The Artificial Intelligence in Teledermatology: A Narrative Review on Opportunities, Perspectives, and Bottlenecks
(This article belongs to the Section Digital Health)
Abstract
:1. Introduction
1.1. Background
1.2. Problems, Research Question, and Purpose of the Study
- To assess the trends and the evolution of the studies in this field;
- To assess the current state of the art methods in teledermatology and artificial intelligence, including their strengths and limitations;
- To identify the potential benefits of integrating teledermatology with artificial intelligence, such as increased accuracy and efficiency in diagnosing skin conditions, to improve patient outcomes and prioritize cost savings;
- To explore the challenges of and barriers to integrating teledermatology with artificial intelligence, such as data privacy concerns, regulatory issues, and the need for specialized expertise;
- To provide guidance on best practices for implementing and using teledermatology and artificial intelligence in dermatology, including recommendations for data collection and management, model development and validation, and clinical decision-making.
2. Methods
- –
- The definition of a process of selection;
- –
- The assessment of the study quality;
- –
- A data analysis/synthesis identifying the emerging patterns.
- 1.
- Set the search query to: “(teledermatology [Title/Abstract]) AND (artificial intelligence [Title/Abstract])”;
- 2.
- Conduct a targeted search on PubMed and Scopus using the search query from step 1;
- 3.
- Exclude conference papers from the search results;
- 4.
- Select studies published in peer-reviewed journals that focus on experiences of integration of artificial intelligence with teledermatology;
- 5.
- For each study, evaluate the following parameters:
- N1: Is the rationale for the study in the introduction clear?
- N2: Is the design of the work appropriate?
- N3: Are the methods described clearly?
- N4: Are the results presented clearly?
- N5: Are the conclusions based and justified by results?
- N6: Did the authors disclose all the conflicts of interest?
- 6.
- Assign a graded score to parameters N1–N5, ranging from 1 (minimum) to 5 (maximum);
- 7.
- For parameter N6, assign a binary assessment of “Yes” or “No” to indicate if the authors disclosed all the conflicts of interest;
- 8.
- Preselect studies that meet the following criteria:
- Parameter N6 must be “Yes”;
- Parameters N1–N5 must have a score greater than 3;
- 9.
- Include the preselected studies in the overview.
3. Results
3.1. Preliminary Considerations on the Results
3.2. Data Syntesys of the Overview of Scientific Papers
- The opportunities and the perspectives. Those studies that have mostly focused on the horizons of the application of TD and AI are included here;
- The role of the tool and the devices. The studies that have addressed the topic by focusing, in particular, on the tool dedicated to AI are included here;
- The applications in quality control. The studies that have addressed the applications of AI in quality control in diagnostic imaging are included here;
- The integration in mHealth. The studies that have addressed the integration in mHealth (where recently self-diagnosis applied to telemonitoring is gaining ground) are included here;
- The integration in the health domain: the acceptance, the standardization, and the management issues. All the studies that have somehow dealt with the aspects related to the integration of the health domain are included here (i.e., those studies that have offered a look at the problems of integration in stable healthcare processes). This topic is broad and includes, for example, studies on accuracy, acceptance, and regulatory and organizational aspects.
- Some studies, in addition to having primarily dealt with one of the issues identified above, have also dealt with other issues that overlap in a secondary way.
3.2.1. The Opportunities and the Perspectives
3.2.2. The Role of the Tools and Devices
3.2.3. The Applications in Quality Control
3.2.4. The Applications in mHealth
3.2.5. Towards the Integration in the Health Domain: The Acceptance, the Standardization, and the Management Issues
- (a)
- Ref. [32] Image post-processing capabilities vary greatly based on the user and the intended function. Technology standards are not always implemented or reported. Critical issues are also detected on the consent procedure and on other aspects of privacy and data confidentiality;
- (b)
- Ref. [33] The choices of different technical applications of image acquisition are hardly ever proposed in the tools. Users of these applications should consider which tools have standardized functionalities capable of improving the image quality.
