Three Epochs of Artificial Intelligence in Health Care.

Importance: Interest in artificial intelligence (AI) has reached an all-time high, and health care leaders across the ecosystem are faced with questions about where, when, and how to deploy AI and how to understand its risks, problems, and possibilities. Observations: While AI as a concept has existed since the 1950s, all AI is not the same. Capabilities and risks of various kinds of AI differ markedly, and on examination 3 epochs of AI emerge. AI 1.0 includes symbolic AI, which attempts to encode human knowledge into computational rules, as well as probabilistic models. The era of AI 2.0 began with deep learning, in which models learn from examples labeled with ground truth. This era brought about many advances both in people's daily lives and in health care. Deep learning models are task-specific, meaning they do one thing at a time, and they primarily focus on classification and prediction. AI 3.0 is the era of foundation models and generative AI. Models in AI 3.0 have fundamentally new (and potentially transformative) capabilities, as well as new kinds of risks, such as hallucinations. These models can do many different kinds of tasks without being retrained on a new dataset. For example, a simple text instruction will change the model's behavior. Prompts such as "Write this note for a specialist consultant" and "Write this note for the patient's mother" will produce markedly different content. Conclusions and Relevance: Foundation models and generative AI represent a major revolution in AI's capabilities, ffering tremendous potential to improve care. Health care leaders are making decisions about AI today. While any heuristic omits details and loses nuance, the framework of AI 1.0, 2.0, and 3.0 may be helpful to decision-makers because each epoch has fundamentally different capabilities and risks.

Advancements in artificial intelligence and machine learning in revolutionising biomarker discovery

Abstract The article explores the significance of biomarkers in clinical research and the advantages of utilizing artificial intelligence (AI) and machine learning (ML) in the discovery process. Biomarkers provide a more comprehensive understanding of disease progression and response to therapy compared to traditional indicators. AI and ML offer a new approach to biomarker discovery, leveraging large amounts of data to identify patterns and optimize existing biomarkers. Additionally, the article touches on the emergence of digital biomarkers, which use technology to assess an individual's physiological and behavioural states, and the importance of properly processing omics and multi-omics data for efficient handling by computer systems. However, the article acknowledges the challenges posed by AI/ML in the identification of biomarkers, including potential biases in the data and the need for diversity in data representation. To address these challenges, the article suggests the importance of regulation and diversity in the development of AI/ML algorithms.

[Explore the history of artificial intelligence, to better define and understand it]. / Parcourir l'histoire de l'intelligence artificielle, pour mieux la définir et la comprendre.

TITLE: Parcourir l'histoire de l'intelligence artificielle, pour mieux la définir et la comprendre. ABSTRACT: L'intelligence artificielle est une expression fourre-tout, qui suscite autant d'espoirs que de craintes. Cette locution a envahi les médias, les conférences, les conversations, mais aussi les appels à projets des institutions de recherche et de diverses associations. On ne peut quasiment plus élaborer de projet de recherche sans mentionner une interface avec l'intelligence artificielle. Dans cet article, après la présentation d'une brève vision historique, nous proposerons une définition de l'intelligence artificielle et un paysage des possibles offerts par celle-ci.

A propositional AI system for supporting epilepsy diagnosis based on the 2017 epilepsy classification: Illustrated by Dravet syndrome.

