Human-in-the-loop machine learning: a state of the art

From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are further categorized based on their functionality (model-, input-, output-based) and scope (local, global). Our analysis shows that attention mechanisms are the most prevalent emerging IAI technique. The use of IAI is growing, distinguishing it from XAI. The major challenges identified are that most XIAI does not explore "global" modelling processes, the lack of best practices, and the lack of systematic evaluation and benchmarks. One important opportunity is to use attention mechanisms to enhance multi-modal XIAI for personalized medicine. Additionally, combining DL with causal logic holds promise. Our discussion encourages the integration of XIAI in Large Language Models (LLMs) and domain-specific smaller models. In conclusion, XIAI adoption in healthcare requires dedicated in-house expertise. Collaboration with domain experts, end-users, and policymakers can lead to ready-to-use XIAI methods across NLP and medical tasks. While challenges exist, XIAI techniques offer a valuable foundation for interpretable NLP algorithms in healthcare.

Processing of Short-Form Content in Clinical Narratives: Systematic Scoping Review

BACKGROUND

Clinical narratives are essential components of electronic health records. The adoption of electronic health records has increased documentation time for hospital staff, leading to the use of abbreviations and acronyms more frequently. This brevity can potentially hinder comprehension for both professionals and patients.

OBJECTIVE

This review aims to provide an overview of the types of short forms found in clinical narratives, as well as the natural language processing (NLP) techniques used for their identification, expansion, and disambiguation.

METHODS

In the databases Web of Science, Embase, MEDLINE, EBMR (Evidence-Based Medicine Reviews), and ACL Anthology, publications that met the inclusion criteria were searched according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for a systematic scoping review. Original, peer-reviewed publications focusing on short-form processing in human clinical narratives were included, covering the period from January 2018 to February 2023. Short-form types were extracted, and multidimensional research methodologies were assigned to each target objective (identification, expansion, and disambiguation). NLP study recommendations and study characteristics were systematically assigned occurrence rates for evaluation.

RESULTS

Out of a total of 6639 records, only 19 articles were included in the final analysis. Rule-based approaches were predominantly used for identifying short forms, while string similarity and vector representations were applied for expansion. Embeddings and deep learning approaches were used for disambiguation.

CONCLUSIONS

The scope and types of what constitutes a clinical short form were often not explicitly defined by the authors. This lack of definition poses challenges for reproducibility and for determining whether specific methodologies are suitable for different types of short forms. Analysis of a subset of NLP recommendations for assessing quality and reproducibility revealed only partial adherence to these recommendations. Single-character abbreviations were underrepresented in studies on clinical narrative processing, as were investigations in languages other than English. Future research should focus on these 2 areas, and each paper should include descriptions of the types of content analyzed.

Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center

INTRODUCTION

Data collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients' medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort.

MATERIALS AND METHODS

Consecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients' comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients' functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared.

RESULTS

The active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings.

CONCLUSIONS

We developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.

Human-in-the-Loop-A Deep Learning Strategy in Combination with a Patient-Specific Gaussian Mixture Model Leads to the Fast Characterization of Volumetric Ground-Glass Opacity and Consolidation in the Computed Tomography Scans of COVID-19 Patients

Background/Objectives: The accurate quantification of ground-glass opacities (GGOs) and consolidation volumes has prognostic value in COVID-19 patients. Nevertheless, the accurate manual quantification of the corresponding volumes remains a time-consuming task. Deep learning (DL) has demonstrated good performance in the segmentation of normal lung parenchyma and COVID-19 pneumonia. We introduce a Human-in-the-Loop (HITL) strategy for the segmentation of normal lung parenchyma and COVID-19 pneumonia that is both time efficient and quality effective. Furthermore, we propose a Gaussian Mixture Model (GMM) to classify GGO and consolidation based on a probabilistic characterization and case-sensitive thresholds. Methods: A total of 65 Computed Tomography (CT) scans from 64 patients, acquired between March 2020 and June 2021, were randomly selected. We pretrained a 3D-UNet with an international dataset and implemented a HITL strategy to refine the local dataset with delineations by teams of medical interns, radiology residents, and radiologists. Following each HITL cycle, 3D-UNet was re-trained until the Dice Similarity Coefficients (DSCs) reached the quality criteria set by radiologists (DSC = 0.95/0.8 for the normal lung parenchyma/COVID-19 pneumonia). For the probabilistic characterization, a Gaussian Mixture Model (GMM) was fitted to the Hounsfield Units (HUs) of voxels from the CT scans of patients with COVID-19 pneumonia on the assumption that two distinct populations were superimposed: one for GGO and one for consolidation. Results: Manual delineation of the normal lung parenchyma and COVID-19 pneumonia was performed by seven teams on 65 CT scans from 64 patients (56 ± 16 years old (μ ± σ), 46 males, 62 with reported symptoms). Automated lung/COVID-19 pneumonia segmentation with a DSC > 0.96/0.81 was achieved after three HITL cycles. The HITL strategy improved the DSC by 0.2 and 0.5 for the normal lung parenchyma and COVID-19 pneumonia segmentation, respectively. The distribution of the patient-specific thresholds derived from the GMM yielded a mean of -528.4 ± 99.5 HU (μ ± σ), which is below most of the reported fixed HU thresholds. Conclusions: The HITL strategy allowed for fast and effective annotations, thereby enhancing the quality of segmentation for a local CT dataset. Probabilistic characterization of COVID-19 pneumonia by the GMM enabled patient-specific segmentation of GGO and consolidation. The combination of both approaches is essential to gain confidence in DL approaches in our local environment. The patient-specific probabilistic approach, when combined with the automatic quantification of COVID-19 imaging findings, enhances the understanding of GGO and consolidation during the course of the disease, with the potential to improve the accuracy of clinical predictions.

