Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal

Generative artificial intelligence in healthcare from the perspective of digital media: Applications, opportunities and challenges

Introduction

The emergence and application of generative artificial intelligence/large language models (hereafter GenAI LLMs) have the potential for significant impact on the healthcare industry. However, there is currently a lack of systematic research on GenAI LLMs in healthcare based on reliable data. This article aims to conduct an exploratory study of the application of GenAI LLMs (i.e., ChatGPT) in healthcare from the perspective of digital media (i.e., online news), including the application scenarios, potential opportunities, and challenges.

Methods

This research used thematic qualitative text analysis in five steps: firstly, developing main topical categories based on relevant articles; secondly, encoding the search keywords using these categories; thirdly, conducting searches for news articles via Google ; fourthly, encoding the sub-categories using the elaborate category system; and finally, conducting category-based analysis and presenting the results. Natural language processing techniques, including the TermRaider and AntConc tool, were applied in the aforementioned steps to assist in text qualitative analysis. Additionally, this study built a framework, using for analyzing the above three topics, from the perspective of five different stakeholders, including healthcare demanders and providers.

Results

This study summarizes 26 applications (e.g., provide medical advice, provide diagnosis and triage recommendations, provide mental health support, etc.), 21 opportunities (e.g., make healthcare more accessible, reduce healthcare costs, improve patients care, etc.), and 17 challenges (e.g., generate inaccurate/misleading/wrong answers, raise privacy concerns, lack of transparency, etc.), and analyzes the reasons for the formation of these key items and the links between the three research topics.

Conclusions

The application of GenAI LLMs in healthcare is primarily focused on transforming the way healthcare demanders access medical services (i.e., making it more intelligent, refined, and humane) and optimizing the processes through which healthcare providers offer medical services (i.e., simplifying, ensuring timeliness, and reducing errors). As the application becomes more widespread and deepens, GenAI LLMs is expected to have a revolutionary impact on traditional healthcare service models, but it also inevitably raises ethical and security concerns. Furthermore, GenAI LLMs applied in healthcare is still in the initial stage, which can be accelerated from a specific healthcare field (e.g., mental health) or a specific mechanism (e.g., GenAI LLMs' economic benefits allocation mechanism applied to healthcare) with empirical or clinical research.

Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers

Background

The utility of large language model-based (LLM) artificial intelligence (AI) chatbots in many aspects of healthcare is becoming apparent though their ability to address patient concerns remains unknown. We sought to evaluate the performance of two well-known, freely-accessible chatbots, ChatGPT and Google Bard, in responding to common questions about stroke rehabilitation posed by patients and their caregivers.

Methods

We collected questions from outpatients and their caregivers through a survey, categorised them by theme, and created representative questions to be posed to both chatbots. We then evaluated the chatbots' responses based on accuracy, safety, relevance, and readability. Interrater agreement was also tracked.

Results

Although both chatbots achieved similar overall scores, Google Bard performed slightly better in relevance and safety. Both provided readable responses with some general accuracy, but struggled with hallucinated responses, were often not specific, and lacked awareness of the possibility for emotional situations with the potential to turn dangerous. Additionally, interrater agreement was low, highlighting the variability in physician acceptance of their responses.

Conclusions

AI chatbots show potential in patient-facing support roles, but issues remain regarding safety, accuracy, and relevance. Future chatbots should address these problems to ensure that they can reliably and independently manage the concerns and questions of stroke patients and their caregivers.

Diagnostic power of ChatGPT 4 in distal radius fracture detection through wrist radiographs

Distal radius fractures rank among the most prevalent fractures in humans, necessitating accurate radiological imaging and interpretation for optimal diagnosis and treatment. In addition to human radiologists, artificial intelligence systems are increasingly employed for radiological assessments. Since 2023, ChatGPT 4 has offered image analysis capabilities, which can also be used for the analysis of wrist radiographs. This study evaluates the diagnostic power of ChatGPT 4 in identifying distal radius fractures, comparing it with a board-certified radiologist, a hand surgery resident, a medical student, and the well-established AI Gleamer BoneView™. Results demonstrate ChatGPT 4's good diagnostic accuracy (sensitivity 0.88, specificity 0.98, diagnostic power (AUC) 0.93), surpassing the medical student (sensitivity 0.98, specificity 0.72, diagnostic power (AUC) 0.85; p = 0.04) significantly. Nevertheless, the diagnostic power of ChatGPT 4 lags behind the hand surgery resident (sensitivity 0.99, specificity 0.98, diagnostic power (AUC) 0.985; p = 0.014) and Gleamer BoneView™(sensitivity 1.00, specificity 0.98, diagnostic power (AUC) 0.99; p = 0.006). This study highlights the utility and potential applications of artificial intelligence in modern medicine, emphasizing ChatGPT 4 as a valuable tool for enhancing diagnostic capabilities in the field of medical imaging.

Reporting guidelines in medical artificial intelligence: a systematic review and meta-analysis

BACKGROUND

The field of Artificial Intelligence (AI) holds transformative potential in medicine. However, the lack of universal reporting guidelines poses challenges in ensuring the validity and reproducibility of published research studies in this field.

METHODS

Based on a systematic review of academic publications and reporting standards demanded by both international consortia and regulatory stakeholders as well as leading journals in the fields of medicine and medical informatics, 26 reporting guidelines published between 2009 and 2023 were included in this analysis. Guidelines were stratified by breadth (general or specific to medical fields), underlying consensus quality, and target research phase (preclinical, translational, clinical) and subsequently analyzed regarding the overlap and variations in guideline items.

RESULTS

AI reporting guidelines for medical research vary with respect to the quality of the underlying consensus process, breadth, and target research phase. Some guideline items such as reporting of study design and model performance recur across guidelines, whereas other items are specific to particular fields and research stages.

CONCLUSIONS

Our analysis highlights the importance of reporting guidelines in clinical AI research and underscores the need for common standards that address the identified variations and gaps in current guidelines. Overall, this comprehensive overview could help researchers and public stakeholders reinforce quality standards for increased reliability, reproducibility, clinical validity, and public trust in AI research in healthcare. This could facilitate the safe, effective, and ethical translation of AI methods into clinical applications that will ultimately improve patient outcomes.

What does it mean for a clinical AI to be just: conflicts between local fairness and being fit-for-purpose?

There have been repeated calls to ensure that clinical artificial intelligence (AI) is not discriminatory, that is, it provides its intended benefit to all members of society irrespective of the status of any protected characteristics of individuals in whose healthcare the AI might participate. There have also been repeated calls to ensure that any clinical AI is tailored to the local population in which it is being used to ensure that it is fit-for-purpose. Yet, there might be a clash between these two calls since tailoring an AI to a local population might reduce its effectiveness when the AI is used in the care of individuals who have characteristics which are not represented in the local population. Here, I explore the bioethical concept of local fairness as applied to clinical AI. I first introduce the discussion concerning fairness and inequalities in healthcare and how this problem has continued in attempts to develop AI-enhanced healthcare. I then discuss various technical aspects which might affect the implementation of local fairness. Next, I introduce some rule of law considerations into the discussion to contextualise the issue better by drawing key parallels. I then discuss some potential technical solutions which have been proposed to address the issue of local fairness. Finally, I outline which solutions I consider most likely to contribute to a fit-for-purpose and fair AI.

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

Wearable activity data can predict functional recovery after musculoskeletal injury: Feasibility of a machine learning approach

Delayed functional recovery after injury is associated with significant personal and socioeconomic burden. Identification of patients at risk for a prolonged recovery after a musculoskeletal injury is thus of high relevance. The aim of the current study was to show the feasibility of using a machine learning assisted model to predict functional recovery based on the pre- and immediate post injury patient activity as measured with wearable systems in trauma patients. Patients with a pre-existing wearable (smartphone and/or body-worn sensor), data availability of at least 7 days prior to their injury, and any musculoskeletal injury of the upper or lower extremity were included in this study. Patient age, sex, injured extremity, time off work and step count as activity data were recorded continuously both pre- and post-injury. Descriptive statistics were performed and a logistic regression machine learning model was used to predict the patient's functional recovery status after 6 weeks based on their pre- and post-injury activity characteristics. Overall 38 patients (7 upper extremity, 24 lower extremity, 5 pelvis, 2 combined) were included in this proof-of-concept study. The average follow-up with available wearable data was 85.4 days. Based on the activity data, a predictive model was constructed to determine the likelihood of having a recovery of at least 50 % of the pre-injury activity state by post injury week 6. Based on the individual activity by week 3 a predictive accuracy of over 80 % was achieved on an independent test set (F1=0,82; AUC=0,86; ACC=8,83). The employed model is feasible to assess the principal risk for a slower recovery based on readily available personal wearable activity data. The model has the potential to identify patients requiring additional aftercare attention early during the treatment course, thus optimizing return to the pre-injury status through focused interventions. Additional patient data is needed to adapt the model to more specifically focus on different fracture entities and patient groups.

The endorsement of general and artificial intelligence reporting guidelines in radiological journals: a meta-research study

BACKGROUND

Complete reporting is essential for clinical research. However, the endorsement of reporting guidelines in radiological journals is still unclear. Further, as a field extensively utilizing artificial intelligence (AI), the adoption of both general and AI reporting guidelines would be necessary for enhancing quality and transparency of radiological research. This study aims to investigate the endorsement of general reporting guidelines and those for AI applications in medical imaging in radiological journals, and explore associated journal characteristic variables.

METHODS

This meta-research study screened journals from the Radiology, Nuclear Medicine & Medical Imaging category, Science Citation Index Expanded of the 2022 Journal Citation Reports, and excluded journals not publishing original research, in non-English languages, and instructions for authors unavailable. The endorsement of fifteen general reporting guidelines and ten AI reporting guidelines was rated using a five-level tool: "active strong", "active weak", "passive moderate", "passive weak", and "none". The association between endorsement and journal characteristic variables was evaluated by logistic regression analysis.

RESULTS

We included 117 journals. The top-five endorsed reporting guidelines were CONSORT (Consolidated Standards of Reporting Trials, 58.1%, 68/117), PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses, 54.7%, 64/117), STROBE (STrengthening the Reporting of Observational Studies in Epidemiology, 51.3%, 60/117), STARD (Standards for Reporting of Diagnostic Accuracy, 50.4%, 59/117), and ARRIVE (Animal Research Reporting of In Vivo Experiments, 35.9%, 42/117). The most implemented AI reporting guideline was CLAIM (Checklist for Artificial Intelligence in Medical Imaging, 1.7%, 2/117), while other nine AI reporting guidelines were not mentioned. The Journal Impact Factor quartile and publisher were associated with endorsement of reporting guidelines in radiological journals.

CONCLUSIONS

The general reporting guideline endorsement was suboptimal in radiological journals. The implementation of reporting guidelines for AI applications in medical imaging was extremely low. Their adoption should be strengthened to facilitate quality and transparency of radiological study reporting.

Finding the Best Match - a Case Study on the (Text-)Feature and Model Choice in Digital Mental Health Interventions

With the need for psychological help long exceeding the supply, finding ways of scaling, and better allocating mental health support is a necessity. This paper contributes by investigating how to best predict intervention dropout and failure to allow for a need-based adaptation of treatment. We systematically compare the predictive power of different text representation methods (metadata, TF-IDF, sentiment and topic analysis, and word embeddings) in combination with supplementary numerical inputs (socio-demographic, evaluation, and closed-question data). Additionally, we address the research gap of which ML model types - ranging from linear to sophisticated deep learning models - are best suited for different features and outcome variables. To this end, we analyze nearly 16.000 open-text answers from 849 German-speaking users in a Digital Mental Health Intervention (DMHI) for stress. Our research proves that - contrary to previous findings - there is great promise in using neural network approaches on DMHI text data. We propose a task-specific LSTM-based model architecture to tackle the challenge of long input sequences and thereby demonstrate the potential of word embeddings (AUC scores of up to 0.7) for predictions in DMHIs. Despite the relatively small data set, sequential deep learning models, on average, outperform simpler features such as metadata and bag-of-words approaches when predicting dropout. The conclusion is that user-generated text of the first two sessions carries predictive power regarding patients' dropout and intervention failure risk. Furthermore, the match between the sophistication of features and models needs to be closely considered to optimize results, and additional non-text features increase prediction results.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00148-z.

Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty-a comparative study

BACKGROUND

Machine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential benefits of a machine-learning model for prediction of postoperative morbidity in fast-track total hip (THA) and knee arthroplasty (TKA).

METHODS

Cohort study in consecutive unselected primary THA/TKA between 2014-2017 from seven Danish centers with established fast-track protocols. Preoperative comorbidity and prescribed medication were recorded prospectively and information on length of stay and readmissions was obtained through the Danish National Patient Registry and medical records. We used a machine-learning model (Boosted Decision Trees) based on boosted decision trees with 33 preoperative variables for predicting "medical" morbidity leading to LOS > 4 days or 90-days readmissions and compared to a logistical regression model based on the same variables. We also evaluated two parsimonious models, using the ten most important variables in the full machine-learning and logistic regression models. Data collected between 2014-2016 (n:18,013) was used for model training and data from 2017 (n:3913) was used for testing. Model performances were analyzed using precision, area under receiver operating (AUROC) and precision recall curves (AUPRC), as well as the Mathews Correlation Coefficient. Variable importance was analyzed using Shapley Additive Explanations values.

RESULTS

Using a threshold of 20% "risk-patients" (n:782), precision, AUROC and AUPRC were 13.6%, 76.3% and 15.5% vs. 12.4%, 74.7% and 15.6% for the machine-learning and logistic regression model, respectively. The parsimonious machine-learning model performed better than the full logistic regression model. Of the top ten variables, eight were shared between the machine-learning and logistic regression models, but with a considerable age-related variation in importance of specific types of medication.

CONCLUSION

A machine-learning model using preoperative characteristics and prescriptions slightly improved identification of patients in high-risk of "medical" complications after fast-track THA and TKA compared to a logistic regression model. Such algorithms could help find a manageable population of patients who may benefit most from intensified perioperative care.

COVID-19 studies involving machine learning methods: A bibliometric study

BACKGROUND

Machine learning (ML) and artificial intelligence (AI) techniques are gaining popularity as effective tools for coronavirus disease of 2019 (COVID-19) research. These strategies can be used in diagnosis, prognosis, therapy, and public health management. Bibliometric analysis quantifies the quality and impact of scholarly publications. ML in COVID-19 research is the focus of this bibliometric analysis.

METHODS

A comprehensive literature study found ML-based COVID-19 research. Web of Science (WoS) was used for the study. The searches included "machine learning," "artificial intelligence," and COVID-19. To find all relevant studies, 2 reviewers searched independently. The network visualization was analyzed using VOSviewer 1.6.19.

RESULTS

In the WoS Core, the average citation count was 13.6 ± 41.3. The main research areas were computer science, engineering, and science and technology. According to document count, Tao Huang wrote 14 studies, Fadi Al-Turjman wrote 11, and Imran Ashraf wrote 11. The US, China, and India produced the most studies and citations. The most prolific research institutions were Harvard Medical School, Huazhong University of Science and Technology, and King Abdulaziz University. In contrast, Nankai University, Oxford, and Imperial College London were the most mentioned organizations, reflecting their significant research contributions. First, "Covid-19" appeared 1983 times, followed by "machine learning" and "deep learning." The US Department of Health and Human Services funded this topic most heavily. Huang Tao, Feng Kaiyan, and Ashraf Imran pioneered bibliographic coupling.

CONCLUSION

This study provides useful insights for academics and clinicians studying COVID-19 using ML. Through bibliometric data analysis, scholars can learn about highly recognized and productive authors and countries, as well as the publications with the most citations and keywords. New data and methodologies from the pandemic are expected to advance ML and AI modeling. It is crucial to recognize that these studies will pioneer this subject.

Consolidated Reporting Guidelines for Prognostic and Diagnostic Machine Learning Modeling Studies: Development and Validation

BACKGROUND

The reporting of machine learning (ML) prognostic and diagnostic modeling studies is often inadequate, making it difficult to understand and replicate such studies. To address this issue, multiple consensus and expert reporting guidelines for ML studies have been published. However, these guidelines cover different parts of the analytics lifecycle, and individually, none of them provide a complete set of reporting requirements.

OBJECTIVE

We aimed to consolidate the ML reporting guidelines and checklists in the literature to provide reporting items for prognostic and diagnostic ML in in-silico and shadow mode studies.

METHODS

We conducted a literature search that identified 192 unique peer-reviewed English articles that provide guidance and checklists for reporting ML studies. The articles were screened by their title and abstract against a set of 9 inclusion and exclusion criteria. Articles that were filtered through had their quality evaluated by 2 raters using a 9-point checklist constructed from guideline development good practices. The average κ was 0.71 across all quality criteria. The resulting 17 high-quality source papers were defined as having a quality score equal to or higher than the median. The reporting items in these 17 articles were consolidated and screened against a set of 6 inclusion and exclusion criteria. The resulting reporting items were sent to an external group of 11 ML experts for review and updated accordingly. The updated checklist was used to assess the reporting in 6 recent modeling papers in JMIR AI. Feedback from the external review and initial validation efforts was used to improve the reporting items.

RESULTS

In total, 37 reporting items were identified and grouped into 5 categories based on the stage of the ML project: defining the study details, defining and collecting the data, modeling methodology, model evaluation, and explainability. None of the 17 source articles covered all the reporting items. The study details and data description reporting items were the most common in the source literature, with explainability and methodology guidance (ie, data preparation and model training) having the least coverage. For instance, a median of 75% of the data description reporting items appeared in each of the 17 high-quality source guidelines, but only a median of 33% of the data explainability reporting items appeared. The highest-quality source articles tended to have more items on reporting study details. Other categories of reporting items were not related to the source article quality. We converted the reporting items into a checklist to support more complete reporting.

CONCLUSIONS

Our findings supported the need for a set of consolidated reporting items, given that existing high-quality guidelines and checklists do not individually provide complete coverage. The consolidated set of reporting items is expected to improve the quality and reproducibility of ML modeling studies.

Relationship between journal impact factor and the thoroughness and helpfulness of peer reviews

The Journal Impact Factor is often used as a proxy measure for journal quality, but the empirical evidence is scarce. In particular, it is unclear how peer review characteristics for a journal relate to its impact factor. We analysed 10,000 peer review reports submitted to 1,644 biomedical journals with impact factors ranging from 0.21 to 74.7. Two researchers hand-coded sentences using categories of content related to the thoroughness of the review (Materials and Methods, Presentation and Reporting, Results and Discussion, Importance and Relevance) and helpfulness (Suggestion and Solution, Examples, Praise, Criticism). We fine-tuned and validated transformer machine learning language models to classify sentences. We then examined the association between the number and percentage of sentences addressing different content categories and 10 groups defined by the Journal Impact Factor. The median length of reviews increased with higher impact factor, from 185 words (group 1) to 387 words (group 10). The percentage of sentences addressing Materials and Methods was greater in the highest Journal Impact Factor journals than in the lowest Journal Impact Factor group. The results for Presentation and Reporting went in the opposite direction, with the highest Journal Impact Factor journals giving less emphasis to such content. For helpfulness, reviews for higher impact factor journals devoted relatively less attention to Suggestion and Solution than lower impact factor journals. In conclusion, peer review in journals with higher impact factors tends to be more thorough, particularly in addressing study methods while giving relatively less emphasis to presentation or suggesting solutions. Differences were modest and variability high, indicating that the Journal Impact Factor is a bad predictor of the quality of peer review of an individual manuscript.

Artifical intelligence use in orthopedics: an ethical point of view

Artificial intelligence (AI) is increasingly being utilized in orthopedics practice. Ethical concerns have arisen alongside marked improvements and widespread utilization of AI. Patient privacy, consent, data protection, cybersecurity, data safety and monitoring, bias, and accountability are some of the ethical concerns.

Artificial intelligence in orthopaedic surgery

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as 'big data', AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI's limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Human intelligence for authors, reviewers and editors using artificial intelligence

We call artificial intelligence any machine that processes information with some purpose, complying with the logical rules of Turing's computation described more than 70 years ago.   These machines work with instructions called algorithms, a finite and well-defined sequence of information processing implemented by automata (computers) or any digital technology to optimize a process. (2) This means that the purpose of artificial intelligence is optimization. Optimization is the ability to do or solve something in the most efficient way possible and, in the best case, using the least amount of resources. The intended optimization is programmed and preset by humans; therefore, these technologies are tools humans create for human purposes.  The optimization capability of artificial intelligence is staggering. It is estimated that using artificial intelligence will facilitate the achievement of 134 of the 169 goals agreed in the 2030 Agenda for Sustainable Development. However, in this evaluation, it was projected that it could negatively affect the progress of 59 goals of the same agreement, being social, economic, educational, legal and gender inequality, the phenomenon most affected by artificial intelligence. This projection shows us that it is necessary to counterbalance the development and implementation of processes mediated by artificial intelligence, to maintain reflection and question the influence of these technological tools, and, above all, to be based on human intelligence. A definition of human intelligence in the data science and artificial intelligence environment would be a collection of contextual tacit knowledge about human values, responsibility, empathy, intuition, or care for another living being that algorithms cannot describe or execute.

Artificial intelligence in medical device software and high-risk medical devices - a review of definitions, expert recommendations and regulatory initiatives

INTRODUCTION

Artificial intelligence (AI) encompasses a wide range of algorithms with risks when used to support decisions about diagnosis or treatment, so professional and regulatory bodies are recommending how they should be managed.

AREAS COVERED

AI systems may qualify as standalone medical device software (MDSW) or be embedded within a medical device. Within the European Union (EU) AI software must undergo a conformity assessment procedure to be approved as a medical device. The draft EU Regulation on AI proposes rules that will apply across industry sectors, while for devices the Medical Device Regulation also applies. In the CORE-MD project (Coordinating Research and Evidence for Medical Devices), we have surveyed definitions and summarize initiatives made by professional consensus groups, regulators, and standardization bodies.

EXPERT OPINION

The level of clinical evidence required should be determined according to each application and to legal and methodological factors that contribute to risk, including accountability, transparency, and interpretability. EU guidance for MDSW based on international recommendations does not yet describe the clinical evidence needed for medical AI software. Regulators, notified bodies, manufacturers, clinicians and patients would all benefit from common standards for the clinical evaluation of high-risk AI applications and transparency of their evidence and performance.

Machine Learning Research Trends in Africa: A 30 Years Overview with Bibliometric Analysis Review

The machine learning (ML) paradigm has gained much popularity today. Its algorithmic models are employed in every field, such as natural language processing, pattern recognition, object detection, image recognition, earth observation and many other research areas. In fact, machine learning technologies and their inevitable impact suffice in many technological transformation agendas currently being propagated by many nations, for which the already yielded benefits are outstanding. From a regional perspective, several studies have shown that machine learning technology can help address some of Africa's most pervasive problems, such as poverty alleviation, improving education, delivering quality healthcare services, and addressing sustainability challenges like food security and climate change. In this state-of-the-art paper, a critical bibliometric analysis study is conducted, coupled with an extensive literature survey on recent developments and associated applications in machine learning research with a perspective on Africa. The presented bibliometric analysis study consists of 2761 machine learning-related documents, of which 89% were articles with at least 482 citations published in 903 journals during the past three decades. Furthermore, the collated documents were retrieved from the Science Citation Index EXPANDED, comprising research publications from 54 African countries between 1993 and 2021. The bibliometric study shows the visualization of the current landscape and future trends in machine learning research and its application to facilitate future collaborative research and knowledge exchange among authors from different research institutions scattered across the African continent.

Detecting Distal Radius Fractures Using a Segmentation-Based Deep Learning Model

Deep learning algorithms can be used to classify medical images. In distal radius fracture treatment, fracture detection and radiographic assessment of fracture displacement are critical steps. The aim of this study was to use pixel-level annotations of fractures to develop a deep learning model for precise distal radius fracture detection. We randomly divided 3785 consecutive emergency wrist radiograph examinations from six hospitals to a training set (3399 examinations) and test set (386 examinations). The training set was used to develop the deep learning model and the test set to assess its validity. The consensus of three hand surgeons was used as the gold standard for the test set. The area under the ROC curve was 0.97 (CI 0.95-0.98) and 0.95 (CI 0.92-0.98) for examinations without a cast. Fractures were identified with higher accuracy in the postero-anterior radiographs than in the lateral radiographs. Our deep learning model performed well in our multi-hospital and multi-radiograph system manufacturer settings. Thus, segmentation-based deep learning models may provide additional benefit. Further research is needed with algorithm comparison and external validation.

Improving Resource Utilization for Arthroplasty Care by Leveraging Machine Learning and Optimization: A Systematic Review

Background

There is a growing demand for total joint arthroplasty (TJA) surgery. The applications of machine learning (ML), mathematical optimization, and computer simulation have the potential to improve efficiency of TJA care delivery through outcome prediction and surgical scheduling optimization, easing the burden on health-care systems. The purpose of this study was to evaluate strategies using advances in analytics and computational modeling that may improve planning and the overall efficiency of TJA care.

Methods

A systematic review including MEDLINE, Embase, and IEEE Xplore databases was completed from inception to October 3, 2022, for identification of studies generating ML models for TJA length of stay, duration of surgery, and hospital readmission prediction. A scoping review of optimization strategies in elective surgical scheduling was also conducted.

Results

Twenty studies were included for evaluating ML predictions and 17 in the scoping review of scheduling optimization. Among studies generating linear or logistic control models alongside ML models, only 1 found a control model to outperform its ML counterpart. Furthermore, neural networks performed superior to or at the same level as conventional ML models in all but 1 study. Implementation of mathematical and simulation strategies improved the optimization efficiency when compared to traditional scheduling methods at the operational level.

Conclusions

High-performing predictive ML-based models have been developed for TJA, as have mathematical strategies for elective surgical scheduling optimization. By leveraging artificial intelligence for outcome prediction and surgical optimization, there exist greater opportunities for improved resource utilization and cost-savings in TJA than when using traditional modeling and scheduling methods.

Predicting the toxicity of nanoparticles using artificial intelligence tools: a systematic review

Nanoparticles have been used extensively in different scientific fields. Due to the possible destructive effects of nanoparticles on the environment or the biological systems, their toxicity evaluation is a crucial phase for studying nanomaterial safety. In the meantime, experimental approaches for toxicity assessment of various nanoparticles are expensive and time-consuming. Thus, an alternative technique, such as artificial intelligence (AI), could be valuable for predicting nanoparticle toxicity. Therefore, in this review, the AI tools were investigated for the toxicity assessment of nanomaterials. To this end, a systematic search was performed on PubMed, Web of Science, and Scopus databases. Articles were included or excluded based on pre-defined inclusion and exclusion criteria, and duplicate studies were excluded. Finally, twenty-six studies were included. The majority of the studies were conducted on metal oxide and metallic nanoparticles. In addition, Random Forest (RF) and Support Vector Machine (SVM) had the most frequency in the included studies. Most of the models demonstrated acceptable performance. Overall, AI could provide a robust, fast, and low-cost tool for the evaluation of nanoparticle toxicity.

Evaluation of AIML + HDR-A Course to Enhance Data Science Workforce Capacity for Hispanic Biomedical Researchers

Artificial intelligence (AI) and machine learning (ML) facilitate the creation of revolutionary medical techniques. Unfortunately, biases in current AI and ML approaches are perpetuating minority health inequity. One of the strategies to solve this problem is training a diverse workforce. For this reason, we created the course "Artificial Intelligence and Machine Learning applied to Health Disparities Research (AIML + HDR)" which applied general Data Science (DS) approaches to health disparities research with an emphasis on Hispanic populations. Some technical topics covered included the Jupyter Notebook Framework, coding with R and Python to manipulate data, and ML libraries to create predictive models. Some health disparities topics covered included Electronic Health Records, Social Determinants of Health, and Bias in Data. As a result, the course was taught to 34 selected Hispanic participants and evaluated by a survey on a Likert scale (0-4). The surveys showed high satisfaction (more than 80% of participants agreed) regarding the course organization, activities, and covered topics. The students strongly agreed that the activities were relevant to the course and promoted their learning (3.71 ± 0.21). The students strongly agreed that the course was helpful for their professional development (3.76 ± 0.18). The open question was quantitatively analyzed and showed that seventy-five percent of the comments received from the participants confirmed their great satisfaction.

MAIC-10 brief quality checklist for publications using artificial intelligence and medical images

The use of artificial intelligence (AI) with medical images to solve clinical problems is becoming increasingly common, and the development of new AI solutions is leading to more studies and publications using this computational technology. As a novel research area, the use of common standards to aid AI developers and reviewers as quality control criteria will improve the peer review process. Although some guidelines do exist, their heterogeneity and extension advocate that more explicit and simple schemes should be applied on the publication practice. Based on a review of existing AI guidelines, a proposal which collects, unifies, and simplifies the most relevant criteria was developed. The MAIC-10 (Must AI Criteria-10) checklist with 10 items was implemented as a guide to design studies and evaluate publications related to AI in the field of medical imaging. Articles published in Insights into Imaging in 2021 were selected to calculate their corresponding MAIC-10 quality score. The mean score was found to be 5.6 ± 1.6, with critical items present in most articles, such as "Clinical need", "Data annotation", "Robustness", and "Transparency" present in more than 80% of papers, while improvements in other areas were identified. MAIC-10 was also observed to achieve the highest intra-observer reproducibility when compared to other existing checklists, with an overall reduction in terms of checklist length and complexity. In summary, MAIC-10 represents a short and simple quality assessment tool which is objective, robust and widely applicable to AI studies in medical imaging.

Development and external validation of automated detection, classification, and localization of ankle fractures: inside the black box of a convolutional neural network (CNN)

Purpose

Convolutional neural networks (CNNs) are increasingly being developed for automated fracture detection in orthopaedic trauma surgery. Studies to date, however, are limited to providing classification based on the entire image—and only produce heatmaps for approximate fracture localization instead of delineating exact fracture morphology. Therefore, we aimed to answer (1) what is the performance of a CNN that detects, classifies, localizes, and segments an ankle fracture, and (2) would this be externally valid?

Methods

The training set included 326 isolated fibula fractures and 423 non-fracture radiographs. The Detectron2 implementation of the Mask R-CNN was trained with labelled and annotated radiographs. The internal validation (or ‘test set’) and external validation sets consisted of 300 and 334 radiographs, respectively. Consensus agreement between three experienced fellowship-trained trauma surgeons was defined as the ground truth label. Diagnostic accuracy and area under the receiver operator characteristic curve (AUC) were used to assess classification performance. The Intersection over Union (IoU) was used to quantify accuracy of the segmentation predictions by the CNN, where a value of 0.5 is generally considered an adequate segmentation.

Results

The final CNN was able to classify fibula fractures according to four classes (Danis-Weber A, B, C and No Fracture) with AUC values ranging from 0.93 to 0.99. Diagnostic accuracy was 89% on the test set with average sensitivity of 89% and specificity of 96%. External validity was 89–90% accurate on a set of radiographs from a different hospital. Accuracies/AUCs observed were 100/0.99 for the ‘No Fracture’ class, 92/0.99 for ‘Weber B’, 88/0.93 for ‘Weber C’, and 76/0.97 for ‘Weber A’. For the fracture bounding box prediction by the CNN, a mean IoU of 0.65 (SD ± 0.16) was observed. The fracture segmentation predictions by the CNN resulted in a mean IoU of 0.47 (SD ± 0.17).

Conclusions

This study presents a look into the ‘black box’ of CNNs and represents the first automated delineation (segmentation) of fracture lines on (ankle) radiographs. The AUC values presented in this paper indicate good discriminatory capability of the CNN and substantiate further study of CNNs in detecting and classifying ankle fractures.

Level of evidence

II, Diagnostic imaging study.

Narrative Review of Machine Learning in Rheumatic and Musculoskeletal Diseases for Clinicians and Researchers: Biases, Goals, and Future Directions

There has been rapid growth in the use of artificial intelligence (AI) analytics in medicine in recent years, including in rheumatic and musculoskeletal diseases (RMDs). Such methods represent a challenge to clinicians, patients, and researchers, given the "black box" nature of most algorithms, the unfamiliarity of the terms, and the lack of awareness of potential issues around these analyses. Therefore, this review aims to introduce this subject area in a way that is relevant and meaningful to clinicians and researchers. We hope to provide some insights into relevant strengths and limitations, reporting guidelines, as well as recent examples of such analyses in key areas, with a focus on lessons learned and future directions in diagnosis, phenotyping, prognosis, and precision medicine in RMDs.

Machine Learning for the Orthopaedic Surgeon: Uses and Limitations

➤

Machine learning is a subset of artificial intelligence in which computer algorithms are trained to make classifications and predictions based on patterns in data. The utilization of these techniques is rapidly expanding in the field of orthopaedic research.

➤

There are several domains in which machine learning has application to orthopaedics, including radiographic diagnosis, gait analysis, implant identification, and patient outcome prediction.

➤

Several limitations prevent the widespread use of machine learning in the daily clinical environment. However, future work can overcome these issues and enable machine learning tools to be a useful adjunct for orthopaedic surgeons in their clinical decision-making.

[Artificial intelligence and novel approaches for treatment of non-union in bone : From established standard methods in medicine up to novel fields of research]

Methods of artificial intelligence (AI) have found applications in many fields of medicine within the last few years. Some disciplines already use these methods regularly within their clinical routine. However, the fields of application are wide and there are still many opportunities to apply these new AI concepts. This review article gives an insight into the history of AI and defines the special terms and fields, such as machine learning (ML), neural networks and deep learning. The classical steps in developing AI models are demonstrated here, as well as the iteration of data rectification and preparation, the training of a model and subsequent validation before transfer into a clinical setting are explained. Currently, musculoskeletal disciplines implement methods of ML and also neural networks, e.g. for identification of fractures or for classifications. Also, predictive models based on risk factor analysis for prevention of complications are being initiated. As non-union in bone is a rare but very complex disease with dramatic socioeconomic impact for the healthcare system, many open questions arise which could be better understood by using methods of AI in the future. New fields of research applying AI models range from predictive models and cost analysis to personalized treatment strategies.

Characteristics, Impact, and Visibility of Scientific Publications on Artificial Intelligence in Dentistry: A Scientometric Analysis

AIM

To analyze the bibliometric characteristics, impact, and visibility of scientific publications on artificial intelligence (AI) in dentistry in Scopus.

MATERIALS AND METHODS

Descriptive and cross-sectional bibliometric study, based on the systematic search of information in Scopus between 2017 and July 10, 2022. The search strategy was elaborated with Medical Subject Headings (MeSH) and Boolean operators. The analysis of bibliometric indicators was performed with Elsevier's SciVal program.

RESULTS

From 2017 to 2022, the number of publications in indexed scientific journals increased, especially in the Q1 (56.1%) and Q2 (30.6%) quartile. Among the journals with the highest production, the majority was from the United States and the United Kingdom, and the Journal of Dental Research has the highest impact (14.9 citations per publication) and the most publications (31). In addition, the Charité - Universitätsmedizin Berlin (FWCI: 8.24) and Krois Joachim (FWCI: 10.09) from Germany were the institution and author with the highest expected performance relative to the world average, respectively. The United States is the country with the highest number of published papers.

CLINICAL SIGNIFICANCE

There is an increasing tendency to increase the scientific production on artificial intelligence in the field of dentistry, with a preference for publication in prestigious scientific journals of high impact. Most of the productive authors and institutions were from Japan. There is a need to promote and consolidate strategies to develop collaborative research both nationally and internationally.

Artificial intelligence and computer vision in orthopaedic trauma : the why, what, and how

Artificial intelligence (AI) is, in essence, the concept of 'computer thinking', encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the 'why'), the current applications (the 'what'), and the approach to unlocking its full potential (the 'how'). Cite this article: Bone Joint J 2022;104-B(8):911-914.

Predictive models for clinical decision making: Deep dives in practical machine learning

The deployment of machine learning for tasks relevant to complementing standard of care and advancing tools for precision health has gained much attention in the clinical community, thus meriting further investigations into its broader use. In an introduction to predictive modelling using machine learning, we conducted a review of the recent literature that explains standard taxonomies, terminology and central concepts to a broad clinical readership. Articles aimed at readers with little or no prior experience of commonly used methods or typical workflows were summarised and key references are highlighted. Continual interdisciplinary developments in data science, biostatistics and epidemiology also motivated us to further discuss emerging topics in predictive and data-driven (hypothesis-less) analytics with machine learning. Through two methodological deep dives using examples from precision psychiatry and outcome prediction after lymphoma, we highlight how the use of, for example, natural language processing can outperform established clinical risk scores and aid dynamic prediction and adaptive care strategies. Such realistic and detailed examples allow for critical analysis of the importance of new technological advances in artificial intelligence for clinical decision-making. New clinical decision support systems can assist in prevention and care by leveraging precision medicine.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation

BACKGROUND

Inflammatory bowel disease (IBD) is a gastrointestinal chronic disease with an unpredictable disease course. Computational methods such as machine learning (ML) have the potential to stratify IBD patients for the provision of individualized care. The use of ML methods for IBD was surveyed, with an additional focus on how the field has changed over time.