3.3. Data Syntesys of the Overview of the Reviews
3.3.1. The Impact of the COVID-19 Pandemic
3.3.2. Opportunities in the Field of the Melanoma, Psoriasis, and Occupational Care
3.3.3. Perspectives in the Health Domain
4. Discussion
4.1. Added Value of the Review
4.2. Interpretation of Results
4.2.1. Opportunities and Perspectives
4.2.2. Emerging Problems and Bottlenecks
- (a)
- targeted agreement initiatives, with reference to position statements and guidelines;
- (b)
- the design of both efficient workflows and plans, allowing for better spread and interaction among the different actors.
4.3. Limitations
5. Conclusions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Kaliyadan, F.; Ramsey, M.L. Teledermatology. In StatPearls; StatPearls Publishing: Treasure Island, FL, USA, 2022. [Google Scholar]
- Pubmed Search. Available online: https://pubmed.ncbi.nlm.nih.gov/?term=teledermatology%5BTitle%2FAbstract%5D&sort=date (accessed on 25 April 2023).
- Santiago, S.; Lu, J. Patient Satisfaction in Teledermatology: An Updated Review. Curr. Dermatol. Rep. 2023. ahead of print. [Google Scholar] [CrossRef]
- Kriwy, P.; Nötzold, A.; Seitz, A.T.; Berger, R. Akzeptanz der Teledermatologie Ergebnisseeiner Befragung sächsischer Haus und HautärztInnen (Acceptance of Teledermatology: Results of a Survey of General Practitioners and Dermatologists in Saxony (Germany)). Gesundheitswesen 2023. ahead of print (In German) [Google Scholar]
- Ibrahim, A.E.; Magdy, M.; Khalaf, E.M.; Mostafa, A.; Arafa, A. Teledermatology in the time of COVID-19. Int. J. Clin. Pract. 2021, 75, e15000. [Google Scholar] [CrossRef] [PubMed]
- Mondal, S.; Mitra, P. The Role of Emerging Technologies to Fight Against COVID-19 Pandemic: An Exploratory Review. Trans. Indian Natl. Acad. Eng. 2022, 7, 157–174. [Google Scholar] [CrossRef] [PubMed]
- Ahuja, G.; Tahmazian, S.; Atoba, S.; Nelson, K. Exploring the Utility of Artificial Intelligence During COVID-19 in Dermatology Practice. Cutis 2021, 108, 71–72. [Google Scholar] [CrossRef]
- Liopyris, K.; Gregoriou, S.; Dias, J.; Stratigos, A.J. Artificial Intelligence in Dermatology: Challenges and Perspectives. Dermatol. Ther. 2022, 12, 2637–2651. [Google Scholar] [CrossRef] [PubMed]
- Giansanti, D. The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We? Healthcare 2020, 9, 30. [Google Scholar] [CrossRef]
- Giansanti, D. (Ed.) The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We? MDPI: Basel, Switzerland, 2022; ISBN 9783036543109. [Google Scholar]
- Majumder, A.; Sen, D. Artificial intelligence in cancer diagnostics and therapy: Current perspectives. Indian J. Cancer 2021, 58, 481–492. [Google Scholar] [CrossRef]
- Le, E.P.V.; Wang, Y.; Huang, Y.; Hickman, S.; Gilbert, F.J. Artificial intelligence in breast imaging. Clin. Radiol. 2019, 74, 357–366. [Google Scholar] [CrossRef]
- van Assen, M.; Banerjee, I.; De Cecco, C.N. Beyond the Artificial Intelligence Hype: What Lies Behind the Algorithms and What We Can Achieve. J. Thorac. Imaging 2020, 35 (Suppl. S1), S3–S10. [Google Scholar] [CrossRef]
- Giansanti, D. The Regulation of Artificial Intelligence in Digital Radiology in the Scientific Literature: A Narrative Review of Reviews. Healthcare 2022, 10, 1824. [Google Scholar] [CrossRef] [PubMed]
- Niazi, M.K.K.; Parwani, A.V.; Gurcan, M.N. Digital pathology and artificial intelligence. Lancet Oncol. 2019, 20, e253–e261. [Google Scholar] [CrossRef] [PubMed]
- Jurmeister, P.; Müller, K.R.; Klauschen, F. Künstliche Intelligenz als Lösung des PathologInnenmangels? (Artificial intelligence: A solution for the lack of pathologists?). Pathologe 2022, 43, 218–221. (In German) [Google Scholar] [CrossRef] [PubMed]
- Viswanathan, V.S.; Toro, P.; Corredor, G.; Mukhopadhyay, S.; Madabhushi, A. The state of the art for artificial intelligence in lung digital pathology. J. Pathol. 2022, 257, 413–429. [Google Scholar] [CrossRef] [PubMed]
- Giovagnoli, M.R.; Giansanti, D. Artificial Intelligence in Digital Pathology: What Is the Future? Part 1: From the Digital Slide Onwards. Healthcare 2021, 9, 858. [Google Scholar] [CrossRef] [PubMed]
- Pubmed Search. Available online: https://pubmed.ncbi.nlm.nih.gov/?term=%22teledermatology%22%5BTitle%2FAbstract%5D+AND+%22artificial+intelligence%22%5BTitle%2FAbstract%5D%E2%80%9D&sort=date&size=200 (accessed on 25 April 2023).
