Age, male gender, and atrial fibrillation predict lower extremity amputation or revascularization in patients with peripheral artery diseases: a population-based investigation

Machine Learning Models Predict the Need of Amputation and/or Peripheral Artery Revascularization in Hypertensive Patients Within 7-Years Follow-Up

Lower extremity amputation and requirement of peripheral artery revascularization are common outcomes of undiagnosed peripheral artery disease patients. In the current work, prediction models for the need of amputation or peripheral revascularization focused on hypertensive patients within seven years follow up are employed. We applied machine learning (ML) models using classifiers such as Extreme Gradient Boost (XGBoost), Random Forest (RF) and Adaptive Boost (AdaBoost), that will allow clinicians to identify the patients at risk of these two endpoints using simple clinical data. We used the non-interventional cohort of the getABI study in the primary care setting, selecting 4,191 hypertensive patients out of 6,474 patients with age over 65 years old and followed up for vascular events or death up to 7 years. During this follow up period, 150 patients underwent either amputation or peripheral revascularization or both. Accuracy, Specificity, Sensitivity and Area under the receiver operating characteristic curve (AUC) were estimated for each machine learning model. The results demonstrate Random Forest as the most accurate model for the prediction of the composite endpoint in hypertensive patients within 7 years follow-up, achieving 73.27 % accuracy.Clinical Relevance-This study assists clinicians to better predict and treat these serious outcomes, amputation and peripheral revascularization in hypertensive patients.

Development and validation of a prediction model for the prolonged length of stay in Chinese patients with lower extremity atherosclerotic disease: a retrospective study

OBJECTIVES

This study aims to develop and internally validate a prediction model, which takes account of multivariable and comprehensive factors to predict the prolonged length of stay (LOS) in patients with lower extremity atherosclerotic disease (LEAD).

DESIGN

This is a retrospective study.

SETTING

China.

PARTICIPANTS, PRIMARY AND SECONDARY OUTCOMES

Data of 1694 patients with LEAD from a retrospective cohort study between January 2014 and November 2021 were analysed. We selected nine variables and created the prediction model using the least absolute shrinkage and selection operator (LASSO) regression model after dividing the dataset into training and test sets in a 7:3 ratio. Prediction model performance was evaluated by calibration, discrimination and Hosmer-Lemeshow test. The effectiveness of clinical utility was estimated using decision curve analysis.

RESULTS

LASSO regression analysis identified age, gender, systolic blood pressure, Fontaine classification, lesion site, surgery, C reactive protein, prothrombin time international normalised ratio and fibrinogen as significant predictors for predicting prolonged LOS in patients with LEAD. In the training set, the prediction model showed good discrimination using a 500-bootstrap analysis and good calibration with an area under the receiver operating characteristic of 0.750. The Hosmer-Lemeshow goodness of fit test for the training set had a p value of 0.354. The decision curve analysis showed that using the prediction model both in training and tests contributes to clinical value.

CONCLUSION

Our prediction model is a valuable tool using easily and routinely obtained clinical variables that could be used to predict prolonged LOS in patients with LEAD and help to better manage these patients in routine clinical practice.

The Impact of Atrial Fibrillation on Outcomes of Peripheral Arterial Disease: Analysis of Routinely Collected Primary Care Data

BACKGROUND

The combination of peripheral arterial disease and atrial fibrillation is linked with high risk of mortality and stroke. This study aims to investigate the impact of atrial fibrillation on patients with diagnosed peripheral arterial disease.

METHODS

This is a retrospective study using The Health Improvement Network database, which contains prospectively collected data from participating primary care practices. Patients with a new diagnosis of peripheral arterial disease between January 8, 1995 and January 5, 2017 were identified in the database alongside relevant demographic information, clinical history, and medications. Every patient in the dataset with peripheral arterial disease and baseline atrial fibrillation (case) was matched to a patient without atrial fibrillation (control) with similar characteristics using propensity score matching. Cox-regression analysis was performed and hazard ratios (HR) calculated for the outcomes of death, stroke, ischemic heart disease, heart failure, and major amputation.

