I am a Nigerian American woman studying computer science at Georgetown University, pursuing a path at the intersection of technology, oncology, and medicine. I chose computer science not simply because I enjoy problem-solving or coding, but because I recognized its potential to address persistent gaps in healthcare, particularly inequities in access, outcomes, and whose perspectives shape medical innovation. Within Georgetown’s computer science department, Black women remain significantly underrepresented. Nationally, Black women make up less than three percent of the computing workforce, and that disparity is reflected in academic spaces. In many of my classes, I am one of very few students who look like me. Rather than discouraging me, this reality clarified my purpose. I wanted to understand how computational systems are built, how algorithms influence decision-making, and how technology can either reinforce inequities or help correct them in medicine. My interest in oncology and translational medicine developed through sustained research experiences across multiple institutions. In the Weiner Lab at Georgetown, I work on pancreatic cancer-focused computational research that directly connects algorithmic design with biological and clinical questions. There, I explicitly developed ApoptiScope, a computational imaging tool designed to quantify apoptosis in three-dimensional tumor models. I was responsible for developing the core code, refining the pipeline, and validating outputs to ensure biological relevance. This work taught me how computational precision and thoughtful design directly shape the quality of cancer research. I have pursued additional research experiences that reinforced my commitment to clinically grounded computation. Through research internships at institutions including Georgetown University, Columbia University, and the University of Cambridge, I have worked on projects examining unintended bias in artificial intelligence, particularly within oncology-related diagnostic systems. These experiences pushed me to think critically about fairness, validation, and accountability in medical AI. Computational tools often show promise in controlled settings but struggle to translate into clinical workflows when they are built without sufficient clinical insight. Working alongside researchers from different disciplines taught me that impactful innovation requires collaboration between computer scientists, clinicians, and patients from the earliest stages of development. This realization solidified my desire to operate fluently in both technical and medical spaces and to bridge the gap between computational optimization and clinical reality. My commitment to community impact is shaped by personal experience and service. As the child of immigrants, I witnessed how navigating healthcare systems can be challenging for families without access to resources or advocacy. Through programs such as CURA and clinical exposure across different hospital wards in Washington, DC, I observed firsthand how social determinants of health influence patient outcomes. These experiences reinforced my belief that technology must be designed with intention and an understanding of the communities it serves. I plan to make an impact by developing computational tools that are clinically usable, ethically grounded, and equitably deployed. Whether through translational cancer research, medical artificial intelligence, or interdisciplinary collaboration between engineers and physicians, my goal is to ensure that advanced technologies move beyond academic settings and into meaningful patient care. I intend to pursue combined medical and research training so I can contribute to both scientific discovery and clinical application. Representation remains central to my goals. Being one of few Black women in computer science and computational oncology comes with responsibility. Through mentorship, visibility, and honest engagement, I hope to inspire the next generation to see themselves in fields where they have historically been excluded. Ultimately, I aim to increase the odds not just for myself, but for those who follow by demonstrating that Black women belong at the forefront of computer science, oncology, and medicine, shaping the future of healthcare with technical excellence and purpose.

Every meaningful decision I have made about my future has been shaped by personal experiences that forced me to grow earlier than I expected. As a Nigerian American woman navigating demanding academic spaces, family expectations, and firsthand exposure to inequities in healthcare, I learned quickly that medicine is not only about scientific knowledge, but also about empathy, accountability, and advocacy. My personal challenges did not push me away from medicine. Instead, they clarified why I am committed to pursuing it. From an early age, I witnessed loved ones navigate fragmented healthcare systems marked by delayed diagnoses, poor communication, and limited care coordination. These experiences became more tangible during my clinical exposure in Washington, DC, where I shadowed oncology patients across different hospital wards. I observed stark differences in care experiences and outcomes between patients in well-resourced settings and those in under-resourced communities, particularly in Wards 7 and 8. Through my involvement with CURA, I learned how social determinants of health, including housing instability, transportation barriers, and access to preventative care, directly shape medical outcomes. Seeing these disparities up close was emotionally challenging, but it also sharpened my sense of responsibility. I realized that medicine cannot be separated from the systems and structures that shape who receives care and how that care is delivered. Academically, I faced moments of self-doubt while balancing a rigorous computer science curriculum alongside pre-medical coursework and research. As a young woman of color in technical and clinical spaces where representation is limited, I often questioned whether I truly belonged. Rather than allowing these doubts to discourage me, I leaned into research as a way to create impact. I created ApoptiScope, a computational imaging tool designed to quantify apoptosis in three-dimensional tumor models. I developed the underlying code, built the image processing pipeline, and iteratively refined the system to ensure it produced reliable and interpretable results. Building ApoptiScope exposed me to the gap between computational innovation and clinical usability. It required me to think beyond algorithmic performance and consider how clinicians interpret data, make decisions, and trust tools placed in front of them. This experience reinforced my desire to pursue medicine as both a clinician and a problem-solver who bridges computational insight with patient-centered care. My personal challenges have shaped the kind of physician I hope to become. They have taught me to listen carefully, to ask better questions, and to remain aware of the systemic forces that influence patient outcomes beyond the exam room. I understand what it means to feel unseen within complex systems, and I carry that awareness into every space I enter. In healthcare, this perspective allows me to advocate for patients whose voices are often overlooked and to design solutions that are both scientifically rigorous and ethically grounded. Medicine, to me, is a commitment to relevance. It requires understanding patients in the context of their lived experiences and using scientific knowledge responsibly to create meaningful change. My journey has prepared me to contribute to healthcare with humility, innovation, and accountability. Through medicine, I aim to help build tools, systems, and relationships that not only treat disease, but also address the inequities that shape health long before a patient ever enters a hospital.