Intelligent systems in healthcare: A systematic survey of explainable user interfaces

With radiology shortages affecting over half of the global population, the potential of artificial intelligence to revolutionize medical diagnosis and treatment is ever more important. However, lacking trust from medical professionals hinders the widespread adoption of AI models in health sciences. Explainable AI (XAI) aims to increase trust and understanding of black box models by identifying biases and providing transparent explanations. This is the first survey that explores explainable user interfaces (XUI) from a medical domain perspective, analysing the visualization and interaction methods employed in current medical XAI systems. We analysed 42 explainable interfaces following the PRISMA methodology, emphasizing the critical role of effectively conveying information to users as part of the explanation process. We contribute a taxonomy of interface design properties and identify five distinct clusters of research papers. Future research directions include contestability in medical decision support, counterfactual explanations for images, and leveraging Large Language Models to enhance XAI interfaces in healthcare.

nnU-Net-based Segmentation of Tumor Subcompartments in Pediatric Medulloblastoma Using Multiparametric MRI: A Multi-institutional Study

Purpose To evaluate nnU-Net-based segmentation models for automated delineation of medulloblastoma tumors on multi-institutional MRI scans. Materials and Methods This retrospective study included 78 pediatric patients (52 male, 26 female), with ages ranging from 2 to 18 years, with medulloblastomas, from three different sites (28 from hospital A, 18 from hospital B, and 32 from hospital C), who had data available from three clinical MRI protocols (gadolinium-enhanced T1-weighted, T2-weighted, and fluid-attenuated inversion recovery). The scans were retrospectively collected from the year 2000 until May 2019. Reference standard annotations of the tumor habitat, including enhancing tumor, edema, and cystic core plus nonenhancing tumor subcompartments, were performed by two experienced neuroradiologists. Preprocessing included registration to age-appropriate atlases, skull stripping, bias correction, and intensity matching. The two models were trained as follows: (a) the transfer learning nnU-Net model was pretrained on an adult glioma cohort (n = 484) and fine-tuned on medulloblastoma studies using Models Genesis and (b) the direct deep learning nnU-Net model was trained directly on the medulloblastoma datasets, across fivefold cross-validation. Model robustness was evaluated on the three datasets when using different combinations of training and test sets, with data from two sites at a time used for training and data from the third site used for testing. Results Analysis on the three test sites yielded Dice scores of 0.81, 0.86, and 0.86 and 0.80, 0.86, and 0.85 for tumor habitat; 0.68, 0.84, and 0.77 and 0.67, 0.83, and 0.76 for enhancing tumor; 0.56, 0.71, and 0.69 and 0.56, 0.71, and 0.70 for edema; and 0.32, 0.48, and 0.43 and 0.29, 0.44, and 0.41 for cystic core plus nonenhancing tumor for the transfer learning and direct nnU-Net models, respectively. The models were largely robust to site-specific variations. Conclusion nnU-Net segmentation models hold promise for accurate, robust automated delineation of medulloblastoma tumor subcompartments, potentially leading to more effective radiation therapy planning in pediatric medulloblastoma. Keywords: Pediatrics, MR Imaging, Segmentation, Transfer Learning, Medulloblastoma, nnU-Net, MRI Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Rudie and Correia de Verdier in this issue.

Deceptively Simple yet Profoundly Impactful: Text Messaging Interventions to Support Health

This paper examines the use of text message (SMS) interventions for health-related behavioral support. It first outlines the historical progress in SMS intervention research publications and the variety of funds from US government agencies. A narrative review follows, highlighting the effectiveness of SMS interventions in key health areas, such as physical activity, diet and weight loss, mental health, and substance use, based on published meta-analyses. It then outlines advantages of text messaging compared to other digital modalities, including the real-time capability to collect information and deliver microdoses of intervention support. Crucial design elements are proposed to optimize effectiveness and longitudinal engagement across communication strategies, psychological foundations, and behavior change tactics. We then discuss advanced functionalities, such as the potential for generative artificial intelligence to improve user interaction. Finally, major challenges to implementation are highlighted, including the absence of a dedicated commercial platform, privacy and security concerns with SMS technology, difficulties integrating SMS interventions with medical informatics systems, and concerns about user engagement. Proposed solutions aim to facilitate the broader application and effectiveness of SMS interventions. Our hope is that these insights can assist researchers and practitioners in using SMS interventions to improve health outcomes and reducing disparities.

Metis: a python-based user interface to collect expert feedback for generative chemistry models

One challenge that current de novo drug design models face is a disparity between the user's expectations and the actual output of the model in practical applications. Tailoring models to better align with chemists' implicit knowledge, expectation and preferences is key to overcoming this obstacle effectively. While interest in preference-based and human-in-the-loop machine learning in chemistry is continuously increasing, no tool currently exists that enables the collection of standardized and chemistry-specific feedback. Metis is a Python-based open-source graphical user interface (GUI), designed to solve this and enable the collection of chemists' detailed feedback on molecular structures. The GUI enables chemists to explore and evaluate molecules, offering a user-friendly interface for annotating preferences and specifying desired or undesired structural features. By providing chemists the opportunity to give detailed feedback, allows researchers to capture more efficiently the chemist's implicit knowledge and preferences. This knowledge is crucial to align the chemist's idea with the de novo design agents. The GUI aims to enhance this collaboration between the human and the "machine" by providing an intuitive platform where chemists can interactively provide feedback on molecular structures, aiding in preference learning and refining de novo design strategies. Metis integrates with the existing de novo framework REINVENT, creating a closed-loop system where human expertise can continuously inform and refine the generative models.Scientific contributionWe introduce a novel Graphical User Interface, that allows chemists/researchers to give detailed feedback on substructures and properties of small molecules. This tool can be used to learn the preferences of chemists in order to align de novo drug design models with the chemist's ideas. The GUI can be customized to fit different needs and projects and enables direct integration into de novo REINVENT runs. We believe that Metis can facilitate the discussion and development of novel ways to integrate human feedback that goes beyond binary decisions of liking or disliking a molecule.

Clinical domain knowledge-derived template improves post hoc AI explanations in pneumothorax classification

OBJECTIVE

Pneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement.

METHOD

We propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of the explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template's boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det).

RESULTS

The proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach.

