Examining labelling guidelines for AI-based software as a medical device: A review and analysis of dermatology mobile applications in Australia.

In recent years, there has been a surge in the development of AI-based Software as a Medical Device (SaMD), particularly in visual specialties such as dermatology. In Australia, the Therapeutic Goods Administration (TGA) regulates AI-based SaMD to ensure its safe use. Proper labelling of these devices is crucial to ensure that healthcare professionals and the general public understand how to use them and interpret results accurately. However, guidelines for labelling AI-based SaMD in dermatology are lacking, which may result in products failing to provide essential information about algorithm development and performance metrics. This review examines existing labelling guidelines for AI-based SaMD across visual medical specialties, with a specific focus on dermatology. Common recommendations for labelling are identified and applied to currently available dermatology AI-based SaMD mobile applications to determine usage of these labels. Of the 21 AI-based SaMD mobile applications identified, none fully comply with common labelling recommendations. Results highlight the need for standardized labelling guidelines. Ensuring transparency and accessibility of information is essential for the safe integration of AI into health care and preventing potential risks associated with inaccurate clinical decisions.

Minimum labelling requirements for dermatology artificial intelligence-based Software as Medical Device (SaMD): A consensus statement.

BACKGROUND/OBJECTIVES: Artificial intelligence (AI) holds remarkable potential to improve care delivery in dermatology. End users (health professionals and general public) of AI-based Software as Medical Devices (SaMD) require relevant labelling information to ensure that these devices can be used appropriately. Currently, there are no clear minimum labelling requirements for dermatology AI-based SaMDs. METHODS: Common labelling recommendations for AI-based SaMD identified in a recent literature review were evaluated by an Australian expert panel in digital health and dermatology via a modified Delphi consensus process. A nine-point Likert scale was used to indicate importance of 10 items, and voting was conducted to determine the specific characteristics to include for some items. Consensus was achieved when more than 75% of the experts agreed that inclusion of information was necessary. RESULTS: There was robust consensus supporting inclusion of all proposed items as minimum labelling requirements; indication for use, intended user, training and test data sets, algorithm design, image processing techniques, clinical validation, performance metrics, limitations, updates and adverse events. Nearly all suggested characteristics of the labelling items received endorsement, except for some characteristics related to performance metrics. Moreover, there was consensus that uniform labelling criteria should apply across all AI categories and risk classes set out by the Therapeutic Goods Administration. CONCLUSIONS: This study provides critical evidence for setting labelling standards by the Therapeutic Goods Administration to safeguard patients, health professionals, consumers, industry, and regulatory bodies from AI-based dermatology SaMDs that do not currently provide adequate information about how they were developed and tested.

Informing a position statement on the use of artificial intelligence in dermatology in Australia.

Artificial Intelligence (AI) is the ability for computers to simulate human intelligence. In dermatology, there is substantial interest in using AI to identify skin lesions from images. Due to increasing research and interest in the use of AI, the Australasian College of Dermatologists has developed a position statement to inform its members of appropriate use of AI. This article presents the ACD Position Statement on the use of AI in dermatology, and provides explanatory information that was used to inform the development of this statement.

A CLOSE-UP guide to capturing clinical images.

Telemedicine is rapidly becoming ubiquitous as the medical profession adjusts its practice to provide optimal care to patients in the context of the COVID19 pandemic. The ability to provide accurate dermatological advice via telemedicine is dependent on the receipt of high-quality clinical images and accurate clinical context, on which clinicians receive little education during medical school and subsequent training. Clinicians can improve their capture, delivery and storage of images using the CLOSE-UP acronym, which encapsulates important considerations in the clinical photography process.

Practice guidelines for teledermatology in Australia.

Despite the potential of teledermatology to increase access to dermatology services and improve patient care, it is not widely practised in Australia. In an effort to increase uptake of teledermatology by Australian dermatologists and support best practice, guidelines for teledermatology for the Australian context have been developed by The University of Queensland's Centre for Online Health in collaboration with The Australasian College of Dermatologists' E-Health Committee. The guidelines are presented in two sections: 1. Guidelines and 2. Notes to support their application in practice, when feasible and appropriate. Content was last updated March 2020 and includes modalities of teledermatology; patient selection and consent; imaging; quality and safety; privacy and security; communication; and documentation and retention of clinical images. The guidelines educate dermatologists about the benefits and limitations of telehealth while articulating how to enhance patient care and reduce risk when practicing teledermatology.

A review of literature supporting the development of practice guidelines for teledermatology in Australia.

Despite the potential of teledermatology to increase access to dermatology services and improve patient care, it is not widely practised in Australia. In an effort to increase uptake of teledermatology, Australian-specific practice guidelines for teledermatology are being developed by the Australasian College of Dermatologist. This paper reports finding from literature reviews that were undertaken to inform the development of these guidelines. Results cover the following sections: Modalities of teledermatology; Patient selection and consent; Imaging; Quality and safety; Privacy and security; Communication; and Documentation and retention. The document educates providers about the benefits and limitations of telehealth while articulating how to enhance patient care and reduce risk when practicing teledermatology.

Smartphone apps for skin cancer diagnosis: Implications for patients and practitioners.

A research team at Stanford recently reported that their deep convolutional neural network had learned to classify skin cancer with a level of competence equivalent to that of board-certified dermatologists. It is possible that in time, and using larger datasets, such software may surpass the average doctor in diagnostic ability, and that highly accurate technology may be available to both clinicians and patients via smartphones. This technology is poised to change the landscape of skin cancer diagnosis for both physicians and patients, but whether such changes are beneficial will depend on how they are regulated and implemented.

Smartphone use in dermatology for clinical photography and consultation: Current practice and the law.

BACKGROUND: Smartphones are rapidly changing the way doctors capture and communicate clinical information, particularly in highly visual specialties such as dermatology. An understanding of how and why smartphones are currently used in clinical practice is critical in order to evaluate professional and legal risks, and to formulate policies that enable safe use of mobile technologies for the maximal benefit of practitioners and patients. METHODS: Australian dermatologists and dermatology trainees were surveyed on their current practices relating to clinical smartphone use. RESULTS: Of the 105 respondents, 101 provided useable results. The data show clinical smartphone use is common and frequent, with more than 50% of respondents sending and receiving images on their smartphones at least weekly. Clinical photographs were usually sent via multimedia message or email and were commonly stored on smartphones (46%). Security measures adopted to protect data were limited. There was inadequate documentation of consent for transmission of photographs and advice provided. Only 22% of respondents were aware of clear policies in their workplace regarding smartphone use, and a majority desired further education on digital image management. CONCLUSIONS: Given the frequency of use and the degree of importance placed on the ability to send and receive clinical images, clinical smartphone use will persist and will likely increase over time. Current practices are insufficient to comply with professional and legal obligations, and increase practitioners' vulnerability to civil and disciplinary proceedings. Further education, realistic policies and adequate software resources are critical to ensure protection of patients, practitioners and the reputation of the dermatological profession.

Open-label extension of a randomized trial investigating safety and efficacy of rhPTH(1-84) in hypoparathyroidism.

Hypoparathyroidism (HypoPT) is a rare disease, often inadequately controlled by conventional treatment. PARALLAX was a mandatory post-marketing trial assessing pharmacokinetics and pharmacodynamics of different dosing regimens of recombinant human parathyroid hormone 1-84 (rhPTH[1-84]) for treating HypoPT. The present study (NCT03364738) was a phase 4, 1-yr open-label extension of PARALLAX. Patients received only 2 doses of rhPTH(1-84) in PARALLAX and were considered treatment-naive at the start of the current study. rhPTH(1-84) was initiated at 50 µg once daily, with doses adjusted based on albumin-corrected serum calcium levels. Albumin-corrected serum calcium (primary outcome measure), health-related quality of life (HRQoL), adverse events, and healthcare resource utilization (HCRU) were assessed. The mean age of the 22 patients included was 50.0 yr; 81.8% were women, and 90.9% were White. By the end of treatment (EOT), 95.5% of patients had albumin-corrected serum calcium values in the protocol-defined range of 1.88 mmol/L to the upper limit of normal. Serum phosphorus was within the healthy range, and albumin-corrected serum calcium-phosphorus product was below the upper healthy limit throughout, while mean 24-h urine calcium excretion decreased from baseline to EOT. Mean supplemental doses of calcium and active vitamin D were reduced from baseline to EOT (2402-855 mg/d and 0.8-0.2 µg/d, respectively). Mean serum bone turnover markers, bone-specific alkaline phosphatase, osteocalcin, procollagen type I N-terminal propeptide, and type I collagen C-telopeptide increased 2-5 fold from baseline to EOT. The HCRU, disease-related symptoms and impact on HRQoL improved numerically between baseline and EOT. Nine patients (40.9%) experienced treatment-related adverse events; no deaths were reported. Treatment with rhPTH(1-84) once daily for 1 yr improved HRQoL, maintained eucalcemia in 95% of patients, normalized serum phosphorus, and decreased urine calcium excretion. The effects observed on urine calcium and the safety profile are consistent with previous findings. Clinical trial identifier: NCT03364738.

Efficacy and Safety of Parathyroid Hormone Replacement With TransCon PTH in Hypoparathyroidism: 26-Week Results From the Phase 3 PaTHway Trial.

