Translational Bioinformatics to Enable Precision Medicine for All: Elevating Equity across Molecular, Clinical, and Digital Realms

Abstract

Objectives: Over the past few years, challenges from the pandemic have led to an explosion of data sharing and algorithmic development efforts in the areas of molecular measurements, clinical data, and digital health. We aim to characterize and describe recent advanced computational approaches in translational bioinformatics across these domains in the context of issues or progress related to equity and inclusion. Methods: We conducted a literature assessment of the trends and approaches in translational bioinformatics in the past few years. Results: We present a review of recent computational approaches across molecular, clinical, and digital realms. We discuss applications of phenotyping, disease subtype characterization, predictive modeling, biomarker discovery, and treatment selection. We consider these methods and applications through the lens of equity and inclusion in biomedicine. Conclusion: Equity and inclusion should be incorporated at every step of translational bioinformatics projects, including project design, data collection, model creation, and clinical implementation. These considerations, coupled with the exciting breakthroughs in big data and machine learning, are pivotal to reach the goals of precision medicine for all.

Leveraging electronic health records to identify risk factors for recurrent pregnancy loss across two medical centers: a case-control study

“…Another limitation is that both UCSF and Stanford are academic medical centers in a similar region of California, so patients in these EHR databases are not representative of pregnant individuals in the general population. While our inter-center validation demonstrates some generalizability, further work is needed to assess generalizability in other populations 76,77 . Lastly, there may be diagnosis-specific differences in how often RPL vs Control patients were evaluated for each diagnosis.…”

Leveraging electronic health records and knowledge networks for Alzheimer’s disease prediction and sex-specific biological insights

“…Prior applications of EHRs for studying AD include deep phenotyping of AD 7 , identification of AD-related associations and hypotheses 8 , and models classifying or predicting a dementia diagnosis from clinical data 9 . Data available in clinical records can also better represent a clinician’s knowledge of a patient’s clinical history at a point in time before further diagnostic studies or imaging, allowing a prediction model to be low cost to implement as a first-line application in primary care or for initial risk stratification 10 . While machine learning (ML) has been previously applied to EHRs for general dementia classification and prediction 11 – 14 , these approaches have limitations.…”

Inclusive Digital Health

“…In the Bioinformatics and Translational Informatics (BTI) section's best papers, co-editors Mary Lauren Benton and Scott McGrath observed several important trends, including the use of deep learning approaches to analyze diverse data types, the development of integrative and web-accessible bioinformatics pipelines, and a continued focus on the power of individual genome sequencing for precision health [12]. The survey paper for BTI by Tang et al addresses how equity and inclusion should be incorporated in every step of bioinformatics projects [13]. More work needs to be done in computational biology to include specific groups of patients in algorithms and avoid algorithm bias, and the amount of data available continues to be a challenge.…”