Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations

2020 ◽  
Vol 30 (6) ◽  
pp. 3576-3584 ◽  
Author(s):  
Michael P. Recht ◽  
Marc Dewey ◽  
Keith Dreyer ◽  
Curtis Langlotz ◽  
Wiro Niessen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice

scholarly journals Interventional radiology and artificial intelligence in radiology: Is it time to enhance the vision of our medical students?

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Pierre Auloge ◽  
Julien Garnon ◽  
Joey Marie Robinson ◽  
Sarah Dbouk ◽  
Jean Sibilia ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Interventional Radiology ◽  
Clinical Practice ◽  
Medical Students ◽  
Medical Curriculum ◽  
New Technology ◽  
Large Population ◽  
The Other ◽  
Clinical Phase ◽  
Preclinical Phase

Abstract Objectives To assess awareness and knowledge of Interventional Radiology (IR) in a large population of medical students in 2019. Methods An anonymous survey was distributed electronically to 9546 medical students from first to sixth year at three European medical schools. The survey contained 14 questions, including two general questions on diagnostic radiology (DR) and artificial intelligence (AI), and 11 on IR. Responses were analyzed for all students and compared between preclinical (PCs) (first to third year) and clinical phase (Cs) (fourth to sixth year) of medical school. Of 9546 students, 1459 students (15.3%) answered the survey. Results On DR questions, 34.8% answered that AI is a threat for radiologists (PCs: 246/725 (33.9%); Cs: 248/734 (36%)) and 91.1% thought that radiology has a future (PCs: 668/725 (92.1%); Cs: 657/734 (89.5%)). On IR questions, 80.8% (1179/1459) students had already heard of IR; 75.7% (1104/1459) stated that their knowledge of IR wasn’t as good as the other specialties and 80% would like more lectures on IR. Finally, 24.2% (353/1459) indicated an interest in a career in IR with a majority of women in preclinical phase, but this trend reverses in clinical phase. Conclusions Development of new technology supporting advances in artificial intelligence will likely continue to change the landscape of radiology; however, medical students remain confident in the need for specialty-trained human physicians in the future of radiology as a clinical practice. A large majority of medical students would like more information about IR in their medical curriculum; almost a quarter of students would be interested in a career in IR.

scholarly journals How can artificial intelligence models assist PD-L1 expression scoring in breast cancer: results of multi-institutional ring studies

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Xinran Wang ◽  
Liang Wang ◽  
Hong Bu ◽  
Ningning Zhang ◽  
Meng Yue ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
Clinical Practice ◽  
Subjective Assessment ◽  
Current Guideline ◽  
Scoring Method ◽  
Programmed Death ◽  
Intelligence Models ◽  
Artificial Intelligence Models ◽  
Scoring Accuracy

AbstractProgrammed death ligand-1 (PD-L1) expression is a key biomarker to screen patients for PD-1/PD-L1-targeted immunotherapy. However, a subjective assessment guide on PD-L1 expression of tumor-infiltrating immune cells (IC) scoring is currently adopted in clinical practice with low concordance. Therefore, a repeatable and quantifiable PD-L1 IC scoring method of breast cancer is desirable. In this study, we propose a deep learning-based artificial intelligence-assisted (AI-assisted) model for PD-L1 IC scoring. Three rounds of ring studies (RSs) involving 31 pathologists from 10 hospitals were carried out, using the current guideline in the first two rounds (RS1, RS2) and our AI scoring model in the last round (RS3). A total of 109 PD-L1 (Ventana SP142) immunohistochemistry (IHC) stained images were assessed and the role of the AI-assisted model was evaluated. With the assistance of AI, the scoring concordance across pathologists was boosted to excellent in RS3 (0.950, 95% confidence interval (CI): 0.936–0.962) from moderate in RS1 (0.674, 95% CI: 0.614–0.735) and RS2 (0.736, 95% CI: 0.683–0.789). The 2- and 4-category scoring accuracy were improved by 4.2% (0.959, 95% CI: 0.953–0.964) and 13% (0.815, 95% CI: 0.803–0.827) (p < 0.001). The AI results were generally accepted by pathologists with 61% “fully accepted” and 91% “almost accepted”. The proposed AI-assisted method can help pathologists at all levels to improve the PD-L1 assay (SP-142) IC assessment in breast cancer in terms of both accuracy and concordance. The AI tool provides a scheme to standardize the PD-L1 IC scoring in clinical practice.

scholarly journals Physicians’ requirements and expectations of future Artificial Intelligence applications for healthcare – a web-based survey in German university hospitals (Preprint)