My “pie in the sky” dream is to become a physician-scientist who fundamentally changes how computational tools are built, evaluated, and trusted in healthcare, especially for diseases where time, bias, and inequity cost lives. I want to lead translational research that does not stop at publishing a model or a paper, but actually reshapes clinical decision-making in a way that is ethical, interpretable, and accessible to communities that are too often left behind. This dream was sparked gradually, not by a single moment, but by a series of realizations that kept colliding. As a young Nigerian American woman moving through academic, research, and clinical spaces, I began to notice how invisible certain communities are in the data that drives modern medicine. In research labs, I saw incredibly powerful computational methods capable of extracting insight from complex biological systems. In clinical settings, I saw patients navigating delayed diagnoses, fragmented care, and outcomes that might have been different if tools were designed with their realities in mind. The disconnect between what was technically possible and what was actually reaching patients stayed with me. My research experiences solidified this dream. Working on my creating ApoptiScope in the Weiner Lab at Georgetown, I helped develop a computational imaging tool to quantify apoptosis in 3D tumor spheroid models. The work was deeply technical, iterative, and demanding, but it also showed me the translational potential of well-designed computational systems. Seeing how an algorithm could turn raw imaging data into something biologically and clinically meaningful made the impact of my work feel tangible. Engaging with cancer models, including pancreatic cancer systems with devastating prognoses, made the stakes impossible to ignore. These are not abstract problems. They are life-and-death decisions happening in real time. At the same time, I became increasingly aware of how bias can quietly shape outcomes. Data that excludes certain populations, models optimized without interpretability, and tools that assume ideal clinical settings all contribute to widening disparities. My “pie in the sky” dream is not just to build better algorithms, but to redefine what “better” means in medicine. I want to help create a future where advanced technology serves as a bridge rather than a barrier. To get there, I know the path will be long and uncomfortable. Pursuing an MD/PhD is a central step, allowing me to remain deeply grounded in both clinical training and rigorous research. I will need to continue strengthening my technical foundation in machine learning and data science, while also developing the clinical intuition to ask the right questions and recognize when a tool is failing the people it is meant to help. I will need mentors, collaboration across disciplines, and the humility to keep learning. This dream feels just out of reach because it asks me to occupy multiple worlds at once, to be fluent in computation, medicine, ethics, and advocacy. But it is precisely that stretch that inspires me. I am committed to growing into someone who can sit at those intersections and build systems that reflect not only technical excellence, but care, equity, and courage.

