mHealth App for Risk Assessment of Pigmented and Nonpigmented Skin Lesions-A Study on Sensitivity and Specificity in Detecting Malignancy

The Role of Artificial Intelligence in the Diagnosis of Melanoma

The incidence of melanoma, the most aggressive form of skin cancer, continues to rise globally, particularly among fair-skinned populations (type I and II). Early detection is crucial for improving patient outcomes, and recent advancements in artificial intelligence (AI) have shown promise in enhancing the accuracy and efficiency of melanoma diagnosis and management. This review examines the role of AI in skin lesion diagnostics, highlighting two main approaches: machine learning, particularly convolutional neural networks (CNNs), and expert systems. AI techniques have demonstrated high accuracy in classifying dermoscopic images, often matching or surpassing dermatologists' performance. Integrating AI into dermatology has improved tasks, such as lesion classification, segmentation, and risk prediction, facilitating earlier and more accurate interventions. Despite these advancements, challenges remain, including biases in training data, interpretability issues, and integration of AI into clinical workflows. Ensuring diverse data representation and maintaining high standards of image quality are essential for reliable AI performance. Future directions involve the development of more sophisticated models, such as vision-language and multimodal models, and federated learning to address data privacy and generalizability concerns. Continuous validation and ethical integration of AI into clinical practice are vital for realizing its full potential for improving melanoma diagnosis and patient care.

Artificial intelligence in the detection of skin cancer: State of the art

The incidence of melanoma is increasing rapidly. This cancer has a good prognosis if detected early. For this reason, various systems of skin lesion image analysis, which support imaging diagnostics of this neoplasm, are developing very dynamically. To detect and recognize neoplastic lesions, such systems use various artificial intelligence (AI) algorithms. This area of computer science applications has recently undergone dynamic development, abounding in several solutions that are effective tools supporting diagnosticians in many medical specialties. In this contribution, a number of applications of different classes of AI algorithms for the detection of this skin melanoma are presented and evaluated. Both classic systems based on the analysis of dermatoscopic images as well as total body systems, enabling the analysis of the patient's whole body to detect moles and pathologic changes, are discussed. These increasingly popular applications that allow the analysis of lesion images using smartphones are also described. The quantitative evaluation of the discussed systems with particular emphasis on the method of validation of the implemented algorithms is presented. The advantages and limitations of AI in the analysis of lesion images are also discussed, and problems requiring a solution for more effective use of AI in dermatology are identified.

Artificial Intelligence in Skin Cancer Diagnosis: A Reality Check

The field of skin cancer detection offers a compelling use case for the application of artificial intelligence (AI) within the realm of image-based diagnostic medicine. Through the analysis of large datasets, AI algorithms have the capacity to classify clinical or dermoscopic images with remarkable accuracy. Although these AI-based applications can operate both autonomously and under human supervision, the best results are achieved through a collaborative approach that leverages the expertise of both AI and human experts. However, it is important to note that most studies focus on assessing the diagnostic accuracy of AI in artificial settings rather than in real-world scenarios. Consequently, the practical utility of AI-assisted diagnosis in a clinical environment is still largely unknown. Furthermore, there exists a knowledge gap concerning the optimal use cases and deployment settings for these AI systems as well as the practical challenges that may arise from widespread implementation. This review explores the advantages and limitations of AI in a variety of real-world contexts, with a specific focus on its value to consumers, general practitioners, and dermatologists.

Artificial intelligence for skin cancer detection and classification for clinical environment: a systematic review

Background

Skin cancer is one of the most common forms worldwide, with a significant increase in incidence over the last few decades. Early and accurate detection of this type of cancer can result in better prognoses and less invasive treatments for patients. With advances in Artificial Intelligence (AI), tools have emerged that can facilitate diagnosis and classify dermatological images, complementing traditional clinical assessments and being applicable where there is a shortage of specialists. Its adoption requires analysis of efficacy, safety, and ethical considerations, as well as considering the genetic and ethnic diversity of patients.

Objective

The systematic review aims to examine research on the detection, classification, and assessment of skin cancer images in clinical settings.

Methods

We conducted a systematic literature search on PubMed, Scopus, Embase, and Web of Science, encompassing studies published until April 4th, 2023. Study selection, data extraction, and critical appraisal were carried out by two independent reviewers. Results were subsequently presented through a narrative synthesis.

Results

Through the search, 760 studies were identified in four databases, from which only 18 studies were selected, focusing on developing, implementing, and validating systems to detect, diagnose, and classify skin cancer in clinical settings. This review covers descriptive analysis, data scenarios, data processing and techniques, study results and perspectives, and physician diversity, accessibility, and participation.

Conclusion

The application of artificial intelligence in dermatology has the potential to revolutionize early detection of skin cancer. However, it is imperative to validate and collaborate with healthcare professionals to ensure its clinical effectiveness and safety.

Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): a pilot feasibility study

Background

Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the conditions and feasibility of a study that incorporates an AI-based app in primary care and evaluates its potential impact.

Methods

We conducted a pilot feasibility study from November 22nd, 2021 to June 9th, 2022 with a mixed-methods design on implementation of an AI-based mHealth app for skin cancer detection in three primary care practices in the Netherlands (Rotterdam, Leiden and Katwijk). The primary outcome was the inclusion and successful participation rate of patients and general practitioners (GPs). Secondary outcomes were the reasons, facilitators and barriers for successful participation and the potential impact in both pathways for future sample size calculations. Patients were offered use of an AI-based mHealth app before consulting their GP. GPs assessed the patients blinded and then unblinded to the app. Qualitative data included observations and audio-diaries from patients and GPs and focus-groups and interviews with GPs and GP assistants.

Findings

Fifty patients were included with a median age of 52 years (IQR 33.5-60.3), 64% were female, and 90% had a light skin type. The average patient inclusion rate was 4-6 per GP practice per month and 84% (n = 42) successfully participated. Similarly, in 90% (n = 45 patients) the GPs also successfully completed the study. GPs never changed their working diagnosis, but did change their treatment plan (n = 5) based on the app's assessments. Notably, 54% of patients with a benign skin lesion and low risk rating, indicated that they would be reassured and cancel their GP visit with these results (p < 0.001).

Interpretation

Our findings suggest that studying implementation of an AI-based mHealth app for detection of skin cancer in the hands of patients or as a diagnostic tool used by GPs in primary care appears feasible. Preliminary results indicate potential to further investigate both intended use settings.

Funding

SkinVision B.V.

New AI-algorithms on smartphones to detect skin cancer in a clinical setting-A validation study

BACKGROUND AND OBJECTIVES

The incidence of skin cancer is rising worldwide and there is medical need to optimize its early detection. This study was conducted to determine the diagnostic and risk-assessment accuracy of two new diagnosis-based neural networks (analyze and detect), which comply with the CE-criteria, in evaluating the malignant potential of various skin lesions on a smartphone. Of note, the intention of our study was to evaluate the performance of these medical products in a clinical setting for the first time.

METHODS

This was a prospective, single-center clinical study at one tertiary referral center in Graz, Austria. Patients, who were either scheduled for preventive skin examination or removal of at least one skin lesion were eligible for participation. Patients were assessed by at least two dermatologists and by the integrated algorithms on different mobile phones. The lesions to be recorded were randomly selected by the dermatologists. The diagnosis of the algorithm was stated as correct if it matched the diagnosis of the two dermatologists or the histology (if available). The histology was the reference standard, however, if both clinicians considered a lesion as being benign no histology was performed and the dermatologists were stated as reference standard.

RESULTS

A total of 238 patients with 1171 lesions (86 female; 36.13%) with an average age of 66.19 (SD = 17.05) was included. Sensitivity and specificity of the detect algorithm were 96.4% (CI 93.94-98.85) and 94.85% (CI 92.46-97.23); for the analyze algorithm a sensitivity of 95.35% (CI 93.45-97.25) and a specificity of 90.32% (CI 88.1-92.54) were achieved.

DISCUSSION

The studied neural networks succeeded analyzing the risk of skin lesions with a high diagnostic accuracy showing that they are sufficient tools in calculating the probability of a skin lesion being malignant. In conjunction with the wide spread use of smartphones this new AI approach opens the opportunity for a higher early detection rate of skin cancer with consecutive lower epidemiological burden of metastatic cancer and reducing health care costs. This neural network moreover facilitates the empowerment of patients, especially in regions with a low density of medical doctors.

REGISTRATION

Approved and registered at the ethics committee of the Medical University of Graz, Austria (Approval number: 30-199 ex 17/18).

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.

Over-Detection of Melanoma-Suspect Lesions by a CE-Certified Smartphone App: Performance in Comparison to Dermatologists, 2D and 3D Convolutional Neural Networks in a Prospective Data Set of 1204 Pigmented Skin Lesions Involving Patients' Perception

Simple Summary

Early detection and resection of cutaneous melanoma are crucial for a good prognosis. However, visual distinction of early melanomas from benign nevi remains challenging. New artificial intelligence-based approaches for risk stratification of pigmented skin lesions provide screening methods for laypersons with increasing use of smartphone applications (apps). Our study aims to prospectively investigate the diagnostic accuracy of a CE-certified smartphone app, SkinVision^®, in melanoma recognition. Based on classification into three different risk scores, the app provides a recommendation to consult a dermatologist. In addition, both patients’ and dermatologists’ perspectives towards AI-based mobile health apps were evaluated. We observed that the app classified a significantly higher number of lesions as high-risk than dermatologists, which would have led to a clinically harmful number of unnecessary excisions. The diagnostic performance of the app in dichotomous classification of 1204 pigmented skin lesions (risk classification for nevus vs. melanoma) remained below advertised rates with low sensitivity (41.3–83.3%) and specificity (60.0–82.9%). The confidence in the app was low among both patients and dermatologists, and no patient favored an assessment by the app alone. Although smartphone apps are a potential medium for increasing awareness of melanoma screening in the lay population, they should be evaluated for certification with prospective real-world evidence.

