For Dr. Tina Hernandez-Boussard, solving health care inequities is only possible when the people who collect, analyze and interpret data to make decisions are as diverse as those affected by those decisions.

While data science can offer important insights into the problems we face, data analytics techniques only provide answers from the data we feed, said Dr. Tina Hernandez-Boussard. Mrs. When these data are unbalanced, the models perform poorly for different populations. (Steve Fisch/Stanford Medicine)

Growing up in a rural community, Tina Hernandez-Boussard never thought she would earn a doctorate, much less that she would be at the forefront of a new field aimed at solving inequities in our healthcare system. through data science. However, with the support of a mentor who recognized her potential and encouraged her, Dr. Hernandez-Boussard, now a professor of medicine and biomedical data science at Stanford University, is leading efforts using the data in medicine to better serve people of all demographic groups, not just those who have traditionally been the focus of biomedical research.

For Hernandez-Boussard, solving inequities within our health system is only possible when we ensure that the people who collect, analyze and interpret data to make decisions are as diverse as those who will be affected by those decisions. . Not only does this make health care fairer, but it also creates more empathetic medicine. By fusing health and data science, Hernandez-Boussard is uniquely positioned to understand both the challenges and opportunities in biomedicine that she and other advocates for equity in healthcare face. In the wake of a pandemic that has drawn attention to the many inequities in our healthcare system for minority and low-income populations, addressing these issues is not just an academic endeavor, but a matter of life or dead.

As Hernandez-Boussard observed at last month’s Women in Data Science conference at Stanford University, one of the biggest challenges facing data science in healthcare is also its biggest opportunity. : creating datasets that include populations and perspectives traditionally excluded from medicine and medical research. Although data science can offer important insights into the problems we face, Hernandez-Boussard reminds us that data analysis techniques, like natural language processing (an interdisciplinary approach to computer science that scratches the human language for data) and machine learning, only provide answers learned from the data we feed. When these data are unbalanced, the models perform poorly for different populations.

For example, the Boussard Lab has worked to identify depressive symptoms in cancer patients undergoing chemotherapy. While it is relatively straightforward to capture the symptoms of severely depressed patients, intermediate symptoms are less easy to discern, particularly among diverse populations who may express these symptoms or feelings differently and who have not traditionally been the subject of research. Various data scientists have the knowledge to understand how people might communicate these symptoms across culture, gender, race, language, and socioeconomic groups. To ask the right questions, data science needs to have diverse problem-solving teams that can better understand the voice of patients.

One of the best ways to improve data-driven medicine, Hernandez-Boussard says, is to ensure that diverse teams of scientists and clinicians are thinking about the right questions to ask. For example, Hernandez-Boussard recalls the time a hospital asked for an algorithm to predict missed appointments. Rather than simply creating such an algorithm, Hernandez-Boussard’s team challenged the hospital to think about why they wanted to predict no-shows instead of using data to find ways to reduce the barriers that prevent patients from keeping their appointments. In this case, what “worked best” for the hospital perpetuated circumstances that restricted certain populations’ access to health care.

To ask the right questions, data science needs to have diverse problem-solving teams that can better understand the voice of patients.

Working with diverse populations allows scientists to challenge preconceived notions of symptoms, diseases, and treatments, while enabling practitioners and patients to work together to overcome histories of harm and misinformation. For data science to effectively address the challenge of unraveling biases in healthcare, the task requires an additional kind of diversity. Not only do data scientists need to ensure that diverse patient voices are better integrated into health systems, but data science as a field must also seek out strategies to create team science problem solving approaches.

In addition to ensuring diversity of gender, race, ethnicity and ability in biomedical data science, Hernandez-Boussard stresses the importance of diversity of background, profession and field of study among the teams of those who study problems in medicine. Collaboration across fields is essential, as the complexities of contemporary science and the issues facing health care require multidisciplinary relationships; with computer scientists partnering with clinicians, engineers working with statisticians and social scientists contributing insights from qualitative research.

Data scientists can only meet the challenge of healthcare inequity and become more collaborative and creative problem solvers by listening to the diverse voices of patients and engaging in conversations with those pushing them out of their zone. of comfort. As lives continue to be lost due to incomplete datasets and resolved solutions, Hernandez-Boussard’s efforts to diversify healthcare data have the potential to save the lives of many who have traditionally been overlooked by medicine.

If you found this article helpful, please consider supporting our Independent Reports and Truth Statement for as little as $5 per month.

Following: