Search

Despite ethical and historical arguments for removing race from algorithms, the consequences of this practice for medical decision-making remain unclear. Eliminating race corrections can have unintended consequences: it can decrease both accuracy and equity, because structural racism distorts the measurement of many variables. We illustrate this using the example of family history of colorectal cancer commonly used in cancer screening. Using data from the Southern Community Cohort Study (SCCS), established to study cancer disparities, we analyze 77,836 adults with no history of colorectal cancer at baseline. First, we compare the prognostic value of self-reported family history for self-reported Black vs. White participants and find that family history is strongly predictive of cancer risk for White, but not Black participants. We then create two screening algorithms that model colorectal cancer risk. The baseline algorithm is race-blind, while the race-corrected algorithm adds Black race both as a main effect and as an interaction family history. The race-corrected algorithm improves upon the race-blind algorithm in a likelihood ratio test (p-value

Supplemental Figure 1. Patient inclusion and exclusion criteria. TNBC: triple negative breast cancer; ALC: absolute lymphocyte count; nSES: neighborhood socioeconomic status. Supplemental Figure 2a and 2b. Association between minimum lymphocyte count (as percentage of total white blood cell count and absolute value) and stromal tumor infiltrating lymphocytes (sTILs), N=77. Figure 2a. sTILs were correlated with minimum % lymphocyte (p=0.02). Figure 2b. sTILs did not have a significant correlation with minimum absolute (abs) lymphocytes (p=0.36) Supplemental Figure 3. Comparison between Absolute Lymphocyte Count (ALC) and percent peripheral lymphocytes Supplemental Figure 4. Distribution of Absolute Lymphocyte Count (ALC) measures at baseline, defined as ALC value measured within the first three months of breast cancer diagnosis. Supplemental Figure 5. Distribution of minimum Absolute Lymphocyte Count (ALC) values at any time point Supplemental Figure 6. Distribution of overall minimum Absolute Lymphocyte Count (ALC) over time Supplemental Table 1. Multivariable analysis of predictors of lymphopenia (absolute lymphocyte count [ALC]

Purpose: Tumor-infiltrating lymphocytes (TIL) in pretreatment biopsies are associated with improved survival in triple-negative breast cancer (TNBC). We investigated whether higher peripheral lymphocyte counts are associated with lower breast cancer–specific mortality (BCM) and overall mortality (OM) in TNBC.Experimental Design: Data on treatments and diagnostic tests from electronic medical records of two health care systems were linked with demographic, clinical, pathologic, and mortality data from the California Cancer Registry. Multivariable regression models adjusted for age, race/ethnicity, socioeconomic status, cancer stage, grade, neoadjuvant/adjuvant chemotherapy use, radiotherapy use, and germline BRCA1/2 mutations were used to evaluate associations between absolute lymphocyte count (ALC), BCM, and OM. For a subgroup with TIL data available, we explored the relationship between TILs and peripheral lymphocyte counts.Results: A total of 1,463 stage I–III TNBC patients were diagnosed from 2000 to 2014; 1,113 (76%) received neoadjuvant/adjuvant chemotherapy within 1 year of diagnosis. Of 759 patients with available ALC data, 481 (63.4%) were ever lymphopenic (minimum ALC n = 70) showed a significant association between TILs and higher peripheral lymphocyte counts during neoadjuvant chemotherapy.Conclusions: Higher peripheral lymphocyte counts predicted lower mortality from early-stage, potentially curable TNBC, suggesting that immune function may enhance the effectiveness of early TNBC treatment. Clin Cancer Res; 24(12); 2851–8. ©2018 AACR.

The use of machine learning (ML) in health care raises numerous ethical concerns, especially as models can amplify existing health inequities. Here, we outline ethical considerations for equitable ML in the advancement of health care. Specifically, we frame ethics of ML in health care through the lens of social justice. We describe ongoing efforts and outline challenges in a proposed pipeline of ethical ML in health, ranging from problem selection to post-deployment considerations. We close by summarizing recommendations to address these challenges., Comment: Annual Reviews in Biomedical Data Science 2021