Abstract

The exponential increase in algorithm-based mobile health (mHealth) applications (apps) for melanoma screening is a reaction to a growing market. However, the performance of available apps remains to be investigated. In this prospective study, we investigated the diagnostic accuracy of a class 1 CE-certified smartphone app in melanoma risk stratification and its patient and dermatologist satisfaction. Pigmented skin lesions ≥ 3 mm and any suspicious smaller lesions were assessed by the smartphone app SkinVision^® (SkinVision^® B.V., Amsterdam, the Netherlands, App-Version 6.8.1), 2D FotoFinder ATBM^® master (FotoFinder ATBM^® Systems GmbH, Bad Birnbach, Germany, Version 3.3.1.0), 3D Vectra^® WB360 (Canfield Scientific, Parsippany, NJ, USA, Version 4.7.1) total body photography (TBP) devices, and dermatologists. The high-risk score of the smartphone app was compared with the two gold standards: histological diagnosis, or if not available, the combination of dermatologists’, 2D and 3D risk assessments. A total of 1204 lesions among 114 patients (mean age 59 years; 51% females (55 patients at high-risk for developing a melanoma, 59 melanoma patients)) were included. The smartphone app’s sensitivity, specificity, and area under the receiver operating characteristics (AUROC) varied between 41.3–83.3%, 60.0–82.9%, and 0.62–0.72% according to two study-defined reference standards. Additionally, all patients and dermatologists completed a newly created questionnaire for preference and trust of screening type. The smartphone app was rated as trustworthy by 36% (20/55) of patients at high-risk for melanoma, 49% (29/59) of melanoma patients, and 8.8% (10/114) of dermatologists. Most of the patients rated the 2D TBP imaging (93% (51/55) resp. 88% (52/59)) and the 3D TBP imaging (91% (50/55) resp. 90% (53/59)) as trustworthy. A skin cancer screening by combination of dermatologist and smartphone app was favored by only 1.8% (1/55) resp. 3.4% (2/59) of the patients; no patient preferred an assessment by a smartphone app alone. The diagnostic accuracy in clinical practice was not as reliable as previously advertised and the satisfaction with smartphone apps for melanoma risk stratification was scarce. MHealth apps might be a potential medium to increase awareness for melanoma screening in the lay population, but healthcare professionals and users should be alerted to the potential harm of over-detection and poor performance. In conclusion, we suggest further robust evidence-based evaluation before including market-approved apps in self-examination for public health benefits.

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.

Usefulness of Smartphones in Dermatology: A US-Based Review

(1) Background: As smartphones have become more widely used, they have become an appealing tool for health-related functions. For dermatology alone, hundreds of applications (apps) are available to download for both patients and providers. (2) Methods: The Google Play Store and Apple App Store were searched from the United States using dermatology-related terms. Apps were categorized based on description, and the number of reviews, download cost, target audience, and use of AI were recorded. The top apps from each category by number of reviews were reported. Additionally, literature on the benefits and limitations of using smartphones for dermatology were reviewed. (3) Results: A total of 632 apps were included in the study: 395 (62.5%) were marketed towards patients, 203 (32.1%) towards providers, and 34 (5.4%) towards both; 265 (41.9%) were available only on the Google Play Store, 146 (23.1%) only on the Apple App Store, and 221 (35.0%) were available on both; and 595 (94.1%) were free to download and 37 (5.9%) had a cost to download, ranging from USD 0.99 to USD 349.99 (median USD 37.49). A total of 99 apps (15.7%) reported the use of artificial intelligence. (4) Conclusions: Although there are many benefits of using smartphones for dermatology, lack of regulation and high-quality evidence supporting the efficacy and accuracy of apps hinders their potential.

Acne detection and severity evaluation with interpretable convolutional neural network models

BACKGROUND

Acne vulgaris is one of the most prevalent skin conditions, which harms not only the patients' physiological conditions, but also their mental health. Early diagnosis and accurate continuous self-monitoring could help control and alleviate their discomfort.

OBJECTIVE

We focus on the development and comparison of deep learning models for locating acne lesions on facial images, thus making estimations on the acne severity on faces via medical criterion.

