Dataset Information

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

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.

SUBMITTER: Nelson CA

PROVIDER: S-EPMC7066525 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundDue to more elderly and patients with complex illnesses, there is an increasing pressure on the healthcare system. General practice especially feels this pressure as being the first point of contact for the patients. Developments in digitalization have undergone fast progress and data-driven artificial intelligence (AI) has shown great potential for use in general practice. To develop AI as a support tool for general practitioners (GPs), access to patients' health data is needed, but patients have concerns regarding data sharing. Furthermore, studies show that trust is important regarding the patient-GP relationship, data sharing, and AI. The aim of this paper is to uncover patient perspectives on trust regarding the patient-GP relationship, data sharing and AI in general practice.MethodThis study investigated 10 patients' perspectives through qualitative interviews and written vignettes were chosen to elicit the patients (interviewees) perspectives on topics that they were not familiar with prior to the interviews. The study specifically investigated perspectives on 1) The patient-GP relationship, 2) data sharing regarding developing AI for general practice, and 3) implementation and use of AI in general practice using thematic analysis. The study took place in the North Denmark Region and the interviewees included had to be registered in general practice and be above 18 years in age. We included four men between 25 to 74 years in age and six women between 27 to 46 years in age.ResultsThe interviewees expressed a high level of trust towards their GP and were willing to share their health data with their GP. The interviewees believed that AI could be a great help to GPs if used as a support tool in general practice. However, it was important for the interviewees that the GP would still be the primary decision maker.ConclusionPatients may be willing to share health data to help implement and use AI in general practice. If AI is implemented in a way that preserves the patient-GP relationship and used as a support tool for the GP, our results indicate that patients may be positive towards the use of AI in general practice.

Project description:BackgroundThe emergence of artificial intelligence (AI) in medicine has prompted the development of numerous ethical guidelines, while the involvement of patients in the creation of these documents lags behind. As part of the European PROFID project we explore patient perspectives on the ethical implications of AI in care for patients at increased risk of sudden cardiac death (SCD).AimExplore perspectives of patients on the ethical use of AI, particularly in clinical decision-making regarding the implantation of an implantable cardioverter-defibrillator (ICD).MethodsSemi-structured, future scenario-based interviews were conducted among patients who had either an ICD and/or a heart condition with increased risk of SCD in Germany (n = 9) and the Netherlands (n = 15). We used the principles of the European Commission's Ethics Guidelines for Trustworthy AI to structure the interviews.ResultsSix themes arose from the interviews: the ability of AI to rectify human doctors' limitations; the objectivity of data; whether AI can serve as second opinion; AI explainability and patient trust; the importance of the 'human touch'; and the personalization of care. Overall, our results reveal a strong desire among patients for more personalized and patient-centered care in the context of ICD implantation. Participants in our study express significant concerns about the further loss of the 'human touch' in healthcare when AI is introduced in clinical settings. They believe that this aspect of care is currently inadequately recognized in clinical practice. Participants attribute to doctors the responsibility of evaluating AI recommendations for clinical relevance and aligning them with patients' individual contexts and values, in consultation with the patient.ConclusionThe 'human touch' patients exclusively ascribe to human medical practitioners extends beyond sympathy and kindness, and has clinical relevance in medical decision-making. Because this cannot be replaced by AI, we suggest that normative research into the 'right to a human doctor' is needed. Furthermore, policies on patient-centered AI integration in clinical practice should encompass the ethics of everyday practice rather than only principle-based ethics. We suggest that an empirical ethics approach grounded in ethnographic research is exceptionally well-suited to pave the way forward.

Project description:As breast screening services move towards use of healthcare AI (HCAI) for screen reading, research on public views of HCAI can inform more person-centered implementation. We synthesise reviews of public views of HCAI in general, and review primary studies of women's views of AI in breast screening. People generally appear open to HCAI and its potential benefits, despite a wide range of concerns; similarly, women are open towards AI in breast screening because of the potential benefits, but are concerned about a wide range of risks. Women want radiologists to remain central; oversight, evaluation and performance, care, equity and bias, transparency, and accountability are key issues; women may be less tolerant of AI error than of human error. Using our recent Australian primary study, we illustrate both the value of informing participants before collecting data, and women's views. The 40 screening-age women in this study stipulated four main conditions on breast screening AI implementation: 1) maintaining human control; 2) strong evidence of performance; 3) supporting familiarisation with AI; and 4) providing adequate reasons for introducing AI. Three solutions were offered to support familiarisation: transparency and information; slow and staged implementation; and allowing women to opt-out of AI reading. We provide recommendations to guide both implementation of AI in healthcare and research on public views of HCAI. Breast screening services should be transparent about AI use and share information about breast screening AI with women. Implementation should be slow and staged, providing opt-out options if possible. Screening services should demonstrate strong governance to maintain clinician control, demonstrate excellent AI system performance, assure data protection and bias mitigation, and give good reasons to justify implementation. When these measures are put in place, women are more likely to see HCAI use in breast screening as legitimate and acceptable.