CONCLUSIONS

In the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.

Algor-ethics: charting the ethical path for AI in critical care

The integration of Clinical Decision Support Systems (CDSS) based on artificial intelligence (AI) in healthcare is groundbreaking evolution with enormous potential, but its development and ethical implementation, presents unique challenges, particularly in critical care, where physicians often deal with life-threating conditions requiring rapid actions and patients unable to participate in the decisional process. Moreover, development of AI-based CDSS is complex and should address different sources of bias, including data acquisition, health disparities, domain shifts during clinical use, and cognitive biases in decision-making. In this scenario algor-ethics is mandatory and emphasizes the integration of 'Human-in-the-Loop' and 'Algorithmic Stewardship' principles, and the benefits of advanced data engineering. The establishment of Clinical AI Departments (CAID) is necessary to lead AI innovation in healthcare, ensuring ethical integrity and human-centered development in this rapidly evolving field.

Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging

Explainable artificial intelligence (XAI) has experienced a vast increase in recognition over the last few years. While the technical developments are manifold, less focus has been placed on the clinical applicability and usability of systems. Moreover, not much attention has been given to XAI systems that can handle multimodal and longitudinal data, which we postulate are important features in many clinical workflows. In this study, we review, from a clinical perspective, the current state of XAI for multimodal and longitudinal datasets and highlight the challenges thereof. Additionally, we propose the XAI orchestrator, an instance that aims to help clinicians with the synopsis of multimodal and longitudinal data, the resulting AI predictions, and the corresponding explainability output. We propose several desirable properties of the XAI orchestrator, such as being adaptive, hierarchical, interactive, and uncertainty-aware.

Associations between the choroid plexus and tau in Alzheimer's disease using an active learning segmentation pipeline

BACKGROUND

The cerebrospinal fluid (CSF), primarily generated by the choroid plexus (ChP), is the major carrier of the glymphatic system. The alternations of CSF production and the ChP can be associated with the Alzheimer's disease (AD). The present work investigated the roles of the ChP in the AD based on a proposed ChP image segmentation pipeline.

METHODS

A human-in-the-loop ChP image segmentation pipeline was implemented with intermediate and active learning datasets. The performance of the proposed pipeline was evaluated on manual contours by five radiologists, compared to the FreeSurfer and FastSurfer toolboxes. The ChP volume and blood flow were investigated among AD groups. The correlations between the ChP volume and AD CSF biomarkers including phosphorylated tau (p-tau), total tau (t-tau), amyloid-β42 (Aβ42), and amyloid-β40 (Aβ40) was investigated using three models (univariate, multiple variables, and stepwise regression) on two datasets with 806 and 320 subjects.

RESULTS

The proposed ChP segmentation pipeline achieved superior performance with a Dice coefficient of 0.620 on the test dataset, compared to the FreeSurfer (0.342) and FastSurfer (0.371). Significantly larger volumes (p < 0.001) and higher perfusion (p = 0.032) at the ChP were found in AD compared to CN groups. Significant correlations were found between the tau and the relative ChP volume (the ChP volume and ChP/parenchyma ratio) in each patient groups and in the univariate regression analysis (p < 0.001), the multiple regression model (p < 0.05 except for the t-tau in the LMCI), and in the step-wise regression model (p < 0.021). In addition, the correlation coefficients changed from - 0.32 to - 0.21 along with the AD progression in the multiple regression model. In contrast, the Aβ42 and Aβ40 shows consistent and significant associations with the lateral ventricle related measures in the step-wise regression model (p < 0.027).

CONCLUSIONS

The proposed pipeline provided accurate ChP segmentation which revealed the associations between the ChP and tau level in the AD. The proposed pipeline is available on GitHub ( https://github.com/princeleeee/ChP-Seg ).

Cybersecurity in the generative artificial intelligence era

Generative Artificial Intelligence (GenAI) are algorithms capable of generating original content. The ability of GenAI to learn and generate novel outputs alike human cognition has taken the world by storm and ushered in a new era. In this review, we explore the role of GenAI in healthcare, including clinical, operational, and research applications, and delve into the cybersecurity risks of this technology. We discuss risks such as data privacy risks, data poisoning attacks, the propagation of bias, and hallucinations. In this review, we recommend risk mitigation strategies to enhance cybersecurity in GenAI technologies and further explore the use of GenAI as a tool in itself to enhance cybersecurity across the various AI algorithms. GenAI is emerging as a pivotal catalyst across various industries including the healthcare domain. Comprehending the intricacies of this technology and its potential risks will be imperative for us to fully capitalise on the benefits that GenAI can bring.

Digital health delivery in respiratory medicine: adjunct, replacement or cause for division?

Digital medicine is already well established in respiratory medicine through remote monitoring digital devices which are used in the day-to-day care of patients with asthma, COPD and sleep disorders. Image recognition software, deployed in thoracic radiology for many applications including lung cancer screening, is another application of digital medicine. Used as clinical decision support, this software will soon become part of day-to-day practice once concerns regarding generalisability have been addressed. Embodied in the electronic health record, digital medicine also plays a substantial role in the day-to-day clinical practice of respiratory medicine. Given the considerable work the electronic health record demands from clinicians, the next tangible impact of digital medicine may be artificial intelligence that aids administration, makes record keeping easier and facilitates better digital communication with patients. Future promises of digital medicine are based on their potential to analyse and characterise the large amounts of digital clinical data that are collected in routine care. Offering the potential to predict outcomes and personalise therapy, there is much to be excited by in this new epoch of innovation. However, these digital tools are by no means a silver bullet. It remains uncertain whether, let alone when, the promises of better models of personalisation and prediction will translate into clinically meaningful and cost-effective products for clinicians.

Comparison of three chatbots as an assistant for problem-solving in clinical laboratory

OBJECTIVES

Data generation in clinical settings is ongoing and perpetually increasing. Artificial intelligence (AI) software may help detect data-related errors or facilitate process management. The aim of the present study was to test the extent to which the frequently encountered pre-analytical, analytical, and postanalytical errors in clinical laboratories, and likely clinical diagnoses can be detected through the use of a chatbot.

