A multicenter prospective cohort study developing and validating a SIRI-based machine learning model and simplified risk score for predicting postherpetic neuralgia - Summary - MDSpire
Advertisement
A multicenter prospective cohort study developing and validating a SIRI-based machine learning model and simplified risk score for predicting postherpetic neuralgia
To evaluate the predictive value of the systemic inflammatory response index (SIRI) for postherpetic neuralgia (PHN) development and to develop a simplified risk scoring tool.
Key Findings:
511 (37.55%) patients developed PHN during follow-up.
SIRI was identified as an independent predictive factor for PHN (OR = 1.448, 95% CI 1.119–1.874, P = 0.005).
The XGBoost model showed AUC values of 0.889 in the training set, 0.857 in the internal test set, and 0.900 in the external validation set.
The simplified risk scoring table achieved an AUC of 0.904 in the external validation set.
Interpretation:
SIRI is a significant independent biomarker for predicting PHN, and the developed machine learning model demonstrates high predictive accuracy.
Limitations:
The study's findings may not be generalizable beyond the included patient population.
Further external validation in diverse populations is needed.
Conclusion:
The study confirms SIRI's role as a predictive biomarker for PHN and presents a clinically practical risk scoring tool.
Turns out biology tracks more than we thought — from a spit test that reads your all-nighter to a surgical outcome that still shows up in household chores two decades later. Plus: habits aren't built gradually. They snap.