METHODS

Different from most existing literature on facial acne analysis, the considered models in this study are object detection models with convolutional neural network (CNN) as backbone and has better interpretability. Thus, they produce more credible results of acne detection and facial acne severity evaluation.

RESULTS

Experiments with real data validate the effectiveness of these models. The highest mean average precision (mAP) is 0.536 on an open source dataset. Corresponding error of acne lesion counting can be as low as 0.43 ± 6.65 on this dataset.

CONCLUSIONS

The presented models have been released to public via deployed as a freely accessible WeChat applet service, which provides continuous out-of-hospital self-monitoring to patients. This also aids the dermatologists to track the progress of this disease and to assess the effectiveness of treatment.

Artificial intelligence: how it works and criteria for assessment

Artificial intelligence is a term used to describe computer technology in the modeling of intelligent behavior and critical thinking comparable to that of humans. To date, some of the first areas of medicine to be influenced by advances in artificial intelligence technologies will be those most dependent on imaging. These include ophthalmology, radiology, and dermatology. In connection with the emergence of numerous medical applications, scientists have formulated criteria for their assessment. This list included: clinical validation, regular application updates, functional focus, cost, availability of an information block for specialists and patients, compliance with the conditions of government regulation, and registration. One of the applications that meet all the requirements is the ProRodinki software package, developed for use by patients and specialists in the Russian Federation. Taking into account a widespread and rapidly developing competitive environment, it is necessary to soberly treat the resources of such applications, not exaggerating their capabilities and not considering them as a substitute for a specialist.

Artificial intelligence in dermatology and healthcare: An overview

Many aspects of our life are affected by technology. One of the most discussed advancements of modern technologies is artificial intelligence. It involves computational methods which in some way mimic the human thought process. Just like other branches, the medical field also has come under the ambit of artificial intelligence. Almost every field in medicine has been touched by its effect in one way or the other. Prominent among them are medical diagnosis, medical statistics, robotics, and human biology. Medical imaging is one of the foremost specialties with artificial intelligence applications, wherein deep learning methods like artificial neural networks are commonly used. artificial intelligence application in dermatology was initially restricted to the analysis of melanoma and pigmentary skin lesions, has now expanded and covers many dermatoses. Though the applications of artificial intelligence are ever increasing, large data requirements, interpretation of data and ethical concerns are some of its limitations in the present day.

Safety concerns with consumer-facing mobile health applications and their consequences: a scoping review

Objective

To summarize the research literature about safety concerns with consumer-facing health apps and their consequences.

Materials and Methods

We searched bibliographic databases including PubMed, Web of Science, Scopus, and Cochrane libraries from January 2013 to May 2019 for articles about health apps. Descriptive information about safety concerns and consequences were extracted and classified into natural categories. The review was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) statement.

Results

Of the 74 studies identified, the majority were reviews of a single or a group of similar apps (n = 66, 89%), nearly half related to disease management (n = 34, 46%). A total of 80 safety concerns were identified, 67 related to the quality of information presented including incorrect or incomplete information, variation in content, and incorrect or inappropriate response to consumer needs. The remaining 13 related to app functionality including gaps in features, lack of validation for user input, delayed processing, failure to respond to health dangers, and faulty alarms. Of the 52 reports of actual or potential consequences, 5 had potential for patient harm. We also identified 66 reports about gaps in app development, including the lack of expert involvement, poor evidence base, and poor validation.

Conclusions

Safety of apps is an emerging public health issue. The available evidence shows that apps pose clinical risks to consumers. Involvement of consumers, regulators, and healthcare professionals in development and testing can improve quality. Additionally, mandatory reporting of safety concerns is needed to improve outcomes.

Use of Mobile Applications in Dermatology

Smartphones and applications related to the same are ubiquitous now. As dermatologists, we have a wide array of smartphone apps at our disposal which we can use to improve our practice in all aspects—clinical, academic, research, and administrative. This article provides an overview of available apps, tips on using apps—both general and specific for dermatology, as well as discusses the scientific validity of some of these apps and the future of smartphone apps in the context of dermatology.

Feasibility Study of a Smartphone Application for Detecting Skin Cancers in People With Albinism

PURPOSE

Albinism affects some facets of the eye’s function and coloration, as well as hair and skin color. The prevalence of albinism is estimated to be one in 2,000-5,000 people in sub-Saharan Africa and one in 270 in Tanzania. People in Tanzania with albinism experience sociocultural and economic disparities. Because of stigma related to albinism, they present to hospitals with advanced disease, including skin cancers. Mobile health (mHealth) can help to bridge some of the gaps in detection and treatment of skin cancers affecting this population.

METHODS

We assessed the feasibility of using a mobile application (app) for detection of skin cancers among people with albinism. The study was approved by the Ocean Road Cancer Institute institutional review board. Data, including pictures of the lesions, were collected using a mobile smartphone and submitted to expert reviewers. Expert reviewers’ diagnosis options were benign, malignant, or unevaluable.

