Development and external validation of a LASSO-based parsimonious nomogram for predicting BPPV recurrence: a multi-center retrospective cohort study - Summary - MDSpire
Advertisement
Development and external validation of a LASSO-based parsimonious nomogram for predicting BPPV recurrence: a multi-center retrospective cohort study
To identify core risk factors and develop a simplified, externally validated nomogram for personalizing recurrence risk stratification in BPPV patients.
Approach:
Key Findings:
1-year recurrence rate was 23.97%, indicating a significant risk for patients.
Nomogram included three core variables: Diabetes Mellitus (OR = 11.42), Non-posterior canal involvement (OR = 4.17), and 25-hydroxyvitamin D deficiency (OR = 3.76), highlighting critical risk factors.
Model demonstrated good discrimination: AUC of 0.905 (training set), 0.872 (internal validation), and 0.853 (external validation).
Calibration curves showed excellent agreement between predicted and observed probabilities.
DCA and CIC confirmed significant net clinical benefit across a wide range of threshold probabilities.
Interpretation:
The developed nomogram integrates metabolic, anatomical, and nutritional markers for early identification of high-risk BPPV patients, aiding in personalized treatment strategies.
Limitations:
Study limited to two medical centers, which may affect generalizability to broader populations.
Retrospective design may introduce bias, limiting causal inferences.
Conclusion:
The nomogram facilitates targeted secondary prevention in clinical practice.
A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness
