Telemedicine Use Among Cardiology Professionals: XGBoost Model Performance

57% of 112 surveyed German healthcare professionals reported using telemedicine. This 5.5 KB Excel file contains the performance metrics and predictor importance analysis from an XGBoost model predicting telemedicine adoption, authored by Pascal Petit and last updated in April 2026. The model achieved an AUROC of 0.88 and 79% accuracy using nested cross-validation.

Use Cases

• Benchmarking predictive model performance for healthcare technology adoption based on the reported AUROC and accuracy metrics.
• Analyzing key determinants of telemedicine use among cardiology professionals based on factors like TM knowledge and specialty mentioned in the description.
• Training similar classification models on survey data for other medical specialties based on the described methodology of using XGBoost and Shapley values.

Strengths

• Model performance is quantitatively reported with specific metrics: AUROC 0.88 and accuracy 0.79.
• The underlying survey data includes 112 healthcare professionals, providing a clear sample size.
• Methodology is described in detail, including the use of XGBoost, nested cross-validation, and Shapley additive explanations.

Limitations

• Row count and column-level documentation for the underlying data are unknown, which limits suitability assessment.
• The dataset is very small at 5.5 KB, indicating it likely contains only summary results, not the raw survey data.
• Geographic coverage is limited to a German survey, which may limit generalizability.

Provenance

Source

Secondary analysis of a German cross-sectional survey.

Collection Method

Survey data analyzed with Bayesian Model Averaging and XGBoost machine learning.

Time Range

null

Freshness

Last updated 2026-04-20 17:49:16; freshness should be verified.

Geography

Germany