PURPOSE: The 2017 epilepsy and seizure diagnosis framework emphasizes epilepsy syndromes and the etiology-based approach. We developed a propositional artificial intelligence (AI) system based on the above concepts to support physicians in the diagnosis of epilepsy. METHODS: We analyzed and built ontology knowledge for the classification of seizure patterns, epilepsy, epilepsy syndrome, and etiologies. Protégé ontology tool was applied in this study. In order to enable the system to be close to the inferential thinking of clinical experts, we classified and constructed knowledge of other epilepsy-related knowledge, including comorbidities, epilepsy imitators, epilepsy descriptors, characteristic electroencephalography (EEG) findings, treatments, etc. We used the Ontology Web Language with Description Logic (OWL-DL) and Semantic Web Rule Language (SWRL) to design rules for expressing the relationship between these ontologies. RESULTS: Dravet syndrome was taken as an illustration for epilepsy syndromes implementation. We designed an interface for the physician to enter the various characteristics of the patients. Clinical data of an 18-year-old boy with epilepsy was applied to the AI system. Through SWRL and reasoning engine Drool's execution, we successfully demonstrate the process of differential diagnosis. CONCLUSION: We developed a propositional AI system by using the OWL-DL/SWRL approach to deal with the complexity of current epilepsy diagnosis. The experience of this system, centered on the clinical epilepsy syndromes, paves a path to construct an AI system for further complicated epilepsy diagnosis.

Online Incremental Classification Resonance Network and Its Application to Human-Robot Interaction.

In human-robot interaction (HRI), classification is one of the most important problems, and it is essential particularly when the robot recognizes the surroundings and chooses a reaction based on a certain situation. Each interaction is different since new people appear or the environment changes, and the robot should be able to adapt to different situations during a brief interaction. Thus, it is imperative that the classification is performed incrementally in real time. In this sense, we propose an online incremental classification resonance network (OICRN) that enables incremental class learning in multi-class classification with high performance online. In OICRN, a scale-preserving projection process is introduced to use the raw input vectors online without a normalization process in advance. The integrated network of the convolutional neural network (CNN) for feature extraction and the OICRN for classification is applied to a robotic system that learns human identities through HRIs. To demonstrate the effectiveness of our network, experiments are carried out on benchmark data sets and on a humanoid robot, Mybot, developed in the Robot Intelligence Technology Laboratory, KAIST.

Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association.

In this white paper, experts from the Digital Pathology Association (DPA) define terminology and concepts in the emerging field of computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. This review offers a historical perspective and describes the potential clinical benefits from research and applications in this field, as well as significant obstacles to adoption. Best practices for implementing computational pathology workflows are presented. These include infrastructure considerations, acquisition of training data, quality assessments, as well as regulatory, ethical, and cyber-security concerns. Recommendations are provided for regulators, vendors, and computational pathology practitioners in order to facilitate progress in the field. © 2019 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland.

Artificial Intelligence Based Hierarchical Clustering of Patient Types and Intervention Categories in Adult Spinal Deformity Surgery: Towards a New Classification Scheme that Predicts Quality and Value.

STUDY DESIGN: Retrospective review of prospectively-collected, multicenter adult spinal deformity (ASD) databases. OBJECTIVE: To apply artificial intelligence (AI)-based hierarchical clustering as a step toward a classification scheme that optimizes overall quality, value, and safety for ASD surgery. SUMMARY OF BACKGROUND DATA: Prior ASD classifications have focused on radiographic parameters associated with patient reported outcomes. Recent work suggests there are many other impactful preoperative data points. However, the ability to segregate patient patterns manually based on hundreds of data points is beyond practical application for surgeons. Unsupervised machine-based clustering of patient types alongside surgical options may simplify analysis of ASD patient types, procedures, and outcomes. METHODS: Two prospective cohorts were queried for surgical ASD patients with baseline, 1-year, and 2-year SRS-22/Oswestry Disability Index/SF-36v2 data. Two dendrograms were fitted, one with surgical features and one with patient characteristics. Both were built with Ward distances and optimized with the gap method. For each possible n patient cluster by m surgery, normalized 2-year improvement and major complication rates were computed. RESULTS: Five hundred-seventy patients were included. Three optimal patient types were identified: young with coronal plane deformity (YC, n = 195), older with prior spine surgeries (ORev, n = 157), and older without prior spine surgeries (OPrim, n = 218). Osteotomy type, instrumentation and interbody fusion were combined to define four surgical clusters. The intersection of patient-based and surgery-based clusters yielded 12 subgroups, with major complication rates ranging from 0% to 51.8% and 2-year normalized improvement ranging from -0.1% for SF36v2 MCS in cluster [1,3] to 100.2% for SRS self-image score in cluster [2,1]. CONCLUSION: Unsupervised hierarchical clustering can identify data patterns that may augment preoperative decision-making through construction of a 2-year risk-benefit grid. In addition to creating a novel AI-based ASD classification, pattern identification may facilitate treatment optimization by educating surgeons on which treatment patterns yield optimal improvement with lowest risk. LEVEL OF EVIDENCE: 4.