- Narative Review Checklist. Available online: https://www.elsevier.com/__data/promis_misc/ANDJ%20Narrative%20Review%20Checklist.pdf (accessed on 25 April 2023).
- Li, C.; Mun, J.H.; Pasquali, P.; Li, H.; Soyer, H.P.; Cui, Y. Editorial: Progress and Prospects on Skin Imaging Technology, Teledermatology and Artificial Intelligence in Dermatology. Front. Med. 2021, 8, 757538. [Google Scholar] [CrossRef]
- Mahmood, F.; Bendayan, S.; Ghazawi, F.M.; Litvinov, I.V. Editorial: The Emerging Role of Artificial Intelligence in Dermatology. Front. Med. 2021, 8, 751649. [Google Scholar] [CrossRef]
- Maqsood, S.; Damaševičius, R. Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare. Neural. Netw. 2023, 160, 238–258. [Google Scholar] [CrossRef]
- Escalé-Besa, A.; Fuster-Casanovas, A.; Börve, A.; Yélamos, O.; Fustà-Novell, X.; Esquius Rafat, M.; Marin-Gomez, F.X.; Vidal-Alaball, J. Using Artificial Intelligence as a Diagnostic Decision Support Tool in Skin Disease: Protocol for an Observational Prospective Cohort Study. JMIR Res. Protoc. 2022, 11, e37531. [Google Scholar] [CrossRef]
- Lee, H.; Ramani, L.T.; Parish, L.C.; Lee, J.B. Tools of dermatology: A historical perspective. Clin. Dermatol. 2021, 39, 555–562. [Google Scholar] [CrossRef]
- Jain, A.; Way, D.; Gupta, V.; Gao, Y.; de Oliveira Marinho, G.; Hartford, J.; Sayres, R.; Kanada, K.; Eng, C.; Nagpal, K.; et al. Development and Assessment of an Artificial Intelligence-Based Tool for Skin Condition Diagnosis by Primary Care Physicians and Nurse Practitioners in Teledermatology Practices. JAMA Netw. Open 2021, 4, e217249. [Google Scholar] [CrossRef]
- Jalaboi, R.; Winther, O.; Galimzianova, A. Explainable Image Quality Assessments in Teledermatological Photography. Telemed. J. e-Health 2023. ahead of print. [Google Scholar] [CrossRef] [PubMed]
- Hernández Montilla, I.; Mac Carthy, T.; Aguilar, A.; Medela, A. Dermatology Image Quality Assessment (DIQA): Artificial intelligence to ensure the clinical utility of images for remote consultations and clinical trials. J. Am. Acad. Dermatol. 2023, 88, 927–928. [Google Scholar] [CrossRef] [PubMed]
- Maier, K.; Zaniolo, L.; Marques, O. Image quality issues in teledermatology: A comparative analysis of artificial intelligence solutions. J. Am. Acad. Dermatol. 2022, 87, 240–242. [Google Scholar] [CrossRef]
- Hadeler, E.; Hong, J.; Mosca, M.; Hakimi, M.; Brownstone, N.; Bhutani, T.; Liao, W. Perspectives on the Future Development of Mobile Applications for Dermatology Clinical Research. Dermatol. Ther. 2021, 11, 1451–1456. [Google Scholar] [CrossRef] [PubMed]
- Po (Harvey) Chin, Y.; Hsin Huang, I.; Yu Hou, Z.; Yu Chen, P.; Bassir, F.; Han Wang, H.; Ting Lin, Y.; Chuan (Jack) Li, Y. User satisfaction with a smartphone-compatible, artificial intelligence-based cutaneous pigmented lesion evaluator. Comput. Methods Programs Biomed. 2020, 195, 105649. [Google Scholar] [CrossRef]
- Sun, M.D.; Kentley, J.; Wilson, B.W.; Soyer, H.P.; Curiel-Lewandrowski, C.N.; Rotemberg, V.M.; Halpern, A.C.; ISIC Technique Working Group. Digital skin imaging applications, part II: A comprehensive survey of post-acquisition image utilization features and technology standards. Skin Res. Technol. 2022, 28, 771–779. [Google Scholar] [CrossRef]
- Sun, M.D.; Kentley, J.; Wilson, B.W.; Soyer, H.P.; Curiel-Lewandrowski, C.N.; Rotemberg, V.; Halpern, A.C.; ISIC Technique Working Group. Digital skin imaging applications, part I: Assessment of image acquisition technique features. Skin Res. Technol. 2022, 28, 623–632. [Google Scholar] [CrossRef]
- Lewinson, R.T.; Vallerand, I.A. The Need for a National Strategy on Artificial Intelligence in Canadian Dermatology. J. Cutan. Med. Surg. 2020, 24, 428–429. [Google Scholar] [CrossRef]
- Sharma, A.; Jindal, V.; Singla, P.; Goldust, M.; Mhatre, M. Will teledermatology be the silver lining during and after COVID-19? Dermatol. Ther. 2020, 33, e13643. [Google Scholar] [CrossRef]
