The clinical and cost burden of coronary calcification in a Medicare cohort: An economic model to address under-reporting and misclassification

A machine learning approach to predicting vascular calcification risk of type 2 diabetes: A retrospective study

BACKGROUND

Recently, patients with type 2 diabetes mellitus (T2DM) have experienced a higher incidence and severer degree of vascular calcification (VC), which leads to an increase in the incidence and mortality of vascular complications in patients with T2DM.

HYPOTHESIS

To construct and validate prediction models for the risk of VC in patients with T2DM.

METHODS

Twenty-three baseline demographic and clinical characteristics were extracted from the electronic medical record system. Ten clinical features were screened with least absolute shrinkage and selection operator method and were used to develop prediction models based on eight machine learning (ML) algorithms (k-nearest neighbor [k-NN], light gradient boosting machine, logistic regression [LR], multilayer perception [(MLP], Naive Bayes [NB], random forest [RF], support vector machine [SVM], XGBoost [XGB]). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and precision.

RESULTS

A total of 1407 and 352 patients were retrospectively collected in the training and test sets, respectively. Among the eight models, the AUC value in the NB model was higher than the other models (NB: 0.753, LGB: 0.719, LR: 0.749, MLP: 0.715, RF: 0.722, SVM: 0.689, XGB:0.707, p < .05 for all). The k-NN model achieved the highest sensitivity of 0.75 (95% confidence interval [CI]: 0.633-0.857), the MLP model achieved the highest accuracy of 0.81 (95% CI: 0.767-0.852) and specificity of 0.875 (95% CI: 0.836-0.912).

CONCLUSIONS

This study developed a predictive model of VC based on ML and clinical features in type 2 diabetic patients. The NB model is a tool with potential to facilitate clinicians in identifying VC in high-risk patients.

Role of Glycosylation in Vascular Calcification

Glycosylation is an important step in post-translational protein modification. Altered glycosylation results in an abnormality that causes diseases such as malignancy and cardiovascular diseases. Recent emerging evidence highlights the importance of glycosylation in vascular calcification. Two major types of glycosylation, N-glycosylation and O-glycosylation, are involved in vascular calcification. Other glycosylation mechanisms, which polymerize the glycosaminoglycan (GAG) chain onto protein, resulting in proteoglycan (PG), also have an impact on vascular calcification. This paper discusses the role of glycosylation in vascular calcification.

Shockwave coronary intravascular lithotripsy system for heavily calcified de novo lesions and the need for a cost-effectiveness analysis

The optimal management for severely calcified coronary artery disease is multi-adjunctive. Different strategies with dedicated devices should be available in the cardiac catheterization laboratory with their selection depending on the nature of the calcific disease and its anatomical distribution. Shockwave Intravascular Lithotripsy (S-IVL) system offers a novel option for lesion preparation of heavily calcified plaques in coronary and peripheral vessels. S-IVL is based on the fundamental principles of lithotripsy, a technology that has been used to modify renal stones for over 30 years. Pulsatile mechanical energy is used to fragment selectively amorphous calcium, sparing soft tissue. S-IVL has the potential of more widespread adoption because of its proven safety, efficacy and operational simplicity, but cost-effectiveness of such advanced technology will need to be analyzed.

AMPK: Potential Therapeutic Target for Vascular Calcification

Vascular calcification (VC) is an urgent worldwide health issue with no available medical treatment. It is an active cell-driven process by osteogenic differentiation of vascular cells with complex mechanisms. The AMP-activated protein kinase (AMPK) serves as the master sensor of cellular energy status. Accumulating evidence reveals the vital role of AMPK in VC progression. AMPK is involved in VC in various ways, including inhibiting runt-related transcription factor 2 signaling pathways, triggering autophagy, attenuating endoplasmic reticulum stress and dynamic-related protein 1-mediated mitochondrial fission, and activating endothelial nitric oxide synthase. AMPK activators, like metformin, are associated with reduced calcification deposits in certain groups of patients, indicating that AMPK is a potential therapeutic target for VC.

