Consideration for Assessing Data/Models/Tools Expiration Supporting Drug Development and Clinical Decision Making

Abstract

Decision making of any kind is informed by data and often by models, tools or other solutions built from data. Data are evaluated for such purposes within a specific context of use (COU) but implicitly we often believe the data to be relevant, accurate and of high quality. In reality, this is not always the case. The status of data for various COUs must constantly be revisited for relevance and information value over time. Using drug development as an example, we postulate that there are indeed occasions where data value diminishes over time and consideration for data expiration with respect to its relevance for decision making should be entertained and at least identified with respect to a time-dependent change in status. Other situations exist which will also necessitate periodic review and condition reassessment. For example, considerations for patient privacy and consent along with compliance to regulatory standards must factor into future recommendations as well. Actions regarding data expiration are proposed as initial thoughts to be expanded upon but this assessment is primarily an attempt to explore factors which impact opinions about data information value for both drug development and clinical decision making.

Keywords: Clinical decision making; Data expiration; Drug development; Regulatory science.

Figure 1

Standard pathway from data to clinical decision-making. Data refers to information gathered during research. Evidence refers to curated data. Guidance refers to evidence presented to support decision-making (this is a combination of explicit guidance among health care professionals, implicit frameworks such as personal algorithms based on experience, and decision support tools). Decision refers to the process of selecting a course of action by synthesizing guidance with the information relating to the specific circumstances of a clinical case. Aggregation includes means of groups, single study conclusions, conclusions from multiple studies. Deduction refers to applying data or evidence within the study population(s). Inference refers to applying data or evidence beyond the study population(s)–generalizability. Pattern-matching refers to the generation and deployment of consistent relationships between information.