1
|
Thribhuvan Reddy D, Grewal I, García Pinzon LF, Latchireddy B, Goraya S, Ali Alansari B, Gadwal A. The Role of Artificial Intelligence in Healthcare: Enhancing Coronary Computed Tomography Angiography for Coronary Artery Disease Management. Cureus 2024; 16:e61523. [PMID: 38957241 PMCID: PMC11218716 DOI: 10.7759/cureus.61523] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/02/2024] [Indexed: 07/04/2024] Open
Abstract
This review aims to explore the potential of artificial intelligence (AI) in coronary CT angiography (CCTA), a key tool for diagnosing coronary artery disease (CAD). Because CAD is still a major cause of death worldwide, effective and accurate diagnostic methods are required to identify and manage the condition. CCTA certainly is a noninvasive alternative for diagnosing CAD, but it requires a large amount of data as input. We intend to discuss the idea of incorporating AI into CCTA, which enhances its diagnostic accuracy and operational efficiency. Using such AI technologies as machine learning (ML) and deep learning (DL) tools, CCTA images are automated to perfection and the analysis is significantly refined. It enables the characterization of a plaque, assesses the severity of the stenosis, and makes more accurate risk stratifications than traditional methods, with pinpoint accuracy. Automating routine tasks through AI-driven CCTA will reduce the radiologists' workload considerably, which is a standard benefit of such technologies. More importantly, it would enable radiologists to allocate more time and expertise to complex cases, thereby improving overall patient care. However, the field of AI in CCTA is not without its challenges, which include data protection, algorithm transparency, as well as criteria for standardization encoding. Despite such obstacles, it appears that the integration of AI technology into CCTA in the future holds great promise for keeping CAD itself in check, thereby aiding the fight against this disease and begetting better clinical outcomes and more optimized modes of healthcare. Future research on AI algorithms for CCTA, making ethical use of AI, and thereby overcoming the technical and clinical barriers to widespread adoption of this new tool, will hopefully pave the way for profound AI-driven transformations in healthcare.
Collapse
Affiliation(s)
| | - Inayat Grewal
- Department of Medicine, Government Medical College and Hospital, Chandigarh, IND
| | | | | | - Simran Goraya
- Department of Medicine, Kharkiv National Medical University, Kharkiv, UKR
| | | | - Aishwarya Gadwal
- Department of Radiodiagnosis, St. John's Medical College and Hospital, Bengaluru, IND
| |
Collapse
|
2
|
Waseem Sabir M, Farhan M, Almalki NS, Alnfiai MM, Sampedro GA. FibroVit-Vision transformer-based framework for detection and classification of pulmonary fibrosis from chest CT images. Front Med (Lausanne) 2023; 10:1282200. [PMID: 38020169 PMCID: PMC10666764 DOI: 10.3389/fmed.2023.1282200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Accepted: 10/23/2023] [Indexed: 12/01/2023] Open
Abstract
Pulmonary Fibrosis (PF) is an immedicable respiratory condition distinguished by permanent fibrotic alterations in the pulmonary tissue for which there is no cure. Hence, it is crucial to diagnose PF swiftly and precisely. The existing research on deep learning-based pulmonary fibrosis detection methods has limitations, including dataset sample sizes and a lack of standardization in data preprocessing and evaluation metrics. This study presents a comparative analysis of four vision transformers regarding their efficacy in accurately detecting and classifying patients with Pulmonary Fibrosis and their ability to localize abnormalities within Images obtained from Computerized Tomography (CT) scans. The dataset consisted of 13,486 samples selected out of 24647 from the Pulmonary Fibrosis dataset, which included both PF-positive CT and normal images that underwent preprocessing. The preprocessed images were divided into three sets: the training set, which accounted for 80% of the total pictures; the validation set, which comprised 10%; and the test set, which also consisted of 10%. The vision transformer models, including ViT, MobileViT2, ViTMSN, and BEiT were subjected to training and validation procedures, during which hyperparameters like the learning rate and batch size were fine-tuned. The overall performance of the optimized architectures has been assessed using various performance metrics to showcase the consistent performance of the fine-tuned model. Regarding performance, ViT has shown superior performance in validation and testing accuracy and loss minimization, specifically for CT images when trained at a single epoch with a tuned learning rate of 0.0001. The results were as follows: validation accuracy of 99.85%, testing accuracy of 100%, training loss of 0.0075, and validation loss of 0.0047. The experimental evaluation of the independently collected data gives empirical evidence that the optimized Vision Transformer (ViT) architecture exhibited superior performance compared to all other optimized architectures. It achieved a flawless score of 1.0 in various standard performance metrics, including Sensitivity, Specificity, Accuracy, F1-score, Precision, Recall, Mathew Correlation Coefficient (MCC), Precision-Recall Area under the Curve (AUC PR), Receiver Operating Characteristic and Area Under the Curve (ROC-AUC). Therefore, the optimized Vision Transformer (ViT) functions as a reliable diagnostic tool for the automated categorization of individuals with pulmonary fibrosis (PF) using chest computed tomography (CT) scans.
