Clinical Relevance and Statistical Significance. How can we achieve both using Real World Data?
March 28, 2023
Clinical Relevance and Statistical Significance. How can we achieve both using Real World Data?
Statistical Significance and Clinical Relevance are two important concepts in the field of medicine, and particularly in clinical research.
Being a bit more specific, statistical significance refers to the likelihood that a result is not due to chance. In other words, it is the probability that an observed effect (for example, a clinical effect resulting from a given treatment) is real and not just due to chance. A statistically significant result is considered meaningful in general terms when the p-value is less than 0.05, meaning that there is less than a 5% chance that the observed effect is due to chance.
Clinical relevance refers to the practical importance of any effect (after a treatment) on a patient’s everyday life (i.e. less pain, higher survival rate or better quality of life). Any result can be considered clinically relevant when it has a meaningful impact on patient outcomes, for example using a patient reported outcome measure (PROM).
These two concepts are related but not equivalent. For many reasons, a given result may be statistically significant but not clinically relevant, or vice versa. For example, a treatment may have a large clinical effect but fail to reach statistically significance due to a small population size or other factors, such as data dispersion or variability.
In summary, statistical significance and clinical relevance are both important for clinical research, the first providing unbiased evidence of a relationship or effect, while the latter represents the practical implications of results obtained in terms of patient care and decision making.
The ideal situation is having a result that is both statistically significant and clinically relevant. One of the best ways to achieve this in clinical trials, is deriving research data from a large number of a homogeneous group of enrolled patients (restricted by inclusion and exclusion criteria). However, in a real world scenario there is high variability and many factors affecting any clinical outcome (disease severity, age, sex, comorbidities, etc).
There is also one more aspect that affects clinical relevance for any real patient population, and is called generalizability, the degree to which you can apply the results of any clinical study to a broader patient population. One good example is that many clinical trials might offer statistical significance and clinical relevance in a restricted study population, but not generalizability.
The use of Real-World Data obtained from daily clinical practice could overcome the previous limitations by allowing clinicians to easily collaborate and aggregate de-identified data. This could lead to the generation of Real-World Evidence that can be considered statistically significant, clinically relevant and generalizable to different patient populations.
RegenMed Circles have been developed with this goal in mind, facilitating data sharing among healthcare practitioners and their industry partners, and putting the patient at the center of their care to advance and progress in any field of medicine and healthcare.
If you want to know more about Circles or how our solutions could help you in different ways, contact us.
Clinical Relevance and Statistical Significance. How can we achieve both using Real World Data?
March 28, 2023
Statistical Significance and Clinical Relevance are two important concepts in the field of medicine, and particularly in clinical research.
Being a bit more specific, statistical significance refers to the likelihood that a result is not due to chance. In other words, it is the probability that an observed effect (for example, a clinical effect resulting from a given treatment) is real and not just due to chance. A statistically significant result is considered meaningful in general terms when the p-value is less than 0.05, meaning that there is less than a 5% chance that the observed effect is due to chance.
Clinical relevance refers to the practical importance of any effect (after a treatment) on a patient’s everyday life (i.e. less pain, higher survival rate or better quality of life). Any result can be considered clinically relevant when it has a meaningful impact on patient outcomes, for example using a patient reported outcome measure (PROM).
These two concepts are related but not equivalent. For many reasons, a given result may be statistically significant but not clinically relevant, or vice versa. For example, a treatment may have a large clinical effect but fail to reach statistically significance due to a small population size or other factors, such as data dispersion or variability.
In summary, statistical significance and clinical relevance are both important for clinical research, the first providing unbiased evidence of a relationship or effect, while the latter represents the practical implications of results obtained in terms of patient care and decision making.
The ideal situation is having a result that is both statistically significant and clinically relevant. One of the best ways to achieve this in clinical trials, is deriving research data from a large number of a homogeneous group of enrolled patients (restricted by inclusion and exclusion criteria). However, in a real world scenario there is high variability and many factors affecting any clinical outcome (disease severity, age, sex, comorbidities, etc).
There is also one more aspect that affects clinical relevance for any real patient population, and is called generalizability, the degree to which you can apply the results of any clinical study to a broader patient population. One good example is that many clinical trials might offer statistical significance and clinical relevance in a restricted study population, but not generalizability.
The use of Real-World Data obtained from daily clinical practice could overcome the previous limitations by allowing clinicians to easily collaborate and aggregate de-identified data. This could lead to the generation of Real-World Evidence that can be considered statistically significant, clinically relevant and generalizable to different patient populations.
RegenMed Circles have been developed with this goal in mind, facilitating data sharing among healthcare practitioners and their industry partners, and putting the patient at the center of their care to advance and progress in any field of medicine and healthcare.
If you want to know more about Circles or how our solutions could help you in different ways, contact us.