In 2022, India recorded over 1.41 million new cancer cases and more than 916,000 deaths.¹ Behind these staggering numbers lies one of the most diverse patient populations in the world.
Yet, as precision oncology transforms how we approach treatment, a critical question arises: If our clinical data primarily reflects a small, narrow slice of patients, how confidently can we personalize care for everyone else? Personalized cancer care offers a powerful promise: treatment tailored to the individual, not just the diagnosis. But that promise is only as reliable as the evidence backing it up.
Two individuals can receive the exact same cancer diagnosis on paper, but their actual clinical journeys can look completely different.
Consider two hypothetical patients in India: Patient A lives in a metro area, sees a specialist early, undergoes comprehensive biomarker testing, and accesses multiple lines of targeted therapy.
Patient B lives in a peri-urban or rural region, is diagnosed at a later stage, travels hours for care, and faces limited diagnostic or financial options from the outset.
Both of these journeys represent the reality of cancer care in India, and both belong in our national evidence base.
Precision oncology looks far beyond the primary tumor site. Factors like tumor biology, unique genomic biomarkers, prior lines of therapy, comorbidities, treatment adherence, and disease progression all shape a patient’s response. When specific patient populations are left out of real-world datasets, an entire chapter of the clinical story goes missing.
The disparities in cancer presentation across India are not hypothetical. They are documented in clinical literature. For instance, a population-based cancer registry study from Varanasi evaluating 6,721 patients revealed stark rural-urban differences in cancer burden, diagnostic confirmation, incidence, and survival outcomes.² Urban patients had significantly higher rates of clinical and histological confirmation, reflecting systemic differences in early access to advanced diagnostics.
This does not mean every rural or urban patient follows a single template. But it does remind us why oncology research in India cannot rely solely on data gathered within the walls of a few premier, well-resourced urban tertiary centers.
Think about this, if the vast majority of our clinical evidence comes from patients treated in high-resource metropolitan hospitals, what critical insights are we missing about the millions who navigate care through an entirely different route? That gap is the core challenge of representation.
Building representative data is not just about accumulating massive volumes of patient records for the sake of sheer scale. It is about capturing the depth and clinical context needed to make sense of those records.
To truly reflect the patient experience, datasets need to connect several moving pieces:
| Data Parameter | Why It Matters for Precision Care |
| Region & Care Setting | Geographic location heavily dictates access to specialists, molecular testing, and advanced therapies. |
| Stage at Diagnosis | Early-stage and advanced presentations follow radically different clinical pathways. |
| Pathology & Biomarkers | Molecular signatures are the backbone of targeted treatment selection. |
| Complete Treatment History | Knowing what was prescribed is only half the story; dose adjustments, switches, and discontinuations reveal real-world tolerability. |
| Comorbidities | Real-world patients rarely present with cancer alone. Diabetes, cardiovascular issues, or infections significantly alter treatment choices. |
| Long-Term Follow-Up | Longitudinal tracking reveals true survival outcomes, quality of life, and disease progression over time. |
Knowing what therapy a patient received is helpful. But understanding why it was chosen, whether it was modified, how the patient tolerated it, and where they were six months later is where real clinical intelligence lives.
It is easy to confuse volume with variety. A database can store millions of electronic health records and still suffer from severe selection bias, completely missing specific geographies, community hospital settings, socio-economic backgrounds, or real-world treatment patterns. Representation is not just about how big a dataset is; it is about who is visible within it.
In precision medicine, where care decisions are becoming hyper-specific, underlying context becomes everything. Richer, more representative datasets empower researchers and clinicians to answer vital questions:
These are nuanced questions that broad, high-level national averages simply cannot answer.
At Mango Sciences, we believe the true potential of health data lies in its depth, diversity, and real-world relevance. Rather than chasing data for the sake of numbers, our focus is on collaborating directly with healthcare providers, across both tier-1 centers and underrepresented regions, to transform complex clinical records into actionable insights. Through our clinical-grade AI and analytics platform, Querent AI™, we structure rich, multi-source real-world data (RWD) from everyday patient care.
This approach gives clinical journeys the context they deserve: illuminating what happened, why it happened, and how we can use those insights to improve care pathways for the next patient.
As precision oncology advances globally, grounding cancer research in authentic, diverse local evidence is the only way to make innovation truly accessible. Personalized cancer care becomes meaningful only when the evidence behind it reflects all the patients it is meant to serve.