 17.23 mg/dL; p = 0.0009), glycemic variability as indicated by standard deviation of blood glucose (- 5.67 mg/dL; p < 0.0001) and high blood glucose index (- 3.77; p < 0.0001). Body weight and body mass index remained substantially stable during the follow-up (- 0.18 kg; p = 0.56 and - 0.12; p = 0.42, respectively). Risk of nocturnal hypoglycemia decreased by 52% [incidence rate ratio 0.48; 95% confidence interval (CI) 0.29-0.77] and risk of total hypoglycemic episodes by 41% (incidence ratio 0.59; 95% CI 0.45-0.83). Basal and short-acting insulin doses decreased by - 1.4 and - 3.1 IU, respectively. CONCLUSION: Switching patients with type 1 diabetes to IDeg from other basal insulins was associated with relevant improvements in metabolic control and glycemic variability without weight gain; the risk of hypoglycemic episodes also significantly declined. FUNDING: Novo Nordisk S.p.A. unconditional grant.

Patient preferences for treatment in type 2 diabetes: the Italian discrete-choice experiment analysis.

AIMS: Several drug classes are now available to achieve a satisfactory metabolic control in patients with type 2 diabetes (T2DM), but patients' preferences may differ. METHODS: In a discrete-choice experiment, we tested T2DM patients' preferences for recent antidiabetic drugs, in the event that their treatment might require intensification. The following attributes were considered: (a) route of administration; (b) type of delivery; (c) timing; (d) risk of adverse events; (e) effects on body weight. Twenty-two possible scenarios were built, transferred into 192 paired choices and proposed to 491 cases naïve to injectable treatments and 171 treated by GLP-1 receptor agonists (GLP-1RAs). Analyses were performed by descriptive statistics and random effects logit regression model. RESULTS: Preferences according to dosing frequency, risk of nausea and urinary tract infections (UTls) were similar across groups, age, sex and BMI. Administration route and delivery type accounted for 1/3 of relative importance; the risk of UTIs, nausea and dosing frequency for ≈ 20% each, and weight loss for only 6%. Two significant interactions emerged (p < 0.01): type of delivery × group, and weight change × BMI class. Irrespective of previous treatment, the three preferred choices were injectable, coupled with weekly dosing and a ready-to-use device (first two choices). In a regression model, being naïve or non-naïve changed the ranking of preferences (p < 0.001), and the order was systematically shifted towards injectable medications in non-naïve subjects. CONCLUSION: Easy-to-deliver, injectable treatment is preferred in T2DM, independently of treatment history, and previous experience with GLP-1RAs strengthens patients' willingness to accept injectable drugs.

Impact of Insulin Degludec in Type 2 Diabetes: Real-World Data on Effectiveness and Safety.

INTRODUCTION: Real-world evidence on effectiveness and safety of insulin degludec (IDeg) in patients with diabetes is a priority. The aim of the study was to evaluate patterns of use and the long-term effectiveness and safety of IDeg in routine clinical practice. METHODS: This was an observational longitudinal study. A retrospective chart review of all patients with type 2 diabetes treated with IDeg was performed and temporal trends in clinical outcomes were assessed. All data was stratified by treatment modality: the switch group consisted of patients already treated with another basal insulin before initiating IDeg; the add-on group consisted of basal insulin-naïve patients. RESULTS: Overall, 247 patients were analyzed (55 in the add-on group and 192 in the switch group), mean age 67.0 ± 10.9 years ,and diabetes duration 16.3 ± 8.9 years. Median (interquartile range) follow-up was 9.7 (8.0-11.9) months. In the add-on group, improvements were found in glycated hemoglobin (HbA1c) (- 1.68%; p < 0.0001), fasting blood glucose (FBG) (- 64.7 mg/dL; p < 0.0001), post-prandial glucose (PPG) (- 81.1 mg/dl; p < 0.0001), and glycemic variability (i.e., standard deviation of blood glucose) (- 11.6 mg/dl; p = 0.04). Even in the switch group, improvements were found in HbA1c (- 0.57%; p < 0.0001), FBG (- 28.1 mg/dL; p < 0.0001), and PPG (- 22.6 mg/dl; p = 0.001). Body weight increase during the follow-up was not statistically significant vs. baseline in both groups. Benefits on overall, nocturnal, and severe hypoglycemia were found in the switch group. CONCLUSION: These real-world data documented that initiating IDeg or switching to IDeg from other basal insulins in type 2 diabetes was associated with significant improvement in metabolic control without significant weight gain; a decrease in the risk of hypoglycemia was observed when switching to IDeg from another basal insulin.

