A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography.

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

Consumers' experiences, preferences, and perceptions of effectiveness in using telehealth for cancer care in Australia.

AIM: COVID-19 accelerated telehealth (video and telephone) use for cancer care to reduce disease exposure and transmission. Understanding consumers' health service delivery needs is required to sustain telehealth activity and develop new models of care. We explored consumers' experiences of telehealth in cancer care and their perspectives on improving and sustaining telehealth uptake in the future. METHODS: Exploratory design mixed-methods study using the Model for Assessment of Telemedicine (MAST) framework. Consumers affected by cancer completed an online survey and semistructured interviews. Quantitative data were analyzed using descriptive statistics and chi-square. Qualitative data from the MAST consumer domain were thematically analyzed. RESULTS: There were 1162 survey respondents and 18 interview participants. Video and telephone were used in cancer care with various providers. Telephone was used more frequently. Most respondents (85%) had reliable internet connections for video, however, 36% were not offered a video consultation. Video compared with telephone users were statistically significantly more likely to be satisfied with the quality of their treatment and perceived their consultation achieved as much as an in-person consultation. Telephone users (51%) compared with video users (31%) were more likely to perceive their concerns would have been better understood by their care provider if they were seen in person. Five themes emerged from the qualitative data. Consumers want modality choice, video provides superior experiences versus telephone, consultation mode preference is fluid, and consultation scheduling and administration need further consideration. CONCLUSION: Consumers support telehealth in cancer care. Consumers want consultation mode choices based on their needs and purpose of consultation.

Telehealth adoption in cancer clinical trials: An Australian perspective.

INTRODUCTION: Cancer clinical trials have traditionally occurred in-person. However, the COVID-19 pandemic has forced adaptions of all aspects of cancer care (including clinical trials) so they can be delivered remotely. We aimed to quantify and qualify current use of telehealth and how it can be further improved and routinely integrated into cancer clinical trials in Australia. METHODS: We used a mixed-method study design, involving surveys of 14 multi-site Collaborative Cancer Clinical Trial Groups members across Australia (n = 98) and qualitative interviews with trial administrators and clinicians (n = 21). RESULTS: The results of our study indicated a strong willingness to use telehealth for certain transactions of clinical trials because it was perceived as a way of increasing efficiency and reach of services. Hybrid models (including telehealth and in-person methods), which considered transaction, cancer type, and patient preferences were most favorable. Additionally, telehealth allowed for greater equity to access and reduced trial burden but interestingly had little effect on increased diversity and recruitment. Factors influencing telehealth service implementation and uptake included communication among trial stakeholders, training, and learning from the experience of others in the clinical trials community. CONCLUSION: Many but not all aspects of clinical trial care are appropriate to be delivered via telehealth. A hybrid approach provides flexibility to trial delivery and may support greater equity of access to trials in the future. Our findings and actionable recommendations support the need for greater planning, training, and guidelines to enable telehealth to be better integrated into clinical trials. Opportunities exist to expand the use of remote patient monitoring to enable more objective data collection from trial participants in the future.

Consumer perceptions on privacy and confidentiality in dermatology for 3D total-body imaging.

As 3D total-body photography for the early detection of melanoma is not yet widely used in clinical practice, we do not have a full understanding of patient's concerns about use, privacy and confidentiality, and if their concerns differ depending on the use-case. We conducted a virtual consumer forum to assess patients concerns about privacy and confidentiality in dermatology imaging for research, artificial intelligence development and for their own clinical care.

Cancer care and management during COVID-19: A comparison of in-person, video and telephone consultations.

In Australia, the COVID-19 pandemic has resulted in the exponential growth in the delivery of telehealth services. Medicare data indicates that the majority of telehealth consultations have used the telephone, despite the known benefits of using video. The aim of this study was to understand the perceived quality and effectiveness of in-person, telephone and videoconsultations for cancer care. Data was collected via online surveys with consumers (n = 1162) and health professionals (n = 59), followed by semi-structured interviews with telehealth experienced health professionals (n = 22) and consumers (n = 18). Data were analysed using descriptive statistics and significance was tested using the chi-square test. A framework analysis and thematic analysis were used for qualitative data. Results indicate telehealth is suitable for use across the cancer care pathway. However, consumers and health professionals perceived videoconsultations facilitated visual communication and improved patients' quality of care. The telephone was appropriate for short transactional consultations such as repeat prescriptions. Consumers were rarely given the choice of consultation modality. The choice of modality depended on a range of factors such as the type of consultation and stage of cancer care. Hybrid models of care utilising in-person, video and telephone should be developed and requires further guidance to promote the adoption of telehealth in cancer care.

