The Integration and Impact of Artificial Intelligence in Otolaryngology-Head and Neck Surgery: Navigating the Last Mile

Incorporating artificial Intelligence and machine learning into otolaryngology requires careful data handling, security, and ethical considerations. Success depends on interdisciplinary cooperation, consistent innovation, and regulatory compliance to improve clinical outcomes, provider experience, and operational effectiveness.

Validation of the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool: a new tool to assess the quality of health information provided by AI platforms

BACKGROUND

The widespread diffusion of Artificial Intelligence (AI) platforms is revolutionizing how health-related information is disseminated, thereby highlighting the need for tools to evaluate the quality of such information. This study aimed to propose and validate the Quality Assessment of Medical Artificial Intelligence (QAMAI), a tool specifically designed to assess the quality of health information provided by AI platforms.

METHODS

The QAMAI tool has been developed by a panel of experts following guidelines for the development of new questionnaires. A total of 30 responses from ChatGPT4, addressing patient queries, theoretical questions, and clinical head and neck surgery scenarios were assessed by 27 reviewers from 25 academic centers worldwide. Construct validity, internal consistency, inter-rater and test-retest reliability were assessed to validate the tool.

RESULTS

The validation was conducted on the basis of 792 assessments for the 30 responses given by ChatGPT4. The results of the exploratory factor analysis revealed a unidimensional structure of the QAMAI with a single factor comprising all the items that explained 51.1% of the variance with factor loadings ranging from 0.449 to 0.856. Overall internal consistency was high (Cronbach's alpha = 0.837). The Interclass Correlation Coefficient was 0.983 (95% CI 0.973-0.991; F (29,542) = 68.3; p < 0.001), indicating excellent reliability. Test-retest reliability analysis revealed a moderate-to-strong correlation with a Pearson's coefficient of 0.876 (95% CI 0.859-0.891; p < 0.001).

CONCLUSIONS

The QAMAI tool demonstrated significant reliability and validity in assessing the quality of health information provided by AI platforms. Such a tool might become particularly important/useful for physicians as patients increasingly seek medical information on AI platforms.

Synthetic, non-person related panoramic radiographs created by Generative Adversarial Networks in research, clinical, and teaching applications

OBJECTIVES

Generative Adversarial Networks (GANs) can produce synthetic images free from personal data. They hold significant value in medical research, where data protection is increasingly regulated. Panoramic radiographs (PRs) are a well-suited modality due to their significant level of standardization while simultaneously displaying a high degree of personally identifiable data.

METHODS

We produced synthetic PRs (syPRs) out of real PRs (rePRs) using StyleGAN2-ADA by NVIDIA©. A survey was performed on 54 medical professionals and 33 dentistry students. They assessed 45 radiological images (20 rePRs, 20 syPRs, and 5 syPRcontrols) as real or synthetic and interpreted a single-image syPR according to the image quality (0-10) and 14 different items (agreement/disagreement). They also rated the importance for the profession (0-10). A follow-up was performed for test-retest reliability with >10% of all participants.

RESULTS

Overall, the sensitivity was 78.2% and the specificity was 82.5%. For professionals, the sensitivity was 79.9% and the specificity was 82.3%. For students, the sensitivity was 75.5% and the specificity was 82.7%. In the single syPR-interpretation image quality was rated at a median of 6 and 11 items were considered as agreement. The importance for the profession was rated at a median score of 7. The Test-retest reliability yielded a value of 0.23 (Cohen's kappa).

CONCLUSIONS

The study marks a comprehensive testing to demonstrate that GANs can produce synthetic radiological images that even health professionals can sometimes not differentiate from real radiological images, thereby being genuinely considered authentic. This enables their utilization and/or modification free from personally identifiable information.

CLINICAL SIGNIFICANCE

Synthetic images can be used for university teaching and patient education without relying on patient-related data. They can also be utilized to upscale existing training datasets to improve the accuracy of AI-based diagnostic systems. The study thereby supports clinical teaching as well as diagnostic and therapeutic decision-making.

Accuracy of machine learning to predict the outcomes of shoulder arthroplasty: a systematic review

BACKGROUND

Artificial intelligence (AI) uses computer systems to simulate cognitive capacities to accomplish goals like problem-solving and decision-making. Machine learning (ML), a branch of AI, makes algorithms find connections between preset variables, thereby producing prediction models. ML can aid shoulder surgeons in determining which patients may be susceptible to worse outcomes and complications following shoulder arthroplasty (SA) and align patient expectations following SA. However, limited literature is available on ML utilization in total shoulder arthroplasty (TSA) and reverse TSA.

METHODS

A systematic literature review in accordance with PRISMA guidelines was performed to identify primary research articles evaluating ML's ability to predict SA outcomes. With duplicates removed, the initial query yielded 327 articles, and after applying inclusion and exclusion criteria, 12 articles that had at least 1 month follow-up time were included.

RESULTS

ML can predict 30-day postoperative complications with a 90% accuracy, postoperative range of motion with a higher-than-85% accuracy, and clinical improvement in patient-reported outcome measures above minimal clinically important differences with a 93%-99% accuracy. ML can predict length of stay, operative time, discharge disposition, and hospitalization costs.

CONCLUSION

ML can accurately predict outcomes and complications following SA and healthcare utilization. Outcomes are highly dependent on the type of algorithms used, data input, and features selected for the model.

LEVEL OF EVIDENCE

III.

Broadening Perspectives of Artificial Intelligence in Echocardiography

Echocardiography frequently serves as the first-line treatment of diagnostic imaging for several pathological entities in cardiology. Artificial intelligence (AI) has been growing substantially in information technology and various commercial industries. Machine learning (ML), a branch of AI, has been shown to expand the capabilities and potential of echocardiography. ML algorithms expand the field of echocardiography by automated assessment of the ejection fraction and left ventricular function, integrating novel approaches such as speckle tracking or tissue Doppler echocardiography or vector flow mapping, improved phenotyping, distinguishing between cardiac conditions, and incorporating information from mobile health and genomics. In this review article, we assess the impact of AI and ML in echocardiography.