Cardiovascular calcification: artificial intelligence and big data accelerate mechanistic discovery

Cardiovascular calcification is a health disorder with increasing prevalence and high morbidity and mortality. The only available therapeutic options for calcific vascular and valvular heart disease are invasive transcatheter procedures or surgeries that do not fully address the wide spectrum of these conditions; therefore, an urgent need exists for medical options. Cardiovascular calcification is an active process, which provides a potential opportunity for effective therapeutic targeting. Numerous biological processes are involved in calcific disease, including matrix remodelling, transcriptional regulation, mitochondrial dysfunction, oxidative stress, calcium and phosphate signalling, endoplasmic reticulum stress, lipid and mineral metabolism, autophagy, inflammation, apoptosis, loss of mineralization inhibition, impaired mineral resorption, cellular senescence and extracellular vesicles that act as precursors of microcalcification. Advances in molecular imaging and big data technology, including in multiomics and network medicine, and the integration of these approaches are helping to provide a more comprehensive map of human disease. In this Review, we discuss ectopic calcification processes in the cardiovascular system, with an emphasis on emerging mechanistic knowledge obtained through patient data and advances in imaging methods, experimental models and multiomics-generated big data. We also highlight the potential and challenges of artificial intelligence, machine learning and deep learning to integrate imaging and mechanistic data for drug discovery.

Hospital cost impact of orbital atherectomy with angioplasty for critical limb ischemia treatment: a modeling approach

AIM

The incremental cost of peripheral orbital atherectomy system (OAS) plus balloon angioplasty (BA) versus BA-only for critical limb ischemia was estimated.

MATERIALS & METHODS

A deterministic simulation model used clinical and healthcare utilization data from the CALCIUM 360° trial and current cost data. Incremental cost of OAS + BA versus BA-only included differential utilization during the procedure and adverse-event costs at 3, 6 and 12-months.

RESULTS

For every 100 procedures, incremental annual costs to the hospital were US$350,930 lower with OAS + BA compared with BA-only. Despite higher upfront costs, savings were realized due to reduced need for revascularization, amputation and end-of-life care over 6-12-month postoperative period.

CONCLUSION

Atherectomy with OAS prior to BA was associated with cost savings to the hospital.

The potential cost-effectiveness of the Diamondback 360® Coronary Orbital Atherectomy System for treating de novo, severely calcified coronary lesions: an economic modeling approach

Background:

Patients who undergo percutaneous coronary intervention (PCI) for severely calcified coronary lesions have long been known to have worse clinical and economic outcomes than patients with no or mildly calcified lesions. We sought to assess the likely cost-effectiveness of using the Diamondback 360^® Orbital Atherectomy System (OAS) in the treatment of de novo, severely calcified lesions from a health-system perspective.

Methods and results:

In the absence of a head-to-head trial and long-term follow up, cost-effectiveness was based on a modeled synthesis of clinical and economic data. A cost-effectiveness model was used to project the likely economic impact. To estimate the net cost impact, the cost of using the OAS technology in elderly (⩾ 65 years) Medicare patients with de novo severely calcified lesions was compared with cost offsets. Elderly OAS patients from the ORBIT II trial (Evaluate the Safety and Efficacy of OAS in Treating Severely Calcified Coronary Lesions) [ClinicalTrials.gov identifier: NCT01092426] were indirectly compared with similar patients using observational data. For the index procedure, the comparison was with Medicare data, and for both revascularization and cardiac death in the following year, the comparison was with a pooled analysis of the Harmonizing Outcomes with Revascularization and Stents in Acute Myocardial Infarction (HORIZONS-AMI)/Acute Catheterization and Urgent Intervention Triage Strategy (ACUITY) trials. After adjusting for differences in age, gender, and comorbidities, the ORBIT II mean index procedure costs were 17% (p < 0.001) lower, approximately US$2700. Estimated mean revascularization costs were lower by US$1240 in the base case. These cost offsets in the first year, on average, fully cover the cost of the device with an additional 1.2% cost savings. Even in the low-value scenario, the use of the OAS is cost-effective with a cost per life-year gained of US$11,895.

Conclusions:

Based on economic modeling, the recently approved coronary OAS device is projected to be highly cost-effective for patients who undergo PCI for severely calcified lesions.