Development of an artificial intelligence system to classify pathology and clinical features on retinal fundus images.

IMPORTANCE: Artificial intelligence (AI) algorithms are under development for use in diabetic retinopathy photo screening pathways. To be clinically acceptable, such systems must also be able to classify other fundus abnormalities and clinical features at the point of care. BACKGROUND: We aimed to develop an AI system that can detect several fundus pathologies and report relevant clinical features. DESIGN: Convolutional neural network training with retrospective data set. PARTICIPANTS: Colour fundus photos were obtained from publicly available fundus image databases. METHODS: Images were uploaded to a web-based AI platform for training and validation of AI classifiers. Separate classifiers were created for each fundus pathology and clinical feature. MAIN OUTCOME MEASURES: Accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC) for each classifier. RESULTS: We obtained 4435 images from publicly available fundus image databases. AI classifiers were developed for each disease state above. Although statistical performance was limited by the small sample size, average accuracy was 89%, average sensitivity was 75%, average specificity was 89% and average AUC was 0.58. CONCLUSION AND RELEVANCE: This study is a proof-of-concept AI system that could be implemented within a diabetic photo-screening pathway. Performance was promising but not yet at the level that would be required for clinical application. We have shown that it is possible for clinicians to develop AI classifiers with no previous programming or AI knowledge, using standard laptop computers.

Accelerated low-rank representation for subspace clustering and semi-supervised classification on large-scale data.

The scalability of low-rank representation (LRR) to large-scale data is still a major research issue, because it is extremely time-consuming to solve singular value decomposition (SVD) in each optimization iteration especially for large matrices. Several methods were proposed to speed up LRR, but they are still computationally heavy, and the overall representation results were also found degenerated. In this paper, a novel method, called accelerated LRR (ALRR) is proposed for large-scale data. The proposed accelerated method integrates matrix factorization with nuclear-norm minimization to find a low-rank representation. In our proposed method, the large square matrix of representation coefficients is transformed into a significantly smaller square matrix, on which SVD can be efficiently implemented. The size of the transformed matrix is not related to the number of data points and the optimization of ALRR is linear with the number of data points. The proposed ALRR is convex, accurate, robust, and efficient for large-scale data. In this paper, ALRR is compared with state-of-the-art in subspace clustering and semi-supervised classification on real image datasets. The obtained results verify the effectiveness and superiority of the proposed ALRR method.

Orthogonal self-guided similarity preserving projection for classification and clustering.

A suitable feature representation can faithfully preserve the intrinsic structure of data. However, traditional dimensionality reduction (DR) methods commonly use the original input features to define the intrinsic structure, which makes the estimated intrinsic structure unreliable since redundant or noisy features may exist in the original input features. Thus a dilemma is that (1) one needs the most suitable feature representation to define the intrinsic structure of data and (2) one should use the proper intrinsic structure of data to perform feature extraction. To address the problem, in this paper we propose a unified learning framework to simultaneously obtain the optimal feature representation and intrinsic structure of data. The structure is learned from the results of feature learning, and the features are learned to preserve the refined structure of data. By leveraging the interactions between the process of determining the most suitable feature representation and intrinsic structure of data, we can capture accurate structure and obtain the optimal feature representation of data. Experimental results demonstrate that our method outperforms state-of-the-art methods in DR and subspace clustering. The code of the proposed method is available at "http://www.yongxu.org/lunwen.html ".