METHODS

A total of 20 case scenarios, 20 multiple-choice, and 20 direct questions related to errors observed in pre-analytical, analytical, and postanalytical processes were developed in English. Difficulty assessment was performed for the 60 questions. Responses by 4 chatbots to the questions were scored in a blinded manner by 3 independent laboratory experts for accuracy, usefulness, and completeness.

RESULTS

According to Chi-squared test, accuracy score of ChatGPT-3.5 (54.4 %) was significantly lower than CopyAI (86.7 %) (p=0.0269) and ChatGPT v4.0. (88.9 %) (p=0.0168), respectively in cases. In direct questions, there was no significant difference between ChatGPT-3.5 (67.8 %) and WriteSonic (69.4 %), ChatGPT v4.0. (78.9 %) and CopyAI (73.9 %) (p=0.914, p=0.433 and p=0.675, respectively) accuracy scores. CopyAI (90.6 %) presented significantly better performance compared to ChatGPT-3.5 (62.2 %) (p=0.036) in multiple choice questions.

CONCLUSIONS

These applications presented considerable performance to find out the cases and reply to questions. In the future, the use of AI applications is likely to increase in clinical settings if trained and validated by technical and medical experts within a structural framework.

A pathologist-AI collaboration framework for enhancing diagnostic accuracies and efficiencies

In pathology, the deployment of artificial intelligence (AI) in clinical settings is constrained by limitations in data collection and in model transparency and interpretability. Here we describe a digital pathology framework, nuclei.io, that incorporates active learning and human-in-the-loop real-time feedback for the rapid creation of diverse datasets and models. We validate the effectiveness of the framework via two crossover user studies that leveraged collaboration between the AI and the pathologist, including the identification of plasma cells in endometrial biopsies and the detection of colorectal cancer metastasis in lymph nodes. In both studies, nuclei.io yielded considerable diagnostic performance improvements. Collaboration between clinicians and AI will aid digital pathology by enhancing accuracies and efficiencies.

Never-Ending Learning for Explainable Brain Computing

Exploring the nature of human intelligence and behavior is a longstanding pursuit in cognitive neuroscience, driven by the accumulation of knowledge, information, and data across various studies. However, achieving a unified and transparent interpretation of findings presents formidable challenges. In response, an explainable brain computing framework is proposed that employs the never-ending learning paradigm, integrating evidence combination and fusion computing within a Knowledge-Information-Data (KID) architecture. The framework supports continuous brain cognition investigation, utilizing joint knowledge-driven forward inference and data-driven reverse inference, bolstered by the pre-trained language modeling techniques and the human-in-the-loop mechanisms. In particular, it incorporates internal evidence learning through multi-task functional neuroimaging analyses and external evidence learning via topic modeling of published neuroimaging studies, all of which involve human interactions at different stages. Based on two case studies, the intricate uncertainty surrounding brain localization in human reasoning is revealed. The present study also highlights the potential of systematization to advance explainable brain computing, offering a finer-grained understanding of brain activity patterns related to human intelligence.

Revolutionizing Cardiology through Artificial Intelligence-Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment-A Comprehensive Review of the Past 5 Years

BACKGROUND

Artificial intelligence (AI) can radically change almost every aspect of the human experience. In the medical field, there are numerous applications of AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, this fact being supported by the exponential increase in the number of publications in which the algorithms play an important role in data analysis, pattern discovery, identification of anomalies, and therapeutic decision making. Furthermore, with technological development, there have appeared new models of machine learning (ML) and deep learning (DP) that are capable of exploring various applications of AI in cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional cardiology, and many others. In this sense, the present article aims to provide a general vision of the current state of AI use in cardiology.

RESULTS

We identified and included a subset of 200 papers directly relevant to the current research covering a wide range of applications. Thus, this paper presents AI applications in cardiovascular imaging, arithmology, clinical or emergency cardiology, cardiovascular prevention, and interventional procedures in a summarized manner. Recent studies from the highly scientific literature demonstrate the feasibility and advantages of using AI in different branches of cardiology.

CONCLUSIONS

The integration of AI in cardiology offers promising perspectives for increasing accuracy by decreasing the error rate and increasing efficiency in cardiovascular practice. From predicting the risk of sudden death or the ability to respond to cardiac resynchronization therapy to the diagnosis of pulmonary embolism or the early detection of valvular diseases, AI algorithms have shown their potential to mitigate human error and provide feasible solutions. At the same time, limits imposed by the small samples studied are highlighted alongside the challenges presented by ethical implementation; these relate to legal implications regarding responsibility and decision making processes, ensuring patient confidentiality and data security. All these constitute future research directions that will allow the integration of AI in the progress of cardiology.

An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight

Introduction

Polysomnographic recordings are essential for diagnosing many sleep disorders, yet their detailed analysis presents considerable challenges. With the rise of machine learning methodologies, researchers have created various algorithms to automatically score and extract clinically relevant features from polysomnography, but less research has been devoted to how exactly the algorithms should be incorporated into the workflow of sleep technologists. This paper presents a sophisticated data collection platform developed under the Sleep Revolution project, to harness polysomnographic data from multiple European centers.

Methods

A tripartite platform is presented: a user-friendly web platform for uploading three-night polysomnographic recordings, a dedicated splitter that segments these into individual one-night recordings, and an advanced processor that enhances the one-night polysomnography with contemporary automatic scoring algorithms. The platform is evaluated using real-life data and human scorers, whereby scoring time, accuracy, and trust are quantified. Additionally, the scorers were interviewed about their trust in the platform, along with the impact of its integration into their workflow.

Results

We found that incorporating AI into the workflow of sleep technologists both decreased the time to score by up to 65 min and increased the agreement between technologists by as much as 0.17 κ.

Discussion

We conclude that while the inclusion of AI into the workflow of sleep technologists can have a positive impact in terms of speed and agreement, there is a need for trust in the algorithms.

