Patient Perspectives on the Use of Artificial Intelligence for Skin Cancer Screening: A Qualitative Study.

Importance: The use of artificial intelligence (AI) is expanding throughout the field of medicine. In dermatology, researchers are evaluating the potential for direct-to-patient and clinician decision-support AI tools to classify skin lesions. Although AI is poised to change how patients engage in health care, patient perspectives remain poorly understood. Objective: To explore how patients conceptualize AI and perceive the use of AI for skin cancer screening. Design, Setting, and Participants: A qualitative study using a grounded theory approach to semistructured interview analysis was conducted in general dermatology clinics at the Brigham and Women's Hospital and melanoma clinics at the Dana-Farber Cancer Institute. Forty-eight patients were enrolled. Each interview was independently coded by 2 researchers with interrater reliability measurement; reconciled codes were used to assess code frequency. The study was conducted from May 6 to July 8, 2019. Main Outcomes and Measures: Artificial intelligence concept, perceived benefits and risks of AI, strengths and weaknesses of AI, AI implementation, response to conflict between human and AI clinical decision-making, and recommendation for or against AI. Results: Of 48 patients enrolled, 26 participants (54%) were women; mean (SD) age was 53.3 (21.7) years. Sixteen patients (33%) had a history of melanoma, 16 patients (33%) had a history of nonmelanoma skin cancer only, and 16 patients (33%) had no history of skin cancer. Twenty-four patients were interviewed about a direct-to-patient AI tool and 24 patients were interviewed about a clinician decision-support AI tool. Interrater reliability ratings for the 2 coding teams were κ = 0.94 and κ = 0.89. Patients primarily conceptualized AI in terms of cognition. Increased diagnostic speed (29 participants [60%]) and health care access (29 [60%]) were the most commonly perceived benefits of AI for skin cancer screening; increased patient anxiety was the most commonly perceived risk (19 [40%]). Patients perceived both more accurate diagnosis (33 [69%]) and less accurate diagnosis (41 [85%]) to be the greatest strength and weakness of AI, respectively. The dominant theme that emerged was the importance of symbiosis between humans and AI (45 [94%]). Seeking biopsy was the most common response to conflict between human and AI clinical decision-making (32 [67%]). Overall, 36 patients (75%) would recommend AI to family members and friends. Conclusions and Relevance: In this qualitative study, patients appeared to be receptive to the use of AI for skin cancer screening if implemented in a manner that preserves the integrity of the human physician-patient relationship.

Measuring psoriatic arthritis symptoms: A core domain in psoriasis clinical trials.

BACKGROUND: The International Dermatology Outcome Measures established a set of core domains to be measured in all psoriasis trials. This set requires that symptoms of psoriatic arthritis (PsA) be measured in all psoriasis studies. OBJECTIVE: To identify the approach to PsA screening and the most appropriate outcome measure for capturing PsA symptoms. METHODS: Following guidelines (ie, the COnsensus-based Standards for the selection of health Measurement INstruments, Core Outcome Measures in Effectiveness Trials Initiative, and Outcome Measures in Rheumatology Handbook), we conducted a consensus-building study that included patients, physicians, industry partners, and patient association representatives. The process consisted of a literature review and quality appraisal of measures for PsA symptoms, a pre-Delphi exercise, a Delphi survey, and a consensus meeting. RESULTS: Among the 297 expert participants in the Delphi survey, 87.5% agreed that all patients in a psoriasis trial should be screened for PsA with a validated screening tool. Regarding the measurement of PsA symptoms, the preferred instrument was the Psoriatic Arthritis Impact of Disease-9 (PsAID9), with the Routine Assessment Patient Index Data-3 (RAPID3) representing an acceptable alternative. LIMITATIONS: Only International Dermatology Outcome Measures members participated in the consensus meeting. CONCLUSION: The overwhelming majority of expert stakeholders agreed that all psoriasis trial participants should be screened for PsA, with PsA symptoms measured by using PsAID9 (or alternatively with RAPID3).

Achieving international consensus on the assessment of psoriatic arthritis in psoriasis clinical trials: an International Dermatology Outcome Measures (IDEOM) initiative.

Psoriatic arthritis (PsA) is rarely assessed in psoriasis randomized controlled trials (RCT); thus, the effect of psoriasis therapy on PsA is unknown. The International Dermatology Outcome Measures (IDEOM) has included "PsA Symptoms" as part of the core domains to be measured in psoriasis RCT. This study aimed to achieve consensus about screening for PsA and how to measure for "PsA Symptoms" in psoriasis RCT. At the IDEOM 2017 Annual Meeting, stakeholders voted on the role of PsA screening in psoriasis RCT. To select measures for "PsA Symptoms", we adapted the Consensus-Based Standards for the Selection of Health Measurement Instruments (COSMIN) guidelines. Three potential measures were selected. At the meeting, stakeholders voted on the validity, feasibility, and responsiveness of these measures. Of the 47 stakeholders, 93% voted that all psoriasis trial participants should be screened for PsA. "PsA Symptoms" measures included Patient Global (PG)-arthritis, Routine Assessment Patient Index Data (RAPID)-3, and Psoriatic Arthritis Impact of Disease (PsAID)-9. During the voting, more than 50% of the voters agreed that RAPID3 and PsAID9 were good measures for PsA Symptoms, able to capture all its essential elements. PsAID9 was considered the most feasible instrument, followed by RAPID3 and PG-arthritis, respectively. Finally, most participants agreed that RAPID3 and PsAID9 were responsive measures. Most study participants voted that all subjects in a psoriasis clinical trial should be screened for PsA. RAPID3 and PsAID9 outperformed PG-arthritis in measuring PsA Symptoms. This will be followed by a Delphi survey involving a larger stakeholder group.