From drug lists to decisions: Why Oncology needs better patient selection guidance

In oncology, knowing which treatments exist is not enough. Clinicians need to know which patients should receive each therapy and why. Living Algorithms focus on patient selection, helping translate options into clear, real-world decisions at the point of care.

The problem with treatment lists

Most oncology resources are good at listing options. They tell you:

• Which drugs are available

• What trials support them

• Where they fit in guidelines
  

But when you're preparing for a consult, that’s not the question you're asking. You're asking: which of these options is right for this patient?

Where the real decision happens

In practice, treatment selection is not just about availability. It depends on:

• Disease characteristics

• Prior therapies

• Patient fitness

• Treatment goals
  

Even when multiple therapies are appropriate, they are not interchangeable.

Choosing between them requires judgment.

A common scenario

Consider a patient with advanced disease. You may be deciding between:

• Hormonal therapy

• Chemotherapy

• Targeted therapy

• Radioligand therapy

• Immunotherapy
  

All are valid options in the right setting.

But the key question is: who gets what, and when?

Why this is harder than it seems

Multiple reasonable options

Many scenarios do not have a single "correct" answer. Instead, there are:

• Several acceptable pathways

• Tradeoffs between efficacy and toxicity

• Differences in timing and sequencing
  

Limited head-to-head data

Most treatments are not directly compared. Clinicians must:

• Interpret separate trials

• Compare outcomes indirectly

• Apply results to their patient
  

Patient variability

Real-world patients differ in meaningful ways:

• Performance status

• Comorbidities

• Prior toxicities

• Preferences and goals
  

These factors often determine the final decision.

What’s missing from most tools

Most tools present treatments without enough context. They show:

• What options exist
  

But not:

• Which patients benefit most

• When to choose one option over another

• How to think through the decision
  

This leaves clinicians to fill in the gaps.

What clinicians actually need

At the point of care, clinicians want clarity on:

• Best candidates for each therapy

• Clinical scenarios where a treatment is preferred

• Situations where an option should be avoided

• Key factors that drive the decision
  

In other words: not just options, but selection

How Living Algorithms approach patient selection

Living Algorithms are designed to solve this exact problem.

What that looks like in practice

Patient-centered pathways

Instead of starting with drugs, you start with:

• Biomarkers

• Stage

• Disease burden

• Prior treatments
  

This immediately narrows the decision space.

Clear decision drivers

For each treatment, you can understand:

• Which patients are best suited

• What clinical factors matter

• How different options compare in context
  

Practical guidance

Selection is tied to real-world considerations:

• Patient fitness

• Treatment goals (curative vs palliative)

• Tolerance for toxicity

• Prior exposures
  

More than one "right" answer

In many cases, Living Algorithms show:

• Multiple reasonable options

• When each is appropriate

• How to think through the tradeoffs
  

This reflects real clinical practice.

A more realistic model of decision making

Oncology decisions are rarely binary. They involve:

• Balancing risks and benefits

• Interpreting incomplete data

• Adapting to individual patients
  

Tools should reflect that complexity.

From options to decisions

There is a difference between:

• Knowing what exists

• Knowing what to do
  

Treatment lists inform, but patient selection guides.

Why this matters more now

Oncology is becoming more complex:

• More therapies

• More biomarkers

• More combinations
  

At the same time:

• Time per patient is limited

• Expectations for precision are higher
  

The cost of unclear decision-making is increasing.

Supporting both trainees and experienced clinicians

Trainees

Need help understanding:

• How to approach decisions

• Why one option is chosen over another
  

Community oncologists

Need:

• Fast, practical guidance

• Support across multiple disease types
  

Specialists

Benefit from:

• Structured confirmation

• Clear comparison of options
  

Bottom line

In oncology, decisions are driven by patient selection, not just treatment availability.

Clinicians need tools that go beyond listing options and help answer:

• Who should get this therapy?

• When should I use it?

• Why is it the right choice here?
  

Living Algorithms are built to provide this clarity, helping clinicians move from options to decisions with confidence.

Try it in practice

The next time you review a treatment pathway, ask: do I know which patients this applies to?

If not, the information is incomplete.

That's where better decision support makes the difference.