- Jones, O.T.; Jurascheck, L.C.; Utukuri, M.; Pannebakker, M.M.; Emery, J.; Walter, F.M. Dermoscopy use in UK primary care: A survey of GPs with a special interest in dermatology. J. Eur. Acad. Dermatol. Venereol. 2019, 33, 1706–1712. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Muñoz-López, C.; Ramírez-Cornejo, C.; Marchetti, M.A.; Han, S.S.; Del Barrio-Díaz, P.; Jaque, A.; Uribe, P.; Majerson, D.; Curi, M.; Del Puerto, C.; et al. Performance of a deep neural network in teledermatology: A single-centre prospective diagnostic study. J. Eur. Acad. Dermatol. Venereol. 2021, 35, 546–553. [Google Scholar] [CrossRef] [PubMed]
- MacLellan, A.N.; Price, E.L.; Publicover-Brouwer, P.; Matheson, K.; Ly, T.Y.; Pasternak, S.; Walsh, N.M.; Gallant, C.J.; Oakley, A.; Hull, P.R.; et al. The use of noninvasive imaging techniques in the diagnosis of melanoma: A prospective diagnostic accuracy study. J. Am. Acad. Dermatol. 2021, 85, 353–359. [Google Scholar] [CrossRef]
- Papachristou, I.; Bosanquet, N. Improving the prevention and diagnosis of melanoma on a national scale: A comparative study of performance in the United Kingdom and Australia. J. Public Health Policy 2020, 41, 28–38. [Google Scholar] [CrossRef] [PubMed]
- Felmingham, C.; MacNamara, S.; Cranwell, W.; Williams, N.; Wada, M.; Adler, N.R.; Ge, Z.; Sharfe, A.; Bowling, A.; Haskett, M.; et al. Improving Skin cancer Management with ARTificial Intelligence (SMARTI): Protocol for a preintervention/postintervention trial of an artificial intelligence system used as a diagnostic aid for skin cancer management in a specialist dermatology setting. BMJ Open 2022, 12, e050203. [Google Scholar] [CrossRef] [PubMed]
- Weber, P.; Sinz, C.; Rinner, C.; Kittler, H.; Tschandl, P. Perilesional sun damage as a diagnostic clue for pigmented actinic keratosis and Bowen’s disease. J. Eur. Acad. Dermatol. Venereol. 2021, 35, 2022–2026. [Google Scholar] [CrossRef] [PubMed]
- Lee, C.; Witkowski, A.; Żychowska, M.; Ludzik, J. The role of mobile teledermoscopy in skin cancer triage and management during the COVID-19 pandemic. Indian J. Dermatol. Venereol. Leprol. 2022. ahead of print. [Google Scholar] [CrossRef] [PubMed]
- Perrone, G.; Bilotta, C.; Tullio, V.; Pirrone, R.; Argo, A.; Zerbo, S. Telehealth modulation and new proposals during the Covid-19 pandemic: A literature review. Clin. Ter. 2022, 173, 489–495. [Google Scholar] [CrossRef]
- Goldust, Y.; Sameem, F.; Mearaj, S.; Gupta, A.; Patil, A.; Goldust, M. COVID-19 and artificial intelligence: Experts and dermatologists perspective. J. Cosmet. Dermatol. 2023, 22, 11–15. [Google Scholar] [CrossRef]
- Havelin, A.; Hampton, P. Telemedicine and e-Health in the Management of Psoriasis: Improving Patient Outcomes—A Narrative Review. Psoriasis 2022, 12, 15–24. [Google Scholar] [CrossRef]
- Mbunge, E.; Batani, J.; Gaobotse, G.; Muchemwa, B. Virtual healthcare services and digital health technologies deployed during coronavirus disease 2019 (COVID-19) pandemic in South Africa: A systematic review. Glob. Health J. 2022, 6, 102–113. [Google Scholar] [CrossRef] [PubMed]
- Skudalski, L.; Waldman, R.; Kerr, P.E.; Grant-Kels, J.M. Melanoma: How and when to consider clinical diagnostic technologies. J. Am. Acad. Dermatol. 2022, 86, 503–512. [Google Scholar] [CrossRef] [PubMed]
- Tognetti, L.; Fiorani, D.; Russo, F.; Lazzeri, L.; Trovato, E.; Flori, M.L.; Moscarella, E.; Cinotti, E.; Rubegni, P. Teledermatology in 2020: Past, present and future perspectives. Ital. J. Dermatol. Venerol. 2021, 156, 198–212. [Google Scholar] [CrossRef] [PubMed]
- Uppal, S.K.; Beer, J.; Hadeler, E.; Gitlow, H.; Nouri, K. The clinical utility of teledermoscopy in the era of telemedicine. Dermatol. Ther. 2021, 34, e14766. [Google Scholar] [CrossRef]
- Greis, C.; Maul, L.V.; Hsu, C.; Djamei, V.; Schmid-Grendelmeier, P.; Navarini, A.A. Künstliche Intelligenz zur Unterstützung der Telemedizin am Beispiel Afrikas (Artificial intelligence to support telemedicine in Africa). Hautarzt 2020, 71, 686–690. (In German) [Google Scholar] [CrossRef]