RESULTS

A total of 77 lesions from different body locations of 69 participants were captured by the NgoziYangu mobile app. Sixty-two lesions (81%) were considered malignant via the app and referred for biopsy and histologic diagnosis. Of those referred, 55 lesions (89%) were biopsied, and 47 lesions (85%) were confirmed as skin malignancies, whereas eight (15%) were benign.

CONCLUSION

With an increasing Internet coverage in Africa, there is potential for smartphone apps to improve health care delivery channels. It is important that mobile apps like NgoziYangu be explored to reduce diagnostic delay and improve the accuracy of detection of skin cancer, especially in stigmatized groups.

Review of smartphone mobile applications for skin cancer detection: what are the changes in availability, functionality, and costs to users over time?

Smartphone applications (apps) are available to consumers for skin cancer prevention and early detection. This study aims to review changes over time in the skin cancer apps available to consumers as well as their functionality and costs. Apps for the prevention of skin cancer were searched on two major smartphone app stores (Android and iOS) in June 2019. The number, functionality, ratings, and price of the apps were described and compared to similar reviews of the skin cancer app market from 2014 to 2017. Overall, the June 2019 search identified 66 apps. Of 39 apps found in 2014, 30 were no longer available in 2019 representing an attrition rate of 77%; of 43 apps available in 2017, attrition was 46.5%. In 2019, 63.6% (n = 42/66) of apps were free to download compared to 53.5% (n = 23/43) in 2017. Input from clinician/professional bodies was evident for 47.0% (n = 31/66) of the apps in 2019 compared to 34.9% (15/43) in 2017. The most common app functionality offered in 2019 was monitoring/tracking of lesions at 48.5% (n = 32/66). Since 2014, there has been a steady increase in the number of apps available for the general public to support the prevention or early detection of skin cancers. There continues to be a high turnover of apps, and many apps still appear to lack clinician input and/or evidence for their safety and value.

Artificial Intelligence in Cutaneous Oncology

Skin cancer, previously known to be a common disease in Western countries, is becoming more common in Asian countries. Skin cancer differs from other carcinomas in that it is visible to our eyes. Although skin biopsy is essential for the diagnosis of skin cancer, decisions regarding whether or not to conduct a biopsy are made by an experienced dermatologist. From this perspective, it is easy to obtain and store photos using a smartphone, and artificial intelligence technologies developed to analyze these photos can represent a useful tool to complement the dermatologist's knowledge. In addition, the universal use of dermoscopy, which allows for non-invasive inspection of the upper dermal level of skin lesions with a usual 10-fold magnification, adds to the image storage and analysis techniques, foreshadowing breakthroughs in skin cancer diagnosis. Current problems include the inaccuracy of the available technology and resulting legal liabilities. This paper presents a comprehensive review of the clinical applications of artificial intelligence and a discussion on how it can be implemented in the field of cutaneous oncology.

Machine Learning in Dermatology: Current Applications, Opportunities, and Limitations

Machine learning (ML) has the potential to improve the dermatologist's practice from diagnosis to personalized treatment. Recent advancements in access to large datasets (e.g., electronic medical records, image databases, omics), faster computing, and cheaper data storage have encouraged the development of ML algorithms with human-like intelligence in dermatology. This article is an overview of the basics of ML, current applications of ML, and potential limitations and considerations for further development of ML. We have identified five current areas of applications for ML in dermatology: (1) disease classification using clinical images; (2) disease classification using dermatopathology images; (3) assessment of skin diseases using mobile applications and personal monitoring devices; (4) facilitating large-scale epidemiology research; and (5) precision medicine. The purpose of this review is to provide a guide for dermatologists to help demystify the fundamentals of ML and its wide range of applications in order to better evaluate its potential opportunities and challenges.

Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies

OBJECTIVE

To examine the validity and findings of studies that examine the accuracy of algorithm based smartphone applications ("apps") to assess risk of skin cancer in suspicious skin lesions.

DESIGN

Systematic review of diagnostic accuracy studies.

DATA SOURCES

Cochrane Central Register of Controlled Trials, MEDLINE, Embase, CINAHL, CPCI, Zetoc, Science Citation Index, and online trial registers (from database inception to 10 April 2019).

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

Studies of any design that evaluated algorithm based smartphone apps to assess images of skin lesions suspicious for skin cancer. Reference standards included histological diagnosis or follow-up, and expert recommendation for further investigation or intervention. Two authors independently extracted data and assessed validity using QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2 tool). Estimates of sensitivity and specificity were reported for each app.

