scholarly journals Key challenges for delivering clinical impact with artificial intelligence

BMC Medicine ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Christopher J. Kelly ◽  
Alan Karthikesalingam ◽  
Mustafa Suleyman ◽  
Greg Corrado ◽  
Dominic King
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Clinical Practice ◽  
Clinical Evaluation ◽  
Performance Metrics ◽  
Main Body ◽  
Negative Consequences ◽  
Technical Accuracy ◽  
Potential Applications ◽  
Randomised Controlled

Abstract Background Artificial intelligence (AI) research in healthcare is accelerating rapidly, with potential applications being demonstrated across various domains of medicine. However, there are currently limited examples of such techniques being successfully deployed into clinical practice. This article explores the main challenges and limitations of AI in healthcare, and considers the steps required to translate these potentially transformative technologies from research to clinical practice. Main body Key challenges for the translation of AI systems in healthcare include those intrinsic to the science of machine learning, logistical difficulties in implementation, and consideration of the barriers to adoption as well as of the necessary sociocultural or pathway changes. Robust peer-reviewed clinical evaluation as part of randomised controlled trials should be viewed as the gold standard for evidence generation, but conducting these in practice may not always be appropriate or feasible. Performance metrics should aim to capture real clinical applicability and be understandable to intended users. Regulation that balances the pace of innovation with the potential for harm, alongside thoughtful post-market surveillance, is required to ensure that patients are not exposed to dangerous interventions nor deprived of access to beneficial innovations. Mechanisms to enable direct comparisons of AI systems must be developed, including the use of independent, local and representative test sets. Developers of AI algorithms must be vigilant to potential dangers, including dataset shift, accidental fitting of confounders, unintended discriminatory bias, the challenges of generalisation to new populations, and the unintended negative consequences of new algorithms on health outcomes. Conclusion The safe and timely translation of AI research into clinically validated and appropriately regulated systems that can benefit everyone is challenging. Robust clinical evaluation, using metrics that are intuitive to clinicians and ideally go beyond measures of technical accuracy to include quality of care and patient outcomes, is essential. Further work is required (1) to identify themes of algorithmic bias and unfairness while developing mitigations to address these, (2) to reduce brittleness and improve generalisability, and (3) to develop methods for improved interpretability of machine learning predictions. If these goals can be achieved, the benefits for patients are likely to be transformational.

AI-Enabled Support System for Melanoma Detection and Classification

2021 ◽  
Vol 10 (4) ◽  
pp. 58-75
Author(s):  
Vivek Sen Saxena ◽  
Prashant Johri ◽  
Avneesh Kumar
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Skin Lesion ◽  
Performance Metrics ◽  
Similarity Index ◽  
Skin Lesions ◽  
Machine Learning Algorithms ◽  
Lesion Area ◽  
Melanoma Detection ◽  
Grabcut Algorithm

Skin lesion melanoma is the deadliest type of cancer. Artificial intelligence provides the power to classify skin lesions as melanoma and non-melanoma. The proposed system for melanoma detection and classification involves four steps: pre-processing, resizing all the images, removing noise and hair from dermoscopic images; image segmentation, identifying the lesion area; feature extraction, extracting features from segmented lesion and classification; and categorizing lesion as malignant (melanoma) and benign (non-melanoma). Modified GrabCut algorithm is employed to generate skin lesion. Segmented lesions are classified using machine learning algorithms such as SVM, k-NN, ANN, and logistic regression and evaluated on performance metrics like accuracy, sensitivity, and specificity. Results are compared with existing systems and achieved higher similarity index and accuracy.

Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review

2019 ◽  
Vol 12 (2) ◽  
pp. 156-164 ◽  
Author(s):  
Nick M Murray ◽  
Mathias Unberath ◽  
Gregory D Hager ◽  
Ferdinand K Hui
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Systematic Review ◽  
Ischemic Stroke ◽  
Acute Stroke ◽  
Feature Detection ◽  
Performance Metrics ◽  
Large Vessel ◽  
Image Feature ◽  
Stroke Treatment

