To create markets that are both efficient and inclusive, platform designers need to be mindful of the potential for discrimination and open to experimentation as they make choices about automation, algorithms, and the use of identifying data.
Specifically, codes were used in place of identifying data and it was ensured that samples of text taken from answers to open questions did not include information that might help to identify the corresponding participant.
All statistical analyses were conducted using SPSS, and t test was used to identify data of any significance within the treatments at P value ≤ 0.05.
Each set of notes was used to identify data on patient age, sex, diagnosis, reported symptoms, medications prescribed, length of stay and outcome.
For example, time for first appointment, reasons/thoughts on weighing and not weighing, weight gain advice, referrals, barriers to weighing, support, health consequences etc. Anonymity of participants was maintained through the use of de - identified data.
However, when attributing risk to the proposed use of identified specimens and data, responses were more heterogeneous.
Formal written parental or patient consent was obtained for the use of any potentially identifying data.
Additionally, this study received an exemption waiver from the University of Massachusetts's Institutional Review Board for the use of previously collected and de-identified data.
Despite this fact, the use of refill data identified a higher percentage of patients with inadequate compliance than electronic monitoring.
As such, the findings from this study are relevant to other similar surveillance systems in terms of approaches for interrogating text data, with similar issues regarding the use of text data identified by researchers using these other systems [ 10].