Tooth-size discrepancy: a clinical necessity

Introduction

The subject of this article is the discovery of dento-dental disharmony (DDD) at the end of treatment. Lack of diagnosis is the source of this type of disappointment.

Material and Method

The diagnosis of DDD is not easily accessible on clinical examination and the compensations it generates mask it, especially if it is associated with other dysmorphoses. The use of indices, the best-known of which is Bolton's, enables diagnosis with the setup, a pre-treatment model which also has many other prognostic interests.

Results

Once DDD has been considered, it can be resolved by adapting dental volumes, either by subtraction or addition.

Conclusion

Advances in computerized diagnosis with artificial intelligence are opening up new avenues for the systematic diagnosis of DDD.

Enhanced adsorption of Bismark Brown R dye by chitosan conjugated magnetic pectin loaded filter mud: A comprehensive study on modeling and mechanisms

Herein, a polymer-based bioadsorbent was prepared by cross-linking chitosan to filter mud and magnetic pectin (Ch-mPC@FM) for the removal of Bismark Brown R dye (BB-R) from wastewater. Morphological characterization analysis indicated that Ch-mPC@FM had a higher surface area and better pore structure than its components. The Artificial Neuron Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were employed to evaluate the simulation and prediction of the adsorption process based on input variables like temperature, pH, dosage, initial BB-R dye concentration, and contact time. ANFIS and ANN demonstrated significant modeling and predictive accuracy, with R2 > 0.93 and R2 > 0.96, and root mean square error < 0.023 and <0.020, respectively. The Langmuir isotherm and the pseudo-second-order kinetic models provided the best fits to the equilibrium and kinetic data. The thermodynamic assessment showed spontaneous and endothermic adsorption with average entropy and enthalpy changes of 119.32 kJ mol-1 K and 403.47 kJ mol-1, respectively. The study of BB-R dye adsorption on Ch-mPC@FM revealed multiple mechanisms, including electrostatic, complexation, pore filling, cation-π interaction, hydrogen bonding, and π-π interactions. The approximate production cost of US$ 5.809 Kg-1 and excellent adsorption capability render Ch-mPC@FM an inexpensive, pragmatic, and ecologically safe bioadsorbent for BB-R dye removal from wastewater.

Agent-based approaches for biological modeling in oncology: A literature review

CONTEXT

Computational modeling involves the use of computer simulations and models to study and understand real-world phenomena. Its application is particularly relevant in the study of potential interactions between biological elements. It is a promising approach to understand complex biological processes and predict their behavior under various conditions.

METHODOLOGY

This paper is a review of the recent literature on computational modeling of biological systems. Our study focuses on the field of oncology and the use of artificial intelligence (AI) and, in particular, agent-based modeling (ABM), between 2010 and May 2023.

RESULTS

Most of the articles studied focus on improving the diagnosis and understanding the behaviors of biological entities, with metaheuristic algorithms being the models most used. Several challenges are highlighted regarding increasing and structuring knowledge about biological systems, developing holistic models that capture multiple scales and levels of organization, reproducing emergent behaviors of biological systems, validating models with experimental data, improving computational performance of models and algorithms, and ensuring privacy and personal data protection are discussed.

From diagnosis to intervention: a review of telemedicine's role in skin cancer care

Skin cancer treatment is a core aspect of dermatology that relies on accurate diagnosis and timely interventions. Teledermatology has emerged as a valuable asset across various stages of skin cancer care including triage, diagnosis, management, and surgical consultation. With the integration of traditional dermoscopy and store-and-forward technology, teledermatology facilitates the swift sharing of high-resolution images of suspicious skin lesions with consulting dermatologists all-over. Both live video conference and store-and-forward formats have played a pivotal role in bridging the care access gap between geographically isolated patients and dermatology providers. Notably, teledermatology demonstrates diagnostic accuracy rates that are often comparable to those achieved through traditional face-to-face consultations, underscoring its robust clinical utility. Technological advancements like artificial intelligence and reflectance confocal microscopy continue to enhance image quality and hold potential for increasing the diagnostic accuracy of virtual dermatologic care. While teledermatology serves as a valuable clinical tool for all patient populations including pediatric patients, it is not intended to fully replace in-person procedures like Mohs surgery and other necessary interventions. Nevertheless, its role in facilitating the evaluation of skin malignancies is gaining recognition within the dermatologic community and fostering high approval rates from patients due to its practicality and ability to provide timely access to specialized care.

An automated approach for real-time informative frames classification in laryngeal endoscopy using deep learning

PURPOSE

Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination.

METHODS

Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model.

RESULTS

ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials.

CONCLUSION

The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.

Organoid bioinks: construction and application

Organoids have emerged as crucial platforms in tissue engineering and regenerative medicine but confront challenges in faithfully mimicking native tissue structures and functions. Bioprinting technologies offer a significant advancement, especially when combined with organoid bioinks-engineered formulations designed to encapsulate both the architectural and functional elements of specific tissues. This review provides a rigorous, focused examination of the evolution and impact of organoid bioprinting. It emphasizes the role of organoid bioinks that integrate key cellular components and microenvironmental cues to more accurately replicate native tissue complexity. Furthermore, this review anticipates a transformative landscape invigorated by the integration of artificial intelligence with bioprinting techniques. Such fusion promises to refine organoid bioink formulations and optimize bioprinting parameters, thus catalyzing unprecedented advancements in regenerative medicine. In summary, this review accentuates the pivotal role and transformative potential of organoid bioinks and bioprinting in advancing regenerative therapies, deepening our understanding of organ development, and clarifying disease mechanisms. .

Survival estimation of oral cancer using fuzzy deep learning

BACKGROUND

Oral cancer is a deadly disease and a major cause of morbidity and mortality worldwide. The purpose of this study was to develop a fuzzy deep learning (FDL)-based model to estimate the survival time based on clinicopathologic data of oral cancer.

