This website is intended for healthcare professionals only.

Hospital Healthcare Europe
Hospital Pharmacy Europe     Newsletter          

Press Releases

Take a look at a selection of our recent media coverage:

EADV: Improvement in AI skin cancer detection as software identifies all melanoma cases

13th October 2023

The use of artificial intelligence (AI) software has shown a 100% detection rate for melanoma and saved over 1,000 face-to-face secondary care consultations during a 10-month period, according to a study presented at the recent European Academy of Dermatology and Venereology (EADV) Congress 2023.

The study was able to able to correctly detect all 59 cases of suspected melanoma between April 2022 and January 2023, as well as 99.5% of all skin cancers (189/190 cases) and 92.5% of pre-cancerous lesions (541/585).

The software assessed 22,356 patients with suspected skin cancers using three versions of an AI software. The first version tested in 2020-21 had an 85.9% detection rate for melanoma (195/227), 83.8% for all skin cancer (903/1,078) and 54.1% for pre-cancerous lesions (496/917).

Lead author Dr Kashini Andrew, a specialist registrar at University Hospitals Birmingham NHS Foundation Trust, commented: ‘The latest version of the software has saved over 1,000 face-to-face consultations in the secondary care setting between April 2022 and January 2023, freeing up more time for patients that need urgent attention.‘

The research team noted that the data is ‘incredibly encouraging‘, however, co-author and colleague, Dr Irshad Zaki, consultant dermatologist, said: ‘We would like to stress that AI should not be used as a standalone tool in skin cancer detection and that AI is not a substitute for consultant dermatologists.‘

Evidence of the need for appropriate clinical oversight was shown among the basal cell carcinoma cases as a single case was missed by the AI tool and later identified at a second read by what the researchers termed ‘a dermatologist “safety net“‘.

Dr Kashini Andrew added: ‘This study has demonstrated how AI is rapidly improving and learning, with the high accuracy directly attributable to improvements in AI training techniques and the quality of data used to train the AI.

‘The role of AI in dermatology and the most appropriate pathway are debated. Further research with appropriate clinical oversight may allow the deployment of AI as a triage tool. However, any pathway must demonstrate cost-effectiveness, and AI is currently not a standalone tool in dermatology. Our data shows the great promise of AI in future provision of healthcare.’

This supports the findings of previous studies including a 2022 systematic review in which the researchers concluded that ‘the performance of artificial intelligence in melanoma is satisfactory and the future for potential applications is enormous‘.

EADV: New analysis shows non-melanoma skin cancer has higher mortality rate than melanoma

12th October 2023

Non-melanoma skin cancer (NMSC) causes more global deaths than melanoma, despite its lower severity, and dark skin phenotypes were found to be at risk, according to research presented at the recent European Academy of Dermatology and Venereology (EADV) Congress 2023.

Using data from the World Health Organization International Agency for Research on Cancer data, the researchers looked at global skin cancer epidemiology, focusing particularly on population risk profiles and impact of dermatologist density on incidence and mortality.

They found that in 2020, NMSC was responsible for 63,731 deaths compared to the 57,043 deaths recorded from melanoma during the same year. However, as NMSC is often underreported in cancer registries, they noted that these figures may be underestimated.

Commenting on the top-line results, lead author of the study, Professor Thierry Passeron, professor and chair of dermatology in the University Hospital of Nice, said: ‘Although NMSC is less likely to be fatal than melanoma skin cancer, its prevalence is strikingly higher. In 2020, NMSC accounted for 78% of all skin cancer cases, resulting in over 63,700 deaths. In contrast, melanoma caused an estimated 57,000 fatalities in the same year. The significantly higher incidence of NMSC has, therefore, led to a more substantial overall impact.‘

Mapping of the data also identified a higher skin cancer incidence in fair-skinned and elderly populations from the USA, Germany, UK, France, Australia and Italy. In Africa, 11,281 skin cancer deaths were registered, demonstrating that even countries with a higher proportion of dark phenotypes are at risk.

Overall, individuals who were at a higher risk of melanoma were the elderly (relative risk, RR = 8.5), organ transplant recipients (RR = 8.0) and those with xeroderma pigmentosum (RR = 2,000). Those who worked outside were also deemed to have greater risk of NMSC than melanoma.

Commenting further on these findings, Professor Passeron said: ‘We have to get the message out that not only melanoma can be fatal, but NMSC also. It‘s crucial to note that individuals with melanin-rich skin are also at risk and are dying from skin cancer. There is a need to implement effective strategies to reduce the fatalities associated with all kinds of skin cancers.‘

When it came to dermatologist density, there was no evidence to suggest having more dermatologists per capita could reduce mortality rates. The researchers found that countries with fewer dermatologists, such as Australia, the UK and Canada, exhibited low mortality-to-incidence ratios.

