Skip to main content

Table 1 Lecture review of the risk factors analysis in patients who have undergone PCIs

From: Machine learning-driven prediction of medical expenses in triple-vessel PCI patients using feature selection

Study

Country

Years

Numbers

Dataset

Algorithms/analysis

Key factors associated with medical cost

Pohlen et al., 2008 [12]

Germany

2002

770

Department of cardiology and angiology

Multivariate analyses

Creatinine > 2 mg/dl, EF ≤ 35%, presence of a thrombus, PCI of a venous bypass, CCS class IV, coronary three-vessel disease and age

Moleerergpoom et al., 2007 [14]

Thailand

-

3,552

TACSR

Univariate, multivariate analyses, stepwise MLR

Age, LOS, hospital type, GP IIb/IIIa inhibitors, thrombolytics, comorbidities (major bleeding, CHF, diabetes), Referred patients

Lee et al., 2013 [15]

Hong Kong

2007–2009

89

CMS

Non-parametric Mann–Whitney tests

Hyperlipidemia, diabetes, or hypertension, Higher-tier consumables (stents and balloons), LOS, antiplatelets and lipid-lowering agents

Afana et al., 2015 [16]

U.S

2001–2009

833,344

NIS

The Wilcoxon rank-sum test

Age, gender, insurance type, procedure type, ICU Stay, hospital location, CCI

Amin et al., 2020 [17]

U.S

2006−2015

1,443,297

Premier

MLR

AKI, ICU, age comorbidities (diabetes, CKD)

Hautala et al., 2023 [13]

Finland

2013–2014

65

Oulu University Hospital

Linear Regression Models

Depression score, LDL Cholesterol, LVEF, age, maximal exercise capacity, quality of life, systolic blood pressure, and diabetes

  1. Abbreviation: NIS Nationwide inpatient sample data, EF Ejection fraction, LOS Length of hospital stay, CMS Clinical management system, CHF Congestive heart failure, CCI Charlson comorbidity index, ICU Intensive care unit, AKI Acute kidney injury, CKD Chronic kidney disease, MLR Multivariable linear regression, TACSR Thai ACS registry, LVEF Left ventricular ejection fraction