METHODS

Electronic medical records of 581 oral squamous cell carcinoma (OSCC) patients, treated with surgery with or without radiochemotherapy, were collected retrospectively from the Oral and Maxillofacial Surgery Clinic and the Regional Cancer Center from 2011 to 2019. The deep learning (DL) model was trained to classify survival time classes based on clinicopathologic data. Fuzzy logic was integrated into the DL model and trained to create FDL-based models to estimate the survival time classes.

RESULTS

The performance of the models was evaluated on a test dataset. The performance of the DL and FDL models for estimation of survival time achieved an accuracy of 0.74 and 0.97 and an area under the receiver operating characteristic (AUC) curve of 0.84 to 1.00 and 1.00, respectively.

CONCLUSIONS

The integration of fuzzy logic into DL models could improve the accuracy to estimate survival time based on clinicopathologic data of oral cancer.

Study of smart grid cyber-security, examining architectures, communication networks, cyber-attacks, countermeasure techniques, and challenges

Smart Grid (SG) technology utilizes advanced network communication and monitoring technologies to manage and regulate electricity generation and transport. However, this increased reliance on technology and connectivity also introduces new vulnerabilities, making SG communication networks susceptible to large-scale attacks. While previous surveys have mainly provided high-level overviews of SG architecture, our analysis goes further by presenting a comprehensive architectural diagram encompassing key SG components and communication links. This holistic view enhances understanding of potential cyber threats and enables systematic cyber risk assessment for SGs. Additionally, we propose a taxonomy of various cyberattack types based on their targets and methods, offering detailed insights into vulnerabilities. Unlike other reviews focused narrowly on protection and detection, our proposed categorization covers all five functions of the National Institute of Standards and Technology cybersecurity framework. This delivers a broad perspective to help organizations implement balanced and robust security. Consequently, we have identified critical research gaps, especially regarding response and recovery mechanisms. This underscores the need for further investigation to bolster SG cybersecurity. These research needs, among others, are highlighted as open issues in our concluding section.

Artificial intelligence for volumetric measurement of cerebral white matter hyperintensities on thick-slice fluid-attenuated inversion recovery (FLAIR) magnetic resonance images from multiple centers

We aimed to develop a new artificial intelligence software that can automatically extract and measure the volume of white matter hyperintensities (WMHs) in head magnetic resonance imaging (MRI) using only thick-slice fluid-attenuated inversion recovery (FLAIR) sequences from multiple centers. We enrolled 1092 participants in Japan, comprising the thick-slice Private Dataset. Based on 207 randomly selected participants, neuroradiologists annotated WMHs using predefined guidelines. The annotated images of participants were divided into training (n = 138) and test (n = 69) datasets. The WMH segmentation model comprised a U-Net ensemble and was trained using the Private Dataset. Two other models were trained for validation using either both thin- and thick-slice MRI datasets or the thin-slice dataset alone. The voxel-wise Dice similarity coefficient (DSC) was used as the evaluation metric. The model trained using only thick-slice MRI showed a DSC of 0.820 for the test dataset, which is comparable to the accuracy of human readers. The model trained with the additional thin-slice dataset showed only a slightly improved DSC of 0.822. This automatic WMH segmentation model comprising a U-Net ensemble trained on a thick-slice FLAIR MRI dataset is a promising new method. Despite some limitations, this model may be applicable in clinical practice.

Artificial intelligence in interventional radiology: state of the art

Artificial intelligence (AI) has demonstrated great potential in a wide variety of applications in interventional radiology (IR). Support for decision-making and outcome prediction, new functions and improvements in fluoroscopy, ultrasound, computed tomography, and magnetic resonance imaging, specifically in the field of IR, have all been investigated. Furthermore, AI represents a significant boost for fusion imaging and simulated reality, robotics, touchless software interactions, and virtual biopsy. The procedural nature, heterogeneity, and lack of standardisation slow down the process of adoption of AI in IR. Research in AI is in its early stages as current literature is based on pilot or proof of concept studies. The full range of possibilities is yet to be explored.Relevance statement Exploring AI's transformative potential, this article assesses its current applications and challenges in IR, offering insights into decision support and outcome prediction, imaging enhancements, robotics, and touchless interactions, shaping the future of patient care.Key points• AI adoption in IR is more complex compared to diagnostic radiology.• Current literature about AI in IR is in its early stages.• AI has the potential to revolutionise every aspect of IR.

Is ChatGPT reliable and accurate in answering pharmacotherapy-related inquiries in both Turkish and English?

INTRODUCTION

Artificial intelligence (AI), particularly ChatGPT, is becoming more and more prevalent in the healthcare field for tasks such as disease diagnosis and medical record analysis. The objective of this study is to evaluate the proficiency and accuracy of ChatGPT in different domains of clinical pharmacy cases and queries.

METHODS

The study NAPLEX® Review Questions, 4th edition, pertaining to 10 different chronic conditions compared ChatGPT's responses to pharmacotherapy cases and questions obtained from McGraw Hill's, alongside the answers provided by the book's authors. The proportion of correct responses was collected and analyzed using the Statistical Package for the Social Sciences (SPSS) version 29.

RESULTS

When tested in English, ChatGPT had substantially higher mean scores than when tested in Turkish. The average accurate score for English and Turkish was 0.41 ± 0.49 and 0.32 ± 0.46, respectively, p = 0.18. Responses to queries beginning with "Which of the following is correct?" are considerably more precise than those beginning with "Mark all the incorrect answers?" 0.66 ± 0.47 as opposed to 0.16 ± 0.36; p = 0.01 in English language and 0.50 ± 0.50 as opposed to 0.14 ± 0.34; p < 0.05in Turkish language.

CONCLUSION

ChatGPT displayed a moderate level of accuracy while responding to English inquiries, but it displayed a slight level of accuracy when responding to Turkish inquiries, contingent upon the question format. Improving the accuracy of ChatGPT in languages other than English requires the incorporation of several components. The integration of the English version of ChatGPT into clinical practice has the potential to improve the effectiveness, precision, and standard of patient care provision by supplementing personal expertise and professional judgment. However, it is crucial to utilize technology as an adjunct and not a replacement for human decision-making and critical thinking.