METHODS

On May 6, 2021, a systematic review was conducted through a search of MEDLINE and Embase databases, with the search structure ("machine learning" OR "artificial intelligence") AND ("Crohn* Disease" OR "Ulcerative Colitis" OR "Inflammatory Bowel Disease"). Exclusion criteria included studies not written in English, no human patient data, publication before 2001, studies that were not peer reviewed, nonautoimmune disease comorbidity research, and record types that were not primary research.

RESULTS

Seventy-eight (of 409) records met the inclusion criteria. Random forest methods were most prevalent, and there was an increase in neural networks, mainly applied to imaging data sets. The main applications of ML to clinical tasks were diagnosis (18 of 78), disease course (22 of 78), and disease severity (16 of 78). The median sample size was 263. Clinical and microbiome-related data sets were most popular. Five percent of studies used an external data set after training and testing for additional model validation.

DISCUSSION

Availability of longitudinal and deep phenotyping data could lead to better modeling. Machine learning pipelines that consider imbalanced data and that feature selection only on training data will generate more generalizable models. Machine learning models are increasingly being applied to more complex clinical tasks for specific phenotypes, indicating progress towards personalized medicine for IBD.

Guidelines for artificial intelligence in medicine: A literature review and content analysis of frameworks (Preprint)

Background

Artificial intelligence (AI) is rapidly expanding in medicine despite a lack of consensus on its application and evaluation.

Objective

We sought to identify current frameworks guiding the application and evaluation of AI for predictive analytics in medicine and to describe the content of these frameworks. We also assessed what stages along the AI translational spectrum (ie, AI development, reporting, evaluation, implementation, and surveillance) the content of each framework has been discussed.

Methods

We performed a literature review of frameworks regarding the oversight of AI in medicine. The search included key topics such as “artificial intelligence,” “machine learning,” “guidance as topic,” and “translational science,” and spanned the time period 2014-2022. Documents were included if they provided generalizable guidance regarding the use or evaluation of AI in medicine. Included frameworks are summarized descriptively and were subjected to content analysis. A novel evaluation matrix was developed and applied to appraise the frameworks’ coverage of content areas across translational stages.

Results

Fourteen frameworks are featured in the review, including six frameworks that provide descriptive guidance and eight that provide reporting checklists for medical applications of AI. Content analysis revealed five considerations related to the oversight of AI in medicine across frameworks: transparency, reproducibility, ethics, effectiveness, and engagement. All frameworks include discussions regarding transparency, reproducibility, ethics, and effectiveness, while only half of the frameworks discuss engagement. The evaluation matrix revealed that frameworks were most likely to report AI considerations for the translational stage of development and were least likely to report considerations for the translational stage of surveillance.

Conclusions

Existing frameworks for the application and evaluation of AI in medicine notably offer less input on the role of engagement in oversight and regarding the translational stage of surveillance. Identifying and optimizing strategies for engagement are essential to ensure that AI can meaningfully benefit patients and other end users.

Machine learning classifiers do not improve prediction of hospitalization > 2 days after fast-track hip and knee arthroplasty compared with a classical statistical risk model

Background and purpose: Prediction of postoperative outcomes and length of hospital stay (LOS) of patients is vital for allocation of healthcare resources. We investigated the performance of prediction models based on machinelearning algorithms compared with a previous risk stratification model using traditional multiple logistic regression, for predicting the risk of a LOS of > 2 days after fast-track total hip and knee replacement. Patients and methods: 3 different machine learning classifiers were trained on data from the Lundbeck Centre for Fast-track Hip and Knee Replacement Database (LCDB) collected from 9,512 patients between 2016 and 2017. The chosen classifiers were a random forest classifier (RF), a support vector machine classifier with a polynomial kernel (SVM), and a multinomial Naïve-Bayes classifier (NB). Results: Comparing performance measures of the classifiers with the traditional model revealed that all the models had a similar performance in terms of F1 score, accuracy, sensitivity, specificity, area under the receiver operating curve (AUC), and area under the precision-recall curve (AUPRC). A feature importance analysis of the RF classifier found hospital, age, use of walking aid, living alone, and joint operated on to be the most relevant input features. None of the classifiers reached a clinically relevant performance with the input data from the LCDB. Interpretation: Despite the promising prospects of machine-learning practices for disease and risk prediction, none of the machine learning models tested outperformed the traditional multiple regression model in predicting which patients in this cohort had a LOS > 2 days.

An increasing number of convolutional neural networks for fracture recognition and classification in orthopaedics : are these externally validated and ready for clinical application?

Aims

The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?

Methods

The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS).

Results

Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN’s performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV).

Conclusion

The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis–Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice.

Cite this article: Bone Jt Open 2021;2(10):879–885.