Predicting Hypertension Subtypes with Machine Learning Using Targeted Metabolites and Their Ratios.
Smarti Reel1, Parminder S Reel1, Zoran Erlic2
1Division of Population Health and Genomics, School of Medicine, University of Dundee, Dundee DD2 4BF, UK.
Metabolites
|August 25, 2022
Summary
This study identifies key metabolite biomarkers using machine learning to distinguish endocrine hypertension subtypes from primary hypertension. These findings can improve diagnosis and treatment for complex hypertension cases.
Area of Science:
- Biochemistry
- Endocrinology
- Machine Learning
Background:
- Hypertension is a significant global health issue, with primary hypertension (PHT) being most common but poorly understood.
- Endocrine hypertension (EHT), caused by hormonal imbalances, is often misdiagnosed as PHT, leading to treatment delays and reduced quality of life.
Purpose of the Study:
- To utilize targeted metabolomics and machine learning to identify biomarkers for classifying and differentiating subtypes of endocrine and primary hypertension.
- To improve the diagnostic accuracy for complex hypertension cases, including Cushing's syndrome (CS) and primary aldosteronism (PA).
Main Methods:
- Employed targeted metabolomics to analyze metabolite profiles.
- Applied high-throughput machine learning models for classification and prediction of hypertension subtypes.
- Validated model performance using a test set.
Main Results:
- Machine learning models achieved 92% specificity in classifying Cushing's syndrome (CS) from primary hypertension (PHT) and EHT from PHT.
- Identified C18:1, C18:2, and Orn/Arg as prominent metabolites and ratios for hypertension identification.
- Determined that sex is an important feature in distinguishing CS from PHT.
Conclusions:
- Targeted metabolomics combined with machine learning offers a promising approach for accurate classification of hypertension subtypes.
- Biomarker discovery can aid in differentiating EHT from PHT, potentially leading to earlier and more effective treatments.
- Further research into sex as a factor in hypertension classification is warranted.
Keywords:
Cushing syndromebiomarkershypertensionmachine learningmetabolomicspheochromocytoma/paragangliomaprimary aldosteronismMore Related Videos
Related Concept Videos
01:30Hypertension III: Clinical Manifestations and Diagnostic Studies
45
Hypertension is asymptomatic and also referred to as the "silent killer" until it progresses to a severe stage or causes target organ disease. Patients may experience symptoms stemming from the strain on blood vessels and tissues in various organs or the heart's increased workload.Physical exams might show no abnormalities other than high blood pressure. Signs of vascular damage, when present, correspond to the organs supplied by the affected vessels, leading to target organ damage. For...
45
01:28Hypertension I: Introduction
63
Hypertension is a widespread, long-term medical condition where blood pressure in the arteries remains elevated. It is characterized by systolic blood pressure readings of 130 mm Hg or above or diastolic blood pressure (DBP) readings of 80 mm Hg or higher. Unmanaged hypertension poses significant health risks, making the distinction between primary (or essential) hypertension and secondary hypertension crucial, as their management and implications vary.Primary HypertensionPrimary hypertension,...
63
01:18Hypertension and Regulation of Blood Pressure
2.3K
Hypertension, the most common cardiovascular disease, is diagnosed through repeated measurements of elevated blood pressure. Its risks, including damage to the kidney, heart, and brain, are directly proportional to blood pressure levels. Starting from 115/75 mm Hg, the risk of cardiovascular disease doubles with each increment of 20/10 mm Hg. The diagnosis relies on blood pressure measurements, not on patient symptoms, as hypertension is often asymptomatic until end-organ damage is imminent or...
2.3K