Conventional therapy for hypoparathyroidism consisting of active vitamin D and calcium aims to alleviate hypocalcemia but fails to restore normal parathyroid hormone (PTH) physiology. PTH replacement therapy is the ideal physiologic treatment for hypoparathyroidism. The double-blind, placebo-controlled, 26-week, phase 3 PaTHway trial assessed the efficacy and safety of PTH replacement therapy for hypoparathyroidism individuals with the investigational drug TransCon PTH (palopegteriparatide). Participants (n = 84) were randomized 3:1 to once-daily TransCon PTH (initially 18 µg/d) or placebo, both co-administered with conventional therapy. The study drug and conventional therapy were titrated according to a dosing algorithm guided by serum calcium. The composite primary efficacy endpoint was the proportion of participants at week 26 who achieved normal albumin-adjusted serum calcium levels (8.3-10.6 mg/dL), independence from conventional therapy (requiring no active vitamin D and ≤600 mg/d of calcium), and no increase in study drug over 4 weeks before week 26. Other outcomes of interest included health-related quality of life measured by the 36-Item Short Form Survey (SF-36), hypoparathyroidism-related symptoms, functioning, and well-being measured by the Hypoparathyroidism Patient Experience Scale (HPES), and urinary calcium excretion. At week 26, 79% (48/61) of participants treated with TransCon PTH versus 5% (1/21) wiplacebo met the composite primary efficacy endpoint (p < 0.0001). TransCon PTH treatment demonstrated a significant improvement in all key secondary endpoint HPES domain scores (all p < 0.01) and the SF-36 Physical Functioning subscale score (p = 0.0347) compared with placebo. Additionally, 93% (57/61) of participants treated with TransCon PTH achieved independence from conventional therapy. TransCon PTH treatment normalized mean 24-hour urine calcium. Overall, 82% (50/61) treated with TransCon PTH and 100% (21/21) wiplacebo experienced adverse events; most were mild (46%) or moderate (46%). No study drug-related withdrawals occurred. In conclusion, TransCon PTH maintained normocalcemia while permitting independence from conventional therapy and was well-tolerated in individuals with hypoparathyroidism. © 2022 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

Beyond Burnout: A Physician Wellness Hierarchy Designed to Prioritize Interventions at the Systems Level.

Burnout has been implicated in higher physician turnover, reduced patient satisfaction, and worsened safety, but understanding the degree of burnout in a given physician or team does not direct leaders to solutions. The model proposed integrates a long list of variables that may ameliorate burnout into a prioritized, easy-to-understand hierarchy. Modified from Maslow's hierarchy, the model directs leaders to address physicians' basic physical and mental health needs first; patient and physician physical safety second; and then address higher-order needs, including respect from colleagues, patients, processes, and the electronic health record; appreciation and connection; and finally, time and resources to heal patients and contribute to the greater good. Assessments based on this model will help leaders prioritize interventions and improve physician wellness.

Using a Simulation of a Frustrated Faculty Member During Department Chair Searches: A Proof of Concept Project.

PROBLEM: Vitae reviews, interviews, presentations, and reference checks are typical components of searches used to screen and select new department chairs/heads, but these strategies may fail to identify leaders who can communicate effectively with faculty in common, tense situations. APPROACH: Between May 2015 and November 2016, the authors piloted simulation scenarios in four department chair searches at Penn State College of Medicine/Penn State Health to assess candidates' skill at handling common, challenging situations with faculty members. In the scenarios, a frustrated faculty member complains that he/she has too little time for academic pursuits. Candidates were provided the scenario approximately two weeks in advance. They were asked to explain their goals prior to the 10-minute simulation, do the simulation, and then debrief with the search committees, who observed the interactions. OUTCOMES: Approximately two-thirds (20/29; 69.0%) of candidates were judged to have successfully passed the simulation and were ultimately advanced. In most cases, the simulations revealed wide variation in candidates' style, substance, and even underlying values that were not otherwise identified through the other parts of the recruitment and screening process. In some cases, candidates who performed well during group and individual interviews did poorly during simulations. NEXT STEPS: The authors will build a larger pool of simulation scenario cases, create a rubric, and formally measure interrater reliability. They will study whether the strategy successfully identifies chairs who will be skilled at navigating common faculty challenges, and if this skill results in greater faculty satisfaction, engagement, and retention.

Rotation placements help students' understanding of intensive care.

It is vital that children's nursing students are fit for practice when they qualify and are able to meet various essential skills as defined by the Nursing and Midwifery Council (NMC). To gain the knowledge and skills required, students need placements in areas where high dependency and potentially intensive care are delivered. Efforts to maximise the number of students experiencing intensive care as a placement have led to the development of the paediatric intensive care unit (PICU) rotation, increasing placements on the PICU from 5 to 40 per cent of the student cohort per year. The lecturer practitioner organises the rotation, providing credible links between university and practice areas, while supporting students and staff in offering a high-quality placement experience. Students say the rotation offers a positive insight into PICU nursing, helping them develop knowledge and skills in a technical area and creating an interest in this specialty.