Machine-learning-based analysis of the sensitivity and specificity on lipid-lowering effect of one-month-administered statins

Few predictive studies have been reported on the efficacy of atorvastatin in reducing lipoprotein cholesterol to be qualified after 1-month course of treatment in different individuals. A total of 14,180 community-based residents aged ≥ 65 received health checkup, 1013 of whom had low-density lipoprotein (LDL) higher than 2.6mmol/L so that they were put on 1-month course of treatment with atorvastatin. At its completion, lipoprotein cholesterol was measured again. With < 2.6 mmol/L considered as the treatment standard, 411 individuals were judged as the qualified group, and 602, and as the unqualified group. The basic sociodemographic features covered 57 items. The data were randomly divided into train sets and test ones. The recursive random-forest algorithm was applied to predicting the patients response to atorvastatin, the recursive feature elimination method, to screening all the physical indicators. The overall accuracy, sensitivity and specificity were calculated, respectively, and so were the receiver operator characteristic curve and the area under the curve of the test set. In the prediction model on the efficacy of 1-month treatment of statins for LDL, the sensitivity, 86.86%; and the specificity, 94.83%. In the prediction model on the efficacy of the same treatment for triglyceride, the sensitivity, 71.21%; and the specificity, 73.46%. As to the prediction of total cholesterol, the sensitivity, 94.38%; and the specificity, 96.55%. And in the case of high-density lipoprotein (HDL), the sensitivity, 84.86%; and the specificity, 100%. recursive feature elimination analysis showed that total cholesterol was the most important feature of atorvastatin efficacy of reducing LDL; that HDL was the most important one of its efficacies of reducing triglycerides; that LDL was the most important one of its efficacies of reducing total cholesterol; and that triglyceride was the most important one of its efficacies of reducing HDL. Random-forest can help predict whether atorvastatin efficacy of reducing lipoprotein cholesterol to be qualified after 1-month course of treatment in different individuals.

[1]  Jie Liu,et al.  Elevated serum uric acid was associated with pre-inflammatory state and impacted the role of HDL-C on carotid atherosclerosis. , 2022, Nutrition, metabolism, and cardiovascular diseases : NMCD.

[2]  K. Dogan,et al.  HDL subgroups and their paraoxonase‐1 activity in the obese, overweight and normal weight subjects , 2021, International journal of clinical practice.

[3]  O. Borst,et al.  Platelet-Derived PCSK9 Is Associated with LDL Metabolism and Modulates Atherothrombotic Mechanisms in Coronary Artery Disease , 2021, International journal of molecular sciences.

[4]  K. Tsioufis,et al.  Real-world Evidence for Adherence and Persistence with Atorvastatin Therapy , 2021, Cardiology and Therapy.

[5]  Dong-mei Huang,et al.  Impact of Low Frequency Electro-acupuncture on Glucose and Lipid Metabolism in Unmarried PCOS Women: A Randomized Controlled Trial , 2021, Chinese Journal of Integrative Medicine.

[6]  S. Krähenbühl,et al.  The Risk of Muscular Events Among New Users of Hydrophilic and Lipophilic Statins: an Observational Cohort Study , 2021, Journal of General Internal Medicine.

[7]  C. Punt,et al.  RAINFOREST: a random forest approach to predict treatment benefit in data from (failed) clinical drug trials. , 2020, Bioinformatics.

[8]  D-Q Zhang,et al.  Effect of atorvastatin on expression of TLR4 and NF-κB in stroke rats and its protective effect on brain. , 2020, European review for medical and pharmacological sciences.

[9]  D. Gaudet,et al.  Statin Initiation: Guideline Concordance and Characteristics of New Users in Quebec, Canada , 2020, Journal of Population Therapeutics and Clinical Pharmacology.

[10]  M. A. Ali Khan,et al.  Statins and Abnormal Liver Function Tests: Is There a Correlation? , 2020, Cureus.

[11]  K. Hashimoto,et al.  Artificial Intelligence in Ovarian Cancer Diagnosis , 2020, AntiCancer Research.

[12]  Ali Kashif Bashir,et al.  COVID-19 Patient Health Prediction Using Boosted Random Forest Algorithm , 2020, Frontiers in Public Health.

[13]  C. Miao,et al.  Metrnl deficiency decreases blood HDL cholesterol and increases blood triglyceride , 2020, Acta Pharmacologica Sinica.