Professor Passeron continued: ‘We therefore need to explore what strategies these countries are employing to reduce the impact of skin cancer in further depth. The involvement of other healthcare practitioners, such as GPs, in the identification and management of this disease may partly explain their success. There remains huge opportunity worldwide to elevate the role of GPs and other healthcare professionals in this process and train them to recognise suspicious lesions early.

‘In alignment with this, there is an ongoing need to develop awareness campaigns that educate the general public about the risks of sun exposure and other relevant risk factors. These campaigns should be tailored to at-risk populations, including those with fair skin, outdoor workers, the elderly and individuals who are immunosuppressed. Importantly, these efforts should also extend to populations that may not typically be considered at high risk, such as darker-skinned populations.’

NMSC has become a significant public health threat with a 2022 study showing that the incidence rate increased from 54.08 per 100,000 population in 1990 to 79.10 per 100,000 in 2019.

EU approval granted for nivolumab as adjuvant treatment for resected stage IIB or IIC melanoma

1st September 2023

Nivolumab (brand name Opdivo) has been approved by the European Commission for use as a monotherapy for the adjuvant treatment of stage IIB or IIC melanoma, its manufacturer Bristol Myers Squibb has announced.

The approved indication is for use in adults and adolescents 12 years of age and older with stage IIB or IIC melanoma, or melanoma with involvement of lymph nodes or metastatic disease who have undergone complete resection.

Combining relatlimab with nivolumab is known to increase progression-free survival compared to the use of nivolumab alone in patients with metastatic or unresectable melanoma.

The EC approval was based on the findings of the CheckMate -76K trial, which evaluated adjuvant nivolumab compared to placebo in patients with completely resected stage IIB or IIC melanoma.

Nivolumab and CheckMate-76k

CheckMate -76K was a randomised phase 3, double-blind study directly comparing adjuvant nivolumab at a dose of 480 mg Q4W for up to 12 months versus placebo in patients with completely resected stage IIB or IIC melanoma.

The primary endpoint of the trial was recurrence-free survival (RFS), with secondary endpoints including overall survival (OS), distant metastases-free survival (DMFS), progression-free survival on next-line therapy (PFS2) and safety endpoints.

Findings from the trial showed that adjuvant nivolumab, after a minimum follow-up of 7.8 months, reduced the risk of recurrence or death by 58% versus placebo (hazard ratio, HR = 0.42, 95% CI 0.30 – 0.59, p < 0.0001).

In addition, the 12-month RFS rate was 89% compared to 79% for placebo. This RFS benefit was observed across predefined subgroups in the trial, including T category and disease stage.

In terms of safety, the pooled dataset of nivolumab as monotherapy found that some of the most frequent adverse reactions, occurring in more than 10% of patients, were fatigue (44%), musculoskeletal pain (28%), diarrhoea (26%), rash (24%) and cough (22%). However, the majority of these adverse reactions were mild to moderate (Grade 1 or 2) in severity.

Peter Mohr, chief physician and head of the Skin Cancer Center, Buxtehude, Department of Dermatology, Elbe-Kliniken, Germany, said: ‘Patients with stage IIB or IIC melanoma are at a high risk of disease recurrence following surgery. This can be a very impactful event for patients. This approval reinforces the benefit that nivolumab may offer when used after resection, potentially preventing the disease from recurring.‘

Reinforcement learning AI model improves accuracy of skin cancer diagnoses

2nd August 2023

Using a reinforcement learning model that includes human preferences, improves the diagnostic accuracy of artificial intelligence (AI) decision support systems for skin cancer, according to the findings of a recent study.

Published in the journal Nature Medicine, researchers from the Department of Dermatology at MedUni Vienna in Austria integrated human decision-making criteria in the form of ‘reward tables‘ into the AI diagnostic system.

This reinforcement learning – a subset of machine learning – allows the system to learn through trial and error, based on both positive and negative feedback from its actions. In other words, it learns from its mistakes and is designed to mimic natural intelligence as closely as possible.

The dermatologist-generated reward tables incorporated the positive and negative consequences of clinical assessments into the decision-making process, from both the physician‘s and the patient‘s perspective. Consequently, an AI diagnosis was not only rated as right or wrong, but rewarded or penalised with a certain number of plus or minus points depending on the impact of the diagnosis or the resulting decisions.

The researchers found greater accuracy in AI diagnostic results was achieved by incorporating this human decision-making criteria, which was designed to balance the benefits and harms of various diagnostic errors, using melanoma and other skin cancers as an example.

Reinforcement learning and diagnostic accuracy

When compared against supervised learning, the reinforcement learning model improved the sensitivity for melanoma diagnosis from 61.4% to 79.5% and for basal cell carcinoma from 79.4% to 87.1%. AI overconfidence was also reduced while simultaneously maintaining accuracy.