Fairness-aware recommendation with meta learning

Fairness has become a critical value online, and the latest studies consider it in many problems. In recommender systems, fairness is important since the visibility of items is controlled by systems. Previous fairness-aware recommender systems assume that sufficient relationship data between users and items are available. However, it is common that new users and items are frequently introduced, and they have no relationship data yet. In this paper, we study recommendation methods to enhance fairness in a cold-start state. Fairness is more significant when the preference of a user or the popularity of an item is unknown. We propose a meta-learning-based cold-start recommendation framework called FaRM to alleviate the unfairness of recommendations. The proposed framework consists of three steps. We first propose a fairness-aware meta-path generation method to eliminate bias in sensitive attributes. In addition, we construct fairness-aware user representations through the meta-path aggregation approach. Then, we propose a novel fairness objective function and introduce a joint learning method to minimize the trade-off between relevancy and fairness. In extensive experiments with various cold-start scenarios, it is shown that FaRM is significantly superior in fairness performance while preserving relevance accuracy over previous work.

A stakeholder analysis to prepare for real-world evaluation of integrating artificial intelligent algorithms into breast screening (PREP-AIR study): a qualitative study using the WHO guide

BACKGROUND

The national breast screening programme in the United Kingdom is under pressure due to workforce shortages and having been paused during the COVID-19 pandemic. Artificial intelligence has the potential to transform how healthcare is delivered by improving care processes and patient outcomes. Research on the clinical and organisational benefits of artificial intelligence is still at an early stage, and numerous concerns have been raised around its implications, including patient safety, acceptance, and accountability for decisions. Reforming the breast screening programme to include artificial intelligence is a complex endeavour because numerous stakeholders influence it. Therefore, a stakeholder analysis was conducted to identify relevant stakeholders, explore their views on the proposed reform (i.e., integrating artificial intelligence algorithms into the Scottish National Breast Screening Service for breast cancer detection) and develop strategies for managing 'important' stakeholders.

METHODS

A qualitative study (i.e., focus groups and interviews, March-November 2021) was conducted using the stakeholder analysis guide provided by the World Health Organisation and involving three Scottish health boards: NHS Greater Glasgow & Clyde, NHS Grampian and NHS Lothian. The objectives included: (A) Identify possible stakeholders (B) Explore stakeholders' perspectives and describe their characteristics (C) Prioritise stakeholders in terms of importance and (D) Develop strategies to manage 'important' stakeholders. Seven stakeholder characteristics were assessed: their knowledge of the targeted reform, position, interest, alliances, resources, power and leadership.

RESULTS

Thirty-two participants took part from 14 (out of 17 identified) sub-groups of stakeholders. While they were generally supportive of using artificial intelligence in breast screening programmes, some concerns were raised. Stakeholder knowledge, influence and interests in the reform varied. Key advantages mentioned include service efficiency, quicker results and reduced work pressure. Disadvantages included overdiagnosis or misdiagnosis of cancer, inequalities in detection and the self-learning capacity of the algorithms. Five strategies (with considerations suggested by stakeholders) were developed to maintain and improve the support of 'important' stakeholders.

CONCLUSIONS

Health services worldwide face similar challenges of workforce issues to provide patient care. The findings of this study will help others to learn from Scottish experiences and provide guidance to conduct similar studies targeting healthcare reform.

STUDY REGISTRATION

researchregistry6579, date of registration: 16/02/2021.

Examining how gamers connect with their avatars to assess their anxiety: A novel artificial intelligence approach

Research has supported that a gamer's attachment to their avatar can offer significant insights about their mental health, including anxiety. To assess this hypothesis, longitudinal data from 565 adult and adolescent participants (Mage = 29.3 years, SD = 10.6) was analyzed at two points, six months apart. Respondents were assessed using the User-Avatar Bond (UAB) scale and the Depression Anxiety Stress Scale (DASS) to measure their connection with their avatar and their risk for anxiety. The records were processed using both untuned and tuned artificial intelligence [AI] classifiers to evaluate present and future anxiety. The findings indicated that AI models are capable of accurately and autonomously discerning cases of anxiety risk based on the gamers' self-reported UAB, age, and duration of gaming, both at present and after six months. Notably, random forest algorithms surpassed other AI models in effectiveness, with avatar compensation emerging as the most significant factor in model training for prospective anxiety. The implications for assessment, prevention, and clinical practice are discussed.

ChatGPT-4 accuracy for patient education in laryngopharyngeal reflux

INTRODUCTION

Chatbot Generative Pre-trained Transformer (ChatGPT) is an artificial intelligence-powered language model chatbot able to help otolaryngologists in practice and research. The ability of ChatGPT in generating patient-centered information related to laryngopharyngeal reflux disease (LPRD) was evaluated.

METHODS

Twenty-five questions dedicated to definition, clinical presentation, diagnosis, and treatment of LPRD were developed from the Dubai definition and management of LPRD consensus and recent reviews. Questions about the four aforementioned categories were entered into ChatGPT-4. Four board-certified laryngologists evaluated the accuracy of ChatGPT-4 with a 5-point Likert scale. Interrater reliability was evaluated.

RESULTS

The mean scores (SD) of ChatGPT-4 answers for definition, clinical presentation, additional examination, and treatments were 4.13 (0.52), 4.50 (0.72), 3.75 (0.61), and 4.18 (0.47), respectively. Experts reported high interrater reliability for sub-scores (ICC = 0.973). The lowest performances of ChatGPT-4 were on answers about the most prevalent LPR signs, the most reliable objective tool for the diagnosis (hypopharyngeal-esophageal multichannel intraluminal impedance-pH monitoring (HEMII-pH)), and the criteria for the diagnosis of LPR using HEMII-pH.

