Association between high sensitivity cardiac troponin and mortality risk in the non-diabetic population: findings from the National Health and Nutrition Examination Survey.

OBJECTIVE: We investigated the association of high-sensitivity cardiac troponin (Hs-cTn) with all-cause and cardiovascular mortality in non-diabetic individuals. METHODS: This study included 10,393 participants without known diabetes and cardiovascular disease from the US National Health and Nutrition Examination Survey (NHANES). Serum Hs-cTnI and Hs-cTnT concentrations were measured. Prediabetes was defined as fasting blood glucose between 100 and 125 mg/dL or HbA1c between 5.7 and 6.4%. Cox proportional hazard models were used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs) for mortality risk. Time-dependent receiver operating characteristics (tROC) curves were utilized to measure the predictive performance of the biomarkers. Net Reclassification Improvement (NRI) were calculated to estimate the improvement in risk classification for adding Hs-cTnT or Hs-cTnI to the standard models based on Framingham risk factors. RESULTS: The mean age of the participants was 48.1 ± 19.1 years, with 53.3% being female and 25.8% being prediabetic. After multivariable adjustment, compared to those with Hs-cTnI concentration less than the limit of detection, the HRs (95% CIs) of the participants with Hs-cTnI concentration higher than the 99th upper reference limit were 1.74 (1.35, 2.24) for all-cause mortality and 2.10 (1.36, 3.24) for cardiovascular mortality. The corresponding HRs (95% CIs) for Hs-cTnT were 2.07 (1.53, 2.81) and 2.92 (1.47, 5.80) for all-cause and cardiovascular mortality. There was a significant interaction between prediabetes and Hs-cTnI on the mortality risk; a positive relationship was only observed in prediabetic individuals. No interaction was observed between prediabetes and Hs-cTnT on mortality risk. The Areas Under tROC indicated both Hs-cTnT and Hs-cTnI show better predictive performance in cardiovascular mortality than in all-cause mortality. NRI (95% CI) for adding Hs-cTnT to the standard model were 0.25 (0.21, 0.27) and 0.33 (0.26, 0.39) for all-cause and cardiovascular mortality. The corresponding NRI (95% CI) for Hs-cTnI were 0.04 (0, 0.06) and 0.07 (0.01, 0.13). CONCLUSIONS: Elevated blood levels of Hs-cTnI and Hs-cTnT are associated with increased mortality. Measurement of Hs-cTnT in non-diabetic subjects, particularly those with prediabetes, may help identify individuals at an increased risk of cardiovascular disease and provide early and more intensive risk factor modification.

Machine learning algorithms identify hypokalaemia risk in people with hypertension in the United States National Health and Nutrition Examination Survey 1999-2018.

BACKGROUND: Hypokalaemia is a side-effect of diuretics. We aimed to use machine learning to identify features predicting hypokalaemia risk in hypertensive patients. METHODS: Participants with hypertension in the United States National Health and Nutrition Examination Survey 1999-2018 were included for analysis. To select the most suitable algorithm, we tested and evaluated five machine learning algorithms commonly employed in epidemiological studies: Logistic Regression, k-Nearest Neighbor, Random Forest, Recursive Partitioning and Regression Trees, and eXtreme Gradient Boosting. These algorithms were accessed using a set of 38 screened features. We then selected the key hypokalaemia-associated features in the hypertension group and their cardiovascular diseases (CVD) subgroup using the SHapley Additive exPlanations (SHAP) values. Using SHAP values, the key features and their impact pattern on hypokalaemia risk were determined. RESULTS: A total of 25,326 hypertensive participants were included for analysis, of whom 4,511 had known CVD. The Random Forest algorithm had the highest AUROC (hypertension dataset: 0.73 [95%CI, 0.71-0.76]; CVD subgroup: 0.72 [95%CI, 0.66-0.78]). Moreover, the nomogram based on the top twelve key features screened by random forest retained good performance: age, sex, race, poverty income ratio, body mass index, systolic and diastolic blood pressure, non-potassium-sparing diuretics use and duration, renin-angiotensin blockers use and duration, and CVD history in hypertension dataset; while in CVD subgroup, the additional key features were comorbid diabetes, education level, smoking status, and use of bronchodilators. CONCLUSION: Our predictive model based on the random forest algorithm performed best among the tested and evaluated five algorithms. Hypokalaemia-associated key features have been identified in hypertensive patients and the subgroup with CVD. These findings from machine learning facilitate the development of artificial intelligence to highlight hypokalaemia risk in hypertension patients.

Our predictive model based on the random forest algorithm performed best among the tested and evaluated five algorithms, and hypokalemia-associated key features have been identified in hypertensive patients and the subgroup with cardiovascular disease.The nomogram we developed including twelve key features might be useful and applied in primary clinical consultations to identify the hypertensive patients at risk of hypokalaemia.These findings from machine learning facilitate the development of artificial intelligence to highlight hypokalaemia risk in hypertension patients.