Long-Term Effectiveness of Liraglutide for Treatment of Type 2 Diabetes in a Real-Life Setting: A 24-Month, Multicenter, Non-interventional, Retrospective Study.

INTRODUCTION: The aim of the study was to evaluate whether the reduction in glycated hemoglobin (HbA1c) observed in clinical trials with liraglutide in type 2 diabetes (T2D) could be attained in routine clinical practice. METHODS: ReaL was a multicenter, non-interventional, observational, retrospective, longitudinal study on the effectiveness of liraglutide, a human glucagon-like peptide-1 analog, in individuals with T2D treated in daily practice in Italy. Between 26 March and 16 November 2015, data were taken from clinical records of patients aged ≥ 18 years with treatment follow-up data of up to 24 months and who received their first prescription of liraglutide in 2011. RESULTS: A total of 1723 patients were included in the analysis. At baseline, mean age was 58.9 years, duration of diabetes was 9.6 years, and HbA1c was 8.3%. At 12 months, 36.1% of patients were prescribed the maximum 1.8 mg dose; 43.5% [95% confidence interval (CI): 40.9; 46.2] of patients attained the primary outcome of a reduction in HbA1c of ≥ 1% point at 12 months. At 24 months, 40.9% (95% CI 38.1; 43.7) of patients had attained the HbA1c target of ≤ 7%. Additionally, body weight significantly decreased by 3.4 kg (95% CI - 3.6; - 3.1, p < 0.0001). CONCLUSION: In this observational study conducted in routine clinical practice for up to 2 years, treatment with liraglutide improved HbA1c and reduced body weight in a similar fashion to that observed under randomized clinical trial conditions. The data support the use of liraglutide as an effective treatment for T2D in clinical practice. FUNDING: Novo Nordisk S.p.A. TRIAL REGISTRATION: ClinicalTrials.gov identifier, NCT02255266.

Effectiveness and safety of liraglutide after three years of treatment.

BACKGROUND: The aim of this study was to evaluate long-term effectiveness and safety of liraglutide in real world. METHODS: A diabetes clinic in Italy systematically collected data of all patients treated with liraglutide. Generalized hierarchical linear regression models for repeated measures were applied to assess trends over time of HbA1c, fasting plasma glucose (FPG), body weight, blood pressure and lipid profile. RESULTS: Overall, 255 patients (mean age: 63.5±9.7 years, men: 56.9%, mean diabetes duration: 12.0±8.1 years) were treated with liraglutide during 36 months. Mean HbA1c levels decreased by -1.0±0.1% (P<0.0001), FPG by -46±6 mg/dL (P<0.0001), and body weight by -3.9±0.8 Kg (P<0.0001). HbA1c reduction was inversely related to diabetes duration, while body weight reduction was directly related to baseline BMI. Significant improvements in HDL-cholesterol and triglycerides levels were also documented. Trends of improvement in systolic blood pressure (SBP) levels were also found, with significant reduction in patients with baseline SBP≥140 mmHg. Treatment was well-tolerated by the vast majority of the patients. Neither severe hypoglycemia nor pancreatitis occurred. Drop-out rate was of 28.2%. Main causes of drop-out were gastrointestinal side effects and lack of efficacy. CONCLUSION: Our analysis documents a prolonged effectiveness and safety of liraglutide, even after three years of treatment. In addition to significant improvement in glycemic control and body weight, liraglutide also provides additional benefits on cardiovascular risk profile, while minimizing the risk of hypoglycemia. However, magnitude of benefits reflects specific patient characteristics that deserve further investigation.