Development and validation of a new scoring system to predict wound healing after endovascular therapy in critical limb ischemia with tissue loss

Application of machine learning algorithms in electronic medical records to predict amputation-free survival after first revascularization in patients with peripheral artery disease

BACKGROUND

This study aimed to apply eight machine learning algorithms to develop the optimal model to predict amputation-free survival (AFS) after first revascularization in patients with peripheral artery disease (PAD).

METHODS

Among 2130 patients from 2011 to 2020, 1260 patients who underwent revascularization were randomly assigned to training set and validation set in an 8:2 ratio. 67 clinical parameters were analyzed by lasso regression analysis. Logistic regression, gradient boosting machine, random forest, decision tree, eXtreme gradient boosting, neural network, Cox regression, and random survival forest (RSF) were applied to develop prediction models. The optimal model was compared with GermanVasc score in testing set comprising patients from 2010.

RESULTS

The postoperative 1/3/5-year AFS were 90%, 79.4%, and 74.1%. Age (HR:1.035, 95%CI: 1.015-1.056), atrial fibrillation (HR:2.257, 95%CI: 1.193-4.271), cardiac ejection fraction (HR:0.064, 95%CI: 0.009-0.413), Rutherford grade ≥ 5 (HR:1.899, 95%CI: 1.296-2.782), creatinine (HR:1.03, 95%CI: 1.02-1.04), surgery duration (HR:1.03, 95%CI: 1.01-1.05), and fibrinogen (HR:1.292, 95%CI: 1.098-1.521) were independent risk factors. The optimal model was developed by RSF algorithm, with 1/3/5-year AUCs in training set of 0.866 (95% CI:0.819-0.912), 0.854 (95% CI:0.811-0.896), 0.844 (95% CI:0.793-0.894), in validation set of 0.741 (95% CI:0.580-0.902), 0.768 (95% CI:0.654-0.882), 0.836 (95% CI:0.719-0.953), and in testing set of 0.821 (95%CI: 0.711-0.931), 0.802 (95%CI: 0.684-0.919), 0.798 (95%CI: 0.657-0.939). The c-index of the model outperformed GermanVasc Score (0.788 vs 0.730). A dynamic nomogram was published on shinyapp (https://wyy2023.shinyapps.io/amputation/).

CONCLUSION

The optimal prediction model for AFS after first revascularization in patients with PAD was developed by RSF algorithm, which exhibited outstanding prediction performance.

Risk Models and Scores in Patients with Peripheral Artery Disease and Chronic Limb-threatening Ischemia: A Comprehensive Review

Peripheral artery disease (PAD) affects more than 200 million patients worldwide and chronic limbthreatening ischemia (CLTI) is the most advanced stage of PAD with very high morbidity and mortality rates. Cardiovascular medicine is trending towards a more personalized approach where each individual patient will be managed according to specific risk factors, disease characteristics, expectations related to their disease and individualized assessment of potential outcomes. For this reason, a number of risk models and scores have been developed during the last few years. Our aim in this comprehensive review article is to provide an overview of selected risk models and scores for patients with PAD and CLTI. Given that some of the published scores were of low quality (minimal discriminatory ability), we included scores that were already externally validated or scores that had promising initial findings. Available scoring systems were grouped in the five following categories according to their utility: i) scores that can detect asymptomatic patients who should be screened for PAD, ii) scores for assessment of functional status and quality of life in patients with PAD, iii) scores assessing risk for amputation and other major adverse limb events among patients with CLTI, iv) scores for the optimal revascularization strategy in each patient and scores predicting successful procedural outcomes; v) scores predicting short or long-term cardiovascular and limb related outcomes after either revascularization or at least angiographic assessment. Limitations of available scoring systems include development and validation in specific populations, lack of external validation (for some of them) and also lack of synchrony with current era endovascular technology. However, with further optimization of current scores and the development of new scores, the field of PAD and CLI can be transitioned to a personalized medicine approach.

Mobile Health-Based Thermometer for Monitoring Wound Healing After Endovascular Therapy in Patients With Chronic Foot Ulcer: Prospective Cohort Study

BACKGROUND

Foot temperature may increase after endovascular therapy, but the relationship between foot temperature and wound healing is unclear.

OBJECTIVE

This study was performed to evaluate the feasibility of a mobile health (mHealth)-based thermometer for foot temperature monitoring in patients with chronic foot ulcer before and after endovascular therapy and to determine the association between temperature change and wound healing time.

METHODS

This was a prospective cohort study. Patients who had a chronic foot ulcer (>3 months) and underwent endovascular therapy between June 2019 and December 2019 were included. The participants received standard medical care and endovascular therapy for revascularization. The mHealth-based thermometer, composed of 4 temperature-sensing chips, was put on the foot before and after endovascular therapy. Data from the chips were transferred to an associated mobile phone app via Bluetooth. Wound healing time was estimated using the Kaplan-Meier method, and the associations between baseline characteristics and clinical outcomes were evaluated using a Cox proportional hazard model.

RESULTS

A total of 163 patients with chronic foot ulcer who underwent endovascular therapy were enrolled and followed up until wound healing was complete or for 180 days. The mean foot temperature before endovascular therapy was 30.6 (SD 2.8 °C). Foot temperature increased significantly (mean 32.1 °C, SD 2.8 °C; P=.01) after the procedure. Wound healing time was significantly different in the Kaplan-Meier curves of the patient group with temperature changes ≥2 °C and the group with temperature changes ≤2 °C (log-rank P<.001). A foot temperature increase ≥2 °C after endovascular therapy was associated with increased wound healing in univariate analysis (hazard ratio [HR] 1.78, 95% CI 1.24-2.76, P=.02), and the association remained significant in multivariate analysis (HR 1.69, 95% CI 1.21-2.67, P=.03).

CONCLUSIONS

The mHealth-based thermometer was feasible and useful for foot temperature monitoring, which may provide health care professionals with a new endpoint for endovascular therapy. Foot temperature increases ≥2 °C after endovascular therapy were associated with faster wound healing in patients with chronic foot ulcer. Further studies are needed, however, to confirm these findings.