CONCLUSION

ChatGPT-4 may provide adequate information on the definition of LPR, differences compared to GERD (gastroesophageal reflux disease), and clinical presentation. Information provided upon extra-laryngeal manifestations and HEMII-pH may need further optimization. Regarding the recent trends identifying increasing patient use of internet sources for self-education, the findings of the present study may help draw attention to ChatGPT-4's accuracy on the topic of LPR.

Diagnostic Accuracy of Artificial Intelligence-Based Algorithms in Automated Detection of Neck of Femur Fracture on a Plain Radiograph: A Systematic Review and Meta-analysis

Objectives

To evaluate the diagnostic accuracy of artificial intelligence-based algorithms in identifying neck of femur fracture on a plain radiograph.

Design

Systematic review and meta-analysis.

Data sources

PubMed, Web of science, Scopus, IEEE, and the Science direct databases were searched from inception to 30 July 2023.

Eligibility criteria for study selection

Eligible article types were descriptive, analytical, or trial studies published in the English language providing data on the utility of artificial intelligence (AI) based algorithms in the detection of the neck of the femur (NOF) fracture on plain X-ray.

Main outcome measures

The prespecified primary outcome was to calculate the sensitivity, specificity, accuracy, Youden index, and positive and negative likelihood ratios. Two teams of reviewers (each consisting of two members) extracted the data from available information in each study. The risk of bias was assessed using a mix of the CLAIM (the Checklist for AI in Medical Imaging) and QUADAS-2 (A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies) criteria.

Results

Of the 437 articles retrieved, five were eligible for inclusion, and the pooled sensitivity of AIs in diagnosing the fracture NOF was 85%, with a specificity of 87%. For all studies, the pooled Youden index (YI) was 0.73. The average positive likelihood ratio (PLR) was 19.88, whereas the negative likelihood ratio (NLR) was 0.17. The random effects model showed an overall odds of 1.16 (0.84-1.61) in the forest plot, comparing the AI system with those of human diagnosis. The overall heterogeneity of the studies was marginal (I2 = 51%). The CLAIM criteria for risk of bias assessment had an overall >70% score.

Conclusion

Artificial intelligence (AI)-based algorithms can be used as a diagnostic adjunct, benefiting clinicians by taking less time and effort in neck of the femur (NOF) fracture diagnosis.

Study registration

PROSPERO CRD42022375449.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43465-024-01130-6.

Assessing the applicability and appropriateness of ChatGPT in answering clinical pharmacy questions

OBJECTIVES

Clinical pharmacists rely on different scientific references to ensure appropriate, safe, and cost-effective drug use. Tools based on artificial intelligence (AI) such as ChatGPT (Generative Pre-trained Transformer) could offer valuable support. The objective of this study was to assess ChatGPT's capacity to correctly respond to clinical pharmacy questions asked by healthcare professionals in our university hospital.

MATERIAL AND METHODS

ChatGPT's capacity to respond correctly to the last 100 consecutive questions recorded in our clinical pharmacy database was assessed. Questions were copied from our FileMaker Pro database and pasted into ChatGPT March 14 version online platform. The generated answers were then copied verbatim into an Excel file. Two blinded clinical pharmacists reviewed all the questions and the answers given by the software. In case of disagreements, a third blinded pharmacist intervened to decide.

RESULTS

Documentation-related issues (n=36) and drug administration mode (n=30) were preponderantly recorded. Among 69 applicable questions, the rate of correct answers varied from 30 to 57.1% depending on questions type with a global rate of 44.9%. Regarding inappropriate answers (n=38), 20 were incorrect, 18 gave no answers and 8 were incomplete with 8 answers belonging to 2 different categories. No better answers than the pharmacists were observed.

CONCLUSIONS

ChatGPT demonstrated a mitigated performance in answering clinical pharmacy questions. It should not replace human expertise as a high rate of inappropriate answers was highlighted. Future studies should focus on the optimization of ChatGPT for specific clinical pharmacy questions and explore the potential benefits and limitations of integrating this technology into clinical practice.

The Evolving Regulatory Paradigm of AI in MedTech: A Review of Perspectives and Where We Are Today

Artificial intelligence (AI)-enabled technologies in the MedTech sector hold the promise to transform healthcare delivery by improving access, quality, and outcomes. As the regulatory contours of these technologies are being defined, there is a notable lack of literature on the key stakeholders such as the organizations and interest groups that have a significant input in shaping the regulatory framework. This article explores the perspectives and contributions of these stakeholders in shaping the regulatory paradigm of AI-enabled medical technologies. The formation of an AI regulatory framework requires the convergence of ethical, regulatory, technical, societal, and practical considerations. These multiple perspectives contribute to the various dimensions of an evolving regulatory paradigm. From the global governance guidelines set by the World Health Organization (WHO) to national regulations, the article sheds light not just on these multiple perspectives but also on their interconnectedness in shaping the regulatory landscape of AI.

[Orthopedics and trauma surgery in the digital age]

BACKGROUND

Digital transformation is shaping the future of orthopedics and trauma surgery. Telemedicine, digital health applications, electronic patient records and artificial intelligence play a central role in this. These technologies have the potential to improve medical care, enable individualized patient treatment plans and reduce the burden on the treatment process. However, there are currently challenges in the areas of infrastructure, regulation, reimbursement and data protection.

REALISING THE TRANSFORMATION

Effective transformation requires a deep understanding of both technology and clinical practice. Orthopedic and trauma surgeons need to take a leadership role by actively engaging with new technologies, designing new treatment processes and enhancing their medical skills with digital and AI competencies. The integration of digital skills into medical education and specialist training will be crucial for actively shaping the digital transformation and exploiting its full potential.

