Not enough oncologists, nurses, pathologists, physicists

There are far too few genetic counsellors. A validated chatbot can do the standard pre-test education, leaving people with complex needs for humans.

Malnutrition is the commonest untreated complication in cancers of the gut, throat and pancreas. Putting a dietitian in the meeting where treatment is decided means it is seen and treated before chemotherapy starts, not after weight has been lost.

AI tools that write clinic notes are spreading fast in cancer clinics. Test them properly: do they save time, do they make mistakes about drugs and doses, and do patients notice a difference?

Test head to head whether an AI that reads the record and the evidence recommends treatments as well as a panel of experts, and whether patients do as well.

Rare cancers are often misdiagnosed, which sends patients down the wrong treatment path. Digital slide sharing could get every case to an expert within days.

Radiation therapists, the staff who deliver daily treatment, can be trained to outline normal organs on scans and to review patients during treatment, work that oncologists now do.

Most screening CT scans are normal. Letting a validated AI clear them, and sending only flagged scans to a radiologist, would let screening scale without more radiologists.

Let validated AI make the first read on routine, high-volume samples like cervical smears and standard breast biopsy stains, so scarce pathologists spend their time on the difficult cases.

Oncologists spend hours a day typing notes. Software that listens to the consultation and drafts the note, the letter and the orders could return that time to seeing patients.

Training a specialist doctor takes ten years or more. Mid-level clinicians can be trained in eighteen months to run protocol-based cancer care under supervision, and there are far more of them.

No one knows exactly how many oncologists, nurses, physicists and pathologists each country has or needs. A public, regularly updated model would let governments plan training and spot shortfalls years ahead.

Most cancer drug approvals depend on a handful of facts already in the chart, such as the diagnosis, biomarker and line of therapy; sending those automatically in a standard format would return most decisions before the patient leaves the room.

Millions of community health workers already visit homes for vaccines and maternal care. Training them to recognise cancer warning signs, guide patients through the system and support home pain care would reach people no hospital does.

Pharmacies are everywhere and open late. They could give HPV vaccines, hand out bowel test kits, run stop-smoking clinics and offer HPV self-sampling under one roof.

Thousands of oncologists trained in poorer countries now work abroad. A structured programme could let them join weekly video case conferences for hospitals back home, improving decisions at almost no cost.

Many countries have one oncologist for millions of people. Train nurses and general doctors to deliver protocolised cancer care with software checks and remote specialist oversight.

Make the first project of every cancer biology doctoral student a funded, pre-registered attempt to repeat a published finding chosen from a curated list of translationally relevant results, with the outcome published in a replication registry. Students learn power analysis, blinding and reporting, and the field gets thousands of replications a year.

Cancer is an evolving population, but treatment decisions are rarely made with an evolutionary biologist present. Add one to the weekly meeting and see whether decisions change.

If a practice's requests are approved almost every time, asking again wastes everyone's money; gold-card rules give such practices automatic approval and audit them instead.

Trained cancer doctors and nurses who have fled conflict or moved countries often spend years unable to practise. A short, competency-based route back to work would add capacity quickly.

Patients are more likely to join a trial when the doctor offering it looks like them or works in their community. Funding more such doctors to become trial leaders would change who is enrolled.

Almost no surgeons or radiation oncologists have time or funding to do research. Dedicated training awards with protected time would build the workforce that surgical and radiotherapy trials need.

Under-the-skin versions of atezolizumab, nivolumab and pembrolizumab take minutes rather than an hour and need no infusion chair, so they can be given by a nurse near home, cutting facility fees and travel.

Doctors who could turn discoveries into trials are buried in clinical work. Hospitals would guarantee them research time and recover the cost from the trials and grants they bring in.

Uganda makes liquid morphine from powder in a simple facility and lets trained nurses prescribe it, giving pain relief to patients that no doctor will ever reach. Other countries could copy this within a year.

Pembrolizumab 400 mg every six weeks is approved and works like 200 mg every three weeks, and it halves the number of clinic visits, infusion chairs and travel days without changing the drug bill.

When a trial changes the standard of care, every oncologist would receive a five-minute, case-based lesson within a month, rather than waiting for the next conference.

Trained nurses following strict written protocols can safely run chemotherapy clinics for common cancers, with an oncologist available by video for decisions and problems.

Most follow-up visits after successful treatment are routine. Nurse practitioners can run them well, giving survivors more time and oncologists more capacity for new patients.

A phone app that works without internet and guides a general doctor or nurse through diagnosing and treating common cancers with the drugs actually available locally.

