User satisfaction with a smartphone-compatible, artificial intelligence-based cutaneous pigmented lesion evaluator

INTRODUCTION Melanoma is the most aggressive type of skin cancer, and it may arise from a cutaneous pigmented lesion. As artificial intelligence (AI)-based teledermatology services hold promise in redefining the melanoma screening paradigm, a study that evaluates user satisfaction with a smartphone-compatible, AI-based cutaneous pigmented lesion evaluator is lacking. METHODS Data was collected between April and May 2019 in Taiwan. To assess user satisfaction with MoleMe, an AI-based cutaneous pigmented lesion evaluator on a smartphone, users were asked to complete a questionnaire designed to evaluate four aspects, including interaction, impact on daily life, usability, and overall performance, after completing a MoleMe evaluation session. For each question, users could rank their satisfaction level from 1 to 5, with five showing strongly satisfied and one showing strongly unsatisfied. The Kruskal-Wallis and Wilcoxon rank-sum tests were used to compare user satisfaction among different age groups, genders, and risk predictions received. RESULT A total of 1231 questionnaires were collected for analysis. Over 90% of the participants were satisfied (score = 4 or 5) and over 75% of the participants were strongly satisfied (score 5) with MoleMe, in terms of usability, interaction, and impact on daily life. The user satisfaction did not show a significant difference between genders, age groups, and risk predictions received. (all P > 0.05) CONCLUSION: With high user satisfaction regardless of age group, gender, and risk prediction received, AI-based teledermatology services on a smartphone such as MoleMe may potentially achieve widespread usage and be beneficial to both patients and physicians.

[1]  Yen-Po Chin,et al.  A patient‐oriented, general‐practitioner‐level, deep‐learning‐based cutaneous pigmented lesion risk classifier on a smartphone , 2020, The British journal of dermatology.

[2]  C. Motosko,et al.  How Should Artificial Intelligence Screen for Skin Cancer and Deliver Diagnostic Predictions to Patients? , 2018, JAMA dermatology.

[3]  R. Sagebiel,et al.  Melanocytic nevi in histologic association with primary cutaneous melanoma of superficial spreading and nodular types: effect of tumor thickness. , 1993, The Journal of investigative dermatology.

[4]  Susan M Swetter,et al.  Focus on early detection to reduce melanoma deaths. , 2015, The Journal of investigative dermatology.

[5]  Jeremy S Bordeaux,et al.  Early detection of melanoma: reviewing the ABCDEs. , 2015, Journal of the American Academy of Dermatology.

[6]  W. Kruskal,et al.  Use of Ranks in One-Criterion Variance Analysis , 1952 .

[7]  H. Haenssle,et al.  Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists , 2018, Annals of oncology : official journal of the European Society for Medical Oncology.

[8]  Eric J Topol,et al.  High-performance medicine: the convergence of human and artificial intelligence , 2019, Nature Medicine.

[9]  Chieh-Chen Wu,et al.  Patient satisfaction with dermatology teleconsultation by using MedX , 2018, Comput. Methods Programs Biomed..

[10]  Carlo Riccardo Rossi,et al.  Melanoma: epidemiology, risk factors, pathogenesis, diagnosis and classification. , 2014, In vivo.

[11]  T. Thompson,et al.  Total body skin examination for skin cancer screening among U.S. adults from 2000 to 2010. , 2014, Preventive medicine.

[12]  R. Dellavalle,et al.  A systematic review of satisfaction with teledermatology , 2017, Journal of telemedicine and telecare.

[13]  Antonio Escobar,et al.  Predictors of patient satisfaction with hospital health care , 2006, BMC Health Services Research.

[14]  M. Rahmqvist,et al.  Patient satisfaction in relation to age, health status and other background factors: a model for comparisons of care units. , 2001, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[15]  Ian Bowns,et al.  Patient satisfaction with teledermatology: quantitative and qualitative results from a randomized controlled trial , 2004, Journal of telemedicine and telecare.

[16]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[17]  D M Parkin,et al.  Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods , 2018, International journal of cancer.

[18]  Ahmedin Jemal,et al.  Incidence of noncutaneous melanomas in the U.S. , 2005, Cancer.