Collapse
Affiliation(s)
| | - Muhammad Farhan
- Department of Computer Science, COMSATS University Islamabad, Sahiwal, Pakistan
| | - Nabil Sharaf Almalki
- Department of Special Education, College of Education, King Saud University, Riyadh, Saudi Arabia
| | - Mrim M. Alnfiai
- Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia
| | - Gabriel Avelino Sampedro
- Faculty of Information and Communication Studies, University of the Philippines Open University, Los Baños, Philippines
- Center for Computational Imaging and Visual Innovations, De La Salle University, Manila, Philippines
| |
Collapse
|
3
|
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:ijerph20105810. [PMID: 37239537 DOI: 10.3390/ijerph20105810] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/16/2023] [Revised: 04/27/2023] [Accepted: 05/03/2023] [Indexed: 05/28/2023]
Abstract
Artificial intelligence (AI) is recently seeing significant advances in teledermatology (TD), also thanks to the developments that have taken place during the COVID-19 pandemic. In the last two years, there was an important development of studies that focused on opportunities, perspectives, and problems in this field. The topic is very important because the telemedicine and AI applied to dermatology have the opportunity to improve both the quality of healthcare for citizens and the workflow of healthcare professionals. This study conducted an overview on the opportunities, the perspectives, and the problems related to the integration of TD with AI. The methodology of this review, following a standardized checklist, was based on: (I) a search of PubMed and Scopus and (II) an eligibility assessment, using parameters with five levels of score. The outcome highlighted that applications of this integration have been identified in various skin pathologies and in quality control, both in eHealth and mHealth. Many of these applications are based on Apps used by citizens in mHealth for self-care with new opportunities but also open questions. A generalized enthusiasm has been registered regarding the opportunities and general perspectives on improving the quality of care, optimizing the healthcare processes, minimizing costs, reducing the stress in the healthcare facilities, and in making citizens, now at the center, more satisfied. However, critical issues have emerged related to: (a) the need to improve the process of diffusion of the Apps in the hands of citizens, with better design, validation, standardization, and cybersecurity; (b) the need for better attention paid to medico-legal and ethical issues; and (c) the need for the stabilization of international and national regulations. Targeted agreement initiatives, such as position statements, guidelines, and/or consensus initiatives, are needed to ensure a better result for all, along with the design of both specific plans and shared workflows.
Collapse
|
4
|
Ilicki J. Challenges in evaluating the accuracy of AI-containing digital triage systems: A systematic review. PLoS One 2022; 17:e0279636. [PMID: 36574438 PMCID: PMC9794085 DOI: 10.1371/journal.pone.0279636] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 12/12/2022] [Indexed: 12/28/2022] Open
Abstract
INTRODUCTION Patient-operated digital triage systems with AI components are becoming increasingly common. However, previous reviews have found a limited amount of research on such systems' accuracy. This systematic review of the literature aimed to identify the main challenges in determining the accuracy of patient-operated digital AI-based triage systems. METHODS A systematic review was designed and conducted in accordance with PRISMA guidelines in October 2021 using PubMed, Scopus and Web of Science. Articles were included if they assessed the accuracy of a patient-operated digital triage system that had an AI-component and could triage a general primary care population. Limitations and other pertinent data were extracted, synthesized and analysed. Risk of bias was not analysed as this review studied the included articles' limitations (rather than results). Results were synthesized qualitatively using a thematic analysis. RESULTS The search generated 76 articles and following exclusion 8 articles (6 primary articles and 2 reviews) were included in the analysis. Articles' limitations were synthesized into three groups: epistemological, ontological and methodological limitations. Limitations varied with regards to intractability and the level to which they can be addressed through methodological choices. Certain methodological limitations related to testing triage systems using vignettes can be addressed through methodological adjustments, whereas epistemological and ontological limitations require that readers of such studies appraise the studies with limitations in mind. DISCUSSION The reviewed literature highlights recurring limitations and challenges in studying the accuracy of patient-operated digital triage systems with AI components. Some of these challenges can be addressed through methodology whereas others are intrinsic to the area of inquiry and involve unavoidable trade-offs. Future studies should take these limitations in consideration in order to better address the current knowledge gaps in the literature.