RESULTS

Nine studies that evaluated six different identifiable smartphone apps were included. Six verified results by using histology or follow-up (n=725 lesions), and three verified results by using expert recommendations (n=407 lesions). Studies were small and of poor methodological quality, with selective recruitment, high rates of unevaluable images, and differential verification. Lesion selection and image acquisition were performed by clinicians rather than smartphone users. Two CE (Conformit Europenne) marked apps are available for download. SkinScan was evaluated in a single study (n=15, five melanomas) with 0% sensitivity and 100% specificity for the detection of melanoma. SkinVision was evaluated in two studies (n=252, 61 malignant or premalignant lesions) and achieved a sensitivity of 80% (95% confidence interval 63% to 92%) and a specificity of 78% (67% to 87%) for the detection of malignant or premalignant lesions. Accuracy of the SkinVision app verified against expert recommendations was poor (three studies).

CONCLUSIONS

Current algorithm based smartphone apps cannot be relied on to detect all cases of melanoma or other skin cancers. Test performance is likely to be poorer than reported here when used in clinically relevant populations and by the intended users of the apps. The current regulatory process for awarding the CE marking for algorithm based apps does not provide adequate protection to the public.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42016033595.

Assessing Access Control Risk for mHealth: A Delphi Study to Categorize Security of Health Data and Provide Risk Assessment for Mobile Apps

Background

Smartphones can tackle healthcare stakeholders' diverse needs. Nonetheless, the risk of data disclosure/breach can be higher when using such devices, due to the lack of adequate security and the fact that a medical record has a significant higher financial value when compared with other records. Means to assess those risks are required for every mHealth application interaction, dependent and independent of its goals/content.

Objective

To present a risk assessment feature integration into the SoTRAACE (Socio-Technical Risk-Adaptable Access Control) model, as well as the operationalization of the related mobile health decision policies.

Methods

Since there is still a lack of a definition for health data security categorization, a Delphi study with security experts was performed for this purpose, to reflect the knowledge of security experts and to be closer to real-life situations and their associated risks.

Results

The Delphi study allowed a consensus to be reached on eleven risk factors of information security related to mobile applications that can easily be adapted into the described SoTRAACE prototype. Within those risk factors, the most significant five, as assessed by the experts, and in descending order of risk level, are as follows: (1) security in the communication (e.g., used security protocols), (2) behavioural differences (e.g., different or outlier patterns of behaviour detected for a user), (3) type of wireless connection and respective encryption, (4) resource sensitivity, and (5) device threat level (e.g., known vulnerabilities associated to a device or its operating system).

Conclusions

Building adaptable, risk-aware resilient access control models into the most generalized technology used nowadays (e.g., smartphones) is crucial to fulfil both the goals of users as well as security and privacy requirements for healthcare data.

Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms

BACKGROUND

Machine learning algorithms achieve expert-level accuracy in skin lesion classification based on clinical images. However, it is not yet shown whether these algorithms could have high accuracy when embedded in a smartphone app, where image quality is lower and there is high variability in image taking scenarios by users. In the past, these applications were criticized due to lack of accuracy.

OBJECTIVE

In this study, we evaluate the accuracy of the newest version of a smartphone application (SA) for risk assessment of skin lesions.

METHODS

This SA uses a machine learning algorithm to compute a risk rating. The algorithm is trained on 131 873 images taken by 31 449 users in multiple countries between January 2016 and August 2018 and rated for risk by dermatologists. To evaluate the sensitivity of the algorithm, we use 285 histopathologically validated skin cancer cases (including 138 malignant melanomas), from two previously published clinical studies (195 cases) and from the SA user database (90 cases). We calculate the specificity on a separate set from the SA user database containing 6000 clinically validated benign cases.

RESULTS

The algorithm scored a 95.1% (95% CI, 91.9-97.3%) sensitivity in detecting (pre)malignant conditions (93% for malignant melanoma and 97% for keratinocyte carcinomas and precursors). This level of sensitivity was achieved with a 78.3% (95% CI, 77.2-79.3%) specificity.

CONCLUSIONS

This SA provides a high sensitivity to detect skin cancer; however, there is still room for improvement in terms of specificity. Future studies are needed to assess the impact of this SA on the health systems and its users.

Poor agreement between the automated risk assessment of a smartphone application for skin cancer detection and the rating by dermatologists

Background

Several smartphone applications (app) with an automated risk assessment claim to be able to detect skin cancer at an early stage. Various studies that have evaluated these apps showed mainly poor performance. However, all studies were done in patients and lesions were mainly selected by a specialist.

Objectives

To investigate the performance of the automated risk assessment of an app by comparing its assessment to that of a dermatologist in lesions selected by the participants.

Methods

Participants of a National Skin Cancer Day were enrolled in a multicentre study. Skin lesions indicated by the participants were analysed by the automated risk assessment of the app prior to blinded rating by the dermatologist. The ratings of the automated risk assessment were compared to the assessment and diagnosis of the dermatologist. Due to the setting of the Skin Cancer Day, lesions were not verified by histopathology.

