ABSTRACT
BACKGROUND: Given the critical importance of Low-density lipoprotein cholesterol (LDL-C) levels in determining cardiovascular risk, it is essential to measure LDL-C accurately. Since the Friedewald formula generates incorrect predictions in many circumstances, new equations have been developed to overcome the Friedewald equations' shortcomings. This study aimed to compare estimated LDL-C with directly measured LDL-C (dLDL-C), as well as their performance in predicting LDL-C, utilizing Friedewald, extended Martin-Hopkins, Sampson, de Cordova, and Vujovic formulas and five machine learning (ML) algorithms. METHODS: A total of 29,504 samples from the ISLAB-2 Core Laboratory were included in the study. All statistical analysis was performed using R version 4.1.2. Statistical Language. RESULTS: Bayesian-Regularized Neural Network (BRNN) (r = 0.957) and Random Forest (RF) (r = 0.957) algorithms showed a higher correlation with dLDL-C than the other equations in all-testing dataset. All ML algorithms demonstrated less bias than pre-existing LDL-C equations with dLDL-C and outperformed the LDL-C estimation equations in terms of concordance in all-testing dataset. CONCLUSIONS: The results of our research indicate that when compared to conventional equations, ML algorithms are much more effective in predicting LDL-C. ML algorithms, aided by a vast dataset, could have the capability to predict LDL-C levels even in cases where triglyceride levels are high, unlike the limited usage of Friedewald formula.
Subject(s)
Machine Learning , Humans , Bayes Theorem , Cholesterol, LDL , TriglyceridesABSTRACT
Background Subclinical hypothyroidism is a situation in which the thyroid-stimulating hormone (TSH) value exceeds the upper limit of normal, but the free triiodothyronine (T3) and thyroxine (T4) values are within the normal range. The etiology is similar to overt hypothyroidism. Case presentation An 18-year-old female patient was referred to our endocrinology clinic due to elevated TSH levels detected during a routine examination. She was clinically euthyroid and had a normal thyroid ultrasound pattern. The TSH concentration was measured twice independently, giving values of 5.65 µIU/mL and 5.47 µIU/mL. The polyethylene glycol (PEG) method for TSH measurement was used to determine the concentration of macro-TSH (m-TSH), a macromolecule formed between TSH and immunoglobulin (Ig). Using the same blood samples for which the TSH levels were found to be high, the PEG method found TSH levels to be within a normal range, with values of 1.50 µIU/mL (5.65-1.50 µIU/mL measured; a decrease of 75%) and 1.26 µIU/mL (5.47-1.26 µIU/mL measured; a decrease of 77%), respectively. The TSH values determined by the PEG precipitation test were markedly low, with PEG-precipitable TSH ratios greater than 75%. Conclusions The cause of 55% of subclinical hypothyroidism is chronic autoimmune thyroiditis. However, it is necessary to exclude other TSH-elevated conditions for diagnosis. One of these conditions is m-TSH, which should be kept in mind even though it is rarely seen. m-TSH should be considered especially in patients who have a TSH value above 10 µIU/mL without hypothyroidism symptoms or who require a higher levothyroxine replacement dose than expected to make them euthyroid.
