Shivan Sivakumar, associate professor in oncology at the University of Birmingham, explains why we need to move beyond early detection and novel therapies.
I’ve spent much of my career in oncology wrestling with a frustrating reality that while we’ve made remarkable strides in diagnosing cancer, our ability to treat it – especially in the survivorship phase – hasn’t kept pace.
We’ve become very good at finding the specific genetic cancer variations through advanced diagnostics, yet cancer treatment can only target 46 of the 750 known mutations which impact the disease’s progression and recurrence.
This gap leaves patients in a vulnerable state post-treatment, often handed the outdated advice to watch and wait for the cancer to return. It’s a passive approach that fails both patients and clinicians, and I believe it’s time to rethink how we address cancer care, particularly for individuals who have survived cancer.
Addressing the survivorship gap
Artificial intelligence (AI) does not just have a role to play in new drug discovery and diagnostics. It has the potential to have a major impact on drug repurposing, which is a faster, cheaper solution and better for patients.
We need to challenge the conventional narrative that the future of cancer treatment lies solely in developing new drugs. Don’t get me wrong, new therapies are vital, but they often take over a decade and billions of pounds before they’re available. Meanwhile, cancer survivors are left without proactive options to prevent recurrence during a time when intervention could dramatically improve outcomes. This survivorship gap, historically underfunded compared to diagnostics and active treatment, represents our greatest opportunity to change lives. The real breakthrough isn’t in chasing elusive new compounds but in leveraging AI to unlock the potential of existing, well-understood drugs to target patient-specific mutations and delay or prevent the cancer’s return.
Consider the scale of the problem. After surgery or chemotherapy, most cancer survivors, across nearly all cancer types, have no standard maintenance treatment. They’re told to monitor for symptoms and hope for the best. This isn’t just a medical oversight; it’s an emotional burden, leaving patients feeling powerless when agency matters most.
Using AI, it’s possible to bridge the gap by analysing more than 100,000 peer-reviewed research papers to identify low-cost, low-toxicity drugs already on the market that can target the full spectrum of 750 cancer driver mutations. This approach isn’t about replacing active treatment but about extending remission through personalised care that empowers patients beyond watching and waiting.
Leveraging AI
In this context, the power of AI lies in its ability to process vast datasets, including biological, clinical and pharmacological, to uncover connections humans might miss. For instance, a study in the National Institutes of Health (NIH) database suggests that anti-inflammatory drugs may reduce the risk of disease recurrence in breast cancer patients by 42%. What AI can do is identify combinations of existing drugs that can simultaneously target multiple cancer vulnerabilities, say four or five at once, maximising impact while minimising toxicity.
These aren’t speculative treatments; they’re based on existing evidence, repurposed for preventative care in ways that are safe, tolerable and affordable for long-term use. Unlike targeted therapies, which are often too toxic or costly for sustained application, the focus is on drugs that patients can integrate into their lives without the fear of debilitating side effects or financial ruin.
This form of AI not only creates value, it also democratises cancer care by making evidence-based interventions available to more patients sooner. It isn’t about profit through exclusivity, it’s about impact through accessibility.
A patient-centric approach
I’m often asked how this aligns with broader trends in oncology, including diagnostics. While initiatives like the UK’s funding of new blood tests for early cancer detection – capable of identifying 12 common cancers with over 99% accuracy – are transformative, they highlight the same diagnostic-treatment mismatch I’ve described. Early detection saves lives only if paired with effective interventions, yet many patients still face the survivorship gap post-treatment.
Work by companies like Astron Health complements such diagnostic advances by ensuring that once cancer is detected or treated, patients aren’t left without options. Using AI to analyse existing knowledge and focus on therapeutic repurposing to reduce the risk of recurrence is a critical next step after diagnosis.
The patient perspective should drive everything we do. Survivorship isn’t just about surviving; it’s about thriving. Imagine a breast cancer survivor with a specific mutation profile receiving a tailored care plan of repurposed drugs, backed by peer-reviewed evidence, that targets her unique recurrence risks. She’s no longer passively waiting for bad news; she’s actively managing her health with affordable, tolerable medications. This shift could redefine survivorship, reducing not just recurrence rates but also the psychological toll of living in limbo.
Of course, challenges remain. Integrating AI-driven repurposing into clinical practice requires overcoming scepticism from healthcare providers. There’s also the hurdle of regulatory acceptance and payer reimbursement for off-label drug use. Yet, the evidence is mounting – studies like those highlighted by the European Society for Medical Oncology (ESMO) emphasise the need for high-quality survivorship care that addresses physical, psychological and recurrence risks.
The AI-powered future of cancer survivorship
Looking ahead, I envision a future where every cancer survivor benefits from a personalised care plan, tailored by AI to their molecular profile and grounded in existing drugs. The survivorship phase, long neglected, could become the frontier of oncology innovation, as noted in discussions around rethinking cancer care models. If we can address all 750 cancer driver mutations through repurposing, rather than the current 46, we’ll offer a comprehensive shield against cancer, not just a partial one.
To get there, we need a collective shift in mindset from patients and clinicians to policymakers and pharma. We must prioritise survivorship as much as early detection, recognising that the post-treatment phase offers an immediate chance to improve outcomes. As reports like the AACR’s forecasts suggest, AI and precision medicine are poised to advance cancer care in 2025 and beyond, including through innovative therapeutic strategies. Cancer care doesn’t need more waiting; it needs action and AI-driven drug repurposing how we deliver it.
I urge the oncology community to rethink where we invest our resources and focus. Money is poured into early detection and novel therapies, yet survivorship remains an afterthought. Let’s change that by harnessing AI to repurpose existing drugs, giving survivors not just hope but tangible, personalised tools to extend remission. The technology is here, the evidence is growing, and the need is undeniable. It’s time to stop watching and waiting and start acting.
