This website is intended for healthcare professionals only.
Take a look at a selection of our recent media coverage:
17th January 2025
Speaking at Hospital Healthcare Europe’s recent Clinical Excellence in Respiratory Care event, Dr Zaheer Mangera shared insights into the lung cancer pathway and its management and diagnosis in accordance with NICE and other guidance, paying particular attention to the benefits and challenges of early diagnosis and lung cancer screening.
Cancer waiting times are never far from the headlines, and recent figures on these targets for all cancers show mixed success, with the target for the faster diagnosis standard being met (77.4% vs 75%) but the 31-day decision to treat and 62-day referral to treat standards falling short of their respective targets (91.0% vs 96% and 69.4% vs 85%).
When it comes to lung cancer, more than 5,000 cases have been identified through the NHS Targeted Lung Health Check Programme since its launch in 2019. Some 76% of these were found at the earliest stages of one and two, offering those patients the best chance of survival.
In fact, NHS data shows a 7.4% improvement in lung cancer early diagnosis rates from April 2023 to March 2024 compared to March 2019 to February 2020. However, the overall picture is varied and there’s still work to be done to ensure targets are met, screening successes continue and patients receive the best treatment as early as possible.
Respiratory consultant Dr ZaheerMangera is the lung cancer lead at North Middlesex University Hospital – now part of the Royal Free London NHS Foundation Trust – in London, UK. Optimising and delivering a successful lung cancer pathway is one of his main focuses, and this requires a careful balance of speed, accuracy and resource.
There hasn’t been much dramatic change to NICE guidance – since 2019, it’s been more subtle. Some of the big changes have been around early diagnosis, specifically lung cancer screening, which I’ll come onto shortly.
The way I look at NG122 is that it provides a basic framework, setting down the minimum criteria for delivering a lung cancer pathway. Lots of the guidance relates to order, process and speed. It doesn’t really provide a manual of how you should treat lung cancer, but it does touch on some important aspects.
Faster diagnosis consumes us as lung cancer physicians – everything is about speed, getting patients discharged off the pathway as quickly as possible, and trying to get those who do have lung cancer through it so they can get treatment at lightning speed.
The document Millimetres Matter, published by the United Kingdom Lung Cancer Coalition in 2018, is an important first stepping stone in terms of speeding up the lung cancer pathway. It recognises that when looking at the T-stage of a tumour, the stage of a patient can change just by a millimetre. And those changes can happen within the course of a 62-day lung cancer pathway.
We want everyone to be sprinting towards that finish line, whether it’s discharging from the pathway or making a lung cancer diagnosis. But we know from numerous lung cancer audits year-on-year that there’s huge variety of performance. Some Trusts are doing an excellent job getting patients through the pathway rapidly, others not so good.
But this speed is important as this report highlights a 16% mortality increase if the time from diagnosis to surgery goes beyond 40 days. So, it’s important we challenge ourselves to 62 days, knowing significant numbers of patients’ cancers will progress within the lifetime of that pathway.
Patient experience is really important. Sometimes my patients say everything’s going too quickly for them, but most want to get their diagnosis the day before yesterday.
Many would have been to their GP or emergency department several times before even arriving on the pathway. It’s all about trying to consistently drive standards up and recognise what specific standards we should be focusing on to even out performance across the different Trusts.
With the lung cancer pathway, Trusts aren’t actually competing with each other, but we want them to be within a hair’s breadth of each-other – like in the Paris Olympics 100m final – because we don’t want to see an ongoing postcode lottery as to whether patients survive the pathway and get access to the best treatments within a rapid timeframe. This all coincides with the faster diagnosis standard.
A lot of my time is spent looking at how many patients are breaching the 62-day pathway and how many are inside it, but the faster diagnosis standard is important. It’s quite a simple principle: within 28 days of the referral being sent by primary care, the patient needs to know whether they have a cancer or not. They don’t necessarily need to know the treatment plan or next steps, but they need to be told that much.
At my Trust – a medium-sized district general hospital in London – the last audit showed that for every 100 GP referrals, there were three cancers found, meaning there are 97 patients sitting there worrying they may have lung cancer. So, the benefits are huge if we can achieve this 28-day target of telling patients.