- Blum, A.; Bosch, S.; Haenssle, H.A.; Fink, C.; Hofmann-Wellenhof, R.; Zalaudek, I.; Kittler, H.; Tschandl, P. Künstliche Intelligenz und Smartphone-Programm—Applikationen (Apps): Bedeutung für die dermatologische Praxis (Artificial intelligence and smartphone program applications (Apps): Relevance for dermatological practice). Hautarzt 2020, 71, 691–698. (In German) [Google Scholar] [CrossRef]
- Young, A.T.; Xiong, M.; Pfau, J.; Keiser, M.J.; Wei, M.L. Artificial Intelligence in Dermatology: A Primer. J. Investig. Dermatol. 2020, 140, 1504–1512. [Google Scholar] [CrossRef]
- Pasquali, P.; Sonthalia, S.; Moreno-Ramirez, D.; Sharma, P.; Agrawal, M.; Gupta, S.; Kumar, D.; Arora, D. Teledermatology and its Current Perspective. Indian Dermatol. Online J. 2020, 11, 12–20. [Google Scholar] [CrossRef]
- Elsner, P.; Bauer, A.; Diepgen, T.L.; Drexler, H.; Fartasch, M.; John, S.M.; Schliemann, S.; Wehrmann, W.; Tittelbach, J. Position paper: Telemedicine in occupational dermatology—Current status and perspectives. J. Dtsch. Dermatol. Ges. 2018, 16, 969–974. [Google Scholar] [CrossRef] [Green Version]
- Alipour, J.; Hayavi-Haghighi, M.H. Opportunities and Challenges of Telehealth in Disease Management during COVID-19 Pandemic: A Scoping Review. Appl. Clin. Inform. 2021, 12, 864–876. [Google Scholar] [CrossRef]
- Giansanti, D.; Morone, G.; Loreti, A.; Germanotta, M.; Aprile, I. A Narrative Review of the Launch and the Deployment of Telemedicine in Italy during the COVID-19 Pandemic. Healthcare 2022, 10, 415. [Google Scholar] [CrossRef] [PubMed]
- Damiani, G.; Conic, R.R.Z.; Pigatto, P.D.M.; Carrera, C.G.; Franchi, C.; Cattaneo, A.; Malagoli, P.; Uppala, R.; Linder, D.; Bragazzi, N.L.; et al. Predicting Secukinumab Fast-Responder Profile in Psoriatic Patients: Advanced Application of Artificial-Neural-Networks (ANNs). J. Drugs Dermatol. 2020, 19, 1241–1246. [Google Scholar] [CrossRef] [PubMed]
- Damiani, G.; Buja, A.; Grossi, E.; Rivera, M.; De Polo, A.; De Luca, G.; Zorzi, M.; Vecchiato, A.; Del Fiore, P.; Saia, M.; et al. Use of an Artificial Neural Network to Identify Patient Clusters in a Large Cohort of Patients with Melanoma by Simultaneous Analysis of Costs and Clinical Characteristics. Acta Derm. Venereol. 2020, 100, adv00323. [Google Scholar] [CrossRef]
- Damiani, G.; Grossi, E.; Berti, E.; Conic, R.R.Z.; Radhakrishna, U.; Pacifico, A.; Bragazzi, N.L.; Piccinno, R.; Linder, D. Artificial neural networks allow response prediction in squamous cell carcinoma of the scalp treated with radiotherapy. J. Eur. Acad. Dermatol. Venereol. 2020, 34, 1369–1373. [Google Scholar] [CrossRef]
- Grossi, E.; Cazzaniga, S.; Crotti, S.; Naldi, L.; Di Landro, A.; Ingordo, V.; Cusano, F.; Atzori, L.; Tripodi Cutrì, F.; Musumeci, M.L.; et al. The constellation of dietary factors in adolescent acne: A semantic connectivity map approach. J. Eur. Acad. Dermatol. Venereol. 2016, 30, 96–100. [Google Scholar] [CrossRef]
- Giansanti, D.; Di Basilio, F. The Artificial Intelligence in Digital Radiology: Part 1: The Challenges, Acceptance and Consensus. Healthcare 2022, 10, 509. [Google Scholar] [CrossRef]
- Giovagnoli, M.R.; Ciucciarelli, S.; Castrichella, L.; Giansanti, D. Artificial Intelligence in Digital Pathology: What Is the Future? Part 2: An Investigation on the Insiders. Healthcare 2021, 9, 1347. [Google Scholar] [CrossRef] [PubMed]
Brief Summary of the Research | |
---|---|
[8] | Great opportunities in using TD and AI for remote diagnosis of skin lesions have been highlighted. |
[21] | Three key elements in TD and AI have been identified: the role and expectations of AI, the applicability of imaging techniques, and the developments in many applications. These elements offer great help in health and define routine models. |
[22] | Important prospects for TD and AI have been identified in virtual diagnosis, research, and development of advanced machine learning models for prognosticating dermatoses and classification, detection, and diagnosis. |
