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

Abstract

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.

Keywords: artificial intelligence; dyslipidemia; low-density lipoprotein cholesterol; machine learning; type 2 diabetes.

Figure 1

Flowchart regarding the selection of patients with type 2 diabetes who visited one of 271 diabetes centres between 2005 and 2019.

Figure 2

Gender differences in LDL-C at time T0, broken down by those who presented an LDL-C below 100 mg/dL and those who did not; **** p-value < 0.0001.

Figure 3

Gender differences in the number of patients presenting with an LDL-C lower than 100 mg/dL (2.60 mmol/L) at time T0, T6M, and T2Y.

Figure 4

The trend of LDL-C averages of different patient groups according to the starting LDL-C range (with a minimum number of 200 patients for curve points).

Figure 5

The trend of LDL-C averages of different patient groups according to different statin administration.

Figure 6

LLM-model with the FR of the most relevant variables predicting achievement of the C-LDL goal at T2Y.

Figure 7

Percentage reduction in LDL-C at T6M compared to baseline based on LDL-C ranges and divided by target attainment at T2Y.

Figure 8

Distribution of patients achieving and not achieving the LDL-C target by type of antidiabetic prescribed.