Progress of MRI in predicting the circumferential resection margin of rectal cancer: A narrative review

Rectal cancer (RC) is the third most frequently diagnosed cancer worldwide, and the status of its circumferential resection margin (CRM) is of paramount significance for treatment strategies and prognosis. CRM involvement is defined as tumor touching or within 1 mm from the outermost part of tumor or outer border of the mesorectal or lymph node deposits to the resection margin. The incidence of involved CRM varied from 5.4 % to 36 %, which may associate with an in consistent definition of CRM, the quality of surgeries, and the different examination modalities. Although T and N status are essential factors in determining whether a patient should receive neoadjuvant therapy before surgery, CRM status is a powerful predictor of local and distant recurrence as well as survival rate. This review explores the significance of CRM, the various assessment methods, and the role of magnetic resonance imaging (MRI) and artificial intelligence-based MRI in predicting CRM status. MRI showed potential advantage in predicting CRM status with a high sensitivity and specificity compared to computed tomography (CT). We also discuss MRI advancements in RC imaging, including conventional MRI with body coil, high-resolution MRI with phased-array coil, and endorectal MRI. Along with a discussion of artificial intelligence-based MRI techniques to predict the CRM status of RCs before and after treatments.

[What contribution can make artificial intelligence to urinary cytology?]

Urinary cytology using the Paris system is still the method of choice for screening high-grade urothelial carcinomas. However, the use of the objective criteria described in this terminology shows a lack of inter- and intra-observer reproducibility. Moreover, if its sensitivity is excellent on instrumented urine, it remains insufficient on voided urine samples. Urinary cytology appears to be an excellent model for the application of artificial intelligence to improve performance, since the objective criteria of the Paris system are defined at cellular level, and the resulting diagnostic approach is presented in a highly "algorithmic" way. Nevertheless, there is no commercially available morphological diagnostic aid, and very few predictive devices are still undergoing clinical validation. The analysis of different systems using artificial intelligence in urinary cytology rises clear prospects for mutual contributions.

Solving Bongard Problems With a Visual Language and Pragmatic Constraints

More than 50 years ago, Bongard introduced 100 visual concept learning problems as a challenge for artificial vision systems. These problems are now known as Bongard problems. Although they are well known in cognitive science and artificial intelligence, only very little progress has been made toward building systems that can solve a substantial subset of them. In the system presented here, visual features are extracted through image processing and then translated into a symbolic visual vocabulary. We introduce a formal language that allows representing compositional visual concepts based on this vocabulary. Using this language and Bayesian inference, concepts can be induced from the examples that are provided in each problem. We find a reasonable agreement between the concepts with high posterior probability and the solutions formulated by Bongard himself for a subset of 35 problems. While this approach is far from solving Bongard problems like humans, it does considerably better than previous approaches. We discuss the issues we encountered while developing this system and their continuing relevance for understanding visual cognition. For instance, contrary to other concept learning problems, the examples are not random in Bongard problems; instead they are carefully chosen to ensure that the concept can be induced, and we found it helpful to take the resulting pragmatic constraints into account.

Can ChatGPT provide appropriate meal plans for NCD patients?

OBJECTIVES

Dietary habits significantly affect health conditions and are closely related to the onset and progression of non-communicable diseases (NCDs). Consequently, a well-balanced diet plays an important role in lessening the effects of various disorders, including NCDs. Several artificial intelligence recommendation systems have been developed to propose healthy and nutritious diets. Most of these systems use expert knowledge and guidelines to provide tailored diets and encourage healthier eating habits. However, new advances in large language models such as ChatGPT, with their ability to produce human-like responses, have led individuals to search for advice in several tasks, including diet recommendations. This study aimed to determine the ability of ChatGPT models to generate appropriate personalized meal plans for patients with obesity, cardiovascular diseases, and type 2 diabetes.

METHODS

Using a state-of-the-art knowledge-based recommendation system as a reference, we assessed the meal plans generated by two large language models in terms of energy intake, nutrient accuracy, and meal variability.

RESULTS

Experimental results with different user profiles revealed the potential of ChatGPT models to provide personalized nutritional advice.

CONCLUSION

Additional supervision and guidance by nutrition experts or knowledge-based systems are required to ensure meal appropriateness for users with NCDs.

A fusion architecture to deliver multipurpose mobile health services

Mobile Health (mHealth) services typically make use of customized software architectures, leading to development-dependent fragmentation. Nevertheless, irrespective of their specific purpose, most mHealth services share common functionalities, where standard pieces could be reused or adapted to expedite service deployment and even extend the follow-up of appearing conditions under the same service. To harness compatibility and reuse, this article presents a data fusion architecture proposing a common design framework for mHealth services. An exhaustive mapping of mHealth functionalities identified in the literature serves as starting point. The architecture is then conceptualized making use of the Joint Directors of Laboratories (JDL) data fusion model. The aim of the architecture is to exploit the multi-source data acquisition capabilities supported by smartphones and Internet of Things devices, and artificial intelligence-enabled feature fusion. A series of interconnected fusion layers ensure streamlined data management; each layer is composed of microservices which may be implemented or omitted depending on the specific goals of the healthcare service. Moreover, the architecture considers essential features related to authentication mechanisms, data sharing protocols, practitioner-patient communication, context-based notifications and tailored visualization interfaces. The effectiveness of the architecture is underscored by its instantiation for four real cases, encompassing risk assessment for youth with mental health issues, remote monitoring for SARS-CoV-2 patients, liquid intake control for kidney disease patients, and peritoneal dialysis treatment support. This breadth of applications exemplifies how the architecture can effectively serve as a guidance framework to accelerate the design of mHealth services.

Performance of ChatGPT and Bard in self-assessment questions for nephrology board renewal

BACKGROUND

Large language models (LLMs) have impacted advances in artificial intelligence. While LLMs have demonstrated high performance in general medical examinations, their performance in specialized areas such as nephrology is unclear. This study aimed to evaluate ChatGPT and Bard in their potential nephrology applications.

METHODS

Ninety-nine questions from the Self-Assessment Questions for Nephrology Board Renewal from 2018 to 2022 were presented to two versions of ChatGPT (GPT-3.5 and GPT-4) and Bard. We calculated the correct answer rates for the five years, each year, and question categories and checked whether they exceeded the pass criterion. The correct answer rates were compared with those of the nephrology residents.

