Table 1

Opportunities and challenged of big data in clinical research

High volumeLarge sample sizes and high statistical powerData may be too large to store and process on a single computer, achievable with cloud computing.
High velocityCan generate timely, relevant researchRisk of getting swamped with new data.
High varietyPotential to use novel sources of data, for example, images, smart devices, genomicsMay need conversion into a usable format
e.g. free text from medical notes to structured data.
Real worldReflects real-world patients and clinical practiceData often messy with missing data, needs lots of work to make research ready.
Not collected for researchCosts less to collect dataMay not contain all the information you want, outcome data may be unavailable and not adjudicated.