Costs to the Medicare Benefits Schedule for general practitioner consultations: A time-series analysis.

The COVID-19 pandemic was a catalyst for the introduction of additional telehealth funding (telehealth item numbers) for general practitioner (GP) consultations through the Medicare Benefits Schedule (MBS) in Australia. This study evaluated the impact of telehealth funding on costs to the MBS for GP consultations from January 2017 to December 2021. An interrupted time series analysis assessed MBS costs (initial and monthly growth) for GP consultations (in-person, videoconference, telephone) before and after additional telehealth item numbers were introduced. From January 2017 to February 2020, total MBS costs for GP consultations were, on average, $545 million per month compared to $592 million per month from March 2020 to December 2021. There was an initial cost increase of approximately $39 million in the first month after additional telehealth funding was introduced (p = 0.0001). Afterwards, there was no significant change in monthly costs (p = 0.539). The introduction of additional MBS telehealth funding increased overall MBS costs for GP consultations. This increased cost for GP telehealth services could save costs to society if it translates into improved continuity of care, decreased hospitalisations, reduced productivity losses and improved patient outcomes. Future policy reform should incorporate a cost-benefit analysis to determine if increased MBS costs for GP consultations are a good investment.

Digital health experiences reported in chronic disease management: An umbrella review of qualitative studies.

INTRODUCTION: Digital health interventions can be useful for the management of chronic disease. The aim of this study was to draw out universal themes to understand how people with chronic conditions experience digital health services, programmes, and interventions, and consequently, better inform future digital health delivery. METHODS: An umbrella review was conducted to identify qualitative systematic reviews reporting digital health experiences in chronic disease. Themes for each included review were independently extracted and appraised by two review authors. Data analysis was conducted using the Constant Comparative method. RESULTS: Twenty-two systematic reviews containing 240 individual studies were selected for inclusion. Mental health was the most common condition (n = 5, 23%), followed by cancer (n = 4, 18%) or a combination of chronic diseases (n = 4, 18%). Common themes across the conditions were categorised under nine headings, including: (i) participation and engagement (strong usability and engagement vs reluctance to use digital health when these concepts are ignored), (ii) trust, confidence, and competence (users felt reassured, however technology illiteracy led to a perceived lack of control), (iii) perceived value, perceived effectiveness, transaction cost (gained from efficient aspects of digital health, but also lost through the burden of keeping up with data entry), (iv) perceived care quality (requiring tailoring and fostering motivation), (v) barriers and threats (related to technology risks and challenges), (vi) health outcomes (improved self-management capability), (vii) relationships (improved participant-health professional interaction, but interpersonal aspects such as face-to-face contact were lacking), (viii) unplanned benefit (where digital health often led to users feeling more empowered in their health journey), and (ix) diversity of experiences (reflecting ambivalence of experiences and discipline-specific experiences). CONCLUSION: People with chronic conditions perceive digital health provides feelings of reassurance and the ability to self-manage their condition. While there is ambivalence across the participant experiences reported within the major themes, this umbrella review has outlined a need for future interventions that are user-friendly, flexible, and tailored to individual users. This will be best achieved through a co-design model, with the consumer actively involved in the planning and design of digital health products and services.

Consumer Preference and Willingness to Pay for Direct-to-Consumer Mobile Teledermoscopy Services in Australia.

OBJECTIVE: To investigate consumer preference and willingness to pay for mobile teledermoscopy services in Australia. METHODS: Consumers who were taking part in a randomised controlled trial comparing mobile teledermoscopy and skin self-examination were asked to complete a survey which incorporated a discrete choice experiment (DCE) and a contingent valuation question. Responses were used to determine their willingness to pay for mobile teledermoscopy services in Australia and their overall service preferences. RESULTS: The 199 consumers who responded were 71% female and had a mean age of 42 years (range, 18-73). The DCE results showed that consumers prefer a trained medical professional to be involved in their skin cancer screening. Consumers were willing to pay AUD 41 to change from a general practitioner reviewing their lesions in-person to having a dermatologist reviewing the teledermoscopy images. Additionally, they were willing to pay for services that had shorter waiting times, that reduced the time away from their usual activities, and that have higher accuracy and lower likelihood of unnecessary excision of a skin lesion. When asked directly about their willingness to pay for a teledermoscopy service using a contingent valuation question, the majority (73%) of consumers selected the lowest two value brackets of AUD 1-20 or AUD 21-40. CONCLUSION: Consumers are willing to pay out of pocket to access services with attributes such as a dermatologist review, improved accuracy, and fewer excisions.

Enhancing a community palliative care service with telehealth leads to efficiency gains and improves job satisfaction.

Telepalliative care services enable clinicians to provide essential palliation services to people with a life-limiting illness in or closer to home. This study aims to explore the costs, service activity and staff experiences resulting from the introduction of telehealth in a community palliative care service in Queensland, Australia. Pre- and post-activity and cost data from the 2016-2017 and 2019-2020 financial years were examined and staff members interviewed. Accounting for inflation and standard wage increases, the labour costs before and after the addition of telehealth were approximately equal. There were small variations in non-labour costs, but these were not directly attributable to the expansion of the telehealth services. Overall, the service activity increased by 189% for standard doctor and nurse consultations, due to the increased efficiency of telehealth compared to the previous outreach (travel) model. Thematic analysis of the staff interview data generated an overarching theme of Increased Job Satisfaction which staff attributed to the patient-centred nature of the telepalliative care service, the increased peer support and increased professional development. Compared with the traditional in-person service, the new telehealth-supported model resulted in equivalent costs, greater efficiency by allowing palliative care to reach more patients and improved staff job satisfaction.

Specialist consultation activity and costs in Australia: Before and after the introduction of COVID-19 telehealth funding.

This study describes and analyses the Medicare Benefits Schedule (MBS) activity and cost data for specialist consultations in Australia, as a result of the coronavirus disease 2019 (COVID-19) pandemic. To achieve this, activity and cost data for MBS specialist consultations conducted from March 2019 to February 2021 were analysed month-to-month. MBS data for in-person, videoconference and telephone consultations were compared before and after the introduction of COVID-19 MBS telehealth funding in March 2020. The total number of MBS specialist consultations claimed per month did not differ significantly before and after the onset of COVID-19 (p = 0.717), demonstrating telehealth substitution of in-person care. After the introduction of COVID-19 telehealth funding, the average number of monthly telehealth consultations increased (p < 0.0001), representing an average of 19% of monthly consultations. A higher proportion of consultations were provided by telephone when compared to services delivered by video. Patient-end services did not increase after the onset of COVID-19, signifying a divergence from the historical service delivery model. Overall, MBS costs for specialist consultations did not vary significantly after introducing COVID-19 telehealth funding (p = 0.589). Telehealth consultations dramatically increased during COVID-19 and patients continued to receive specialist care. After the onset of COVID-19, the cost per telehealth specialist consultation was reduced, resulting in increased cost efficiency to the MBS.

A patient-centric dataset of images and metadata for identifying melanomas using clinical context.

Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.

The Future of Precision Prevention for Advanced Melanoma.

Precision prevention of advanced melanoma is fast becoming a realistic prospect, with personalized, holistic risk stratification allowing patients to be directed to an appropriate level of surveillance, ranging from skin self-examinations to regular total body photography with sequential digital dermoscopic imaging. This approach aims to address both underdiagnosis (a missed or delayed melanoma diagnosis) and overdiagnosis (the diagnosis and treatment of indolent lesions that would not have caused a problem). Holistic risk stratification considers several types of melanoma risk factors: clinical phenotype, comprehensive imaging-based phenotype, familial and polygenic risks. Artificial intelligence computer-aided diagnostics combines these risk factors to produce a personalized risk score, and can also assist in assessing the digital and molecular markers of individual lesions. However, to ensure uptake and efficient use of AI systems, researchers will need to carefully consider how best to incorporate privacy and standardization requirements, and above all address consumer trust concerns.

Queensland Telepaediatric Service: A Review of the First 15 Years of Service.