In addition, reinforcement learning increased the rate of correct diagnoses made by dermatologists by 12.0% and improved the rate of optimal management decisions from 57.4% to 65.3%.

Commenting on the importance of the results, study lead Harald Kittler, said: ‘In this way, the AI learned to take into account not only image-based features, but also consequences of misdiagnosis in the assessment of benign and malignant skin manifestations.‘

The improved performance of AI-based skin cancer diagnosis also occurs because reinforcement learning reduces the AI‘s overconfidence in its own predictions, making more nuanced and human-compatible suggestions.

‘This, in turn, helps physicians make more accurate decisions tailored to individual patients in complex medical scenarios,‘ Kittler added.

Cancer cells can either shrink or super size to enable survival

1st February 2023

A study has revealed how cancer cells either shrink or super size during drug therapy or other environmental challenges to enable survival

In a study published in Science Advances, researchers from the Institute of Cancer research in London, have identified how cancer cells can either shrink or become super sized as a means of survival, in the face of drug treatment or any other challenges that might occur within their environment.

Although it is acknowledged that there are differences in the size of cell types, there is also a recognition that for proliferating cell types, there is little variation in cell size. This implies that there is some mechanism or checkpoint, responsible for ensuring that cells maintain a particular size during the proliferative phase. Clearly, this checkpoint is disturbed in cancer and it is known that cancers will arise due to the accumulation of mutations in genes and which alter the normal proliferation, differentiation and death process.

In the current study, researchers used a combination of biochemical profiling and mathematical analyses, to examine how genetic changes affect the size of cancer cells. They focused on skin melanoma cells which are known to be driven by two genetic mutations, a BRAF gene (60%) and an NRAS mutation (20 – 30%) and examined differences in the size and shape of these cells with the two mutations.

Interestingly, the team found that BRAF-mutant cancer cells were very small, whereas NRAS-mutant cells were much bigger and larger still, when the cells were drug resistant. It seemed that small cells were able to better tolerate DNA damage, due to high concentrations of DNA repair proteins such as PARP, BRCA1 or ATM1.

The researchers believed that their findings might help clinicians to decide upon the choice of treatment. For instance, small cells were likely be more vulnerable to PARP inhibitors, i.e., drugs affecting the proteins responsible for DNA repair. In contrast, the larger NRAS-mutant cells, already had lots of DNA damage, which the cells were unable to repair and hence unlikely to respond well to PARP inhibitors, whereas immunotherapy might be a better option. The team think that both the BRAF and NRAS mutations may cause changes in cell size by affecting levels of a protein known as CCND1, which is involved in cell division, growth and maintenance of the cytoskeleton, as well as its interactions with other proteins.

Commenting on the study, lead author, Professor Chris Bakal, from the Institute of Cancer research, said ‘Cancer cells can shrink or grow to enhance their ability to repair or contain DNA damage, and that in turn can make them resistant to certain treatments.’ He added that the study had a potential diagnostic value. For instance, ‘by looking at cell size, pathologists could predict whether a drug will work, or if the cells will be resistant. In the future, it might even be possible to use AI to help guide the pathologist, by making a rapid assessment about the size of cells and so the treatments that are most likely to work.’

Higher fish intake associated with increased risk of melanoma

15th June 2022

A large prospective cohort study found that a higher fish intake was linked with an increased risk of both malignant and in situ melanoma

A higher fish intake appears to be associated with a greater risk of developing both malignant and in situ melanoma according to the results of a prospective cohort study by a group of US researchers.

Melanoma of the skin is the 17th most common cancer worldwide and in 2020, there were an estimated 325 000 new cases and 57 000 deaths. Although a family history and sun exposure have become well recognised as risk factors for the development of a melanoma, dietary factors may also play an important role.

For example, caffeine intake may have beneficial and protective effects against cutaneous malignant melanoma, while higher citrus fruit intake and alcohol consumption may have a detrimental effect.

Furthermore, while some data point to a diet rich in omega-3 fatty acids as being protective against melanoma, other work has found no such beneficial effect. However, one study has suggested that a higher fish intake is associated with a higher risk of melanoma though the data supporting this was not provided in the paper.

For the present study, the US team used data generated by the US National Institute of Health (NIH)-AARP Diet and Health Study and sought to determine the relationship between a higher fish intake, as well as the type of fish and the risk of melanoma.

The NIH-AARP cohort study collected data on fish intake as part of a food-frequency questionnaire and which was differentiated as fried fish, fish sticks, non-fried fish or sea-food and canned tuna.