If we look at the National Optimal Lung Cancer Pathway (NOLCP), we’re expecting Trusts to ensure that the patient has had an X-ray, ideally, before they’ve even seen us. We’re also looking at the CT being done within 72 hours of that referral.
We’re failing at this in my Trust quite abysmally at the moment, which is really disappointing. It’s even more disappointing that we were achieving this pre-Covid and so post-Covid there has clearly been a catastrophic collapse in how we arrange and deliver our radiology. There are lots of different factors behind that, but we certainly haven’t been able to achieve this CT target for quite some time.
But the way we mitigate that is by trying to fast-track high-risk patients, particularly those with an X-ray abnormal for lung cancer specifically. Something being developed in a number of Trusts, which I think is live in Manchester, is artificial intelligence (AI) reporting of X-rays. If there is an abnormality, it can get flagged for reporting by a radiographer or radiologist earlier on. This is one area where we may be able to pick up these high-risk cancers much more quickly.
Ideally, we want patients to meet a lung cancer specialist – or a clinical nurse specialist in Trusts that have them – within the first six days. By day 14, we want the whole panel of tests done: PET/CT, if relevant, spirometry and more advanced lung function tests like gas transfer.
Then by day 21, we want that full multidisciplinary team (MDT) discussion where we make a treatment plan, so by day 28 we’re giving the patient the all-clear or telling them the diagnosis. That gives plenty of time to get treatment started by day 49 – the maximum length of the NOLCP.
The paradigm shift is that rather than giving ourselves 62 days, we’re trying to get that treatment within 49 days, which is what we’re increasingly being audited against. Although the National Lung Cancer Audit is still publishing the 62-day results, but it’s the 49 days that’s quite important now.
More hospitals have endobronchial ultrasound (EBUS) as part of their suite of investigations compared to a decade ago, so there’s less referral into other centres. But time to EBUS can still be problematic and patients in some areas, particularly for general anaesthetic EBUS procedures.
We’ve also seen a whole range of barriers in my own Trust around PET/CT scans. We’ve been waiting three to four weeks for a PET/CT and more recently have got them done within three to four days as more scanners come online. The issues are the physical infrastructure required to get a PET/CT scanner in, radiology reporting limitations and the fact that there won’t be this scanner in every hospital – there is going to be a hub and spoke model.
Perhaps most pertinent barrier is getting access to molecular markers for treatment plans, epidermal growth factor receptor (EGFR) status and immunohistochemistry. In my practice, it can be a full four weeks from the day I take the biopsy before we’ve got access to the full molecular markers.
Another innovation is access to circulating tumour DNA (ctDNA) blood tests. It’s been online for over a year, and my Trust has been part of a pilot for the last six months. A simple blood test is sent to a specialist lab and you get a very detailed report within two weeks. It’s particularly good if you’ve got somebody with stage three cancers or above where there’s metastases and some tumour DNA has spilt into the blood. We’re getting quite a few false negatives where the patient may well have cancer, but there’s just not enough tumour DNA present for any meaningful results to be gained from the blood test. But this can speed things up, and you can use it alongside your biopsy results to determine appropriate treatments.
The first thing to say about early diagnosis is that within the NHS, there is almost a pseudo screening programme, given how many patients are receiving all kinds of CT scans that incidentally pick up early lung cancers.
These are all very fruitful pathways for us lung cancer physicians because we tend to pick up asymptomatic lung cancer from, say, the chance CT colonogram that may have included a CT chest as part of its protocol. There are hundreds of CT coronary angiograms being done every month at our local tertiary cardiology centre and we’ll see a small percentage of them, but it actually ends up being quite a large number with reported nodules.
For those of you working alongside rapid diagnostic centres where, typically, patients will present with symptoms of weight loss, but no clear pathway for them to be referred to, they’ll be churning out quite a lot of CT chest-abdomen-pelvis. There’s direct access to CT pancreas in many areas for GPs, which can sometimes include a CT chest – the list goes on. We’re seeing lots of imaging, and we’re finding lots of incidental findings, and it’s quite a rich resource.
