ABSTRACT
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.
Subject(s)
Artificial Intelligence , Mass Screening/methods , Melanoma/diagnosis , Skin Neoplasms/diagnosis , Adult , Aged , Biopsy , Early Detection of Cancer/methods , Female , Grounded Theory , Health Services Accessibility , Humans , Interviews as Topic , Male , Middle Aged , Observer Variation , Patient Acceptance of Health Care , Physician-Patient Relations , Qualitative Research , Reproducibility of ResultsABSTRACT
BACKGROUND: Search algorithms used to identify patients with alopecia areata (AA) need to be validated prior to use in large databases. OBJECTIVES: The aim of the study is to assess whether patients with an International Statistical Classification of Diseases and Related Health Problems (ICD) 9 or 10 code for AA have a true diagnosis of AA. MATERIALS AND METHODS: A multicenter retrospective review was performed at Columbia University Irving Medical Center, Brigham and Women's Hospital, and Massachusetts General Hospital to determine whether patients with an ICD 9 codes (704.01 - AA) or ICD 10 codes (L63.0 -Alopecia Totalis, L63.1 - Alopecia Universalis, L63.2 - Ophiasis, L63.8 - other AA, and L63.9 - AA, unspecified) for AA met diagnostic criteria for the disease. RESULTS: Of 880 charts, 97.5% had physical examination findings consistent with AA, and 90% had an unequivocal diagnosis. AA was diagnosed by a dermatologist in 87% of the charts. The positive predictive value (PPV) of the ICD 9 code 704.01 was 97% (248/255). The PPV for the ICD 10 codes were 64% (75/118) for L63.0, 86% (130/151) for L63.1, 50% (1/2) for L63.2, 91% (81/89) for L63.8, and 93% (247/265) for L63.9. Overall, 89% (782/880) of patients with an ICD code for AA were deemed to have a true diagnosis of AA. CONCLUSIONS: Patients whose medical records contain an AA-associated ICD code have a high probability of having the condition.
ABSTRACT
Tumor necrosis factor a (TNF-α)-targeted therapies have expanded the therapeutic options for patients with inflammatory bowel disease (IBD), rheumatoid arthritis (RA), psoriasis, and psoriatic arthritis (PsA) and have significantly improved patients' quality of life. Paradoxically, anti-TNF-α agents may induce psoriatic eruptions or worsen preexisting psoriatic skin disease. Currently, there is no standard approach for the management of TNF inhibitor-induced psoriasis. Here, we conduct a literature review on TNF inhibitor-induced psoriasis and introduce a novel treatment algorithm for maintaining otherwise effective anti-TNF therapy versus switching to a different class as appropriate in the management of patients with IBD, RA, psoriasis, or PsA.