[23] | A proposed unified CAD model approach using AI showed to provide both lesion segmenting and classifying at the skin level with high performance and accuracy in imaging parameters. |
[24] | External testing was demonstrated essential for regulating the development of machine learning models in primary care settings. |
[25] | Important steps in the evolution of the tools that can be used in TD and AI have resumed. In this area, together with new technologies, new approaches and methodologies must coexist with historically consolidated methods. |
[26] | An automatic TD and AI tool improved the diagnosis of skin lesions by non-dermatologists, such as nurse practitioners or primary care specialists, with high potential for improving healthcare quality in dermatology. |
[27] | Quality assessment tools based on AI could identify criticalities in image quality, demonstrating performance similar to that of dermatologists and improving the TD process. |
[28] | A tool demonstrated a quality detection performance like that of dermatologists, allowing an improvement of the TD process. |
[29] | AI showed a leading role in ensuring the usefulness of a certain image in TD, and that different solutions for quality assessment require tuning for specific TD applications. |
[30] | The use of mobile applications demonstrated the potential to improve the participation in research projects during the pandemic. Pros and cons have been highlighted. |
[31] | A study on the assessment of user satisfaction with a smartphone-compatible application using an AI algorithm was proposed. The results highlighted both a high satisfaction and that the Apps were promising for all the actors of the health domain. |
[32] | A study in two parts was proposed. The first part highlighted that image postprocessing capabilities varied greatly based on the user and the intended function. Second, technology standards were not always implemented or reported. Critical issues were also detected on the consent procedure and on other aspects of privacy and data confidentiality. |
[33] | The second part of the study (se immediately above) highlighted that: the choices of different technical applications of image acquisition were hardly ever proposed in the tools, and users of these applications should consider which tools had standardized functionalities capable of improving the image quality. |
[34] | The problem of standards was addressed in a study with specific reference to the reality of the Canadian nation. |
[35] | A survey highlighted the belief that after COVID-19 this technology: could be of aid; will not replace but support professionals; and needed specific regulatory measures. |
[36] | A survey concluded that the technological innovations, including the use of AI and TD, could contribute to improving and enlarging the use of dermoscopy among general practitioners. |
[37] | An AI algorithm was evaluated in a telemedicine setting configured for TD where patients provided images via telemedicine. The study demonstrated that this configuration of the healthcare process was promising both in triage and in the assessment of skin lesions. |
[38] | An applied specific tool had very high specificity and sensitivity in TD and AI applications, showing potential to assist the clinical decision-making process. |
[39] | The accuracy of two countries in the national screenings in a certain dermatological field was compared. It was deduced that TD and AI could aid in speeding up the early diagnosis of melanoma, making the process easier and more economical without stressing the structures of the health systems. |
[40] | A project in progress was summarized. The aim was to: compare the decision taken by an AI-based classifier with that of the teledermatologist, the histopathologist, and other key professional figures. Consequently, to assess the impact on diagnostic and process management decisions including time, costs, personnel, and activities. |