Background and purposeAcute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes. This report is a systematic review of AI in acute LVO stroke identification and triage, and characterizes LVO detection software.MethodsA systematic review of acute stroke diagnostic-focused AI studies from January 2014 to February 2019 in PubMed, Medline, and Embase using terms: ‘artificial intelligence’ or ‘machine learning or deep learning’ and ‘ischemic stroke’ or ‘large vessel occlusion’ was performed.ResultsVariations of AI, including ML methods of random forest learning (RFL) and convolutional neural networks (CNNs), are used to detect LVO strokes. Twenty studies were identified that use ML. Alberta Stroke Program Early CT Score (ASPECTS) commonly used RFL, while LVO detection typically used CNNs. Image feature detection had greater sensitivity with CNN than with RFL, 85% versus 68%. However, AI algorithm performance metrics use different standards, precluding ideal objective comparison. Four current software platforms incorporate ML: Brainomix (greatest validation of AI for ASPECTS, uses CNNs to automatically detect LVOs), General Electric, iSchemaView (largest number of perfusion study validations for thrombectomy), and Viz.ai (uses CNNs to automatically detect LVOs, then automatically activates emergency stroke treatment systems).ConclusionsAI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

scholarly journals Big data, machine learning and artificial intelligence: a neurologist’s guide

2020 ◽  
pp. practneurol-2020-002688
Author(s):  
Stephen D Auger ◽  
Benjamin M Jacobs ◽  
Ruth Dobson ◽  
Charles R Marshall ◽  
Alastair J Noyce
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Big Data ◽  
Clinical Practice ◽  
Clinical Data ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Basic Principles ◽  
Biological Neural Networks

Modern clinical practice requires the integration and interpretation of ever-expanding volumes of clinical data. There is, therefore, an imperative to develop efficient ways to process and understand these large amounts of data. Neurologists work to understand the function of biological neural networks, but artificial neural networks and other forms of machine learning algorithm are likely to be increasingly encountered in clinical practice. As their use increases, clinicians will need to understand the basic principles and common types of algorithm. We aim to provide a coherent introduction to this jargon-heavy subject and equip neurologists with the tools to understand, critically appraise and apply insights from this burgeoning field.

Fairness and Ethics in Artificial Intelligence-Based Medical Imagining

2022 ◽  
pp. 71-85
Author(s):  
Satvik Tripathi ◽  
Thomas Heinrich Musiolik
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Patient Care ◽  
Data Sharing ◽  
Ethical Issues ◽  
Medical Systems ◽  
Healthcare Facilities ◽  
The World ◽  
Potential Applications ◽  
Medical Imagining

Artificial intelligence has a huge array of current and potential applications in healthcare and medicine. Ethical issues arising due to algorithmic biases are one of the greatest challenges faced in the generalizability of AI models today. The authors address safety and regulatory barriers that impede data sharing in medicine as well as potential changes to existing techniques and frameworks that might allow ethical data sharing for machine learning. With these developments in view, they also present different algorithmic models that are being used to develop machine learning-based medical systems that will potentially evolve to be free of the sample, annotator, and temporal bias. These AI-based medical imaging models will then be completely implemented in healthcare facilities and institutions all around the world, even in the remotest areas, making diagnosis and patient care both cheaper and freely accessible.

scholarly journals Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

2021 ◽  
Author(s):  
Riemer H. J. A. Slart ◽  
Michelle C. Williams ◽  
Luis Eduardo Juarez-Orozco ◽  
Christoph Rischpler ◽  
Marc R. Dweck ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Computed Tomography ◽  
Clinical Practice ◽  
Nuclear Cardiology ◽  
European Association ◽  
Imaging Techniques ◽  
Cardiovascular Imaging ◽  
Position Paper ◽  
Daily Clinical Practice

AbstractIn daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

scholarly journals Comparative Study on Reliability of Transfer Learning to Classify Plant-Based Diseases

2021 ◽  
Vol 10 (6) ◽  
pp. 154-160
Author(s):  
N Rohan Sai ◽  
◽  
T Sudarshan Rao ◽  
G. L. Aruna Kumari ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Network Architecture ◽  
Agricultural Sector ◽  
Performance Metrics ◽  
Primary Objective ◽  
The Other ◽  
Common Disease ◽  
Classification Problems

