D-dimer and inflammatory markers in the peripheral arterial disease

Interpretable machine learning models for detecting peripheral neuropathy and lower extremity arterial disease in diabetics: an analysis of critical shared and unique risk factors

BACKGROUND

Diabetic peripheral neuropathy (DPN) and lower extremity arterial disease (LEAD) are significant contributors to diabetic foot ulcers (DFUs), which severely affect patients' quality of life. This study aimed to develop machine learning (ML) predictive models for DPN and LEAD and to identify both shared and distinct risk factors.

METHODS

This retrospective study included 479 diabetic inpatients, of whom 215 were diagnosed with DPN and 69 with LEAD. Clinical data and laboratory results were collected for each patient. Feature selection was performed using three methods: mutual information (MI), random forest recursive feature elimination (RF-RFE), and the Boruta algorithm to identify the most important features. Predictive models were developed using logistic regression (LR), random forest (RF), and eXtreme Gradient Boosting (XGBoost), with particle swarm optimization (PSO) used to optimize their hyperparameters. The SHapley Additive exPlanation (SHAP) method was applied to determine the importance of risk factors in the top-performing models.

RESULTS

For diagnosing DPN, the XGBoost model was most effective, achieving a recall of 83.7%, specificity of 86.8%, accuracy of 85.4%, and an F1 score of 83.7%. On the other hand, the RF model excelled in diagnosing LEAD, with a recall of 85.7%, specificity of 92.9%, accuracy of 91.9%, and an F1 score of 82.8%. SHAP analysis revealed top five critical risk factors shared by DPN and LEAD, including increased urinary albumin-to-creatinine ratio (UACR), glycosylated hemoglobin (HbA1c), serum creatinine (Scr), older age, and carotid stenosis. Additionally, distinct risk factors were pinpointed: decreased serum albumin and lower lymphocyte count were linked to DPN, while elevated neutrophil-to-lymphocyte ratio (NLR) and higher D-dimer levels were associated with LEAD.

CONCLUSIONS

This study demonstrated the effectiveness of ML models in predicting DPN and LEAD in diabetic patients and identified significant risk factors. Focusing on shared risk factors may greatly reduce the prevalence of both conditions, thereby mitigating the risk of developing DFUs.

African-American ethnicity is associated with higher plasma levels of D-dimer in adults with hypertension

BACKGROUND

African Americans with hypertension have higher cardiovascular morbidity and mortality than hypertensives from other ethnic groups. Plasma D-dimer, a fragment generated from fibrin during lysis of mature clot in vivo, is a predictor of adverse cardiovascular events.

OBJECTIVE

We investigated whether plasma levels of D-dimer differ between African American (AA) and non-Hispanic white (NHW) adults with hypertension.

METHODS

Participants included 933 AA (65 +/- 9 years, 72% women) and 821 NHW (61 +/- 9 years, 56% women) from the community. D-dimer was measured using an immunoturbidimetric assay. Multivariable regression analyses, stratified by gender, were performed to assess whether AA ethnicity was associated with D-dimer levels after adjustment for age, body mass index (BMI), total and high-density lipoprotein (HDL) cholesterol, systolic blood pressure, diabetes, history of smoking, medication (statin and aspirin) use, lifestyle variables (physical activity, alcohol intake, and education), estimated glomerular filtration rate (eGFR), and a marker of inflammation, C-reactive protein (CRP).

RESULTS

D-dimer levels were higher in AA men and women than in their NHW counterparts (mean +/- SD; men 256 +/- 199 vs. 190 +/- 183 ng mL(-1), P < 0.001; women, 290 +/- 233 vs. 225 +/- 195 ng mL(-1), P < 0.001). In both sexes, after adjustment for age, conventional risk factors, medication use, and lifestyle variables, AA ethnicity remained associated with higher D-dimer levels (P = 0.002 in men, P = 0.006 in women). These associations remained significant after additional adjustment for eGFR and plasma CRP (P = 0.003 in men, P < 0.0001 in women).

CONCLUSIONS

Among adults with hypertension, AA ethnicity was independently associated with higher plasma levels of D-dimer.