The message is that all lung MDTs – whether diagnostic or treatment – are absolutely being flooded with incidental findings but as some of these are picking up early lung cancers, it’s very difficult for us to say we want that Pandora’s box to be closed and we want this imaging to be a bit more thoughtful and a bit more targeted. This is going to be an area that becomes increasingly important for us to navigate.
Lung cancer screening has captured the imagination of the UK, particularly of England, and we’re seeing more lung cancer pathways. Some are hospital-based, some are in community hospitals, and some are roaming around with patients sometimes being invited to screening on lorries in supermarket car parks.
The lung cancer screening story started back in the 1970s, but real major changes to practice were first initiated by a study initiated in the 2000s and reported on around 2010/11. Here, America’s National Lung Screening Trial found you could secure a 20% reduction in lung cancer mortality if you started screening high-risk patients, typically smokers between age 50 and 70. Subsequent studies, like the European Nelson Study, found a mortality reduction of up to 26%.
It answered the question, beyond any reasonable doubt, that if you want to try to improve cancer mortality, earlier diagnosis is the strategy, and you need an appropriate tool to do that. A non-contrast, low-dose CT is a very effective way of ruling in or ruling out lung cancers.
One interesting outcome is a differential in the mortality gain between men and women. In the Nelson Study, for example, you can get up to 33% improvement in mortality in females compared to males where it’s around 25%, and it’s listed as a risk reduction.
This doesn’t necessarily change our approach, but it tells us a bit about the biology of cancer in women, and how they may well have more treatment options and better response to treatments. But remember, this population are smokers or ex-smokers, so it doesn’t answer the whole question about the difference between men and women but it’s an interesting observation.
In the UK, you have to be between the age of 55 and 75, you need to be registered with a GP, and you need to have a smoking history. Different risk assessment tools or prediction models are used – whether it’s LLPv2 or a PLCO – and, depending on the risk score, you can be invited for a CT scan screening.
There are lots of challenges around targeted lung health checks and the first is how many patients are agreeing to have a scan. CT scans aren’t usually as problematic as other types of screening – such as bowel screening – and may feel less invasive for some patients, but they still require the patient to engage, taking time off work or travelling quite some distance in some cases.
Nationally, the most recent update reveals around 42% of patients have a CT scan when invited. Some areas, like North East London, for example, have an uptick of around 80%.
It all depends what strategies are in place to try to improve uptake and how you can engage with your community and engage with people who may be at risk, including people without English as their first language and other groups that are more difficult to reach.
The number of nodules that our colleagues are finding in these targeted health checks is monumental. AI reporting and having a clear protocol for these does help, and a lot of these incidental findings can be dismissed without ever coming directly into an NHS lung cancer pathway.
In my experience, we’re only seeing those who are genuinely higher risk or are borderline. We’re not seeing too many patients who just need a standard lung nodule follow-up.
It’s a challenge in terms of aligning clinical systems and ensuring everything works, given most hospitals don’t have integrated systems. You’ll have a targeted lung health check serving a number of different hospitals that all have different systems that don’t talk to each other.
Where I work, we’re still receiving referrals by email, which of course is problematic if an email isn’t read or actioned in the usual way.
There are questions over whether we should be scanning younger or older patients and that will always be a big debate – have we got the age groups correct?
And this is all being done in the context of an under-resourced lung cancer service. Looking at the national picture, our mortality rates are still well behind most of Europe. A lot of this is to do with the actual resources and numbers of PET/CT scanners, chest physicians and oncologists.
We can identify other life-threatening findings, like an aortic aneurysm that’s about to rupture, for example. Patients will get spirometry during the testing phases as well, so you can diagnose COPD. The CT findings themselves can offer important lung findings, such as undiagnosed pulmonary fibrosis or other interstitial lung diseases – bronchiectasis, for example – and cardiac conditions such as the degree of calcification of the coronary arteries.
It’s also an opportunity to offer a tobacco dependency service, because many of these patients will be current smokers, and so it’s a good way of offering a treatment for their tobacco dependency.
Click here to read part two of Dr Mangera’s overview of lung cancer management and diagnosis, which focuses on the evolution of the neoadjuvant lung cancer pathway and notable changes to the TNM standards used to classify malignant tumours.
View the agenda and register for our next Clinical Excellence in Respiratory Care event now.