[19]  A Biggeri,et al.  Cutaneous melanoma histologically associated with a nevus and melanoma de novo have a different profile of risk: results from a case-control study. , 1999, Journal of the American Academy of Dermatology.

[20]  K Kroenke,et al.  Predictors of patient satisfaction. , 2001, Social science & medicine.

[21]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[22]  A. Armstrong,et al.  Impact of live interactive teledermatology on diagnosis, disease management, and clinical outcomes. , 2012, Archives of dermatology.

[23]  N. Shaw,et al.  Patient satisfaction with teledermatology is related to perceived quality of life , 2001, The British journal of dermatology.

[24]  Michael P Schön,et al.  Association of Patient Risk Factors and Frequency of Nevus-Associated Cutaneous Melanomas. , 2016, JAMA dermatology.

[25]  S. Han,et al.  Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm. , 2018, The Journal of investigative dermatology.

[26]  A Halpern,et al.  Clinically recognized dysplastic nevi. A central risk factor for cutaneous melanoma. , 1997, JAMA.

[27]  Arnold M. Epstein,et al.  Older Patients' Health Status and Satisfaction With Medical Care in an HMO Population , 1990, Medical care.

[28]  A. Stratigos,et al.  Emerging trends in the epidemiology of melanoma , 2014, The British journal of dermatology.

[29]  S. Swetter,et al.  State of the science on prevention and screening to reduce melanoma incidence and mortality: The time is now , 2016, CA: a cancer journal for clinicians.

[30]  J. Emery,et al.  Smartphone applications for melanoma detection by community, patient and generalist clinician users: a review , 2015, British Journal of Dermatology.

[31]  Giuseppe Argenziano,et al.  A meta‐analysis of nevus‐associated melanoma: Prevalence and practical implications , 2017, Journal of the American Academy of Dermatology.

[32]  C-W Huang,et al.  Mobile teledermatology for a prompter and more efficient dermatological care in rural Mongolia , 2015, The British journal of dermatology.

[33]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[34]  H. Soyer,et al.  Consumer acceptance of patient‐performed mobile teledermoscopy for the early detection of melanoma , 2016, The British journal of dermatology.

[35]  E. Holly,et al.  Number of melanocytic nevi as a major risk factor for malignant melanoma. , 1987, Journal of the American Academy of Dermatology.

[36]  K Kroenke,et al.  Patient satisfaction and quality of care. , 1997, Military medicine.

[37]  Anna Finnane,et al.  Recent trends in teledermatology and teledermoscopy , 2018, Dermatology practical & conceptual.

[38]  Jeffrey E Gershenwald,et al.  Final version of 2009 AJCC melanoma staging and classification. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[39]  C. Mathers,et al.  Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012 , 2015, International journal of cancer.

[40]  Ahmed Hosny,et al.  Artificial intelligence in radiology , 2018, Nature Reviews Cancer.

[41]  L Hue,et al.  Real‐time mobile teledermoscopy for skin cancer screening targeting an agricultural population: an experiment on 289 patients in France , 2015, Journal of the European Academy of Dermatology and Venereology : JEADV.

[42]  Xiaoyu Cui,et al.  Assessing the effectiveness of artificial intelligence methods for melanoma:A retrospective review. , 2019, Journal of the American Academy of Dermatology.

[43]  J. Whited,et al.  Teledermatology. Current status and future directions. , 2001, American journal of clinical dermatology.

[44]  Mohammed Nabhan,et al.  Melanoma screening: A plan for improving early detection , 2016, Annals of medicine.

[45]  Jonathan J Deeks,et al.  Smartphone applications for triaging adults with skin lesions that are suspicious for melanoma. , 2018, The Cochrane database of systematic reviews.

[46]  John Paoli,et al.  Smartphone teledermoscopy referrals: a novel process for improved triage of skin cancer patients. , 2015, Acta dermato-venereologica.

[47]  Y. Fujisawa,et al.  Deep‐learning‐based, computer‐aided classifier developed with a small dataset of clinical images surpasses board‐certified dermatologists in skin tumour diagnosis , 2018, The British journal of dermatology.

[48]  J. Naeyaert,et al.  Clinical practice. Dysplastic nevi. , 2003, The New England journal of medicine.

[49]  Sandra Nolte,et al.  Systematic skin cancer screening in Northern Germany. , 2012, Journal of the American Academy of Dermatology.