As a young Nigerian American woman and computer science major, my goals are shaped by a desire to use computation as a tool for research, equity, and real-world impact. I am driven by the belief that computer science is most powerful when it is applied intentionally, especially in fields like healthcare where technical decisions can directly affect patient outcomes. My primary computer science goal is to develop strong technical expertise in machine learning, data-driven modeling, and algorithmic systems, while remaining grounded in how these tools function in messy, high-stakes environments rather than idealized datasets. My research experiences have played a central role in shaping this goal. Working in biomedical and oncology-focused research labs has taught me how computational tools can translate raw biological data into meaningful insight. In the Weiner Lab at Georgetown, I created ApoptiScope, a computational imaging tool designed to quantify apoptosis in 3D tumor spheroid models. Through this project, I gained hands-on experience with image analysis, iterative model development, and validating computational outputs against biological ground truth. More importantly, I saw how careful algorithmic design could make experimental results more interpretable and clinically relevant. Engaging with cancer models, including pancreatic cancer systems with notoriously poor prognoses, reinforced my interest in using computation to improve early detection, risk stratification, and treatment monitoring. Beyond the technical work, research exposed me to the broader limitations of current healthcare systems. I observed how fragmented workflows, delayed diagnoses, and biased data disproportionately affect underrepresented communities. These experiences made it clear that strong algorithms alone are not enough. Tools must be designed with accessibility, interpretability, and equity in mind, or they risk reinforcing the very disparities they aim to solve. As someone who exists at the intersection of multiple underrepresented identities, I feel a responsibility to be intentional about who benefits from the technologies I help build. My non–computer science goals are centered on medicine, translational research, and service. I plan to pursue an MD/PhD so I can remain deeply engaged in research while gaining the clinical training necessary to understand patient needs firsthand. I am particularly drawn to oncology and translational science, where computational tools can bridge the gap between experimental discovery and patient care. Medical training will allow me to ask better research questions, evaluate the clinical utility of models, and advocate for technologies that genuinely improve outcomes rather than remaining confined to academic pipelines. In the future, I hope to combine these goals by working at the intersection of computer science, clinical medicine, and research. I want to design computational systems that clinicians can realistically use and trust, while ensuring that they are ethically grounded and equitable. My long-term vision is to work as a physician-scientist leading translational research efforts that integrate machine learning into clinical workflows, particularly for diseases like pancreatic cancer where improved prediction and monitoring could be life-changing. By bridging computational expertise with clinical insight, I aim to help ensure that advances in technology meaningfully benefit underrepresented communities and move healthcare toward a more just and effective future.

One healthcare problem I want to help solve is the failure to identify and intervene early in chronic and high-mortality diseases within under-resourced communities. This gap is especially clear in conditions like pancreatic cancer, where delayed diagnosis and fragmented care often lead to poor outcomes. Too often, patients are not flagged as high risk until their disease has already progressed, and the healthcare system responds reactively rather than preventively. These delays are then framed as unavoidable, when in reality they are shaped by access barriers, care bottlenecks, and inequitable resource allocation. A major reason this persists is how risk is traditionally modeled. Many healthcare risk tools rely heavily on historical utilization and claims data, which reflect access more than true biological risk. Patients who face transportation challenges, limited clinic availability, or inconsistent follow-up may appear low risk simply because they interact less with the system. This leads to underestimation of risk in populations that would benefit most from earlier intervention and contributes to insurance and care inequities. My research experience in the Weiner Lab working on pancreatic cancer has reinforced how interconnected risk truly is. While developing ApoptiScope, a computational imaging tool designed to quantify apoptosis in 3D tumor spheroid models, I saw firsthand how small delays in detection and treatment evaluation can significantly affect downstream outcomes. Translational cancer research makes it clear that biological risk does not exist in isolation. It is shaped by how efficiently data, diagnostics, and clinical decisions move through the healthcare system. Schlosser’s Healthcare Risk Equilibrium framework provides a way to model this reality. Rather than treating risk as a static individual attribute, it allows risk to propagate through networks of care. Missed appointments, delayed referrals, limited access to oncology specialists, and medication gaps all interact to amplify patient vulnerability over time. I would represent this system as a network where nodes include patients, clinics, pharmacies, and neighborhood-level contextual factors, with edges capturing interactions such as visit frequency, no-show rates, and treatment delays. Using iterative risk propagation, baseline clinical risk derived from physiological and diagnostic data is combined with network-driven risk to reach an equilibrium score. Eigenvector-based methods are especially useful here, as they identify structural risk amplifiers within the system. High-centrality nodes often correspond to overloaded clinics or care bottlenecks that disproportionately contribute to late diagnoses and poor outcomes, particularly in aggressive cancers like pancreatic cancer. This approach reframes risk in a way that supports fairness and targeted intervention. By distinguishing biological vulnerability from system-driven risk, healthcare teams can intervene earlier and more appropriately, whether through intensified clinical monitoring, improved care coordination, or structural investments in access. Ultimately, applying these methods allows healthcare systems to move beyond reactive care and toward earlier, more equitable intervention grounded in both biology and system-level insight.