17th October 2024
Hospital Healthcare Europe (HHE) is delighted to welcome respiratory consultant Dr Zaheer Mangera as a speaker on the diagnosis and management of lung cancer at the upcoming Clinical Excellence in Respiratory Care event on 25 November 2024.
Dr Mangera, who is the lung cancer lead at North Middlesex University Hospital NHS Trust, will touch on guidelines from the National Institute for Health and Care Excellence as he considers the importance of early diagnosis and indications for chest radiotherapy, helping patients to understand what their risk factors are and what interventions are available to them, plus the effectiveness of diagnostic and staging investigations.
This session complements his contribution to the previous Clinical Excellence in Respiratory Care event in May 2024 in which he joined a panel discussion on the use of diagnostic imaging for respiratory conditions, with a particular focus on lung cancer.
Dr Mangera will also join colleagues from Sheffield Teaching Hospitals NHS Foundation Trust and Royal Brompton Hospital for a panel discussion on the management of pulmonary hypertension as a multidisciplinary team.
Find out more about the upcoming Clinical Excellence in Respiratory Care event and register for free to hear the latest from Dr Mangera on lung cancer and more.
This latest event in HHE’s Clinical Excellence series brings together renowned experts from recognised Centres of Excellence and other key institutions to share best practice and explore the latest advances in respiratory care including diagnosing lung cancer, personalised approaches to asthma and COPD treatment and managing pulmonary hypertension and sleep disordered breathing.
Providing the opportunity to gain CPD hours, the day-long event will also focus on how to best use multidisciplinary teams (MDT) and improve patient care in this area. The agenda has been created by HHE with guidance from industry experts to offer respiratory physicians and members of the wider MDT a comprehensive overview of this broad clinical area.
To coincide with this event and others in the Clinical Excellence series, a whole host of additional content and interviews with prominent clinicians from Centres of Excellence and beyond have been published on the HHE website – look out for the orange Clinical Excellence tag in the Cardiovascular and Respiratory zones.
This includes a summary of a fascinating session from cardio-oncologist Dr Rebecca Dobson on the need and demand for cardio-oncology services, how they’ve developed over time and the current state of play in this evolving field.
The Clinical Excellence schedule for 2025 will be announced soon, including new clinical areas, so watch this space.
19th December 2023
The UK’s devolved nations could detect greater numbers of lung cancer cases with improved screening programmes, new analyses by Cancer Research UK have found as the charity calls for governments to ’urgently implement’ such programmes.
Lung cancer is the leading cause of cancer death in England, Scotland, Wales and Northern Ireland and smokers and former smokers aged 55-74 are at greatest risk.
In November 2022, the National Screening Committee (NSC) recommended that everyone in this group be screened but, to date, only England has initiated a screening programme on this advice.
Almost 900,000 people were invited for checks during the pilot stages in England. Of the 200,000 scans carried out, more than 2,000 people were detected as having lung cancer, and 76% of those were identified at an earlier stage (stage 1 or 2) compared to 29% identified outside of the pilot programme in 2019.
Cancer Research UK’s latest analyses suggests that equivalent lung cancer screening programmes in the devolved nations could diagnose around 4,000 more lung cancer patients in Scotland at an early stage over the next decade, as well as 2,400 more people in Wales and 1,400 in Northern Ireland.
If just 50% of eligible people took part in screening, earlier lung cancer diagnosis could save 2,300 lives in Scotland, 1,000 lives in Wales and 600 lives in Northern Ireland over the next 10 years, Cancer Research UK said.
Professor David Weller, professor of general practice at the University of Edinburgh, believes a nationwide screening programme ’has the potential to be a game changer when it comes to reducing the burden of lung cancer in Scotland’.
He said: ’For too long, lung cancer has been perceived as a disease you can’t do anything about, but we know that diagnosis at an early stage really can make a difference.
’Major trials of targeted lung cancer screening show significant reductions in mortality from lung cancer. Pilot studies in the UK and internationally consistently show people being diagnosed with lung cancer at an earlier stage.’
In Scotland, a pilot project called LUNGSCOT – of which Professor Weller is the principal investigator – is exploring the challenges for local lung cancer screening. It is running in Lothian with funding released for Grampian, Greater Glasgow and Clyde, and the Highlands and Islands.
