Around 30,000 avoidable cases of cancer annually can be attributed to socio-economic deprivation. Health outcomes are often considerably worse for disadvantaged and under-represented groups and this holds true for skin cancer as well. As with all health inequalities, there are many contributing factors and careful thought is needed on how best to solve them when it comes to skin cancer.
DERM assessments do not discriminate – they are based on dermoscopic image alone and no demographic factors are taken into account. If for any reason the characteristics of a particular mole or lesion render it not suitable for assessment by DERM (e.g. it is ulcerated or under the nails), the patient’s case is automatically routed to a dermatologist assessment, ensuring timely and uncompromised access to care. Across all protected groups, speed of access to care would be increased due to reduced waiting times relative to dermatologist appointments.
We recognise the anxiety felt when using technology on under-represented groups and take this very seriously. To ensure we provide – and can monitor – a service that is safe and efficient for all patients, we always conduct sub-group analyses making sure we understand how our pathways are impacting patients from all backgrounds.
avoidable cases of cancer annually can be attributed to socio-economic deprivation¹
of skin cancer in the UK is diagnosed in Black and Asian patients²
of skin cancers diagnosed are found on routine pathways³
Delays in routine pathways disproportionately affect Black, Asian and older patients⁴
improvement in 5 year melanoma survival for patients referred on the appropriate USSC pathway⁵
¹ Cancer Research [Internet]; Available from: https://news.cancerresearchuk.org/2022/02/15/health-inequalities-we-have-a-moral-duty-to-reduce-them/
² Delon C, Brown K, Payne N, Kotrotsios Y, Vernon S, Shelton J, et al. Differences in cancer incidence by broad ethnic group in England, 2013–2017. Br J Cancer. (2022) 126:1765–73.
³ CancerData [Internet]. www.cancerdata.nhs.uk. NHS; Available from: https://www.cancerdata.nhs.uk/cwt_conversion_and_detection
⁴ http://www.ncin.org.uk/publications/routes_to_diagnosis
⁵ Pacifico M, Pearl R, Grover R. The UK Government two-week rule and its impact on melanoma prognosis: an evidence-based study. Ann R Coll Surg Engl. (2007) 89:609–15.
Patients across all Fitzpatrick skin types can go through a Skin Analytics pathway to be assessed by DERM.
DERM has been deployed across the NHS since 2020 and over this time we have been monitoring post-deployment performance as part of our post market surveillance. Over this time we have seen more than 135,000 patients in our NHS pathways and have demonstrated that our services are accessible across patients with all skin types (Fitzpatrick I-VI).
Skin cancer is more prevalent in patients with lighter skin types and so this is also reflected in the patient population which we have seen presented to our pathways. 3% of cases NHS organisations have seen with the Skin Analytics platform have been recorded as having Fitzpatrick type V/VI skin. Similarly, national NHS data shows ~3% of patients on the urgent suspected skin cancer pathway are Black or Asian.
Despite AI’s potential to facilitate faster cancer diagnoses, amongst the healthcare community there is concern that it could actually worsen outcomes for under-represented patients. The concern is that the under-representation of darker-skinned individuals in skin image datasets could cause AI to perform badly at identifying cancers in these patients.
While this anxiety is understandable, encouragingly, our latest real-world data suggests that this is not the case for DERM, which has correctly identified all melanoma, SCCs and BCCs it has assessed in patients with Fitzpatrick V and VI since 2020.
Not all AI is the same though, so while our device is showing positive real-world performance, conclusions should not be extrapolated to other AI algorithms.
It’s important to put the use of DERM into the context of what is happening to patients right now.
The impact of DERM in skin cancer pathways can be summarised as being built on the accuracy in decision making (sensitivity of DERM) and the capacity it can create.
We know that patients with darker skin types have their cancer diagnosed at a later stage⁶ and that either means clinicians have a lower decision accuracy or there is a problem with access. So improving either one of those using DERM should deliver improvements in this inequality.
The key is to recognise where the technology can deliver clear and pronounced patient benefits.
⁶https://www.skincancer.org/skin-cancer-information/skin-cancer-facts/#ethnicity