Let specially trained cancer pharmacists prescribe anti-sickness drugs, growth-factor support and routine dose adjustments under protocols, freeing oncologists for decisions only they can make.

There are too few genetic counsellors to see every patient who should have an inherited-risk test. Let the cancer team order the test with a short consent script, and use video counsellors for those with results that matter.

Medical physicists, who keep radiotherapy machines accurate and safe, are in even shorter supply than oncologists in under-resourced systems. Routine linac quality assurance is now largely automated and log-file based, so one physicist could review it remotely while trained radiation therapists take the measurements, covering three to five machines once regulators define the supervision standard.

Train and pay people who have been through cancer to guide newly diagnosed patients through the system, especially where oncologists and nurses are scarce.

Much of a pathologist's day is preparation, measuring and describing specimens. Trained assistants can do that, and AI can pre-screen slides, so each pathologist reports far more cancers.

Project ECHO is a weekly video class where district doctors and nurses present real cases to a specialist team, learn by doing, and build a network. It worked for hepatitis C and could work for cancer.

Every targeted result on this roadmap depends on a test happening fast enough to act on. In England nobody publishes what share of lung cancers are tested, how long the test takes, or, in Wales and Northern Ireland, how long the lung pathway takes at all.

Half of cancer patients need radiotherapy and most of the world cannot get it. Commit to low-cost machines, automated planning and trained staff so that access is universal by 2040.

Rather than sending a handful of trainees to Europe or America, build a few large training centres in Africa and South Asia that train the whole team together, with local case mix and local costs.

Radiation oncologists and physicists from poorer countries who train abroad commonly emigrate, and money alone does not keep them. A package combining a return-of-service bond, salary top-ups, a guarantee of working equipment, academic links and a predictable career path, co-funded by government and donors, should be trialled with five-year retention measured.

Not every survivor needs to see an oncologist every six months for years. Sort people by recurrence risk, send low-risk survivors back to their family doctor with a clear plan, and guarantee rapid return if something changes.

Sweden's MASAI trial showed AI can safely replace one of two radiologists. Rolling it out region by region in a randomised order would prove it works at national scale and that interval cancers do not rise.

Hospitals without enough physicists could upload scans to a shared planning centre, where AI drafts the treatment plan and remote experts finish and check it within a day.

Hospitals rarely know which step, the scanner, the biopsy, the pathologist or the clinic slot, is causing the queue. Modelling the pathway like a factory line shows where a small change would remove weeks of waiting.

In much of Africa and South Asia there is about one pathologist per million people, so the pathologist, not the tissue sample, is the diagnostic bottleneck. A slide scanner in each district lab, routing images to a pooled roster of pathologists including diaspora volunteers, could give a diagnosis in days instead of months; the gap is scale and financing.

Surgery cures more cancers than any other treatment, but most district hospitals refer everything to a distant centre. Train and mentor general surgeons to do common cancer operations well, with specialists checking results.

Lymphoma is among the most curable common cancers where the drugs exist. Rituximab is thirty years old and still out of reach for many of the people who need it.

Give the nurses and pharmacists who take patients' calls a tool that walks them through recognising and managing side effects of modern cancer drugs, including when to escalate.

Give oncologists and cancer nurses the training, time and production support to reach people where they actually get information, on social video and podcasts.

The only randomised trial of screening colonoscopy cut bowel cancer by 18 percent because only 42 percent of the people invited turned up. A test that is 20 percent more sensitive but is taken by the same people buys far less than an invitation that 20 percent more people accept.

Poorer patients with lung cancer are less likely to be offered surgery or chemotherapy, at the same stage, in systems that are free at the point of use. That is a fixable problem in how care is delivered, not a fact about the disease.

Postdocs who make a translatable discovery usually leave it behind when their contract ends. A two-year fellowship with salary, a project budget of $250,000 to $500,000 and mentors from drug development, regulation and the clinic would pay them to turn it into a candidate drug, diagnostic or device, with the option to license it or found a company.

Every positive stool test in England, from the screening programme and from the symptomatic pathway, ends in a colonoscopy. The thresholds have been lowered faster than the capacity to act on them, and who performs the test decides whether it prevents anything.

Drawing targets and planning radiotherapy takes hours of scarce expert time. Properly tested AI could do much of it, letting the same staff treat far more patients, if regulators and payers set clear rules for proving and paying for it.

A large trial showed that palliative care delivered by video works as well as in person for people with advanced lung cancer. Payers should cover it so that distance from a hospital no longer decides who gets it.

In Kerala, trained community volunteers, backed by nurses and doctors, provide most home palliative care to the dying. The model reaches more people at lower cost than any clinic-based service and could be copied.