An artificial intelligence model for detecting pathological lymph node metastasis in prostate cancer using whole slide images: a retrospective, multicentre, diagnostic study

Background

The pathological examination of lymph node metastasis (LNM) is crucial for treating prostate cancer (PCa). However, the limitations with naked-eye detection and pathologist workload contribute to a high missed-diagnosis rate for nodal micrometastasis. We aimed to develop an artificial intelligence (AI)-based, time-efficient, and high-precision PCa LNM detector (ProCaLNMD) and evaluate its clinical application value.

Methods

In this multicentre, retrospective, diagnostic study, consecutive patients with PCa who underwent radical prostatectomy and pelvic lymph node dissection at five centres between Sep 2, 2013 and Apr 28, 2023 were included, and histopathological slides of resected lymph nodes were collected and digitised as whole-slide images for model development and validation. ProCaLNMD was trained at a dataset from a single centre (the Sun Yat-sen Memorial Hospital of Sun Yat-sen University [SYSMH]), and externally validated in the other four centres. A bladder cancer dataset from SYSMH was used to further validate ProCaLNMD, and an additional validation (human-AI comparison and collaboration study) containing consecutive patients with PCa from SYSMH was implemented to evaluate the application value of integrating ProCaLNMD into the clinical workflow. The primary endpoint was the area under the receiver operating characteristic curve (AUROC) of ProCaLNMD. In addition, the performance measures for pathologists with ProCaLNMD assistance was also assessed.

Findings

In total, 8225 slides from 1297 patients with PCa were collected and digitised. Overall, 8158 slides (18,761 lymph nodes) from 1297 patients with PCa (median age 68 years [interquartile range 64-73]; 331 [26%] with LNM) were used to train and validate ProCaLNMD. The AUROC of ProCaLNMD ranged from 0.975 (95% confidence interval 0.953-0.998) to 0.992 (0.982-1.000) in the training and validation datasets, with sensitivities > 0.955 and specificities > 0.921. ProCaLNMD also demonstrated an AUROC of 0.979 in the cross-cancer dataset. ProCaLNMD use triggered true reclassification in 43 (4.3%) slides in which micrometastatic tumour regions were initially missed by pathologists, thereby correcting 28 (8.5%) missed-diagnosed cases of previous routine pathological reports. In the human-AI comparison and collaboration study, the sensitivity of ProCaLNMD (0.983 [0.908-1.000]) surpassed that of two junior pathologists (0.862 [0.746-0.939], P = 0.023; 0.879 [0.767-0.950], P = 0.041) by 10-12% and showed no difference to that of two senior pathologists (both 0.983 [0.908-1.000], both P > 0.99). Furthermore, ProCaLNMD significantly boosted the diagnostic sensitivity of two junior pathologists (both P = 0.041) to the level of senior pathologists (both P > 0.99), and substantially reduced the four pathologists' slide reviewing time (-31%, P < 0.0001; -34%, P < 0.0001; -29%, P < 0.0001; and -27%, P = 0.00031).

Interpretation

ProCaLNMD demonstrated high diagnostic capabilities for identifying LNM in prostate cancer, reducing the likelihood of missed diagnoses by pathologists and decreasing the slide reviewing time, highlighting its potential for clinical application.

Funding

National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, the Guangdong Provincial Clinical Research Centre for Urological Diseases, and the Science and Technology Projects in Guangzhou.

Patient and public involvement workshop to shape artificial intelligence-supported connected asthma self-management research

Digital interventions with artificial intelligence (AI) can potentially support people with asthma to reduce the risk of exacerbation. Engaging patients throughout the development process is essential to ensure usability of the intervention for the end-users. Using our Connected for Asthma (C4A) intervention as an exemplar, we explore how patient involvement can shape a digital intervention. Seven Patient and Public Involvement (PPI) colleagues from the Asthma UK Centre for Applied Research participated in four advisory workshops to discuss how they would prefer to use/interact with AI to support living with their asthma, the benefit and caveats to use the AI that incorporated asthma monitoring and indoor/outdoor environmental data. Discussion focussed on the three most wanted use cases identified in our previous studies. PPI colleagues wanted AI to support data collection, remind them about self-management tasks, teach them about asthma environmental triggers, identify risk, and empower them to confidently look after their asthma whilst emphasising that AI does not replace clinicians. The discussion informed the key components in the next C4A interventions, including the approach to interacting with AI, the technology features and the research topics. Attendees highlighted the importance of considering health inequities, the presentation of data, and concerns about data accuracy, data privacy, security and ownership. We have demonstrated how patient roles can shift from that of 'user' (the traditional 'tester' of a digital intervention), to a co-design partner who shapes the next iteration of the intervention. Technology innovators should seek practical and feasible strategies to involve PPI colleagues throughout the development cycle of a digital intervention; supporting researchers to explore the barriers, concerns, enablers and advantages of implementing digital healthcare.

"Better than my professor?" How to develop artificial intelligence tools for higher education

Artificial Intelligence (AI) tools are currently designed and tested in many fields to improve humans' ability to make decisions. One of these fields is higher education. For example, AI-based chatbots ("conversational pedagogical agents") could engage in conversations with students in order to provide timely feedback and responses to questions while the learning process is taking place and to collect data to personalize the delivery of course materials. However, many existent tools are able to perform tasks that human professionals (educators, tutors, professors) could perform, just in a timelier manner. While discussing the possible implementation of AI-based tools in our university's educational programs, we reviewed the current literature and identified a number of capabilities that future AI solutions may feature, in order to improve higher education processes, with a focus on distance higher education. Specifically, we suggest that innovative tools could influence the methodologies by which students approach learning; facilitate connections and information attainment beyond course materials; support the communication with the professor; and, draw from motivation theories to foster learning engagement, in a personalized manner. Future research should explore high-level opportunities represented by AI for higher education, including their effects on learning outcomes and the quality of the learning experience as a whole.

