Positive Predictive Value of Melanoma Diagnosis in Store-and-Forward Teledermatology

Store-and-Forward Teledermatology for Assessing Skin Cancer in 2023: Literature Review

BACKGROUND

The role of teledermatology for skin lesion assessment has been a recent development, particularly, since the COVID-19 pandemic has impacted the ability to assess patients in person. The growing number of studies relating to this area reflects the evolving interest.

OBJECTIVE

This literature review aims to analyze the available research on store-and-forward teledermatology for skin lesion assessment.

METHODS

MEDLINE was searched for papers from January 2010 to November 2021. Papers were searched for assessment of time management, effectiveness, and image quality.

RESULTS

The reported effectiveness of store-and-forward teledermatology for skin lesion assessment produces heterogeneous results likely due to significant procedure variations. Most studies show high accuracy and diagnostic concordance of teledermatology compared to in-person dermatologist assessment and histopathology. This is improved through the use of teledermoscopy. Most literature shows that teledermatology reduces time to advice and definitive treatment compared to outpatient clinic assessment.

CONCLUSIONS

Overall, teledermatology offers a comparable standard of effectiveness to in-person assessment. It can save significant time in expediting advice and management. Image quality and inclusion of dermoscopy have a considerable bearing on the overall effectiveness.

Digital skin imaging applications, part II: a comprehensive survey of post-acquisition image utilization features and technology standards

BACKGROUND

Despite the increasing ubiquity and accessibility of teledermatology applications, few studies have comprehensively surveyed their features and technical standards. Importantly, features implemented after the point of capture are often intended to augment image utilization, while technical standards affect interoperability with existing healthcare systems. We aim to comprehensively survey image utilization features and technical characteristics found within publicly discoverable digital skin imaging applications.

MATERIALS AND METHODS

Applications were identified and categorized as described in Part I. Included applications were then further assessed by three independent reviewers for post-imaging content, tools, and functionality. Publicly available information was used to determine the presence or absence of relevant technology standards and/or data characteristics.

RESULTS

A total of 20 post-image acquisition features were identified across three general categories: (1) metadata attachment, (2) functional tools (i.e., those that utilized images or in-app content to perform a user-directed function), and (3) image processing. Over 80% of all applications implemented metadata features, with nearly half having metadata features only. Individual feature occurred and feature richness varied significantly by primary audience (p < 0.0001) and function (p < 0.0001). On average, each application included under three features. Less than half of all applications requested consent for user-uploaded photos and fewer than 10% provided clear data use and privacy policies.

CONCLUSION

Post-imaging functionality in skin imaging applications varies significantly by primary audience and intended function, though nearly all applications implemented metadata labeling. Technical standards are often not implemented or reported consistently. Gaps in the provision of clear consent, data privacy, and data use policies should be urgently addressed.

Digital skin imaging applications, part I: Assessment of image acquisition technique features

BACKGROUND

The rapid adoption of digital skin imaging applications has increased the utilization of smartphone-acquired images in dermatology. While this has enormous potential for scaling the assessment of concerning skin lesions, the insufficient quality of many consumer/patient-taken images can undermine clinical accuracy and potentially harm patients due to lack of diagnostic interpretability. We aim to characterize the current state of digital skin imaging applications and comprehensively assess how image acquisition features address image quality.

MATERIALS AND METHODS

Publicly discoverable mobile, web, and desktop-based skin imaging applications, identified through keyword searches in mobile app stores, Google Search queries, previous teledermatology studies, and expert recommendations were independently assessed by three reviewers. Applications were categorized by primary audience (consumer-facing, nonhospital-based practice, or enterprise/health system), function (education, store-and-forward teledermatology, live-interactive teledermatology, electronic medical record adjunct/clinical imaging storage, or clinical triage), in-app connection to a healthcare provider (yes or no), and user type (patient, provider, or both).

RESULTS

Just over half (57%) of 191 included skin imaging applications had at least one of 14 image acquisition technique features. Those that were consumer-facing, intended for educational use, and designed for both patient and physician users had significantly greater feature richness (p < 0.05). The most common feature was the inclusion of text-based imaging tips, followed by the requirement to submit multiple images and body area matching.

CONCLUSION

Very few skin imaging applications included more than one image acquisition technique feature. Feature richness varied significantly by audience, function, and user categories. Users of digital dermatology tools should consider which applications have standardized features that improve image quality.

Virtual lesion clinic - Evaluation of a teledermatology triage system for referrals for suspected melanoma

INTRODUCTION

The Virtual Lesion Clinic (VLC) of Waitematā District Health Board (WDHB) improves melanoma assessment and treatment using teledermatology. The VLC is reserved for pigmented lesions referred as suspected melanoma from primary care but indeterminate at the initial triage.

OBJECTIVES

To assess the efficacy of the VLC diagnosis of melanoma.

METHODS

A retrospective audit of suspected melanoma referrals (1 January 2012 to 31 December 2016) was conducted. Lesions were referred to the VLC if diagnostic uncertainty remained at the initial triage. VLC patients attended MoleMap imaging centres, a dermatologist reviewed history and images remotely and suggested a diagnosis and management plan. Post VLC provisional diagnosis of melanoma, all lesions subsequently excised were reviewed. A positive predictive value (PPV) was calculated using concordance between VLC diagnosis of melanoma and histopathological diagnosis of melanoma. Number needed to excise (NNE) for melanoma was derived, as well as an invasive to in-situ melanoma ratio (IM:MIS) and false negative rate (FNR).

RESULTS

The VLC received 1874 referrals for 3546 lesions during the 5-year study period. Six hundred and seventy-nine lesions were recommended excision/biopsy or specialist face-to-face assessment, and 504 lesions were subsequently excised. The PPV was 62%, NNE 1.62 and IM:MIS 0.76 for lesions suspected to be melanoma at VLC assessment. The VLC had a melanoma-specific FNR of 7%.

CONCLUSIONS

The VLC is effective in early diagnosis of melanoma with a high positive predictive value, low number needed to excise and low false negative rate amongst lesions referred as suspected melanoma.

Inter-rater variability in patch test readings and final interpretation using store-forward teledermatology

BACKGROUND

Data regarding teledermatology for patch testing are limited.

OBJECTIVES

Compare patch test readings and final interpretation by two in-person dermatologists (IPDs) with eight teledermatologists (TDs).

METHODS

Patch tested patients had photographs taken of 70 screening series of allergens at 48 hours and second readings. Eight TDs reviewed photos and graded reactions (negative, irritant, doubtful, +, ++, +++) at 48 hours and second readings; in addition, they coded a final interpretation (allergic, indeterminant, irritant, negative) for each reaction. TDs rated overall image quality and confidence level for each patient and patch test reaction, respectively. Percentage of TD-IPD agreement based on clinical significance (success, indeterminate, and failure) was calculated. Primary outcome was agreement at the second reading.

RESULTS

Data were available for 99, 101, and 66 participants at 48 hours, second reading, and final interpretation, respectively. Pooled failure (+/++/+++ vs negative) at second reading was 13.6% (range 7.9%-20.4%). Pooled failure at 48 hours and final interpretation was 5.4% (range 2.9%-6.8%) and 24.6% (range 10.2%-36.8%), respectively. Confidence in readings was statistically correlated with quality of images and disagreement.

CONCLUSION

For patch testing, teledermatology has significant limitations including clinically significant pooled failure percentages of 13.6% for second readings and 24.6% for final interpretation.