As we see an ever-increasing shift toward implementing Artificial Intelligence into our everyday lives, keeping humans involved in research and clinical trials is essential. 

Impactful studies that generate evidence used to influence policy and clinical decision-making are often limited in size due to budget, time frame, and capacity to engage and nurture relationships with study participants. For example, in our study about environmental associations with high preterm birth rates in Puerto Rico the number of participants in the study may be too small for many AI methods small, but the data collected is incredibly rich with information. 

The ability to tease out the importance of this data isn't found in an off-the-shelf AI application but rather in a data scientist who can thoughtfully and ethically extract information from this data to provide the most reliable evidence. 

The problem: Health data analyses require a nuanced understanding and a keen human eye to view and understand the patterns and outcomes that could be highly impactful, beyond the frequent goal of AI models: prediction at all costs.  

The solution: While AI can be great for massive datasets in a clinical study, s(human) data scientists shine in situations that need a nuanced understanding of the gray area of healthcare