An active machine learning approach for optimal design of magnesium alloys using Bayesian optimisation

In the pursuit of magnesium (Mg) alloys with targeted mechanical properties, a multi-objective Bayesian optimisation workflow is presented to enable optimal Mg-alloy design. A probabilistic Gaussian process regressor model was trained through an active learning loop, while balancing the exploration and exploitation trade-off via an acquisition function of the upper confidence bound. New candidate alloys suggested by the optimiser within each iteration were appended to the training data, and the performance of this sequential strategy was validated via a regret analysis. Using the proposed approach, the dependency of the prediction error on the training data was overcome by considering both the predictions and their associated uncertainties. The method developed here, has been packaged into a web tool with a graphical user-interactive interface (GUI) that allows the proposed optimal Mg-alloy design strategy to be deployed.

Generative AI in Medical Practice: In-Depth Exploration of Privacy and Security Challenges

As advances in artificial intelligence (AI) continue to transform and revolutionize the field of medicine, understanding the potential uses of generative AI in health care becomes increasingly important. Generative AI, including models such as generative adversarial networks and large language models, shows promise in transforming medical diagnostics, research, treatment planning, and patient care. However, these data-intensive systems pose new threats to protected health information. This Viewpoint paper aims to explore various categories of generative AI in health care, including medical diagnostics, drug discovery, virtual health assistants, medical research, and clinical decision support, while identifying security and privacy threats within each phase of the life cycle of such systems (ie, data collection, model development, and implementation phases). The objectives of this study were to analyze the current state of generative AI in health care, identify opportunities and privacy and security challenges posed by integrating these technologies into existing health care infrastructure, and propose strategies for mitigating security and privacy risks. This study highlights the importance of addressing the security and privacy threats associated with generative AI in health care to ensure the safe and effective use of these systems. The findings of this study can inform the development of future generative AI systems in health care and help health care organizations better understand the potential benefits and risks associated with these systems. By examining the use cases and benefits of generative AI across diverse domains within health care, this paper contributes to theoretical discussions surrounding AI ethics, security vulnerabilities, and data privacy regulations. In addition, this study provides practical insights for stakeholders looking to adopt generative AI solutions within their organizations.

Structured information extraction from scientific text with large language models

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.

Application scenario-oriented molecule generation platform developed for drug discovery

Design of molecules for candidate compound selection is one of the central challenges in drug discovery due to the complexity of chemical space and requirement of multi-parameter optimization. Here we present an application scenario-oriented platform (ID4Idea) for molecule generation in different scenarios of drug discovery. This platform utilizes both library or rule based and generative based algorithms (VAE, RNN, GAN, etc.), in combination with various AI learning types (pre-training, transfer learning, reinforcement learning, active learning, etc.) and input representations (1D SMILES, 2D graph, 3D shape, binding site, pharmacophore, etc.), to enable customized solutions for a given molecular design scenario. Besides the usual generation followed screening protocol, goal-directed molecule generation can also be conducted towards predefined goals, enhancing the efficiency of hit identification, lead finding, and lead optimization. We demonstrate the effectiveness of ID4Idea platform through case studies, showcasing customized solutions for different design tasks using various input information, such as binding pockets, pharmacophores, and compound representations. In addition, remaining challenges are discussed to unlock the full potential of AI models in drug discovery and pave the way for the development of novel therapeutics.

Standigm ASK™: knowledge graph and artificial intelligence platform applied to target discovery in idiopathic pulmonary fibrosis

Standigm ASK™ revolutionizes healthcare by addressing the critical challenge of identifying pivotal target genes in disease mechanisms-a fundamental aspect of drug development success. Standigm ASK™ integrates a unique combination of a heterogeneous knowledge graph (KG) database and an attention-based neural network model, providing interpretable subgraph evidence. Empowering users through an interactive interface, Standigm ASK™ facilitates the exploration of predicted results. Applying Standigm ASK™ to idiopathic pulmonary fibrosis (IPF), a complex lung disease, we focused on genes (AMFR, MDFIC and NR5A2) identified through KG evidence. In vitro experiments demonstrated their relevance, as TGFβ treatment induced gene expression changes associated with epithelial-mesenchymal transition characteristics. Gene knockdown reversed these changes, identifying AMFR, MDFIC and NR5A2 as potential therapeutic targets for IPF. In summary, Standigm ASK™ emerges as an innovative KG and artificial intelligence platform driving insights in drug target discovery, exemplified by the identification and validation of therapeutic targets for IPF.

Revisiting the role of HR in the age of AI: bringing humans and machines closer together in the workplace

The functions of human resource management (HRM) have changed radically in the past 20 years due to market and technological forces, becoming more cross-functional and data-driven. In the age of AI, the role of HRM professionals in organizations continues to evolve. Artificial intelligence (AI) is transforming many HRM functions and practices throughout organizations creating system and process efficiencies, performing advanced data analysis, and contributing to the value creation process of the organization. A growing body of evidence highlights the benefits AI brings to the field of HRM. Despite the increased interest in AI-HRM scholarship, focus on human-AI interaction at work and AI-based technologies for HRM is limited and fragmented. Moreover, the lack of human considerations in HRM tech design and deployment can hamper AI digital transformation efforts. This paper provides a contemporary and forward-looking perspective to the strategic and human-centric role HRM plays within organizations as AI becomes more integrated in the workplace. Spanning three distinct phases of AI-HRM integration (technocratic, integrated, and fully-embedded), it examines the technical, human, and ethical challenges at each phase and provides suggestions on how to overcome them using a human-centric approach. Our paper highlights the importance of the evolving role of HRM in the AI-driven organization and provides a roadmap on how to bring humans and machines closer together in the workplace.

AI and professional liability assessment in healthcare. A revolution in legal medicine?