For the present study, the researchers determined the total fish intake as the sum of fried fish, non-fried fish and tuna intake. Using regression analysis, the researchers adjusted for several factors such as body mass index, age, gender, family history of cancer etc and categorised total fish into in quintiles, with the first quintile representing < 5.6 g/fish/day and the fifth > 28.3 g/fish/day.

Higher fish intake and the development of melanoma

A total of 491,367 individuals with a median baseline age of 62 years (59.6% male) were followed for a median of 15.5 years. During the period of follow-up, there were 5,034 cases of malignant melanoma and 3,284 melanoma in situ.

In fully adjusted models, when comparing the lowest to highest intake of fish, there was a significantly increased risk for malignant melanoma (hazard ratio, HR = 1.22, 95% CI 1.11 – 1.35) and for melanoma in situ (HR = 1.28, 95% CI 1.13 – 1.44).

When analysing the type of fish, the risk of malignant melanoma was elevated for the highest intake of tuna (HR = 1.20) and non-fried fish (HR = 1.18) although there was significantly lower risk for the highest intake fried fish (HR = 0.90, 95% CI 0.83 – 0.98). This pattern was also true for melanoma in situ.

The authors suggested that these results could be explained by the contamination of fish by polychlorinated biphenyls, dioxins etc. While they could not offer any direct proof to support this hypothesis, there is some research which shows a  direct association between dietary polychlorinated biphenyls and risk of melanoma.

They concluded that future studies were needed to replicate these findings and to identify the components of fish responsible for the observed associations.

Citation
Li Y et al. Fish intake and risk of melanoma in the NIH-AARP diet and health study Cancer Causes Control 2022

Study shows immune checkpoint inhibitors combined with radiotherapy offers no survival benefit in melanoma

8th April 2022

Immune checkpoint inhibitors and radiotherapy offer no survival benefit in melanoma, although 12-month progression-free survival is improved, according to a study

A meta-analysis by researchers from Beijing Tongren Hospital, Capital Medical University, Beijing, China, has concluded that adding radiotherapy to immune checkpoint inhibitors (ICIs)for the treatment of patients with melanoma offers no overall survival benefit despite a significant improvement in 12-month progression-free survival.

According to the World Cancer Research Fund, melanoma is the 19th most commonly occurring cancer in men and women, with nearly 300,000 new cases reported in 2018. Among patients whose melanoma has undergone metastases, ICIs, monoclonal antibodies which target the programmed death cell protein 1 (PD-1), the programmed death-ligand 1 (PD-L1), or the cytotoxic T-lymphocyte-associated protein 4 (CTLA-4), represent the standard of care

Nevertheless, while effective, when used as mono-therapy, ICIs produce an overall response rate ranging from 0% to 17%, though these figures increase to more than 33.3% when the agents are combined.

Radiotherapy is routinely used in treatment of solid cancers, such as hepatocellular carcinoma (HCC) and several preclinical and clinical studies have explored the efficacy of combining radiotherapy and ICIs in HCC and with promising outcomes. Moreover, a meta-analysis of 11 studies found that combining ICIs with radiotherapy showed better local efficacy than ICI mono-therapy for treating melanoma brain metastasis.

Despite this, few studies have systematically examined the combined effect of ICIs and radiotherapy in the treatment of patients with melanoma.

For the present study, the Chinese team set out to summarise the efficacy of radiotherapy in combination with ICIs in the treatment of non-brain metastatic melanoma. They included all available trials such as single-arm and control studies in which the endpoints of overall response rate (ORR), overall survival (OS) or progression-free survival (PFS) were reported. The team used regression analysis and presented their results using odds ratios.

Immune checkpoint inhibitors and radiotherapy outcomes

After an extensive literature search, 9 articles (7 retrospective studies and 2 prospective cohort trials) involving 624 patients were identified and included in the analysis.

Combing radiotherapy with ICIs led to a higher ORR compared with ICIs alone (35% vs 20.4%, p = 0.004) However, in terms of OS, the 12-month odds ratio (OR) comparing the combination to ICI treatment alone was 1.83 (95% CI 0.32 – 5.52, p = 0.69) and hence not significantly different.

While there was no significant difference between the two treatment options in PFS at 6-months (OR = 0.53, 95% CI 0.26 – 1.08, p = 0.08), this difference became significant at 12-months (OR = 0.48, 95% CI 0.29 – 0.80, p = 0.005).

Commenting on these findings, the authors highlighted that with most studies being retrospective in nature and no randomised trials, there was a need for prospective trials to further explore the efficacy of combining radiotherapy with ICIs in melanoma.

They concluded that while, at present, there was no evidence of a survival benefit by combining the two therapies, an improvement in PFS was evident but further high quality trials were required to confirm these findings.

Citation
Yin G et al. Efficacy of radiotherapy combined with immune checkpoint inhibitors in patients with melanoma: a systemic review and meta-analysis Melanoma Res 2022

x