RESULTS

The overall correct answer rates for GPT-3.5, GPT-4, and Bard were 31.3% (31/99), 54.5% (54/99), and 32.3% (32/99), respectively, thus GPT-4 significantly outperformed GPT-3.5 (p < 0.01) and Bard (p < 0.01). GPT-4 passed in three years, barely meeting the minimum threshold in two. GPT-4 demonstrated significantly higher performance in problem-solving, clinical, and non-image questions than GPT-3.5 and Bard. GPT-4's performance was between third- and fourth-year nephrology residents.

CONCLUSIONS

GPT-4 outperformed GPT-3.5 and Bard and met the Nephrology Board renewal standards in specific years, albeit marginally. These results highlight LLMs' potential and limitations in nephrology. As LLMs advance, nephrologists should understand their performance for future applications.

Artificial intelligence in the practice of forensic medicine: a scoping review

Forensic medicine is a thriving application field for artificial intelligence (AI). Indeed, AI applications intended to forensic pathologists or forensic physicians have emerged since the last decade. For example, AI models were developed to help estimate the biological age of migrants or human remains. However, the uses of AI applications by forensic pathologists or physicians and their levels of integration in medicolegal practices are not well described yet. Therefore, a scoping review was conducted on PubMed, ScienceDirect, and Scopus databases. This review included articles that mention any AI application used by forensic pathologists or physicians in practice or any AI model applied in one expertise field of the forensic pathologist or physician. Articles in other languages than English or French or dealing mainly with complementary analyses handled by experts who are not forensic pathologists or physicians or with AI to analyze data for research purposes in forensic medicine were excluded from this review. All the relevant information was retrieved in each article from a grid analysis derived and adapted from the TRIPOD checklist. This review included 35 articles and revealed that AI applications are developed in thanatology and in clinical forensic medicine. However, those applications seem to mainly remain in research and development stages. Indeed, the use of AI applications by forensic pathologists or physicians is not actual due to issues discussed in this article. Finally, the integration of AI in daily medicolegal practice involves not only forensic pathologists or physicians but also legal professionals.

ChatGPT: What Every Pediatric Surgeon Should Know About Its Potential Uses and Pitfalls

ChatGPT - currently the most popular generative artificial intelligence system - has been revolutionizing the world and healthcare since its release in November 2022. ChatGPT is a conversational chatbot that uses machine learning algorithms to enhance its replies based on user interactions and is a part of a broader effort to develop natural language processing that can assist people in their daily lives by understanding and responding to human language in a useful and engaging way. Thus far, many potential applications within healthcare have been described, despite its relatively recent release. This manuscript offers the pediatric surgical community a primer on this new technology and discusses some initial observations about its potential uses and pitfalls. Moreover, it introduces the perspectives of medical journals and surgical societies regarding the use of this artificial intelligence chatbot. As ChatGPT and other large language models continue to evolve, it is the responsibility of the pediatric surgery community to stay abreast of these changes and play an active role in safely incorporating them into our field for the benefit of our patients. LEVEL OF EVIDENCE: V.

Predictive health monitoring: Leveraging artificial intelligence for early detection of infectious diseases in nursing home residents through discontinuous vital signs analysis

This research addresses the problem of detecting acute respiratory, urinary tract, and other infectious diseases in elderly nursing home residents using machine learning algorithms. The study analyzes data extracted from multiple vital signs and other contextual information for diagnostic purposes. The daily data collection process encounters sampling constraints due to weekends, holidays, shift changes, staff turnover, and equipment breakdowns, resulting in numerous nulls, repeated readings, outliers, and meaningless values. The short time series generated also pose a challenge to analysis, preventing the extraction of seasonal information or consistent trends. Blind data collection results in most of the data coming from periods when residents are healthy, resulting in excessively imbalanced data. This study proposes a data cleaning process and then builds a mechanism that reproduces the basal activity of the residents to improve the classification of the disease. The results show that the proposed basal module-assisted machine learning techniques allow anticipating diagnostics 2, 3 or 4 days before doctors decide to start treatment with antibiotics, achieving a performance measured by the area-under-the-curve metric of 0.857. The contributions of this work are: (1) a new data cleaning process; (2) the analysis of contextual information to improve data quality; (3) the generation of a baseline measure for relative comparison; and (4) the use of either binary (disease/no disease) or multiclass classification, differentiating among types of infections and showing the advantages of multiclass versus binary classification. From a medical point of view, the anticipated detection of infectious diseases in institutionalized individuals is brand new.

Development and validation of an artificial intelligence-based model for detecting urothelial carcinoma using urine cytology images: a multicentre, diagnostic study with prospective validation

Background

Urine cytology is an important non-invasive examination for urothelial carcinoma (UC) diagnosis and follow-up. We aimed to explore whether artificial intelligence (AI) can enhance the sensitivity of urine cytology and help avoid unnecessary endoscopy.

Methods

In this multicentre diagnostic study, consecutive patients who underwent liquid-based urine cytology examinations at four hospitals in China were included for model development and validation. Patients who declined surgery and lacked associated histopathology results, those diagnosed with rare subtype tumours of the urinary tract, or had low-quality images were excluded from the study. All liquid-based cytology slides were scanned into whole-slide images (WSIs) at 40 × magnification and the WSI-labels were derived from the corresponding histopathology results. The Precision Urine Cytology AI Solution (PUCAS) was composed of three distinct stages (patch extraction, features extraction, and classification diagnosis) and was trained to identify important WSI features associated with UC diagnosis. The diagnostic sensitivity was mainly used to validate the performance of PUCAS in retrospective and prospective validation cohorts. This study is registered with the ChiCTR, ChiCTR2300073192.