RESULTS

Prevalence of atrial fibrillation in this cohort was 10.2%. All patients with peripheral arterial disease and atrial fibrillation (n = 5685) were matched with 5685 patients without atrial fibrillation but otherwise similar characteristics. After multivariate analysis, atrial fibrillation was independently associated with mortality (HR 1.18; 95% confidence interval [CI], 1.12-1.26; P < .01), cerebrovascular events (HR 1.35; 95% CI, 1.17-1.57; P < .01), and heart failure (HR 1.87; 95% CI, 1.62-2.15; P < .01), but not with ischemic heart disease or limb loss.

CONCLUSION

In peripheral arterial disease patients, atrial fibrillation is a risk factor for mortality, stroke, and heart failure. This emphasizes the need for proactive surveillance and holistic management of these patients.

Incidence and risk factors of lower extremity amputations in people with type 2 diabetes in Taiwan, 2001-2010

BACKGROUND

Diabetic patients have an increased risk of lower extremity amputations (LEAs). In the present study we analyzed the incidence of LEA in patients with type 2 diabetes mellitus (T2DM) in Taiwan from 2001 to 2010, and determined risk factors for LEA.

METHODS

Data from the Taiwan National Health Insurance Research Database collected between 1 January 2001 and 31 December 2010 were analyzed. First, the incidence of LEA in the diabetic population was calculated. Subsequently, patients with new-onset T2DM during the study period were selected, and Cox's proportional hazards model was used to identify factors associated with LEA. The characteristics of patients who underwent major and multiple amputations were also analyzed.

RESULTS

From 2001 to 2010, 1588 non-traumatic LEAs were performed among the study subjects; 776 (48.9%) were minor and 812 (51.1%) were major LEAs. Over the period in question, the incidence of LEAs decreased from 3.08 to 1.65 per 1000 person-years. Factors associated with LEA included peripheral arterial occlusive disease (hazard ratio [HR] 4.134; 95% confidence interval [CI] 2.72-6.29), diabetic neuropathy (HR 2.34; 95% CI 1.62-3.38), diabetic retinopathy (HR 2.07; 95% CI 1.12-3.82), heart failure (HR 2.13; 95% CI 1.45-3.15), male gender (HR 1.64; 95% CI 1.24-2.18), and adult onset diabetes (HR 1.02; 95% CI 1.01-1.04). Patients with a history of stroke were more likely to undergo major and multiple amputations (P < 0.001 and P < 0.01, respectively).

CONCLUSIONS

The incidence of LEA in the Taiwan diabetic population decreased over the study period. The results indicate that efforts to improve diabetic care should be supported and sustainable, especially for those at high risk.

Outcomes and characteristics of patients undergoing percutaneous angioplasty followed by below-knee or above-knee amputation for peripheral artery disease

OBJECTIVE

Little is known about long-term outcomes among patients who receive percutaneous angioplasty (PTA) for peripheral artery disease (PAD) then undergo below-knee or above-knee amputations. We sought to determine clinical outcomes associated with below-knee or above-knee amputation, along with possible explanatory factors and treatment strategies.

METHODS

Using data from Taiwan's National Health Insurance Research Database from 1997 to 2010, 7,568 adult patients were divided into three groups: lower extremity preserved (LE), below-knee amputation (BK) and above-knee amputation (AK). We assessed outcomes including major adverse cardiovascular events (MACE) and associated risk factors.

RESULTS

Overall MACE was significantly higher in the AK group compared to the LE and BK groups, over a mean follow-up of 2.45 years (hazard ratio [HR]: 1.81; 95% confidence interval [CI]: 1.50-2.18 for AK vs. LE; HR: 1.67; 95% CI: 1.36-2.06 for AK vs. BK). However MACE were similar for the BK and LE groups (HR: 1.08; 95% CI: 0.98-1.20). Overall mortality was highest in the AK group (HR: 1.65, 95% CI: 1.34-2.04 for AK vs. BK). As for patient characteristics, atrial fibrillation was more prevalent in the AK group than in the BK group (17% vs. 7%). Independent risk factors associated with death after above- or below-knee amputation included advanced age, heart failure, dialysis, male gender and high patient volume.

CONCLUSION

The MACE rate was highest in the AK group, whereas the LE and BK groups were similar in this regard. Furthermore, overall mortality increased with larger area of amputation.