[28] | Applications of AI in Dermatology Image Quality Assessment was discussed. AI was was find useful to ensure the clinical utility of images for remote consultations and clinical trials. |
[41] | Applications and perspectives on sun damage perilesions were reported, showing strengths and weakness of the applications. |
Brief Summary of the Research | |
---|---|
[42] | The use of mobile teledermoscopy (mTD) as a tool to improve communication and diagnosis between physicians, general practitioners, and patients was described. Patients could monitor suspicious skin lesions and send images for teleconsultation with the help of various AI-based Apps. It was highlighted that while this technology offered a promising solution in the post-COVID era, it should be noted that AI algorithms used in these Apps were not specific to dermoscopy, which could lead to problems with diagnostic accuracy. |
[43] | The role of technological innovation in various sectors of healthcare during the COVID-19 pandemic, including dermatology, was highlighted. The review reported that technology had enabled the sharing and rapid detection of cutaneous signs and symptoms of COVID-19, resulting in reduced face-to-face visits and cost and time savings |
[44] | The development of AI during the COVID-19 pandemic with reference to dermatology was addressed. Research showed that the use of TD and AI was strategic to discern six clinical dermatological patterns with a probable prognostic connection to COVID-19. |
[45] | The application of the TD and AI in psoriasis was investigated highlighting: the presence of a high number of Apps designed to help and guide to discern and/or monitor the pathology, and criticalities due to scarce App testing, validation, and publication data. |
[46] | The technological efforts to face COVID-19 in South Africa were remarked on in the review. It was reported that, among all the technologies, TD and AI provided an important contribution to the battle against COVID-19. |
[47] | The application of TD and AI in melanoma was investigated, highlighting that the novel noninvasive melanoma detection techniques were useful in the early detection of the pathology, as well as several useful pieces of advice on the use of different noninvasive techniques in clinical practice. |
[48] | It was reported a map point on the state of the art advances in TD and AI from both technological and clinical perspectives, including the role of AI and web platforms. The review highlighted the benefits of TD and AI, but also identified three limits to its implementation: the absence of clear regulations for TD and AI practice, the need for efficient workflows and plans to better interact with different actors, and the absence of agreement initiatives such as position statements and guidelines. |
[49] | The review focused on mobile TD (mTD) and its advantages in the health domain, such as low cost, practicality, and user-friendliness. mTD was considered not useful for monitoring chronic conditions that required continuous follow up and therapy tuning. Recommendations include expanding the applications of mTD in other fields and focusing more on the investigation of the role of AI and image assessment in TD. |
[50] | The review discussed the advantages of TD and AI in countries with limited resources and complex territories such as in Africa. It highlighted the importance of increasing the volume of medical data to improve the performance of AI models and systems. |
[51] | The review faced the potential disadvantages and risks of using AI in TD, particularly in the context of mHealth. The study recommended that satisfactory use of AI in mHealth required high-quality images, easy patient data upload, data exchange for both image upload and results download, as well as robust cybersecurity, and full disclosure of medical reimbursement and medico-legal aspects. |