Kernel association for classification and prediction: a survey.

Kernel association (KA) in statistical pattern recognition used for classification and prediction have recently emerged in a machine learning and signal processing context. This survey outlines the latest trends and innovations of a kernel framework for big data analysis. KA topics include offline learning, distributed database, online learning, and its prediction. The structural presentation and the comprehensive list of references are geared to provide a useful overview of this evolving field for both specialists and relevant scholars.

Trends in extreme learning machines: a review.

Extreme learning machine (ELM) has gained increasing interest from various research fields recently. In this review, we aim to report the current state of the theoretical research and practical advances on this subject. We first give an overview of ELM from the theoretical perspective, including the interpolation theory, universal approximation capability, and generalization ability. Then we focus on the various improvements made to ELM which further improve its stability, sparsity and accuracy under general or specific conditions. Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks. These newly emerging algorithms greatly expand the applications of ELM. From implementation aspect, hardware implementation and parallel computation techniques have substantially sped up the training of ELM, making it feasible for big data processing and real-time reasoning. Due to its remarkable efficiency, simplicity, and impressive generalization performance, ELM have been applied in a variety of domains, such as biomedical engineering, computer vision, system identification, and control and robotics. In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.

Deep learning in neural networks: an overview.

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

Robust framework to combine diverse classifiers assigning distributed confidence to individual classifiers at class level.

We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes.

Combined kernel-based BDT-SMO classification of hyperspectral fused images.

To solve the poor generalization and flexibility problems that single kernel SVM classifiers have while classifying combined spectral and spatial features, this paper proposed a solution to improve the classification accuracy and efficiency of hyperspectral fused images: (1) different radial basis kernel functions (RBFs) are employed for spectral and textural features, and a new combined radial basis kernel function (CRBF) is proposed by combining them in a weighted manner; (2) the binary decision tree-based multiclass SMO (BDT-SMO) is used in the classification of hyperspectral fused images; (3) experiments are carried out, where the single radial basis function- (SRBF-) based BDT-SMO classifier and the CRBF-based BDT-SMO classifier are used, respectively, to classify the land usages of hyperspectral fused images, and genetic algorithms (GA) are used to optimize the kernel parameters of the classifiers. The results show that, compared with SRBF, CRBF-based BDT-SMO classifiers display greater classification accuracy and efficiency.

A classification of user-generated content into consumer decision journey stages.

In the last decades, the availability of digital user-generated documents from social media has dramatically increased. This massive growth of user-generated content has also affected traditional shopping behaviour. Customers have embraced new communication channels such as microblogs and social networks that enable them not only just to talk with friends and acquaintances about their shopping experience, but also to search for opinions expressed by complete strangers as part of their decision making processes. Uncovering how customers feel about specific products or brands and detecting purchase habits and preferences has traditionally been a costly and highly time-consuming task which involved the use of methods such as focus groups and surveys. However, the new scenario calls for a deep assessment of current market research techniques in order to better interpret and profit from this ever-growing stream of attitudinal data. With this purpose, we present a novel analysis and classification of user-generated content in terms of it belonging to one of the four stages of the Consumer Decision Journey Court et al. (2009) (i.e. the purchase process from the moment when a customer is aware of the existence of the product to the moment when he or she buys, experiences and talks about it). Using a corpus of short texts written in English and Spanish and extracted from different social media, we identify a set of linguistic patterns for each purchase stage that will be then used in a rule-based classifier. Additionally, we use machine learning algorithms to automatically identify business indicators such as the Marketing Mix elements McCarthy and Brogowicz (1981). The classification of the purchase stages achieves an average precision of 74%. The proposed classification of texts depending on the Marketing Mix elements expressed achieved an average precision of 75% for all the elements analysed.

A multi-label, semi-supervised classification approach applied to personality prediction in social media.