Project description:BackgroundSkin cancer is the most common cancer type affecting humans. Traditional skin cancer diagnosis methods are costly, require a professional physician, and take time. Hence, to aid in diagnosing skin cancer, artificial intelligence (AI) tools are being used, including shallow and deep machine learning-based methodologies that are trained to detect and classify skin cancer using computer algorithms and deep neural networks.ObjectiveThe aim of this study was to identify and group the different types of AI-based technologies used to detect and classify skin cancer. The study also examined the reliability of the selected papers by studying the correlation between the data set size and the number of diagnostic classes with the performance metrics used to evaluate the models.MethodsWe conducted a systematic search for papers using Institute of Electrical and Electronics Engineers (IEEE) Xplore, Association for Computing Machinery Digital Library (ACM DL), and Ovid MEDLINE databases following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. The studies included in this scoping review had to fulfill several selection criteria: being specifically about skin cancer, detecting or classifying skin cancer, and using AI technologies. Study selection and data extraction were independently conducted by two reviewers. Extracted data were narratively synthesized, where studies were grouped based on the diagnostic AI techniques and their evaluation metrics.ResultsWe retrieved 906 papers from the 3 databases, of which 53 were eligible for this review. Shallow AI-based techniques were used in 14 studies, and deep AI-based techniques were used in 39 studies. The studies used up to 11 evaluation metrics to assess the proposed models, where 39 studies used accuracy as the primary evaluation metric. Overall, studies that used smaller data sets reported higher accuracy.ConclusionsThis paper examined multiple AI-based skin cancer detection models. However, a direct comparison between methods was hindered by the varied use of different evaluation metrics and image types. Performance scores were affected by factors such as data set size, number of diagnostic classes, and techniques. Hence, the reliability of shallow and deep models with higher accuracy scores was questionable since they were trained and tested on relatively small data sets of a few diagnostic classes.

Project description:BackgroundIn the incidental pulmonary nodule and breast cancer screening settings, high-quality patient-centered communication can improve adherence to evaluation and mitigate patient distress. Although guidelines emphasize shared decision-making before lung cancer screening, little is known about patient-clinician communication after lung cancer screening.Research questionHow do patients and clinicians perceive communication and results notification after lung cancer screening, and are there approaches that may mitigate or exacerbate distress?Study design and methodsWe conducted interviews and focus groups with 49 patients who underwent lung cancer screening in the prior year and 36 clinicians who communicate screening results (primary care providers, pulmonologists, nurses), recruited from lung cancer screening programs at 4 hospitals. We analyzed transcripts using conventional content analysis.ResultsClinicians and patients diverged in their impressions of the quality of communication after lung cancer screening. Clinicians recognized the potential for patient distress and tailored their approach to disclosure based on how clinically concerning they perceived results to be. Disclosure of normal or low-risk findings usually occurred by letter; clinicians believed this process was efficient and well received by patients. Yet many patients were dissatisfied: several could not recall receiving results at all, and others reported that receiving results by letter left them confused and concerned, with little opportunity to ask questions. By contrast, patients with larger nodules typically received results during an immediate phone call or clinic visit, and both patients and clinicians agreed that these conversations represented high-quality communication that met patient needs. Regardless of their cancer risk, patients who learned their results in a conversation appreciated the opportunity to discuss both the meaning of the nodule and the evaluation plan, and to have their concerns addressed, preempting distress.InterpretationTension exists between clinicians' interest in efficiency of results notification by letter in low-risk cases and patients' need to understand and be reassured about screening results, their implications, and the plan for subsequent screening or nodule evaluation-even when clinicians did not perceive results as concerning. Brief conversations to discuss lung cancer screening results may improve patient understanding and satisfaction while reducing distress.

Project description:BACKGROUND:Patients are increasingly seeking Web-based symptom checkers to obtain diagnoses. However, little is known about the characteristics of the patients who use these resources, their rationale for use, and whether they find them accurate and useful. OBJECTIVE:The study aimed to examine patients' experiences using an artificial intelligence (AI)-assisted online symptom checker. METHODS:An online survey was administered between March 2, 2018, through March 15, 2018, to US users of the Isabel Symptom Checker within 6 months of their use. User characteristics, experiences of symptom checker use, experiences discussing results with physicians, and prior personal history of experiencing a diagnostic error were collected. RESULTS:A total of 329 usable responses was obtained. The mean respondent age was 48.0 (SD 16.7) years; most were women (230/304, 75.7%) and white (271/304, 89.1%). Patients most commonly used the symptom checker to better understand the causes of their symptoms (232/304, 76.3%), followed by for deciding whether to seek care (101/304, 33.2%) or where (eg, primary or urgent care: 63/304, 20.7%), obtaining medical advice without going to a doctor (48/304, 15.8%), and understanding their diagnoses better (39/304, 12.8%). Most patients reported receiving useful information for their health problems (274/304, 90.1%), with half reporting positive health effects (154/302, 51.0%). Most patients perceived it to be useful as a diagnostic tool (253/301, 84.1%), as a tool providing insights leading them closer to correct diagnoses (231/303, 76.2%), and reported they would use it again (278/304, 91.4%). Patients who discussed findings with their physicians (103/213, 48.4%) more often felt physicians were interested (42/103, 40.8%) than not interested in learning about the tool's results (24/103, 23.3%) and more often felt physicians were open (62/103, 60.2%) than not open (21/103, 20.4%) to discussing the results. Compared with patients who had not previously experienced diagnostic errors (missed or delayed diagnoses: 123/304, 40.5%), patients who had previously experienced diagnostic errors (181/304, 59.5%) were more likely to use the symptom checker to determine where they should seek care (15/123, 12.2% vs 48/181, 26.5%; P=.002), but they less often felt that physicians were interested in discussing the tool's results (20/34, 59% vs 22/69, 32%; P=.04). CONCLUSIONS:Despite ongoing concerns about symptom checker accuracy, a large patient-user group perceived an AI-assisted symptom checker as useful for diagnosis. Formal validation studies evaluating symptom checker accuracy and effectiveness in real-world practice could provide additional useful information about their benefit.