In November 2000, the Queensland Telepaediatric Service (QTS) was established in Brisbane, Australia, to support the delivery of telehealth services to patients and clinicians in regional and remote locations. The QTS was built on a centralized coordination model, where telehealth services could be effectively managed by a dedicated telehealth coordinator. In doing so, telehealth referral and consultation processes were efficient and clinicians felt better supported as they adjusted to new processes for engaging with patients. We have conducted a retrospective review of activity associated with the QTS and summarized key activities which have arisen from this extensive program of work. Telehealth service records and associated publications were used to describe the evolution of the QTS over a 15-year period. From November 2000 to March 2016, 23,054 telehealth consultations were delivered for 37 pediatric clinical specialties. The most common service areas included child and youth mental health, neurology, burns care, surgery, and ear nose and throat services. A range of different telehealth service models were developed to align with different clinical service needs and location of services. Whilst most work involved video consultation between hospitals, some services involved the delivery of telehealth services into the home, schools or community health centres. Despite its longevity, the QTS was not immune to the usual challenges associated with telehealth implementation, service redesign and sustainability. Experience reported from the QTS will be useful for other health services seeking to develop comprehensive telehealth services in a rapidly changing healthcare environment.

Evaluation of the efficacy of 3D total-body photography with sequential digital dermoscopy in a high-risk melanoma cohort: protocol for a randomised controlled trial.

INTRODUCTION: Melanoma is Australia's fourth most common cancer. Early detection is fundamental in maximising health outcomes and minimising treatment costs. To date, population-based screening programmes have not been justified in health economic studies. However, a skin surveillance approach targeting high-risk individuals could improve the cost-benefit ratio. METHODS AND ANALYSIS: This paper describes a 2-year longitudinal randomised controlled trial (RCT) to compare routine clinical care (control) with an intensive skin surveillance programme (intervention) consisting of novel three-dimensional (3D) total-body photography (TBP), sequential digital dermoscopy and melanoma-risk stratification, in a high-risk melanoma cohort. Primary outcomes will evaluate clinical, economic and consumer impact of the intervention. Clinical outcomes will evaluate differences in the rate of lesion excisions/biopsies per person, benign to malignant ratio for excisions and thickness of melanomas diagnosed. A health economic analysis using government data repositories will capture healthcare utilisation and costs relating to skin surveillance. Consumer questionnaires will examine intervention acceptability, the psychological impact, and attitudes towards melanoma risk and sun protective behaviour. Secondary outcomes include the development of a holistic risk algorithm incorporating clinical, phenotypic and genetic factors to facilitate the identification of those most likely to benefit from this surveillance approach. Furthermore, the feasibility of integrating the intervention with teledermatology to enhance specialist care in remote locations will be evaluated. This will be the first RCT to compare a targeted surveillance programme utilising new 3D TBP technology against current routine clinical care for individuals at high risk of melanoma. ETHICS AND DISSEMINATION: This study has received Human Research Ethics Committee (HREC) approval from both Metro South Health HREC (HREC/17/QPAH/816) and The University of Queensland HREC (2018000074). TRIAL REGISTRATION NUMBER: ANZCTR12618000267257; Pre-results.

What do Australian dermatologists expect to be paid for store-and-forward teledermoscopy? A preliminary investigation.

INTRODUCTION: Determining appropriate remuneration for teledermoscopy service is important because inadequate remuneration can be a barrier to practitioner uptake and participation. This study explores dermatologist remuneration expectations for a single lesion store-and-forward teledermoscopy consultation. METHODS: Fourteen dermatologists participated in telephone interviews during May-June 2017. Questions regarding remuneration focused on a clinical scenario involving teledermoscopy of a single lesion suspected to be skin cancer. The initial scenario was an existing patient, with a provisional diagnosis of benign neoplasm from the images, to be followed-up with routine skin checks, taking three minutes to review. Participants indicated their remuneration expectation by selecting from an ascending array of pre-determined remuneration ranges. The question was repeated a further four times with one aspect of the scenario changed each time; consultation length, source (patient or general practitioner), required follow-up, and a new rather than existing patient. Participants were also asked how appropriate they thought teledermoscopy was for the scenario, and whether they would choose to undertake the consultation presented. RESULTS: Nine dermatologists selected the AU$61-90 or AU$91-120 remuneration ranges for the initial scenario. When given the opportunity to comment on teledermoscopy service provision in Australia, respondents reflected that it was a valuable, advanced dermatology service, but they would prefer face-to-face consultation with patients where possible to allow for a full body examination. DISCUSSION: Dermatologists expect to be remunerated in the range of AU$61-120 for a single lesion store-and-forward teledermoscopy consultation when face-to-face examination is not possible.

Models of care in tele-ophthalmology: A scoping review.

