AAAlexander D. G. Anderson

Alexander D. G. Anderson

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Alexander D. G. Anderson has a total of 28 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Performance of the ‘DermDx’ algorithm in triaging suspected skin cancers: results of the AI-SCSS study

    by Alexander D G Anderson, Hannah Morgan, Neha Kasaravalli, Pascale Guitera, James Jurkiewicz, Majid Razmara, Maryam Sadeghi

    Background: The evidence base for the use of artificial intelligence (AI) in skin cancer diagnosis consists largely of artificial ‘reader’ studies and incomplete postimplementation survey data, leading to the National Institute for Clinical Excellence placing restrictions on use in the UK and raising questions regarding the value of AI as a medical device vs. traditional human teledermatology. Objectives: To assess the real-world performance of a convolutional neural network-based system (‘DermDx’; MetaOptima Technology) in triaging skin lesions referred to secondary care on a UK suspected skin cancer pathway. Methods: This was a blinded observational study to evaluate the performance of an AI algorithm on a consecutive series of referred patients with skin lesions of concern (March–April 2024). It was conducted at a single-centre secondary care National Health Service dermatology department in Cornwall, UK. All lesions referred from primary care on a suspected skin cancer pathway and imaged in a community lesion imaging clinic were eligible for inclusion. Exclusion criteria included the absence of research consent; acral, mucosal, umbilical and eyelid lesions; and inadequate image quality or artefacts. Dermoscopic images were captured with an Apple iPad and a DermLite DL4 dermatoscope, and dermoscopic images were assessed retrospectively in a blinded manner using the DermDx algorithm. Notes review was performed at 1 year to identify misdiagnoses. The main outcome measure for this study was to determine the sensitivity for detection of malignant and premalignant lesions. Results: A total of 1024 lesions were included; 298 (29.1%) lesions were malignant, 271 (26.5%) were premalignant and 455 (44.4%) benign. The algorithm categorized 273 (26.7%) as low risk and 751 (73.3%) as high risk. Sensitivity for malignant and premalignant lesions was 98.1% [n = 558/569, 95% confidence interval (CI) 96.5–99.0]. Specificity for malignant and premalignant lesions was 57.6% (n = 262/455, 95% CI 53.0–62.0). The area under the receiver operating characteristic curve was 0.918 (95% CI 0.900–0.935). DermDx missed 2 of 298 (0.7%) skin cancers. Dermatologists missed 5 of 298 (1.7%) skin cancers (P = 0.25). Use of DermDx as a triage tool would have reduced face-to-face consultations by 26.7%. Conclusions: The DermDx algorithm performed extremely well as a binary classification tool, with sensitivity for malignancy at least as good as that of dermatologists in this real-world setting.

  • Clinically relevant recurrence of basal cell carcinoma following primary treatment with hypofractionated kilovoltage radiotherapy: A single-centre retrospective review

    by Emma M I Porter, Chloe White, Eveline Tucker, Hannah Morgan, Huw W S Greenish, Toby Talbot, Grant Stewart, Alexander D G Anderson

    Basal cell carcinoma (BCC) is the most common type of skin cancer, for which national guidance recommends surgical excision first-line, though superficial radiotherapy can be offered as a non-invasive alternative. Our study retrospectively evaluated patients for 3 years following radiotherapy to treat primary BCC to establish rates of recurrence. Of 287 treated BCCs, there were 8 recurrences (2.8%) within 3 years of treatment.

  • Low-cost community lesion imaging clinics for suspected skin cancer are safe and effective: a retrospective observational cohort study

    by Hannah Morgan, Huw Greenish, Emma Porter, Chloe White, Victoria Owen, Eveline Tucker, Colin Fleming, Alexander D G Anderson

    Teletriage is increasingly used to address the current skin cancer capacity crisis, with limited data regarding its efficacy and safety. We set up a network of low-cost community lesion imaging clinics (CLICs) using healthcare assistants and readily available equipment. Case notes were retrospectively reviewed to record teletriage outcomes, ultimate diagnoses, misdiagnosis of index lesions and re-presentation with incidental skin cancers. In total, 1398 patients attended a CLIC from January to May 2024: 544 were added to a day case list, 475 were triaged to urgent face-to-face appointments, 342 were discharged, 18 were offered routine follow-up and 19 were referred directly to another specialty. Of the discharged cohort, three patients had a change in diagnosis from benign to malignant (missed skin cancer rate 0.7%). Six patients had further incidental skin cancers diagnosed. This study supports implementation of low-cost CLICs as an alternative to traditional face-to-face review for patients referred with suspected skin cancer.

  • Prospective analysis of sunbed use by age group: how effective is public health messaging?

    by Chloe White, Emma Porter, Huw Greenish, Hannah Morgan, Eveline Tucker, Alexander Anderson

    Despite public health messaging and targeted campaigns regarding sun awareness and safety, sunbed use remains consistent across all age groups in the UK. We conducted a prospective analysis of sunbed use among patients referred through a suspected skin cancer pathway to an NHS dermatology department. We consider motivational factors behind continuing sunbed use, as well as clinician support for legislation in the UK to prevent it.