Collapse
|
5
|
Wiener AA, Schumacher JR, Racz JM, Weber SM, Xu YG, Neuman HB. Incidence of Second Primary Melanoma in Cutaneous Melanoma Survivors. Ann Surg Oncol 2022; 29:5925-5932. [PMID: 35505144 DOI: 10.1245/s10434-022-11725-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Accepted: 03/16/2022] [Indexed: 11/18/2022]
Abstract
BACKGROUND Cutaneous melanoma survivors are at increased risk of a second primary melanoma. Valid estimates facilitate counseling on recommended surveillance after a melanoma diagnosis. However, most estimates of 5- and 10-year incidences of second melanomas are from older cohorts and/or single institutions. This study aimed to determine the 5- and 10-year incidences of second primary cutaneous melanomas in survivors of cutaneous melanoma. METHODS The Surveillance, Epidemiology, and End Results (SEER) database was used to identify cases of non-metastatic, first cutaneous melanoma diagnosed between 1998 and 2012 (follow-up through December 2017). Eligible survivors were 18 years old or older who underwent surgery as a treatment component. Kaplan-Meier survival analysis was used to estimate 5- and 10-year incidences of a second melanoma, excluding new diagnoses within 3 months after the initial diagnosis. Patients were censored at second melanoma diagnosis, death, or 10-years, whichever was first. Multivariable Cox regression analysis was used to identify factors associated with a second cutaneous melanoma diagnosis. RESULTS The study cohort comprised 152,811 patients. The incidence of second primary melanoma was 3.9% at 5 years (95% confidence interval [CI], 3.8-4.0%) and 6.7% at 10 years (95% CI, 6.6-6.9%). Older age, male sex, and regional disease were associated with increased risk of a second primary melanoma diagnosis. CONCLUSION Melanoma survivors are at risk of a second primary melanoma, making routine skin surveillance part of recommended follow-up evaluation. A higher incidence of second melanoma with older age and regional disease at presentation is possibly explained by increased health care use providing more diagnostic opportunities, whereas male sex may represent an inherent risk factor.
Collapse
Affiliation(s)
- Alyssa A Wiener
- Department of Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Jessica R Schumacher
- Department of Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Jennifer M Racz
- Department of Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Sharon M Weber
- Department of Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Yaohui G Xu
- Department of Dermatology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Heather B Neuman
- Department of Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
| |
Collapse
|
6
|
McNoe BM, Gage R, Signal L. What can Aotearoa New Zealand learn from the Australian Sunsmart Story? A qualitative study. Aust N Z J Public Health 2022; 46:387-393. [PMID: 35436015 DOI: 10.1111/1753-6405.13243] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Revised: 02/01/2022] [Accepted: 02/01/2022] [Indexed: 11/28/2022] Open
Abstract
OBJECTIVE To explore the views of stakeholders in Australia concerning skin cancer primary prevention and identify successful strategies used that may be translatable to other jurisdictions. METHODS In-depth stakeholder interviews with experts engaged in skin cancer prevention advocacy and action in Australia. RESULTS A number of important facilitators were identified including: the use of good scientific evidence (including economic), strong leadership, legislation and strategic documents, engaging the media particularly with the use of personal stories and garnering public support. A number of barriers were also identified including: a lack of funding (particularly nationally), variation by state, apathy and the long latency of skin cancer. CONCLUSIONS Advocates identified a number of key strategies that were used to gain momentum in achieving Australia's comprehensive Sunsmart program. These included: strong leadership, legislation including that banning solaria and workplace health and safety legislation, a critical mass of key advocates from a range of disciplines including clinicians and patients, and the advantageous use of media to drive change. IMPLICATIONS FOR PUBLIC HEALTH Australia demonstrates what can be achieved when skin cancer prevention is taken seriously. The challenge for other nations is to apply the lessons learnt in Australia to our own jurisdictions.
Collapse
Affiliation(s)
- Bronwen M McNoe
- Social and Behavioural Research Unit, Department of Preventive and Social Medicine, Dunedin School of Medicine, University of Otago, Dunedin, New Zealand
| | - Ryan Gage
- Health Promotion and Policy Research Unit, Department of Public Health, University of Otago, Wellington, New Zealand
| | - Louise Signal
- Health Promotion and Policy Research Unit, Department of Public Health, University of Otago, Wellington, New Zealand
| |
Collapse
|
7
|
Zhang H, Wang Y, Zheng Q, Tang K, Fang R, Wang Y, Sun Q. Research Interest and Public Interest in Melanoma: A Bibliometric and Google Trends Analysis. Front Oncol 2021; 11:629687. [PMID: 33680968 PMCID: PMC7930473 DOI: 10.3389/fonc.2021.629687] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2020] [Accepted: 01/04/2021] [Indexed: 12/19/2022] Open
Abstract
INTRODUCTION Melanoma is a severe skin cancer that metastasizes quickly. Bibliometric analysis can quantify hotspots of research interest. Google Trends can provide information to address public concerns. METHODS The top 15 most frequently cited articles on melanoma each year from 2015 to 2019, according to annual citations, were retrieved from the Web of Science database. Original articles, reviews, and research letters were included in this research. For the Google Trends analysis, the topic "Melanoma" was selected as the keyword. Online search data from 2004 to 2019 were collected. Four countries (New Zealand, Australia, the United States and the United Kingdom) were selected for seasonal analysis. Annual trends in relative search volume and seasonal variation were analyzed, and the top related topics and rising related topics were also selected and analyzed. RESULTS The top 15 most frequently cited articles each year were all original articles that focused on immunotherapy (n=8), omics (n=5), and the microbiome (n=2). The average relative search volume remained relatively stable across the years. The seasonal variation analysis revealed that the peak appeared in summer, and the valley appeared in winter. The diseases associated with or manifestations of melanoma, treatment options, risk factors, diagnostic tools, and prognosis were the topics in which the public was most interested. Most of the topics revealed by bibliometric and Google Trends analyses were consistent, with the exception of issues related to the molecular biology of melanoma. CONCLUSION This study revealed the trends in research interest and public interest in melanoma, which may pave the way for further research.
Collapse
|