Cardiovascular diseases, mainly myocardial infarction and stroke, are the leading cause of death globally. Therefore, epidemiological research seems necessary to prevent cardiovascular events and mortality. However, real-world data from obesity metrics has intrinsic limitations for the assessment of causality. Despite of historical studies showing that the body mass index (BMI), the waist-to-hip ratio (WHR) and the waist circumference (WC) have been associated with increased risk of myocardial infarction, they might not be accurate from a causal inference. Our aim was to summarize historical and novel findings about obesity metrics and myocardial infarction to evidence causal association biases. Method: an epidemiological review study was conducted while being original research when adding new anthropometrics in study design. Mathematical inequalities between the simple body measurements in anthropometrically healthy adults were described. Mean values and cut-offs for classic and several newer anthropometric variables were established. Classic metrics, ratios between the means of the simple measurements, a modulus |x| as a result of subtracting some measurement means from others (e.g., mean fat free mass minus fat mass) and somatotype ratings were collated. Mathematically, a non-zero difference for each modulus |x| in any population study would indicate an unbalanced distribution of the measurements between groups being compared, and therefore, the risk exposure levels differing. Thus, when between-groups the high-risk body compositions and somatotype ratings differ, any metric-associated risk is biased from a causal inference. After investigating large epidemiological studies, the historical omission of key anthropometric variables is stated, and as being uncontrolled confounding factors distorted causal inferences. Therefore, a protective overestimate of fat free mass and hip circumference over fat mass and WC, respectively, always occurred. Similarly, when the waist-to-height ratio values of >0.5 are associated; a protective underestimate of height over WC occurs. Any metric-associated risk is biased if prediction is made from WC or technologically measured body compositions without accounting for relative risk volume measures. In conclusion, summarizing the historical and novel findings regarding risk prediction, BMI, WHR and WC alone show evidence of causal association biases because of high-risk body compositions and risk exposure levels always differ between the groups being compared.