[52] | The study reviewed dermatological applications of deep learning and categorized them into three fields: TD, clinical assessment augmentation, and dermatopathology. It stressed the importance of using standardized metrics for performance assessment of deep learning models and for addressing equity and ethical issues when applying these tools in clinical use. |
[53] | The review highlighted the importance of TD as a valid alternative to face-to-face visits and a useful tool for tele-consultation, tele-education, second opinions, and remote monitoring. It was also discussed the potential of combining artificial intelligence with TD techniques and medical imaging theory and the legal and ethical issues surrounding these applications. |
[54] | The potential of both store and forward TD and real-time TD in supporting specialists in occupational medicine for preventive care and cancer screening was reported. The study concluded that TD could play an important role in the prevention and monitoring of occupational skin pathologies and that Apps, including AI software, could have a strategic role in the self-monitoring of workers in high-risk job positions. |
Advantages/Opportunities | |
---|---|
1 | Improved quality of care, healthcare processes, and cost savings. |
2 | Reduced stress in healthcare facilities. |
3 | Increased citizen satisfaction and care, also in disadvantaged realities. |
4 | Early detection of skin cancer, leading to a reduction in unnecessary referrals, wait times, and cost of care. |
5 | Opportunities in specific sectors, such as the skin cancer, the sun perilesions, and the occupational medicine. |
6 | Utility as a triage and monitoring tool. |
7 | Integration with mHealth for self-care and remote diagnosis. |
8 | Balanced view on the use of AI and positive opinions on the opportunities. |
9 | Image quality control through appropriate tools and models. |
10 | Similar elements of process improvement, quality control, workflow revision as in digital radiology and digital pathology. |
Problem/Bottlenecks | |
---|---|
1 | Targeted agreement initiatives, with reference to position statements and guidelines (including regulations and ethics), to accompany the rapid developments of TD and AI (especially in mHealth) are strongly needed |
2 | Efficient workflows and plans are necessary to allow for better spread and interaction among the different actors involved in the use of TD and AI. |
3 | Synergistic regulatory initiatives are indispensable, both at an international and local level, to address the shortcomings of complex systems in TD and AI, as well as in other sectors. |
4 | It is crucial to focus on the peculiarities of the use of Apps in TD and AI in the hands of citizens. This includes clarifying validation processes, paying attention to cybersecurity aspects, and carefully focusing on system design, standards, and completeness of features proposed to citizens. |
5 | Before applying TD and AI in eHealth and mHealth applications, it is necessary to provide for the disclosure of all medico-legal (including reimbursement) and ethical aspects. |
6 | The risks of self-care, where citizens control/monitor themselves in a pathological way or without consulting experts, must be avoided when designing Apps for citizens. |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Giansanti, D. The Artificial Intelligence in Teledermatology: A Narrative Review on Opportunities, Perspectives, and Bottlenecks. Int. J. Environ. Res. Public Health 2023, 20, 5810. https://doi.org/10.3390/ijerph20105810
Giansanti D. The Artificial Intelligence in Teledermatology: A Narrative Review on Opportunities, Perspectives, and Bottlenecks. International Journal of Environmental Research and Public Health. 2023; 20(10):5810. https://doi.org/10.3390/ijerph20105810
Chicago/Turabian StyleGiansanti, Daniele. 2023. "The Artificial Intelligence in Teledermatology: A Narrative Review on Opportunities, Perspectives, and Bottlenecks" International Journal of Environmental Research and Public Health 20, no. 10: 5810. https://doi.org/10.3390/ijerph20105810