Results

We included 125 participants (199 lesions). The app was not able to analyse 90 cases (45%) of which nine BCC, four atypical naevi and one lentigo maligna. Thirty lesions (67%) with a high and 21 with a medium risk (70%) rating by the app were diagnosed as benign naevi or seborrhoeic keratoses. The interobserver agreement between the ratings of the automated risk assessment and the dermatologist was poor (weighted kappa = 0.02; 95% CI −0.08‐0.12; P = 0.74).

Conclusions

The rating of the automated risk assessment was poor. Further investigations about the diagnostic accuracy in real‐life situations are needed to provide consumers with reliable information about this healthcare application.

Patient Attitudes and Their Awareness Towards Skin Cancer-Related Apps: Cross-Sectional Survey

BACKGROUND

In the emerging era of digitalization and electronic health, skin cancer-related apps represent useful tools to support dermatologic consultation and examination. Yet, little is known about how patients perceive the value of such apps.

OBJECTIVE

The aim of this study was to investigate patient attitudes and their awareness toward skin cancer-related apps.

METHODS

A cross-sectional study including 200 patients from the oncological outpatient unit was conducted at the University Hospital (LMU Munich, Germany) between September and December 2018. Patients were asked to complete a self-administered questionnaire on the popularity and usefulness of health-related and skin cancer-related apps. A descriptive analysis was performed with the expression of categorical variables as frequencies and percentages. For continuous variables, the median and range were indicated. Contingency tables and chi-square tests were performed to investigate associations between sociodemographic data and selected items of the questionnaire.

RESULTS

A total of 98.9% (195/197) of patients had never used skin cancer-related apps or could not remember. In 49.7% (93/187) of cases, patients were unsure about the usefulness of skin cancer apps, whereas 42.6% (78/183) thought that skin cancer apps could supplement or support the professional skin examination performed by a physician. However, 47.9% (90/188) were interested in acquiring more information by their dermatologists about skin cancer apps. Young age (P=.002), male gender (P=.02), a previous history of melanoma (P=.004), and higher educational level (P=.002) were significantly associated with a positive attitude. Nevertheless, 55.9% (105/188) preferred a printed patient brochure on skin cancer to downloading and using an app.

CONCLUSIONS

The experience and knowledge of skin cancer-related apps was surprisingly low in this population, although there was a high general interest in more information about such apps. Printed patient brochures were the preferred information source.

The mTST - An mHealth approach for training and quality assurance of tuberculin skin test administration and reading

Background

The Tuberculin Skin Test (TST) is a relatively simple test for detecting latent tuberculosis infection (LTBI) but requires regular quality assurance to ensure proper technique for administration and reading. The objective of this study was to estimate the accuracy and reproducibility of an mhealth approach (the mTST) to measure the size of swelling immediately following TST administration (TST injection bleb) and after 48–72 hours (TST induration).

Methods

Five non-clinical and one clinical reviewer measured the size of TST injection blebs, and TST indurations using smartphone acquired photos of sites of TST administration and readings in patients, or saline injections in volunteers. The reference standard was the onsite measurement (measured by an experienced TB nurse) of the actual TST injection bleb, or induration. Agreement of reviewers’ measurements with the reference standard, as well as agreement within and between reviewers, was estimated using Cohen's kappa coefficient.

Results

Using the mTST method to assess bleb size in 64 photos of different TST injections, agreement between reviewers, and the reference standard was very good to excellent (κ ranged from 0.75 to 0.87), and within-reviewer reproducibility of readings was excellent (κ ranged from 0.86 to 0.96). Using the mTST method to assess TST induration in 72 photos, reviewers were able to detect no induration (<5mm) and induration of 15mm or greater with accuracy of 95% and 92% respectively, but accuracy was only 20% and 77% for reactions of 5-9mm and 10-14mm respectively.

Conclusion

The mTST approach appears to be a reliable tool to assess TST administration. The mTST approach was accurate to read indurations of 0-4mm or 15+mm, but less accurate for reactions of 5-14mm. We believe the mTST approach could be useful for training and quality assurance in locations where on-site supervision is not possible.