The adoption of advanced artificial intelligence (AI) systems in healthcare is transforming the healthcare-delivery landscape. Artificial intelligence may enhance patient safety and improve healthcare outcomes, but it presents notable ethical and legal dilemmas. Moreover, as AI streamlines the analysis of the multitude of factors relevant to malpractice claims, including informed consent, adherence to standards of care, and causation, the evaluation of professional liability might also benefit from its use. Beginning with an analysis of the basic steps in assessing professional liability, this article examines the potential new medical-legal issues that an expert witness may encounter when analyzing malpractice cases and the potential integration of AI in this context. These changes related to the use of integrated AI, will necessitate efforts on the part of judges, experts, and clinicians, and may require new legislative regulations. A new expert witness will be likely necessary in the evaluation of professional liability cases. On the one hand, artificial intelligence will support the expert witness; however, on the other hand, it will introduce specific elements into the activities of healthcare workers. These elements will necessitate an expert witness with a specialized cultural background. Examining the steps of professional liability assessment indicates that the likely path for AI in legal medicine involves its role as a collaborative and integrated tool. The combination of AI with human judgment in these assessments can enhance comprehensiveness and fairness. However, it is imperative to adopt a cautious and balanced approach to prevent complete automation in this field.

Closed-Loop Uncertainty: The Evaluation and Calibration of Uncertainty for Human-Machine Teams under Data Drift

Though an accurate measurement of entropy, or more generally uncertainty, is critical to the success of human-machine teams, the evaluation of the accuracy of such metrics as a probability of machine correctness is often aggregated and not assessed as an iterative control process. The entropy of the decisions made by human-machine teams may not be accurately measured under cold start or at times of data drift unless disagreements between the human and machine are immediately fed back to the classifier iteratively. In this study, we present a stochastic framework by which an uncertainty model may be evaluated iteratively as a probability of machine correctness. We target a novel problem, referred to as the threshold selection problem, which involves a user subjectively selecting the point at which a signal transitions to a low state. This problem is designed to be simple and replicable for human-machine experimentation while exhibiting properties of more complex applications. Finally, we explore the potential of incorporating feedback of machine correctness into a baseline naïve Bayes uncertainty model with a novel reinforcement learning approach. The approach refines a baseline uncertainty model by incorporating machine correctness at every iteration. Experiments are conducted over a large number of realizations to properly evaluate uncertainty at each iteration of the human-machine team. Results show that our novel approach, called closed-loop uncertainty, outperforms the baseline in every case, yielding about 45% improvement on average.

Harnessing human and machine intelligence for planetary-level climate action

The ongoing global race for bigger and better artificial intelligence (AI) systems is expected to have a profound societal and environmental impact by altering job markets, disrupting business models, and enabling new governance and societal welfare structures that can affect global consensus for climate action pathways. However, the current AI systems are trained on biased datasets that could destabilize political agencies impacting climate change mitigation and adaptation decisions and compromise social stability, potentially leading to societal tipping events. Thus, the appropriate design of a less biased AI system that reflects both direct and indirect effects on societies and planetary challenges is a question of paramount importance. In this paper, we tackle the question of data-centric knowledge generation for climate action in ways that minimize biased AI. We argue for the need to co-align a less biased AI with an epistemic web on planetary health challenges for more trustworthy decision-making. A human-in-the-loop AI can be designed to align with three goals. First, it can contribute to a planetary epistemic web that supports climate action. Second, it can directly enable mitigation and adaptation interventions through knowledge of social tipping elements. Finally, it can reduce the data injustices associated with AI pretraining datasets.

Continuous flow synthesis of pyridinium salts accelerated by multi-objective Bayesian optimization with active learning

We report a human-in-the-loop implementation of the multi-objective experimental design via a Bayesian optimization platform (EDBO+) towards the optimization of butylpyridinium bromide synthesis under continuous flow conditions. The algorithm simultaneously optimized reaction yield and production rate (or space-time yield) and generated a well defined Pareto front. The versatility of EDBO+ was demonstrated by expanding the reaction space mid-campaign by increasing the upper temperature limit. Incorporation of continuous flow techniques enabled improved control over reaction parameters compared to common batch chemistry processes, while providing a route towards future automated syntheses and improved scalability. To that end, we applied the open-source Python module, nmrglue, for semi-automated nuclear magnetic resonance (NMR) spectroscopy analysis, and compared the acquired outputs against those obtained through manual processing methods from spectra collected on both low-field (60 MHz) and high-field (400 MHz) NMR spectrometers. The EDBO+ based model was retrained with these four different datasets and the resulting Pareto front predictions provided insight into the effect of data analysis on model predictions. Finally, quaternization of poly(4-vinylpyridine) with bromobutane illustrated the extension of continuous flow chemistry to synthesize functional materials.

Implementation of a Hybrid Intelligence System Enabling the Effectiveness Assessment of Interaction Channels Use in HMI

The article presents a novel idea of Interaction Quality Sensor (IQS), introduced in the complete solution of Hybrid INTelligence (HINT) architecture for intelligent control systems. The proposed system is designed to use and prioritize multiple information channels (speech, images, videos) in order to optimize the information flow efficiency of interaction in HMI systems. The proposed architecture is implemented and validated in a real-world application of training unskilled workers-new employees (with lower competencies and/or a language barrier). With the help of the HINT system, the man-machine communication information channels are deliberately chosen based on IQS readouts to enable an untrained, inexperienced, foreign employee candidate to become a good worker, while not requiring the presence of either an interpreter or an expert during training. The proposed implementation is in line with the labor market trend, which displays significant fluctuations. The HINT system is designed to activate human resources and support organizations/enterprises in the effective assimilation of employees to the tasks performed on the production assembly line. The market need of solving this noticeable problem was caused by a large migration of employees within (and between) enterprises. The research results presented in the work show significant benefits of the methods used, while supporting multilingualism and optimizing the preselection of information channels.

Design of New Dispersants Using Machine Learning and Visual Analytics

Artificial intelligence (AI) is an emerging technology that is revolutionizing the discovery of new materials. One key application of AI is virtual screening of chemical libraries, which enables the accelerated discovery of materials with desired properties. In this study, we developed computational models to predict the dispersancy efficiency of oil and lubricant additives, a critical property in their design that can be estimated through a quantity named blotter spot. We propose a comprehensive approach that combines machine learning techniques with visual analytics strategies in an interactive tool that supports domain experts' decision-making. We evaluated the proposed models quantitatively and illustrated their benefits through a case study. Specifically, we analyzed a series of virtual polyisobutylene succinimide (PIBSI) molecules derived from a known reference substrate. Our best-performing probabilistic model was Bayesian Additive Regression Trees (BART), which achieved a mean absolute error of 5.50±0.34 and a root mean square error of 7.56±0.47, as estimated through 5-fold cross-validation. To facilitate future research, we have made the dataset, including the potential dispersants used for modeling, publicly available. Our approach can help accelerate the discovery of new oil and lubricant additives, and our interactive tool can aid domain experts in making informed decisions based on blotter spot and other key properties.

