Sensitivity Analyses of a Scoring System for a Contraception Decision Aid

Area of Science:

• Reproductive Health
• Health Informatics
• Decision Science

Background:

• Transgender and gender-nonconforming (TGNC) individuals assigned female at birth (AFAB) require tailored contraception decision support.
• Existing decision aids may not adequately address the specific needs of TGNC AFAB individuals.
• Formal validation of decision support systems is crucial for clinical utility.

Purpose of the Study:

• To conduct formal analyses of a scoring system for a contraception decision aid.
• To support transgender and gender-nonconforming (TGNC) assigned female at birth (AFAB) individuals in their contraceptive choices.
• To develop and validate a methodology for assessing decision factors and system recommendations.

Main Methods:

• Development of a methodology framework for assessing decision factor weights.
• Conducting univariate and multivariate sensitivity analyses.
• Utilizing data visualization to identify critical values in weight assignment.

Main Results:

• Successful identification of critical values in weight assignment that influence system recommendations.
• Contributions to the development and validation of the decision aid's knowledge base.
• Enabled provision of explainable recommendations and informed future research directions.

Conclusions:

• The developed methodology is critical for validating decision support systems for TGNC AFAB individuals.
• Sensitivity analyses enhance the reliability and explainability of contraceptive recommendations.
• Further research is needed to explore advanced analyses and generalizability to other applications.