  • Acute ulceration of the scalp in an older patient

    by Olivia Fairhurst, Alexander Anderson

    A 76-year-old man presented with rapidly progressing scalp ulcers. Biopsies showed only benign inflammation despite systemic inflammation. This case demonstrates how unexplained cutaneous lesions may reflect serious systemic disease, highlighting the importance of broad differential diagnosis.

  • Open Access

    Are skin lesion superclinics associated with decision fatigue? A controlled, observational study

    by Huw W S Greenish, Hafsa Faarax Shirwac, Hannah Morgan, Harry Heath, Emma Porter, Sarah Carswell, Chloe White, Neha Kasaravalli, Alexander D G Anderson

    Skin cancer superclinics have been proposed as an innovative solution to current capacity shortfalls. The aim of this study was to investigate whether this model was associated with decision fatigue. Consecutive patients with suspected skin cancer who attended a superclinic in 2022 were compared with patients seen by the same clinician in standard clinics. Proxy markers of decision fatigue were cancer pickup rates and the proportion of patients discharged without histology following their initial clinic visit. Of 345 patients seen in superclinics, 100 (29.0%) had an ultimate diagnosis of skin malignancy vs. 161 of 588 patients (27.4%) seen in standard clinics (P = 0.598). Among the superclinic patients, 47.0% (n = 162/345) were discharged without intervention vs. 50.0% (n = 294/588) of patients in the standard clinic group (P = 0.369). The superclinic model did not appear to be associated with decision fatigue in the one clinician studied and proved a safe and effective means of providing clinical care, improving capacity and delivering training.


  • Real-world melanoma miss rate in an NHS hospital dermatology service: a retrospective study

    by Alexander D G Anderson, Hafsa F Shirwac, Hannah Morgan, Huw Greenish, Sarah Carswell, Victoria Owen, Harry Heath, James Koutsis, Pascale Guitera

    This retrospective study assessed the melanoma miss rate of dermatology clinicians working in a secondary care NHS hospital. Nine of 428 primary invasive melanomas (2.1%) diagnosed over a 2-year period had been dismissed as benign in the same service within the preceding year (missed diagnosis). A further four cases (0.9%) were classed as possible misses and a final four (0.9%) as delayed diagnosis.


  • Skin cancer referrals by nonmedical practitioners: a prospective observational study

    by Alexander D G Anderson, Sarah Carswell, Harry Heath, James Koutsis, Pascale Guitera

    The aim of this study was to investigate the appropriateness of suspected skin cancer referrals made by nonmedical practitioners (NMPs) and compare this with referrals made by local general practitioners (GPs). Data were collected prospectively from patients referred from primary care to a UK hospital dermatology department. The profession of the referrer was ascertained from review of referral letters and direct questioning. Patient records and subsequent histology reports were reviewed to determine the ultimate diagnoses. Eighty-nine per cent of patients (n = 668/753) were referred by GPs vs. 11.3% (n = 85/753) by NMPs. Fifty-one per cent of patients (n = 340/668) in the GP group and 55% (n = 47/85) in the NMP group were discharged without intervention (P = 0.45). An ultimate diagnosis of skin malignancy was made in 196 of 668 (29.3%) patients in the GP and 25 of 85 (29%) patients in the NMP group (P = 0.99). These early data suggest significant potential for NMPs to become more involved in skin lesion assessment.


  • Open Access

    Commentary: Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance

    by Alexander D. G. Anderson, Serigne N. Lo, Pascale Guitera

    Commentary: Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance


  • A simple method for the analysis of urinary sucralose for use in tests of intestinal permeability

    by A D G Anderson, P Poon, G M Greenway, J MacFie

    Background: Sucralose is a unique disaccharide probe which is stable in the colon and can be used to assess permeability over the whole gut. Additional information can be gained when sucralose is administered in combination with lactulose and a monosaccharide such as L-rhamnose in the form of a 'triple sugar test.' We describe a simple assay for urinary sucralose by HPLC with refractive index detection (HPLC-RI). Methods: Phenyl-β-D-glucopyranoside (internal standard) was added to 10 mL of urine, which was then passed through a 0.45 μm syringe filter. Elution was with 30% methanol (1 mL/min) on a reverse-phase C18 column. Detection was by refractive index, and integration based upon peak areas. Sixty standards of sucralose in human urine were analysed in order to quantify analytical variation. Results: The standard curve for urinary sucralose was linear from 25 to 500 mg/L ( r>0.99). The limit of detection was 11 mg/L. Analytical recovery of sucralose at concentrations of 25, 50 and 100 mg/L was 101.5% (CV 7.59%), 102.9% (CV 5.82%) and 105.0% (CV 4.26%), respectively Conclusions: The technique described represents a simple assay for urinary sucralose which performed with acceptable accuracy and precision and should facilitate the use of the triple sugar test in clinical research.