2020 ◽  
Author(s):  
Oliver Maassen ◽  
Sebastian Fritsch ◽  
Julia Gantner ◽  
Saskia Deffge ◽  
Julian Kunze ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice ◽  
Patient Care ◽  
Biomedical Research ◽  
Positive Attitude ◽  
Patient Data ◽  
University Hospitals ◽  
Web Based ◽  
Wide Range ◽  
Medical Disciplines

BACKGROUND The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice of physicians from almost all medical disciplines and in most areas of healthcare. While expectations for AI in medicine are high, practical implementations of AI for clinical practice are still scarce in Germany. Moreover, physicians’ requirements and expectations of AI in medicine and their opinion on the usage of anonymized patient data for clinical and biomedical research has not been investigated widely in German university hospitals. OBJECTIVE Evaluate physicians’ requirements and expectations of AI in medicine and their opinion on the secondary usage of patient data for (bio)medical research e.g. for the development of machine learning (ML) algorithms in university hospitals in Germany. METHODS A web-based survey was conducted addressing physicians of all medical disciplines in 8 German university hospitals. Answers were given on Likert scales and general demographic responses. Physicians were asked to participate locally via email in the respective hospitals. RESULTS 121 (39.9%) female and 173 (57.1%) male physicians (N=303) from a wide range of medical disciplines and work experience levels completed the online survey. The majority of respondents either had a positive (130/303, 42.9%) or a very positive attitude (82/303, 27.1%) towards AI in medicine. A vast majority of physicians expected the future of medicine to be a mix of human and artificial intelligence (273/303, 90.1%) but also requested a scientific evaluation before the routine implementation of AI-based systems (276/303, 91.1%). Physicians were most optimistic that AI applications would identify drug interactions (280/303, 92.4%) to improve patient care substantially but were quite reserved regarding AI-supported diagnosis of psychiatric diseases (62/303, 20.5%). 82.5% of respondents (250/303) agreed that there should be open access to anonymized patient databases for medical and biomedical research. CONCLUSIONS Physicians in stationary patient care in German university hospitals show a generally positive attitude towards using most AI applications in medicine. Along with this optimism, there come several expectations and hopes that AI will assist physicians in clinical decision making. Especially in fields of medicine where huge amounts of data are processed (e.g., imaging procedures in radiology and pathology) or data is collected continuously (e.g. cardiology and intensive care medicine), physicians’ expectations to substantially improve future patient care are high. However, for the practical usage of AI in healthcare regulatory and organizational challenges still have to be mastered.

scholarly journals Artificial Intelligence in Public Health Dentistry

2021 ◽  
Vol 5 (9) ◽  
pp. RV1-RV5
Author(s):  
Sahrish Tariq ◽  
Nidhi Gupta ◽  
Preety Gupta ◽  
Aditi Sharma
Keyword(s):  
Public Health ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Clinical Practice ◽  
Correct Diagnosis ◽  
Scientific Research ◽  
Modern Science ◽  
Appropriate Technology ◽  
Human Element ◽  
New Knowledge

The educational needs must drive the development of the appropriate technology”. They should not be viewed as toys for enthusiasts. Nevertheless, the human element must never be dismissed. Scientific research will continue to offer exciting technologies and effective treatments. For the profession and the patients, it serves to benefit fully from modern science, new knowledge and technologies must be incorporated into the mainstream of dental education. The technologies of modern science have astonished and intrigued our imagination. Correct diagnosis is the key to a successful clinical practice. In this regard, adequately trained neural networks can be a boon to diagnosticians, especially in conditions having multifactorial etiology.

Artificial intelligence in clinical practice: Implications for physiotherapy education

2019 ◽  
Author(s):  
Michael Rowe ◽  
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice ◽  
Economic Education ◽  
Steam Engine ◽  
Cognitive Capacity ◽  
Data Sets ◽  
Human Beings ◽  
Physiotherapy Practice ◽  
Recent Emergence ◽  
Physiotherapy Education

About 200 years ago the invention of the steam engine triggered a wave of unprecedented development and growth in human social and economic systems, whereby human labour was either augmented or completely supplanted by machines. The recent emergence of artificially intelligent machines has seen human cognitive capacity enhanced by computational agents that are able to recognise previously hidden patterns within massive data sets. The characteristics of this technological advance are already influencing all aspects of society, creating the conditions for disruption to our social, economic, education, health, legal and moral systems, and which may have a more significant impact on human progress than did the steam engine. As this emerging technology becomes increasingly embedded within devices and systems, the fundamental nature of clinical practice will evolve, resulting in a healthcare system that may require concomitant changes to health professions education. Clinicians in the near future will find themselves working with information networks on a scale well beyond the capacity of human beings to grasp, thereby necessitating the use of artificial intelligence (AI) to analyse and interpret the complex interactions of data, patients and the newly-constituted care teams that will emerge. This paper describes some of the possible influences of AI-based technologies on physiotherapy practice, and the subsequent ways in which physiotherapy education will need to change in order to graduate professionals who are fit for practice in a 21st-century health system.