Beyond Dr. Google: the evidence on consumer-facing digital tools for diagnosis

Over a third of adults go online to diagnose their health condition. Direct-to-consumer (DTC), interactive, diagnostic apps with information personalization capabilities beyond those of static search engines are rapidly proliferating. While these apps promise faster, more convenient and more accurate information to improve diagnosis, little is known about the state of the evidence on their performance or the methods used to evaluate them. We conducted a scoping review of the peer-reviewed and gray literature for the period January 1, 2014–June 30, 2017. We found that the largest category of evaluations involved symptom checkers that applied algorithms to user-answered questions, followed by sensor-driven apps that applied algorithms to smartphone photos, with a handful of evaluations examining crowdsourcing. The most common clinical areas evaluated were dermatology and general diagnostic and triage advice for a range of conditions. Evaluations were highly variable in methodology and conclusions, with about half describing app characteristics and half examining actual performance. Apps were found to vary widely in functionality, accuracy, safety and effectiveness, although the usefulness of this evidence was limited by a frequent failure to provide results by named individual app. Overall, the current evidence base on DTC, interactive diagnostic apps is sparse in scope, uneven in the information provided and inconclusive with respect to safety and effectiveness, with no studies of clinical risks and benefits involving real-world consumer use. Given that DTC diagnostic apps are rapidly evolving, rigorous and standardized evaluations are essential to inform decisions by clinicians, patients, policymakers and other stakeholders.

Use of Smartphones for Early Detection of Melanoma: Systematic Review

Background

The early diagnosis of melanoma is associated with decreased mortality. The smartphone, with its apps and the possibility of sending photographs to a dermatologist, could improve the early diagnosis of melanoma.

Objective

The aim of our review was to report the evidence on (1) the diagnostic performance of automated smartphone apps and store-and-forward teledermatology via a smartphone in the early detection of melanoma, (2) the impact on the patient’s medical-care course, and (3) the feasibility criteria (focusing on the modalities of picture taking, transfer of data, and time to get a reply).

Methods

We conducted a systematic search of PubMed for the period from January 1, 2007 (launch of the first smartphone) to November 1, 2017.

Results

The results of the 25 studies included 13 concentrated on store-and-forward teledermatology, and 12 analyzed automated smartphone apps. Store-and-forward teledermatology opens several new perspectives, such as it accelerates the care course (less than 10 days vs 80 days), and the related procedures were assessed in primary care populations. However, the concordance between the conclusion of a teledermatologist and the conclusion of a dermatologist who conducts a face-to-face examination depended on the study (the kappa coefficient range was .20 to .84, median κ=.60). The use of a dermoscope may improve the concordance (the kappa coefficient range was .29 to .87, median κ=.74). Regarding automated smartphone apps, the major concerns are the lack of assessment in clinical practice conditions, the lack of assessment in primary care populations, and their low sensitivity, ranging from 7% to 87% (median 69%). In this literature review, up to 20% of the photographs transmitted were of insufficient quality. The modalities of picture taking and encryption of the data were only partially reported.

Conclusions

The use of store-and-forward teledermatology could improve access to a dermatology consultation by optimizing the care course. Our review confirmed the absence of evidence of the safety and efficacy of automated smartphone medical apps. Further research is required to determine quality criteria, as there was major variability among the studies.

Photoaging Mobile Apps as a Novel Opportunity for Melanoma Prevention: Pilot Study

Background

Around 90% of melanomas are caused by ultraviolet (UV) exposure and are therefore eminently preventable. Unhealthy tanning behavior is mostly initiated in early adolescence, often with the belief that it increases attractiveness; the problems related to skin atrophy and malignant melanoma are too far in the future to fathom. Photoaging desktop programs, in which an image is altered to predict future appearance, have been successful in positively influencing behavior in adiposity or tobacco prevention settings.

Objective

To develop and test a photoaging app designed for melanoma prevention.

Methods

We harnessed the widespread availability of mobile phones and adolescents’ interest in appearance to develop a free mobile app called Sunface. This app has the user take a self-portrait (ie, a selfie), and then photoages the image based on Fitzpatrick skin type and individual UV protection behavior. Afterward, the app explains the visual results and aims at increasing self-competence on skin cancer prevention by providing guideline recommendations on sun protection and the ABCDE rule for melanoma self-detection. The underlying aging algorithms are based on publications showing UV-induced skin damage by outdoor as well as indoor tanning. To get a first impression on how well the app would be received in a young target group, we included a total sample of 25 students in our cross-sectional pilot study with a median age of 22 (range 19-25) years of both sexes (11/25, 44% female; 14/25, 56% male) attending the University of Essen in Germany.

Results

The majority of enrolled students stated that they would download the app (22/25, 88%), that the intervention had the potential to motivate them to use sun protection (23/25, 92%) and that they thought such an app could change their perceptions that tanning makes you attractive (19/25, 76%). Only a minority of students disagreed or fully disagreed that they would download such an app (2/25, 8%) or that such an app could change their perceptions on tanning and attractiveness (4/25, 16%).

Conclusions

Based on previous studies and the initial study results presented here, it is reasonable to speculate that the app may induce behavioral change in the target population. Further work is required to implement and examine the effectiveness of app-based photoaging interventions within risk groups from various cultural backgrounds.