Back

Advanced lung cancer inflammation index as a predictor of all-cause and cardiovascular mortality among American hypertensive patients

Hu, N.; Feng, Y.; He, L.

2024-10-23 cardiovascular medicine
10.1101/2024.10.22.24315955 medRxiv
Show abstract

BACKGROUNDThe predictive value of advanced lung cancer inflammation index (ALI) in all-cause mortality and cardiovascular mortality among hypertensive patients has not been thoroughly investigated. METHOD AND RESULTSA total of 2805 hypertensive patients from the National Health and Nutrition Examination Surveys from 2005-2006 to 2017-2018 were ultimately included in the analysis. Over the study period, participants were followed up for an average of 57.6 months, during which 311 deaths occurred, with 89 deaths attributed to cardiovascular causes. Survey-weighted restricted cubic spline (RCS) analysis revealed a nonlinear negative correlation between ALI and both all-cause and cardiovascular mortality among hypertensive patients. Survey-weighted Cox proportional hazards models revealed that in the highest ALI quartile experienced a 53.8% reduction in all-cause mortality and an 83.5% reduction in cardiovascular mortality compared with those in the lowest quartile. Survey-weighted Kaplan-Meier survival analysis also revealed that the all-cause mortality and cardiovascular mortality of hypertensive patients in the high ALI group were significantly lower than those in the low ALI group. Time-dependent ROC curves were used to assess the accuracy of survival outcomes and the area under the curve (AUC) values for the ability of ALI to predict all-cause mortality at 1, 3, and 5 years among hypertensive patients were 0.772, 0.672, and 0.634, respectively, whereas the AUC values for predicting cardiovascular mortality were 0.735, 0.760, and 0.723, respectively. CONCLUSIONSALI can be a valuable and effective tool for identifying high-risk hypertensive patients and guiding targeted interventions.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.