Diversity and Representation Among United States Participants in Amgen Clinical Trials.

OBJECTIVE: Describe the demographic profile of US participants in Amgen clinical trials over a 10-year period and variations across therapeutic areas, indications, and geographies. METHODS: Cross-sectional retrospective study including participants enrolled (2005-2020) in phase 1-3 trials completed between January 1, 2012 and June 30, 2021. RESULTS: Among 31,619 participants enrolled across 258 trials, one-fifth represented racial minority populations (Asian, 3%; Black or African American, 17%; American Indian or Alaska Native, Native Hawaiian or Other Pacific Islander, multiracial, each < 1%); fewer than one-fifth (16%) represented an ethnic minority population (Hispanic or Latino). Compared with census data, representation of racial and ethnic groups varied across US states. Across most therapeutic areas (bone, cardiovascular, hematology/oncology, inflammation, metabolic disorders, neuroscience) except nephrology, participants were predominantly White (72-81%). A similar proportion of males and females were enrolled between 2005 and 2016; male representation was disproportionately higher than female between 2016 and 2020. Across most medical indications, the majority of participants were 18-65 years of age. CONCLUSIONS AND RELEVANCE: While the clinical research community is striving to achieve diversity and proportional representation across clinical trials, certain populations remain underrepresented. Our data provide a baseline assessment of the diversity and representation of US participants in Amgen-sponsored clinical trials and add to a growing body of evidence on the importance of diversity in clinical research. These data provide a foundation for strategies aimed at supporting more equitable and representative research, and a baseline from which to assess the impact of future strategies to advance health equity.

Data-driven strategies for increasing patient diversity in Bristol Myers Squibb-sponsored US oncology clinical trials.

BACKGROUND/AIMS: Determining whether clinical trial findings are applicable to diverse, real-world patient populations can be challenging when the full demographic characteristics of enrolled patients are not consistently reported. Here, we present the results of a descriptive analysis of racial and ethnic demographic information for patients in Bristol Myers Squibb (BMS)-sponsored oncology trials in the United States (US) and describe factors associated with increased patient diversity. METHODS: BMS-sponsored oncology trials conducted at US sites with study enrollment dates between 1 January 2013 and 31 May 2021 were analyzed. Patient race/ethnicity information was self-reported in case report forms. As principal investigators (PIs) did not report their own race/ethnicity, a deep-learning algorithm (ethnicolr) was used to predict PI race/ethnicity. Trial sites were linked to counties to understand the role of county-level demographics. The impact of working with patient advocacy and community-based organizations to increase diversity in prostate cancer trials was analyzed. The magnitude of associations between patient diversity and PI diversity, US county demographics, and recruitment interventions in prostate cancer trials were assessed by bootstrapping. RESULTS: A total of 108 trials for solid tumors were analyzed, including 15,763 patients with race/ethnicity information and 834 unique PIs. Of the 15,763 patients, 13,968 (89%) self-reported as White, 956 (6%) Black, 466 (3%) Asian, and 373 (2%) Hispanic. Among 834 PIs, 607 (73%) were predicted to be White, 17 (2%) Black, 161 (19%) Asian, and 49 (6%) Hispanic. A positive concordance was observed between Hispanic patients and PIs (mean = 5.9%; 95% confidence interval (CI) = 2.4, 8.9), a less positive concordance between Black patients and PIs (mean = 1.0%; 95% CI = -2.7, 5.5), and no concordance between Asian patients and PIs. Geographic analyses showed that more non-White patients enrolled in study sites in counties with higher proportions of non-White residents (e.g. a county population that was 5%-30% Black had 7%-14% more Black patients enrolled in study sites). Following purposeful recruitment efforts in prostate cancer trials, 11% (95% CI = 7.7, 15.3) more Black men enrolled in prostate cancer trials. CONCLUSION: Most patients in these clinical trials were White. PI diversity, geographic diversity, and recruitment efforts were related to greater patient diversity. This report constitutes an essential step in benchmarking patient diversity in BMS US oncology trials and enables BMS to understand which initiatives may increase patient diversity. While complete reporting of patient characteristics such as race/ethnicity is critical, identifying diversity improvement tactics with the highest impact is essential. Strategies with the greatest concordance to clinical trial patient diversity should be implemented to make meaningful improvements to the diversity of clinical trial populations.

Deep Learning With Electronic Health Records for Short-Term Fracture Risk Identification: Crystal Bone Algorithm Development and Validation.

BACKGROUND: Fractures as a result of osteoporosis and low bone mass are common and give rise to significant clinical, personal, and economic burden. Even after a fracture occurs, high fracture risk remains widely underdiagnosed and undertreated. Common fracture risk assessment tools utilize a subset of clinical risk factors for prediction, and often require manual data entry. Furthermore, these tools predict risk over the long term and do not explicitly provide short-term risk estimates necessary to identify patients likely to experience a fracture in the next 1-2 years. OBJECTIVE: The goal of this study was to develop and evaluate an algorithm for the identification of patients at risk of fracture in a subsequent 1- to 2-year period. In order to address the aforementioned limitations of current prediction tools, this approach focused on a short-term timeframe, automated data entry, and the use of longitudinal data to inform the predictions. METHODS: Using retrospective electronic health record data from over 1,000,000 patients, we developed Crystal Bone, an algorithm that applies machine learning techniques from natural language processing to the temporal nature of patient histories to generate short-term fracture risk predictions. Similar to how language models predict the next word in a given sentence or the topic of a document, Crystal Bone predicts whether a patient's future trajectory might contain a fracture event, or whether the signature of the patient's journey is similar to that of a typical future fracture patient. A holdout set with 192,590 patients was used to validate accuracy. Experimental baseline models and human-level performance were used for comparison. RESULTS: The model accurately predicted 1- to 2-year fracture risk for patients aged over 50 years (area under the receiver operating characteristics curve [AUROC] 0.81). These algorithms outperformed the experimental baselines (AUROC 0.67) and showed meaningful improvements when compared to retrospective approximation of human-level performance by correctly identifying 9649 of 13,765 (70%) at-risk patients who did not receive any preventative bone-health-related medical interventions from their physicians. CONCLUSIONS: These findings indicate that it is possible to use a patient's unique medical history as it changes over time to predict the risk of short-term fracture. Validating and applying such a tool within the health care system could enable automated and widespread prediction of this risk and may help with identification of patients at very high risk of fracture.