Data Collection Theory in Healthcare Research: The Minimum Dataset in Quantitative Studies

There is considerable interest in data analytics because of its value in informing decisions in healthcare. Data variables can be derived from routinely collected records or from primary studies. The level of detail for individual variables in quantitative studies is often disregarded. In this work, we aim to present the concept of a minimum dataset for any variable. The most basic level of data collection is the value of a variable. In addition, there may be an indicator of severity and a measure of duration or how long the value has been present. The time course defines how the values for a variable fluctuated over time. The validity or accuracy of the values for a variable is also important to avoid spurious findings. Finally, there may be additional modifiers which drastically change the impact of a variable. In conclusion, the minimum dataset is a framework which can be used for the purposes of study design and appraisal of studies. Not all data requires full consideration of the minimum dataset framework for each variable, but the framework may be important if more detailed results are desired.