Social media allow web users to create and share content pertaining to different subjects, exposing their activities, opinions, feelings and thoughts. In this context, online social media has attracted the interest of data scientists seeking to understand behaviours and trends, whilst collecting statistics for social sites. One potential application for these data is personality prediction, which aims to understand a user's behaviour within social media. Traditional personality prediction relies on users' profiles, their status updates, the messages they post, etc. Here, a personality prediction system for social media data is introduced that differs from most approaches in the literature, in that it works with groups of texts, instead of single texts, and does not take users' profiles into account. Also, the proposed approach extracts meta-attributes from texts and does not work directly with the content of the messages. The set of possible personality traits is taken from the Big Five model and allows the problem to be characterised as a multi-label classification task. The problem is then transformed into a set of five binary classification problems and solved by means of a semi-supervised learning approach, due to the difficulty in annotating the massive amounts of data generated in social media. In our implementation, the proposed system was trained with three well-known machine-learning algorithms, namely a Naïve Bayes classifier, a Support Vector Machine, and a Multilayer Perceptron neural network. The system was applied to predict the personality of Tweets taken from three datasets available in the literature, and resulted in an approximately 83% accurate prediction, with some of the personality traits presenting better individual classification rates than others.

Active learning framework with iterative clustering for bioimage classification.

Advances in imaging systems have yielded a flood of images into the research field. A semi-automated facility can reduce the laborious task of classifying this large number of images. Here we report the development of a novel framework, CARTA (Clustering-Aided Rapid Training Agent), applicable to bioimage classification that facilitates annotation and selection of features. CARTA comprises an active learning algorithm combined with a genetic algorithm and self-organizing map. The framework provides an easy and interactive annotation method and accurate classification. The CARTA framework enables classification of subcellular localization, mitotic phases and discrimination of apoptosis in images of plant and human cells with an accuracy level greater than or equal to annotators. CARTA can be applied to classification of magnetic resonance imaging of cancer cells or multicolour time-course images after surgery. Furthermore, CARTA can support development of customized features for classification, high-throughput phenotyping and application of various classification schemes dependent on the user's purpose.

Progression of patterns (POP): a machine classifier algorithm to identify glaucoma progression in visual fields.

PURPOSE: We evaluated Progression of Patterns (POP) for its ability to identify progression of glaucomatous visual field (VF) defects. METHODS: POP uses variational Bayesian independent component mixture model (VIM), a machine learning classifier (MLC) developed previously. VIM separated Swedish Interactive Thresholding Algorithm (SITA) VFs from a set of 2,085 normal and glaucomatous eyes into nine axes (VF patterns): seven glaucomatous. Stable glaucoma was simulated in a second set of 55 patient eyes with five VFs each, collected within four weeks. A third set of 628 eyes with 4,186 VFs (mean ± SD of 6.7 ± 1.7 VFs over 4.0 ± 1.4 years) was tested for progression. Tested eyes were placed into suspect and glaucoma categories at baseline, based on VFs and disk stereoscopic photographs; a subset of eyes had stereophotographic evidence of progressive glaucomatous optic neuropathy (PGON). Each sequence of fields was projected along seven VIM glaucoma axes. Linear regression (LR) slopes generated from projections onto each axis yielded a degree of confidence (DOC) that there was progression. At 95% specificity, progression cutoffs were established for POP, visual field index (VFI), and mean deviation (MD). Guided progression analysis (GPA) was also compared. RESULTS: POP identified a statistically similar number of eyes (P > 0.05) as progressing compared with VFI, MD, and GPA in suspects (3.8%, 2.7%, 5.6%, and 2.9%, respectively), and more eyes than GPA (P = 0.01) in glaucoma (16.0%, 15.3%, 12.0%, and 7.3%, respectively), and more eyes than GPA (P = 0.05) in PGON eyes (26.3%, 23.7%, 27.6%, and 14.5%, respectively). CONCLUSIONS: POP, with its display of DOC of progression and its identification of progressing VF defect pattern, adds to the information available to the clinician for detecting VF progression.