Can improvement and innovation save the NHS? A lecture by Prof Mary Dixon Woods

A highly recommended watch for anyone interested in leadership, patient safety, quality improvement and implementation. That is, if you haven'y yet come across it.
Mary Dixon-Woods' lecture Can improvement and innovation save the NHS? is both thought-provoking and refreshing. It provides an opportunity to pause and reflect on where we are in our improvement journey.
Among the many nuggets is a reflection on the "priority thickets" described in recent NHS literature, and the reality that health systems are often trying to improve everything, everywhere, all at once.
One observation particularly resonated with me. Reflecting on decades of inquiries and reports into healthcare failings, she notes that sometimes the only thing that changes between one report and the next is the font.
A sobering thought.
The good news is that this lecture is not simply a critique. It also points towards practical ways forward, supported by evidence, resources and examples.
An hour very well spent.

Watch the video here: https://www.thisinstitute.cam.ac.uk/blog/can-improvement-and-innovation-save-the-nhs/
 

Thanks @Jules I've used AI to summarise this. Will watch the full presnetation too!

“Can improvement and innovation save the NHS?” by Professor Mary Dixon-Woods

Below is an AI generated concise summary report of the video “Can improvement and innovation save the NHS?”, a keynote by Professor Mary Dixon-Woods published by THIS Institute in May 2026. The lecture argues that improvement and innovation can help the NHS, but only when they are evidence-based, realistically implemented, attentive to inequality, and supported by well-functioning organisations rather than treated as universal solutions in themselves.^[1][2]

Executive summary

The lecture presents a sober assessment of current NHS performance across access, timeliness, quality, effectiveness, and equity, using examples such as elective delays, cancer treatment delays, unwarranted variation in diabetes and breast cancer care, and persistent inequities in maternity outcomes. Professor Dixon-Woods argues that these problems are not simply deficits of effort or goodwill, but symptoms of deeper organisational, policy, and system design failures that limit the impact of improvement work.^[2]

Her central message is that innovation and improvement are necessary but insufficient unless they are grounded in evidence, matched to context, and protected from hype, overclaiming, and poorly designed large-scale programmes. She cautions that the NHS has often adopted interventions with excessive optimism, weak evaluation, and inadequate attention to implementation, creating cycles of enthusiasm followed by disappointment.^[2]

Main arguments

The lecture identifies several core challenges facing the NHS: care is not consistently accessible, timely, high quality, effective, or equitable, and these deficits vary substantially by geography, deprivation, ethnicity, and sex. Examples cited include falling public satisfaction, persistent elective backlogs, non-compliance with guidance in some diagnostic testing, and marked disparities in maternal mortality and severe morbidity.^[2]

A major theme is that variation should not be dismissed as inevitable background noise, because it often indicates remediable organisational weakness, uneven capability, or failure to apply existing knowledge reliably. The lecture also highlights the continued use of some low-value activity alongside failures to deliver proven beneficial care, showing that both underuse and overuse coexist in the NHS.^[2]

Improvement lessons

Professor Dixon-Woods argues that improvement succeeds least when it is treated as a slogan, a centrally imposed programme, or an assumption that any change is inherently beneficial. She emphasizes that large-scale initiatives often fail when they are oversold, under-specified, weakly evaluated, and inattentive to frontline realities, staffing pressures, and competing operational demands.^[2]

The lecture supports a more disciplined model of improvement: test interventions properly, understand mechanisms, use robust evidence, and distinguish genuinely effective innovation from attractive but weakly evidenced ideas. In practice, this means improvement should be designed as serious applied inquiry rather than as advocacy, branding, or policy theatre.^[2]

Governance implications

For board and governance audiences, the lecture implies that oversight should focus not only on performance outcomes but on the organisational conditions that make safe and effective improvement possible. These conditions include the ability to identify risk early, hear uncomfortable information, respond to variation, evaluate change honestly, and sustain attention on inequity as well as aggregate performance.^[2]

The talk is particularly relevant to patient safety governance because it links poor outcomes to structural and cultural issues rather than isolated individual failings. It therefore supports governance approaches that emphasise system surveillance, speaking up, learning capability, and critical scrutiny of improvement claims before scale-up.^[2]

Actions for leaders

A practical reading of the lecture suggests five priorities for NHS leaders and boards:

·        Treat major improvement claims as propositions requiring evidence, not as self-validating solutions.^[2]

·        Target unwarranted variation as a governance signal of uneven quality and possible safety risk.^[2]

·        Examine inequity explicitly, especially where deprivation, ethnicity, sex, or geography are linked to worse outcomes.^[2]

·        Avoid adopting innovations at scale without credible implementation planning and evaluation.^[2]

·        Strengthen organisational conditions for learning, challenge, and candour so that weak signals are detected earlier.^[2]

An example of the lecture’s practical relevance is its treatment of maternity inequity: disparities in mortality and morbidity are presented not as unfortunate externalities but as evidence that service design and care delivery are failing some groups more than others. That framing is directly applicable to board assurance, quality committees, and patient safety improvement programmes.^[2]

Would you like this converted into a more formal board paper style with headings such as background, key issues, implications, and recommendations?
 

1.     https://www.youtube.com/watch?v=E_iCWIazGtU

2.     https://support.google.com/youtube/answer/15930243?hl=en-GB