A pilot is also running in Cwm Taf Morgannwg in Wales, where charities including Cancer Research UK are running a public petition in the hopes of raising the issue in the Senedd.
In Northern Ireland, there are no plans or pilots to report due to the lack of a Northern Irish Executive following the 2022 elections. That said, authors of the Northern Ireland Cancer Strategy 2022-2032 have said they intend to implement all NSC recommendations.
Debbie King, Cancer Research UK’s senior external affairs manager in the devolved nations, said: ’Lung screening matters because it means more people can be diagnosed at an earlier stage, when treatment is more likely to be successful.
’A fully-funded national targeted lung cancer screening programme in Northern Ireland, Scotland and Wales is a real chance to reduce the toll of this disease.
’There have been big improvements in how we diagnose and treat other forms of cancer, but long-term lung cancer survival in the UK isn’t much higher than it was 50 years ago. This is unacceptable when evidence shows that earlier diagnosis through targeted lung cancer screening can potentially help thousands of people live longer healthier lives.’
These latest analyses were published shortly after Cancer Research UK released its manifesto for reducing cancer deaths by 20,000 a year by 2040.
While overall cancer deaths have halved over the last 50 years, progress is at risk of stalling in the UK, the charity said.
As part of the manifesto, Cancer Research UK has called on the next UK Government to address variation in treatment across different geographical areas, which includes optimising cancer screening programmes and accelerating the roll-out of the lung cancer screening programme in England.
On the manifesto, former national cancer director at the Department of Health and chair of the National Screening Committee, Professor Sir Mike Richards, said: ’Cancer outcomes in the UK are lagging behind comparable countries like Denmark. We need consistent funding and long-term strategies to make the UK the best in the world for cancer survival.’
26th June 2023
All smokers and ex-smokers aged 55-74 will have their risk of cancer assessed in the England’s first-ever national lung cancer screening programme.
The programme will be based on the Targeted Lung Health Check (TLHC) programme, which has been piloted in parts of England.
Under the plans, which will cost £270m annually once fully implemented, GP records will be used to identify patients for screening.
The first phase of the lung cancer screening scheme will reach 40% of the eligible population by March 2025, with the aim of 100% coverage by March 2030, the Government’s announcement said.
Patients will have their risk of cancer assessed based on their smoking history and other factors and those considered high risk will be invited for specialist scans every two years.
It is estimated the rollout will mean 325,000 people will be eligible for a first scan each year with 992,000 scans expected per year in total.
The UK National Screening Committee recommended in November that all four nations in the UK should implement a national lung cancer screening programme.
It said the TLHC programme would be a ‘practical starting point’ for implementation in England while a UK-wide programme needed ‘more modelling’.
During the pilots, approximately 70% of the screening took place in mobile units to ‘ensure easy access’ and ‘focused on more deprived areas where people are four times more likely to smoke’.
Almost 900,000 people were invited for checks, 375,000 risk assessments made and 200,000 scans were carried out.
Of these, more than 2,000 people were detected as having lung cancer, with 76% identified at an earlier stage compared to 29% identified outside of the pilot programme in 2019.
Urging patients receiving an invitation for lung cancer screening to go to their GP and take it up, NHS chief executive Amanda Pritchard said: ‘The NHS lung trucks programme is already delivering life-changing results, with people living in the most deprived areas now more likely to be diagnosed at an earlier stage, giving them a better chance of successful treatment.’
Health secretary Steve Barclay said: ‘Through our [lung cancer] screening programme we are now seeing more diagnoses at stage 1 and stage 2 in the most deprived communities, which is both a positive step and a practical example of how we are reducing health inequalities.
‘Rolling this out further will prolong lives by catching cancer earlier and reducing the levels of treatment required not just benefiting the patient but others waiting for treatment.
‘I am determined to combat cancer on all fronts through better prevention, detection, treatment and research.‘
Cancer Research UK’s chief executive, Michelle Mitchell, said: ‘This is really positive news for a cancer type that takes more lives than any other. Targeted lung screening across England could diagnose people most at risk at an earlier stage, when treatment is more likely to be successful.