The objective of this review was to identify and describe telehealth models of care for ophthalmic services. We conducted a scoping review of the literature to identify how ophthalmic care can be delivered by telehealth. We searched the PubMed database to identify relevant articles which were screened based on pre-defined inclusion criteria. For included articles, data were extracted, categorised and analysed. Synthesis of findings was performed narratively. The scoping review included 78 articles describing 62 discrete tele-ophthalmic models of care. Tele-ophthalmic models of care can be used for consultative service, screening, triage and remote supervision. The majority of services were for general eye care and triage ( n = 17; 26%) or emergency services ( n = 8; 12%). The most common conditions for disease-specific models of care were diabetic retinopathy ( n = 14; 21%), and glaucoma ( n = 8; 12%). Most models of care involved local clinicians capturing images and transmitting them to an ophthalmologist for assessment. This scoping review demonstrated tele-ophthalmology to be feasible for consultation, screening, triage and remote supervision applications across a broad range of ophthalmic conditions. A large number of models of care have been identified and described in this review. Considerable collaboration between patient-end clinicians and substantial infrastructure is typically required for tele-ophthalmology.

Direct-to-consumer mobile teledermoscopy for skin cancer screening: Preliminary results demonstrating willingness-to-pay in Australia.

Introduction Internationally, teledermoscopy has been found to have clinical and economic efficacy. This study aims to identify the attributes of a mobile teledermoscopy service that consumers prefer. This preliminary study was set within a broader randomised control trial (RCT) investigating the effectiveness of direct to consumer mobile teledermoscopy. Methods We undertook a discrete choice experiment (DCE). The DCE comprised 24 choice sets, divided into in two blocks of 12. For each choice set, respondents were asked to make discrete choices between two opt-out choices and two skin cancer screening service options described by seven attributes. A mixed logit model was used to estimate preferences for skin cancer screening services. Consumer preferences weights were used to calculate marginal willingness-to-pay (WTP) for skin cancer screening services. Results The DCE was completed by 113 consumer respondents. Consumers' preference for dermatologist involvement in their diagnosis, increased accuracy, and reduced excisions were all statistically significant in driving choice between service models. Consumers preferred having a professional involved in their skin cancer screening, rather than performing a self-examination. Consumers were only WTP $1.18 to change from a GP visit to mobile teledermoscopy (diagnosis using a phone camera). However, they were WTP $43 to have their results reviewed by a dermatologist rather than a GP, and $117 to increase the chance of detecting a melanoma if it was present from 65-75% to 95%. Conclusion Skin cancer screening services which are delivered by health professionals, rather than skin self-examination, are preferred by consumers. Consumers were willing to pay for their preferred skin cancer screening method, especially if a dermatologist was involved.

Cost-effectiveness of Skin Cancer Referral and Consultation Using Teledermoscopy in Australia.

Importance: International literature has shown that teledermoscopy referral may be a viable method for skin cancer referral; however, no economic investigations have occurred in Australia. Objective: To assess the cost-effectiveness of teledermoscopy as a referral mechanism for skin cancer diagnosis and management in Australia. Design, Setting, and Participants: Cost-effectiveness analysis using a decision-analytic model of Australian primary care, informed by publicly available data. Interventions: We compared the costs of teledermoscopy referral (electronic referral containing digital dermoscopic images) vs usual care (a written referral letter) for specialist dermatologist review of a suspected skin cancer. Main Outcomes and Measures: Cost and time in days to clinical resolution, where clinical resolution was defined as diagnosis by a dermatologist or excision by a general practitioner. Probabilistic sensitivity analysis was performed to examine the uncertainty of the main results. Results: Findings from the decision-analytic model showed that the mean time to clinical resolution was 9 days (range, 1-50 days) with teledermoscopy referral compared with 35 days (range, 0-138 days) with usual care alone (difference, 26 days; 95% credible interval [CrI], 13-38 days). The estimated mean cost difference between teledermoscopy referral (A$318.39) vs usual care (A$263.75) was A$54.64 (95% CrI, A$22.69-A$97.35) per person. The incremental cost per day saved to clinical resolution was A$2.10 (95% CrI, A$0.87-A$5.29). Conclusions and Relevance: Using teledermoscopy for skin cancer referral and triage in Australia would cost A$54.64 extra per case on average but would result in clinical resolution 26 days sooner than usual care. Implementation recommendations depend on the preferences of the Australian health system decision makers for either lower cost or expedited clinical resolution. Further research around the clinical significance of expedited clinical resolution and its importance for patients could inform implementation recommendations for the Australian setting.