One of the essential factors contributing to a plant's growth is identifying and preventing diseases in the early stages. Healthy plants are essential for a rich production. Recent advances in Deep learning - a subset of Artificial Intelligence and Machine Learning are playing a pivotal role in solving image classification problems and can be applied to the agricultural sector for crop surveillance and early anomaly identification. For this research, we used an open-source dataset of leaf images divided into three classes, two of which are the most common disease types found on many crops; the graphical characterizations for the three classes are images of leaves with Powdery Residue, images of leaves with Rusty Spots, and images of Healthy leaves. The primary objective of this research is to present a pre-trained ImageNet network architecture that is well suited for dealing with plant-based data, even when sample sizes collected are limited. We used different convolutional neural network-based architectures such as InceptionV3, MobileNetV2, Xception, VGG16, and VGG19 to classify plant leaf images with visually different representations of each disease. Xception, MobileNetV2, and DenseNet had a considerable advantage over all the performance metrics recorded among the other networks trained.

scholarly journals Artificial intelligence in human genomics and biomedicine

2021 ◽  
Vol 30 (3) ◽  
pp. 30-36
Author(s):  
Reinhard Heil ◽  
Nils B. Heyen ◽  
Martina Baumann ◽  
Bärbel Hüsing ◽  
Daniel Bachlechner ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Clinical Practice ◽  
Individual Differences ◽  
Biomedical Research ◽  
Innovation System ◽  
Complex Data ◽  
Causal Knowledge ◽  
Human Genomics ◽  
Key Issues

The increasing availability of extensive and complex data has made human genomics and its applications in (bio)medicine an at­ tractive domain for artificial intelligence (AI) in the form of advanced machine learning (ML) methods. These methods are linked not only to the hope of improving diagnosis and drug development. Rather, they may also advance key issues in biomedicine, e. g. understanding how individual differences in the human genome may cause specific traits or diseases. We analyze the increasing convergence of AI and genom­ics, the emergence of a corresponding innovation system, and how these associative AI methods relate to the need for causal knowledge in biomedical research and development (R&D) and in medical prac­tice. Finally, we look at the opportunities and challenges for clinical practice and the implications for governance issues arising from this convergence.

Brain Computations

2020 ◽  
Author(s):  
Edmund T. Rolls
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Brain Function ◽  
Computational Science ◽  
Theoretical Physics ◽  
Medical Sciences ◽  
Computational Approaches ◽  
Potential Applications ◽  
The Subject ◽  
The Brain

The subject of this book is how the brain works. In order to understand this, it is essential to know what is computed by different brain systems; and how the computations are performed. The aim of this book is to elucidate what is computed in different brain systems; and to describe current computational approaches and models of how each of these brain systems computes. Understanding the brain in this way has enormous potential for understanding ourselves better in health and in disease. Potential applications of this understanding are to the treatment of the brain in disease; and to artificial intelligence which will benefit from knowledge of how the brain performs many of its extraordinarily impressive functions. This book is pioneering in taking this approach to brain function: to consider what is computed by many of our brain systems; and how it is computed. The book will be of interest to all scientists interested in brain function and how the brain works, whether they are from neuroscience, or from medical sciences including neurology and psychiatry, or from the area of computational science including machine learning and artificial intelligence, or from areas such as theoretical physics.

Machine-driven earth exploration: Artificial intelligence in oil and gas

2021 ◽  
Vol 40 (4) ◽  
pp. 298-301
Author(s):  
Tariq Alkhalifah ◽  
Ali Almomin ◽  
Ali Naamani
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Fault Detection ◽  
Oil And Gas ◽  
Image Resolution ◽  
The Earth ◽  
Recent Advances ◽  
Potential Applications ◽  
Boundary Mapping

Artificial intelligence (AI), specifically machine learning (ML), has emerged as a powerful tool to address many of the challenges we face as we try to illuminate the earth and make the proper prediction of its content. From fault detection, to salt boundary mapping, to image resolution enhancements, the quest to teach our computing devices how to perform these tasks accurately, as well as quantify the accuracy, has become a feasible and sought-after objective. Recent advances in ML algorithms and availability of the modules to apply such algorithms enabled geoscientists to focus on potential applications of such tools. As a result, we held the virtual workshop, Artificially Intelligent Earth Exploration Workshop: Teaching the Machine How to Characterize the Subsurface, 23–26 November 2020.

Sign in / Sign up

Export Citation Format

Share Document