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.

The Burden of Obesity in Type 1 Diabetic Subjects: A Sex-specific Analysis From the AMD Annals Initiative.

OBJECTIVE: Obesity is a growing emergency in type 1 diabetes (T1D). Sex differences in obesity prevalence and its clinical consequences in adult T1D subjects have been poorly investigated. The aim of this study was to investigate the prevalence of obesity and severe obesity, clinical correlates, and potential sex differences in a large cohort of T1D subjects participating to the AMD (Associazione Medici Diabetologi) Annals Initiative in Italy. RESEARCH DESIGN AND METHODS: The prevalence of obesity [body mass index(BMI) ≥30 kg/m2] and severe obesity (BMI ≥ 35 kg/m2) according to sex and age, as well as obesity-associated clinical variables, long-term diabetes complications, pharmacological treatment, process indicators and outcomes, and overall quality of care (Q-score) were evaluated in 37 436 T1D subjects (45.3% women) attending 282 Italian diabetes clinics during 2019. RESULTS: Overall, the prevalence of obesity was similar in the 2 sexes (13.0% in men and 13.9% in women; mean age 50 years), and it increased with age, affecting 1 out of 6 subjects ages >65 years. Only severe obesity (BMI >35 kg/m2) was more prevalent among women, who showed a 45% higher risk of severe obesity, compared with men at multivariate analysis. Cardiovascular disease risk factors (lipid profile, glucose, and blood pressure control), and the overall quality of diabetes care were worse in obese subjects, with no major sex-related differences. Also, micro- and macrovascular complications were more frequent among obese than nonobese T1D men and women. CONCLUSIONS: Obesity is a frequent finding in T1D adult subjects, and it is associated with a higher burden of cardiovascular disease risk factors, micro- and macrovascular complications, and a lower quality of care, with no major sex differences. T1D women are at higher risk of severe obesity.

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.

A suitable palpation technique allows to identify skin lipohypertrophic lesions in insulin-treated people with diabetes.

BACKGROUND: Lipohypertrophy (LH) is a major complication of subcutaneous insulin treatment brought about by multiple overlapping injections and/or needle reuse. It is responsible for unacceptable glucose oscillations due to a high rate of hypoglycaemic episodes and rebound glucose spikes. Skin ultrasound scans (USS), the gold standard for its detection, is too expensive for screening purposes. AIMS: To define a structured method allowing health professionals (HPs) to identify LH lesions as inexpensively and correctly as possible. METHODS: Out of 129 insulin-treated people with diabetes identified by USS as having LH lesions, only 40 agreed to participate in the study (24 females, age 54 ± 15 years, daily insulin dosage 57 ± 12 IU). Each was blindly examined by four well trained and four non-trained HPs according to a standard method involving repeated well codified maneuvers. RESULTS: A specific training allowed inexperienced HPs to acquire high diagnostic accuracy in identifying LH lesions independent of site, size, shape, and even BMI. This kind of training also allowed to reach a 97 % consistency rate among HPs as compared to USS, while the lack of training was associated with a wide variability and inconsistency of identification results. CONCLUSIONS: Diabetes teams should follow systematically the simple procedure reported in this paper for the diagnosis of LH and try to get it further implemented and progressively refined in large scale studies. This would have a major impact on patient education in terms of (1) correct injection technique and (2) ability to identify lesions early enough to prevent poor metabolic outcome.

Insulin resistance in morbid obesity: reversal with intramyocellular fat depletion.

Obesity is a frequent cause of insulin resistance and poses a major risk for diabetes. Abnormal fat deposition within skeletal muscle has been identified as a mechanism of obesity-associated insulin resistance. We tested the hypothesis that dietary lipid deprivation may selectively deplete intramyocellular lipids, thereby reversing insulin resistance. Whole-body insulin sensitivity (by the insulin clamp technique), intramyocellular lipids (by quantitative histochemistry on quadriceps muscle biopsies), muscle insulin action (as the expression of Glut4 glucose transporters), and postprandial lipemia were measured in 20 morbidly obese patients (BMI = 49 +/- 8 [mean +/- SD] kg x m(-2)) and 7 nonobese control subjects. Patients were restudied 6 months later after biliopancreatic diversion (BPD; n = 8), an operation that induces predominant lipid malabsorption, or hypocaloric diet (n = 9). At 6 months, BPD had caused the loss of 33 +/- 10 kg through lipid malabsorption (documented by a flat postprandial triglyceride profile). Despite an attained BMI still in the obese range (39 +/- 8 kg x m(-2)), insulin resistance (23 +/- 3 micromol/min per kg of fat-free mass; P < 0.001 vs. 53 +/- 13 of control subjects) was fully reversed (52 +/- 11 micromol/min per kg of fat-free mass; NS versus control subjects). In parallel with this change, intramyocellular-but not perivascular or interfibrillar-lipid accumulation decreased (1.63 +/- 1.06 to 0.22 +/- 0.44 score units; P < 0.01; NS vs. 0.07 +/- 0.19 of control subjects), Glut4 expression was restored, and circulating leptin concentrations were normalized. In the diet group, a weight loss of 14 +/- 12 kg was accompanied by very modest changes in insulin sensitivity and intramyocellular lipid contents. We conclude that lipid deprivation selectively depletes intramyocellular lipid stores and induces a normal metabolic state (in terms of insulin-mediated whole-body glucose disposal, intracellular insulin signaling, and circulating leptin levels) despite a persistent excess of total body fat mass.