‘For the screening programme to succeed, the UK Government must ensure that sufficient diagnostic equipment and staff are in place – a comprehensive and fully-funded NHS workforce plan for England will be vital to this.
‘Given smoking is the leading cause of lung cancer, it’s good to see that smoking cessation will be part of the programme. This needs to be embedded across all sites and stop smoking services must be properly funded to ensure people can quit smoking for good.
‘Other UK nations now need to follow suit to ensure everyone eligible can benefit from these potentially lifesaving lung checks.‘
A version of this story was originally published by our sister publication Pulse.
1st February 2023
Using a single low-dose computed tomography scan and a deep learning model enabled predictions of lung cancer risk over one to six years.
US and Taiwanese researchers have shown that the use of a single low-dose computed tomography (CT) scan, together with a deep learning algorithm, allows for a prediction of an individual’s risk of lung cancer over the next six years.
The use of low-dose CT screening has been shown to reduce mortality from lung cancer. Such screening allows for the early detection of the disease and hence the potential for better patient outcomes, although it has been suggested that the current screening guidelines might overlook vulnerable populations with a disproportionate lung cancer burden.
Nevertheless, the efficiency of lung cancer screening could be improved by individualising the assessment of future cancer risk. The problem is determining how this can achieved. To date, there are some data to support the use of clinical risk assessment models that incorporate various factors compared to simply using age and cumulative smoking exposure.
However, there are enormous possibilities created by greater use of artificial intelligence and deep learning models. In fact, it has become possible to utilise low-dose CT scan results and the presence of pulmonary nodules, into a model and to therefore optimise the screening process. But how useful are other pieces of information gathered from a CT scan beyond the presence of nodules, and could this other information be used by a deep learning model to predict future cancer risk?
This was the aim of the current study in which researchers developed a model, which they termed ‘Sybil’ using the entire volumetric low-dose CT data, without clinical and demographic information, to predict an individual’s future cancer risk.
Sybil was able to run in the background of a radiology reading station and did not require annotation by a radiologist. The model was validated using information from three independent screening datasets which included individuals who were non-smokers.
In total, data were retrieved from over 27,000 patients held in three separate databases. Sybil achieved an area under the curve (AUC) of 0.92, 0.86 and 0.94, for the one-year prediction of lung cancer for each of these datasets. In addition, the concordance indices over six years were 0.75, 0.81 and 0.80 for the same three data sets.
The authors concluded that Sybil was able to accurately predict individual’s future risk of lung cancer based on a single low-dose CT scan and called for further studies to better understand Sybil’s clinical application.
Citation
Mikheal PG et al. Sybil: a validated Deep learning model to predict future lung cancer risk from a single low-dose chest computed tomography. Clin Oncol 2023.
4th August 2022
The lung cancer risk of both current light and former heavy smokers for whom screening with a computer tomography (CT) scan is not currently recommended appears to be 10-folder higher than those who have never smoked according to the findings of a study by US researchers.
The World Health Organization estimates that across the globe in 2020, there were 2.21 million cases of lung cancer and which led to 1.8 million deaths. Thus attempts to screen for the early signs of lung cancer might potentially reduce the number of lung cancer deaths.
The development of low-dose helical computed tomography (CT) scanning has shown that low-dose CT enables the detection of many lung cancer tumours at an early stage. In fact, a recent trial concluded that among high-risk individuals who underwent CT screening, lung-cancer mortality was significantly lower compared to those who did not undergo screening.
Consequently, screening recommendations with low-dose computed tomography (LDCT) have been produced and suggest annual screening for adults aged 50 to 80 years who have a 20 pack-year smoking history and currently smoke or have quit within the past 15 years. Screening, however, is not advocated for former smokers with a 20 pack-year or greater smoking history who quit 15 or more years ago (former heavy smokers) or for current smokers with a smoking history of 20 pack-years or less (current non-heavy smokers). The reasons for excluding these two groups is not clear but presumably is related to an expected lower lung cancer risk.
But how valid is this recommended exclusion? This was the basis for the present study in which researchers sought to examine the level of cancer risk among these two groups for whom screening is not recommended.