An extensive survey on the use of supervised machine learning techniques in the past two decades for prediction of drug side effects

Approved drugs for sale must be effective and safe, implying that the drug's advantages outweigh its known harmful side effects. Side effects (SE) of drugs are one of the common reasons for drug failure that may halt the whole drug discovery pipeline. The side effects might vary from minor concerns like a runny nose to potentially life-threatening issues like liver damage, heart attack, and death. Therefore, predicting the side effects of the drug is vital in drug development, discovery, and design. Supervised machine learning-based side effects prediction task has recently received much attention since it reduces time, chemical waste, design complexity, risk of failure, and cost. The advancement of supervised learning approaches for predicting side effects have emerged as essential computational tools. Supervised machine learning technique provides early information on drug side effects to develop an effective drug based on drug properties. Still, there are several challenges to predicting drug side effects. Thus, a near-exhaustive survey is carried out in this paper on the use of supervised machine learning approaches employed in drug side effects prediction tasks in the past two decades. In addition, this paper also summarized the drug descriptor required for the side effects prediction task, commonly utilized drug properties sources, computational models, and their performances. Finally, the research gap, open problems, and challenges for the further supervised learning-based side effects prediction task have been discussed.

A human-in-the-loop based Bayesian network approach to improve imbalanced radiation outcomes prediction for hepatocellular cancer patients with stereotactic body radiotherapy

Background

Imbalanced outcome is one of common characteristics of oncology datasets. Current machine learning approaches have limitation in learning from such datasets. Here, we propose to resolve this problem by utilizing a human-in-the-loop (HITL) approach, which we hypothesize will also lead to more accurate and explainable outcome prediction models.

Methods

A total of 119 HCC patients with 163 tumors were used in the study. 81 patients with 104 tumors from the University of Michigan Hospital treated with SBRT were considered as a discovery dataset for radiation outcomes model building. The external testing dataset included 59 tumors from 38 patients with SBRT from Princess Margaret Hospital. In the discovery dataset, 100 tumors from 77 patients had local control (LC) (96% of 104 tumors) and 23 patients had at least one grade increment of ALBI (I-ALBI) during six-month follow up (28% of 81 patients). Each patient had a total of 110 features, where 15 or 20 features were identified by physicians as expert knowledge features (EKFs) for LC or I-ALBI prediction. We proposed a HITL based Bayesian network (HITL-BN) approach to enhance the capability of selecting important features from imbalanced data in terms of accuracy and explainability through humans' participation by integrating feature importance ranking and Markov blanket algorithms. A pure data-driven Bayesian network (PD-BN) method was applied to the same discovery dataset of HCC patients as a benchmark.

Results

In the training and testing phases, the areas under receiver operating characteristic curves of the HITL-BN models for LC or I-ALBI prediction during SBRT are 0.85 (95% confidence interval: 0.75-0.95) or 0.89 (0.81-0.95) and 0.77 or 0.78, respectively. They significantly outperformed the during-treatment PD-BN model in predicting LC or I-ALBI based on the discovery cross-validation and testing datasets from the Delong tests.

Conclusion

By allowing the human expert to be part of the model building process, the HITL-BN approach yielded significantly improved accuracy as well as better explainability when dealing with imbalanced outcomes in the prediction of post-SBRT treatment response of HCC patients when compared to the PD-BN method.

Application of streaming analytics for Artificial Lift systems: a human-in-the-loop approach for analysing clustered time-series data from progressive cavity pumps

Assessing real-time performance of Artificial Lift Pumps is a prevalent time-series problem to tackle for natural gas operators in Eastern Australia. Multiple physics, data-driven, and hybrid approaches have been investigated to analyse or predict pump performance. However, these methods present a challenge in running compute-heavy algorithms on streaming time-series data. As there is limited research on novel approaches to tackle multivariate time-series analytics for Artificial Lift systems, this paper introduces a human-in-the-loop approach, where petroleum engineers label clustered time-series data to aid in streaming analytics. We rely on our recently developed novel approach of converting streaming time-series data into heatmap images to assist with real-time pump performance analytics. During this study, we were able to automate the labelling of streaming time-series data, which helped petroleum and well surveillance engineers better manage Artificial Lift Pumps through machine learning supported exception-based surveillance. The streaming analytics system developed as part of this research used historical time-series data from three hundred and fifty-nine (359) coal seam gas wells. The developed method is currently used by two natural gas operators, where the operators can accurately detect ten (10) performance-related events and five (5) anomalous events. This paper serves a two-fold purpose; first, we describe a step-by-step methodology that readers can use to reproduce the clustering method for multivariate time-series data. Second, we demonstrate how a human-in-the-loop approach adds value to the proposed method and achieves real-world results.

Constructing Explainable Classifiers from the Start—Enabling Human-in-the Loop Machine Learning

Interactive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not only for accuracy but perhaps for characterisation and discrimination rules, where separating one class from others is the primary objective. Moreover, this interaction enables humans to explore and gain insights into the dataset as well as validate the learned models. Validation requires transparency and interpretable classifiers. The huge relevance of understandable classification has been recently emphasised for many applications under the banner of explainable artificial intelligence (XAI). We use parallel coordinates to deploy an IML system that enables the visualisation of decision tree classifiers but also the generation of interpretable splits beyond parallel axis splits. Moreover, we show that characterisation and discrimination rules are also well communicated using parallel coordinates. In particular, we report results from the largest usability study of a IML system, confirming the merits of our approach.