Clinical Practice Ontology Automatic Learning from SOAP Reports

2016 ◽  
pp. 349-363
Author(s):  
David Mendes ◽  
Irene Pimenta Rodrigues ◽  
Carlos Fernandes Baeta
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice ◽  
Natural Language ◽  
Knowledge Base ◽  
Clinical Information ◽  
Knowledge Structure ◽  
Daily Routine ◽  
Automatic Learning ◽  
Controlled Natural Language ◽  
Practice Knowledge

We show how we implemented an end-to-end process to automatically develop a clinical practice knowledge base acquiring from SOAP notes. With our contribution we intend to overcome the “Knowledge Acquisition Bottleneck” problem by jump-starting the knowledge gathering from the most widely available source of clinical information that are natural language reports. We present the different phases of our process to populate automatically a proposed ontology with clinical assertions extracted from daily routine SOAP notes. The enriched ontology becomes a reasoning able knowledge base that depicts accurately and realistically the clinical practice represented by the source reports. With this knowledge structure in place and novel state-of-the-art reasoning capabilities, based in consequence driven reasoners, a clinical QA system based in controlled natural language is introduced that reveals breakthrough possibilities regarding the applicability of Artificial Intelligence techniques to the medical field.

scholarly journals Neurological update: neuroimaging in dementia

2020 ◽  
Vol 267 (11) ◽  
pp. 3429-3435
Author(s):  
Timothy Rittman
Keyword(s):  
Artificial Intelligence ◽  
Positron Emission Tomography ◽  
Clinical Practice ◽  
Imaging Techniques ◽  
Emission Tomography ◽  
Structural Imaging ◽  
Regulatory Issues ◽  
Positron Emission ◽  
Remarkable Progress

Abstract Neuroimaging for dementia has made remarkable progress in recent years, shedding light on diagnostic subtypes of dementia, predicting prognosis and monitoring pathology. This review covers some updates in the understanding of dementia using structural imaging, positron emission tomography (PET), structural and functional connectivity, and using big data and artificial intelligence. Progress with neuroimaging methods allows neuropathology to be examined in vivo, providing a suite of biomarkers for understanding neurodegeneration and for application in clinical trials. In addition, we highlight quantitative susceptibility imaging as an exciting new technique that may prove to be a sensitive biomarker for a range of neurodegenerative diseases. There are challenges in translating novel imaging techniques to clinical practice, particularly in developing standard methodologies and overcoming regulatory issues. It is likely that clinicians will need to lead the way if these obstacles are to be overcome. Continued efforts applying neuroimaging to understand mechanisms of neurodegeneration and translating them to clinical practice will complete a revolution in neuroimaging.

scholarly journals Blockchain in Healthcare: Insights on COVID-19

2020 ◽  
Vol 17 (19) ◽  
pp. 7167 ◽  
Author(s):  
Antonio Fusco ◽  
Grazia Dicuonzo ◽  
Vittorio Dell’Atti ◽  
Marco Tatullo
Keyword(s):  
Artificial Intelligence ◽  
Risk Management ◽  
Clinical Practice ◽  
Swot Analysis ◽  
Healthcare Management ◽  
Evidence Based ◽  
Clinical Workflow ◽  
Strategic Role ◽  
Digital Healthcare ◽  
Artificial Intelligence Systems

The SARS-CoV2 pandemic has impacted risk management globally. Blockchain has been increasingly applied to healthcare management, as a strategic tool to strengthen operative protocols and to create the proper basis for an efficient and effective evidence-based decisional process. We aim to validate blockchain in healthcare, and to suggest a trace-route for a COVID19-safe clinical practice. The use of blockchain in combination with artificial intelligence systems allows the creation of a generalizable predictive system that could contribute to the containment of pandemic risk on national territory. A SWOT analysis of the adoption of a blockchain-based prediction model in healthcare and SARS-CoV-2 infection has been carried out to underline opportunities and limits to its adoption. Blockchain could play a strategic role in future digital healthcare: specifically, it may work to improve COVID19-safe clinical practice. The main concepts, and particularly those related to clinical workflow, obtainable from different blockchain-based models have been reported here and critically discussed.

Sign in / Sign up

Export Citation Format

Share Document