The researchers used patient data from the Cardiovascular Health Study which enrolled nearly 6,000 community-dwelling older adults (65 years and older) although their analysis was restricted to individuals who were free of cancer at enrolment and for whom pack-year smoking history and smoking cessation data were available. The main outcome of interest was incident lung cancer during follow-up.
Lung cancer risk over time
A total of 4279 participants with a mean age of 72.8 years (57.3% female) were included and followed for a median of 13.3 years. There were 861 current non-heavy smokers and 615 former heavy smokers and 1,973 never smokers who were used as the reference point.
During follow-up, lung cancer occurred in 0.5% of never smokers, 5% of current non-heavy smokers and 5% of former heavy smokers.
The age-adjusted hazard ratio (HR) for incident lung cancer for current non-heavy smokers was 10.06 (95% CI 3.41 – 29.70) and 10.22 (95% CI 4.86 – 21.50) for former heavy smokers, i.e., the two groups for whom screening is not recommended. The mortality risk for current, non-heavy smokers was 53% higher (HR = 1.53, 95% CI 1.22 – 1.92) and 18% higher (HR = 1.18, 95% CI 1.05 – 1.32) for former heavy smokers.
The authors concluded that there appears to be a very high lung cancer risk among those who are excluded from the recommendations for CT screening and called for future studies to examine whether annual screening could reduce lung cancer mortality in these populations.
Citation
Faselis C et al. Assessment of Lung Cancer Risk Among Smokers for Whom Annual Screening Is Not Recommended JAMA Oncol 2022
13th January 2022
Using a standalone artificial intelligence (AI) reader for lung cancer screening with ultra low-dose computed tomography (ULDCT) could potentially reduce the workload of radiologists by over 80%. This was the conclusion of a study by a team from the Department of Epidemiology, University of Groningen, Groningen, The Netherlands.
Lung cancer was responsible for 2.21 million cases and 1.8 million deaths in 2020 and volume-based, low-dose CT screening of high-risk patients has been shown to significantly reduce lung-cancer mortality compared to those who underwent no screening. Moreover, low-dose CT lung cancer screening has become an evidence-based reality.
However, the introduction of such screening will undoubtedly create an enormous increase in the workload of radiologists and while the use of a standalone AI as a second reader for lung cancer screening with CT has shown much promise, how well an AI system could perform as a standalone system remains uncertain.
For the present study, the Dutch researchers, sought to evaluate the performance of a standalone AI as an impartial reader in ULDCT lung cancer baseline screening compared to that of experienced radiologists and a consensus read reference standard.
They used a dataset of CT scans from participants who underwent a baseline scan and who were found to have at least one solid nodule of any size in their scan. Other inclusion criteria for the study were: participants aged 50 – 80 years, > 30 pack-years smoking history, current or former smoker and those who did not develop lung cancer within two years of their baseline scan.
All of the participant’s scans were independently analysed by five thoracic radiologists and the standalone AI then independently analysed all the scans to detect, measure and classify nodules. In addition, an independent consensus read was performed by a panel of three, experienced radiologists and who sought to determine the number of positive misclassifications (PM) and negative misclassifications (NM).
A PM was classified as nodules > 100 cubic mms and NM < 100 cubic mms. The results from the 5 radiologist reader and the standalone AI were compared to the consensus read to determine the number of PM and NM results as well as the number of discrepancies.
Findings
A total of 283 participants with a mean age of 64.6 years (56.9% male) with a total of 1149 lung nodules were analysed.
The consensus read was 83 PMs and 200 NMs and the standalone AI had 61 discrepancies (53 PM and 8 NM) compared to a total of 43, 36, 29, 28 and 50 from the five respective radiologists. From these results, the authors calculated that when using a standalone AI as the main reader for general lung cancer screening, there would be a workload reduction of between 77.4% and 86.7%.
The authors concluded that a standalone AI could significantly reduce the workload of radiologists in lung cancer screening.
Citation
Lancaster HL et al. Outstanding negative prediction performance of solid pulmonary nodule volume AI for ultra-LDCT baseline lung cancer screening risk stratification. Lung Cancer 2022.
IMPORTANT LINKS
MORE FROM COGORA
© Cogora 2025
Cogora Limited. 1 Giltspur Street, London EC1A 9DD
Registered in the United Kingdom. Reg. No. 2147432
