Matthew B Schabath

Easy ensemble classifier-group and intersectional fairness and threshold (EEC-GIFT): a fairness-aware machine learning framework for lung cancer screening eligibility using real-world data

Abstract Background We use real-world data to develop a lung cancer screening (LCS) eligibility mechanism that is both accurate and free from racial bias. Methods Our data came from the Prostate, Lung, Colorectal, and Ovarian (PLCO) cancer screening trial. We built a systematic fairness-aware machine learning framework by integrating a Group and Intersectional Fairness and Threshold (GIFT) strategy with an easy ensemble classifier—(EEC-) or logistic regression—(LR-) based model. The best LCS eligibility mechanism EEC-GIFT* and LR-GIFT* were applied to the testing dataset and their performances were compared to the 2021 US Preventive Services Task Force (USPSTF) criteria and PLCOM2012 model. The equal opportunity difference (EOD) of developing lung cancer between Black and White smokers was used to evaluate mechanism fairness. Results The fairness of LR-GIFT* or EEC-GIFT* during training was notably greater than that of the LR or EEC models without greatly reducing their accuracy. During testing, the EEC-GIFT* (85.16% vs 78.08%, P < .001) and LR-GIFT* (85.98% vs 78.08%, P < .001) models significantly improved sensitivity without sacrificing specificity compared to the 2021 USPSTF criteria. The EEC-GIFT* (0.785 vs 0.788, P = .28) and LR-GIFT* (0.785 vs 0.788, P = .30) showed similar area under receiver operating characteristic curve values compared to the PLCOM2012 model. While the average EODs between Blacks and Whites were significant for the 2021 USPSTF criteria (0.0673, P < .001), PLCOM2012 (0.0566, P < .001), and LR-GIFT* (0.0081, P < .001), the EEC-GIFT* model was unbiased (0.0034, P = .07). Conclusion Our EEC-GIFT* LCS eligibility mechanism can significantly mitigate racial biases in eligibility determination without compromising its predictive performance.

Development of a Culturally Sensitive Intervention for Cervical Cancer Screening Promotion for Latinx Transgender Individuals

ABSTRACT Introduction Trans men and non‐binary people face some of the most challenging cancer health disparities. Primary care physicians could play a key in addressing these, but many clinicians' lack the necessary skill to discuss cervical screening with trans people as these are not routinely taught in medical school. Thus, the objective of this study was to develop an intervention to foster medical students' skills for cervical cancer screening and to examine its initial impact and feasibility. Methods Our research team is comprised of academic researchers, clinicians, and community members. Together, we developed a 2‐h intervention which we implemented using Standardized Patient Simulations (TM actors portraying the role of a TM patient) to observe provider behaviors (general care behaviors, gender affirming behaviors and cervical cancer preventive behaviors) and self‐reported measures to examine study outcomes. The total sample consisted of 37 third‐year medical students. Welch's t ‐test was used to compare the intervention effects on all outcomes. Results Results suggest the intervention had medium to large effects on all examined behaviors. Behaviors improved in the experimental group compared to the control group and all changes were statistically significant. In general, the intervention was seen as feasible and appropriate with participants mentioning it was “very helpful” and emphasizing the importance of discussing trans health care as part of their medical training as this improves their “confidence.” Discussion Although the sample size was small, results show a potentially promising intervention. We provide an overview of the content of the intervention and discuss future research directions.