[14]  Li Yang,et al.  Study of cardiovascular disease prediction model based on random forest in eastern China , 2020, Scientific Reports.

[15]  L. Goldstein,et al.  Atorvastatin Reduces First and Subsequent Vascular Events Across Vascular Territories in the SPARCL Trial. , 2020, Journal of the American College of Cardiology.

[16]  J. Pyo,et al.  Effect of acetylcholinesterase inhibitors on post-stroke cognitive impairment and vascular dementia: A meta-analysis , 2020, PloS one.

[17]  E. Connolly,et al.  Statin Therapy in Ischemic Stroke Models: A Meta-Analysis , 2019, Translational Stroke Research.

[18]  E. D. de Faria,et al.  Excess weight mediates changes in HDL pool that reduce cholesterol efflux capacity and increase antioxidant activity. , 2019, Nutrition, metabolism, and cardiovascular diseases : NMCD.

[19]  Gretchen A. Stevens,et al.  National trends in total cholesterol obscure heterogeneous changes in HDL and non-HDL cholesterol and total-to-HDL cholesterol ratio: a pooled analysis of 458 population-based studies in Asian and Western countries , 2019, International journal of epidemiology.

[20]  X. Correig,et al.  HDL Triglycerides: A New Marker of Metabolic and Cardiovascular Risk , 2019, International journal of molecular sciences.

[21]  Jihoon G. Yoon,et al.  Machine Learning–Based Model for Prediction of Outcomes in Acute Stroke , 2019, Stroke.

[22]  B. Shan,et al.  Gray matter reduction related to decreased serum creatinine and increased triglyceride, Hemoglobin A1C, and low-density lipoprotein in subjects with obesity , 2019, Neuroradiology.

[23]  L. Moja,et al.  Comparison of statins for secondary prevention in patients with ischemic stroke or transient ischemic attack: a systematic review and network meta-analysis , 2019, BMC Medicine.

[24]  R. Akinyemi,et al.  Stroke, cerebrovascular diseases and vascular cognitive impairment in Africa , 2019, Brain Research Bulletin.

[25]  Lisa Hellerstein,et al.  Recursive Feature Elimination by Sensitivity Testing , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[26]  Thalia Shoshana Field,et al.  Canadian stroke best practice recommendations: Secondary prevention of stroke, sixth edition practice guidelines, update 2017 , 2018, International journal of stroke : official journal of the International Stroke Society.

[27]  Yongjun Wang,et al.  Pathogenesis of epileptic seizures and epilepsy after stroke , 2018, Neurological research.

[28]  N. Barnard,et al.  Association between plant-based diets and plasma lipids: a systematic review and meta-analysis , 2017, Nutrition reviews.

[29]  O. Godefroy,et al.  Vascular cognitive impairment: Advances and trends. , 2017, Revue neurologique.

[30]  P. Yaghmaei,et al.  Atorvastatin inhibits cholesterol-induced caspase-3 cleavage through down-regulation of p38 and up-regulation of Bcl-2 in the rat carotid artery , 2017, Cardiovascular journal of Africa.

[31]  Meijuan Zhang,et al.  The levels of triglyceride and total cholesterol in methamphetamine dependence , 2017, Medicine.

[32]  Kui Zhang,et al.  Recursive random forest algorithm for constructing multilayered hierarchical gene regulatory networks that govern biological pathways , 2017, PloS one.

[33]  F. Verdonk,et al.  Statins prevent cognitive impairment after sepsis by reverting neuroinflammation, and microcirculatory/endothelial dysfunction , 2017, Brain, Behavior, and Immunity.

[34]  E. Björnsson Hepatotoxicity of statins and other lipid‐lowering agents , 2017, Liver international : official journal of the International Association for the Study of the Liver.

[35]  Ping Feng,et al.  Prostate cancer prediction using the random forest algorithm that takes into account transrectal ultrasound findings, age, and serum levels of prostate-specific antigen , 2016, Asian journal of andrology.

[36]  Eric E. Smith,et al.  Canadian Stroke Best Practice Recommendations: Secondary Prevention of Stroke Guidelines, Update 2014 , 2015, International journal of stroke : official journal of the International Stroke Society.

[37]  Sujoy Ghosh,et al.  Uric Acid and Its Correlation with Various Metabolic Parameters: A Population-Based Study , 2019, Indian journal of endocrinology and metabolism.