Findings

Between January 1, 2018 and October 31, 2022, 2641 patients were retrospectively recruited in the training cohort, and 2335 in retrospective validation cohorts; 400 eligible patients were enrolled in the prospective validation cohort between July 7, 2023 and September 15, 2023. The sensitivity of PUCAS ranged from 0.922 (95% CI: 0.811-0.978) to 1.000 (0.782-1.000) in retrospective validation cohorts, and was 0.896 (0.837-0.939) in prospective validation cohort. The PUCAS model also exhibited a good performance in detecting malignancy within atypical urothelial cells cases, with a sensitivity of over 0.84. In the recurrence detection scenario, PUCAS could reduce 57.5% of endoscopy use with a negative predictive value of 96.4%.

Interpretation

PUCAS may help to improve the sensitivity of urine cytology, reduce misdiagnoses of UC, avoid unnecessary endoscopy, and reduce the clinical burden in resource-limited areas. The further validation in other countries is needed.

Funding

National Natural Science Foundation of China; Key Program of the National Natural Science Foundation of China; the National Science Foundation for Distinguished Young Scholars; the Science and Technology Planning Project of Guangdong Province; the National Key Research and Development Programme of China; Guangdong Provincial Clinical Research Centre for Urological Diseases.

Artificial intelligence to analyze magnetic resonance imaging in rheumatology

Rheumatic disorders present a global health challenge, marked by inflammation and damage to joints, bones, and connective tissues. Accurate, timely diagnosis and appropriate management are crucial for favorable patient outcomes. Magnetic resonance imaging (MRI) has become indispensable in rheumatology, but interpretation remains laborious and variable. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers a means to improve and advance MRI analysis. This review examines current AI applications in rheumatology MRI analysis, addressing diagnostic support, disease classification, activity assessment, and progression monitoring. AI demonstrates promise, with high sensitivity, specificity, and accuracy, achieving or surpassing expert performance. The review also discusses clinical implementation challenges and future research directions to enhance rheumatic disease diagnosis and management.

Artificial intelligence-adjudicated spatiotemporal dispersion: A patient-unique fingerprint of persistent atrial fibrillation

BACKGROUND

Spatiotemporal dispersion-guided ablation is a tailored approach for patients in persistent atrial fibrillation (PsAF). The characterization of dispersion extent and distribution and its association with common clinical descriptors of PsAF patients has not been studied.

OBJECTIVES

Artificial intelligence-adjudicated dispersion extent and distribution (AI-DED) was obtained with a machine/deep learning classifier (VX1 Software, Volta Medical) in PsAF patients undergoing ablation. The purpose of this study was to test the hypothesis that AI-DED is unique to each patient and independent of common procedural and clinical parameters.

METHODS

In a subanalysis of the Ev-AIFib study (NCT03434964), spatiotemporal dispersion maps were built with VX1 software in 78 consecutive persistent and long-standing PsAF patients. AI-DED was quantified using 2 distinct approaches (visual regional characterization or automated global quantification of AI-DED).

RESULTS

AI-DED paired-subregion Euclidean distance measurements between 78 patients (average distance 5.07 ± 0.60; min 2.23; max 9.75) demonstrate that AI-DED is a patient-unique characteristic of PsAF. Importantly, both AF type and AF history do not correlate with AI-DED levels (R2 = 0.006, P = .53; and R2 = 0.03, P = .25, respectively). The most extensive AI-DED levels are not associated with poorer procedural (83%, 81%, and 83% of AF termination in low, medium, and high dispersion groups, respectively; P = .954) and long-term (88%, 75%, and 91% of freedom from AF/atrial tachycardia after multiple procedures; P = .517) outcomes.

CONCLUSION

The atrial distribution and extent of multipolar electrogram spatiotemporal dispersion follow a nonrandom, albeit patient-unique, distribution in PsAF patients. AI-DED may represent a procedure-implementable fingerprint of the PsAF substrate.

Application of artificial intelligence in hypertension

Hypertension is an important modifiable risk factor for morbidity and mortality associated with cardiovascular disease. The incidence of hypertension is increasing not only in Korea but also in many Western countries due to the aging of the population and the increase in unhealthy lifestyles. However, hypertension control rates remain low due to poor adherence to antihypertensive medications, low awareness of hypertension, and numerous factors that contribute to hypertension, including diet, environment, lifestyle, obesity, and genetics. Because artificial intelligence (AI) involves data-driven algorithms, AI is an asset to understanding chronic diseases that are influenced by multiple factors, such as hypertension. Although several hypertension studies using AI have been published recently, most are exploratory descriptive studies that are often difficult for clinicians to understand and have little clinical relevance. This review aims to provide a clinician-centered perspective on AI by showing recent studies on the relevance of AI for patients with hypertension. The review is organized into sections on blood pressure measurement and hypertension diagnosis, prognosis, and management.

Geographical discrimination of Asian red pepper powders using 1H NMR spectroscopy and deep learning-based convolution neural networks

This study investigated an innovative approach to discriminate the geographical origins of Asian red pepper powders by analyzing one-dimensional 1H NMR spectra through a deep learning-based convolution neural network (CNN). 1H NMR spectra were collected from 300 samples originating from China, Korea, and Vietnam and used as input data. Principal component analysis - linear discriminant analysis and support vector machine models were employed for comparison. Bayesian optimization was used for hyperparameter optimization, and cross-validation was performed to prevent overfitting. As a result, all three models discriminated the origins of the test samples with over 95 % accuracy. Specifically, the CNN models achieved a 100 % accuracy rate. Gradient-weighted class activation mapping analysis verified that the CNN models recognized the origins of the samples based on variations in metabolite distributions. This research demonstrated the potential of deep learning-based classification of 1H NMR spectra as an accurate and reliable approach for determining the geographical origins of various foods.

Diagnostic Performance of Deep Learning in Video-Based Ultrasonography for Breast Cancer: A Retrospective Multicentre Study

OBJECTIVE

Although ultrasound is a common tool for breast cancer screening, its accuracy is often operator-dependent. In this study, we proposed a new automated deep-learning framework that extracts video-based ultrasound data for breast cancer screening.

METHODS

Our framework incorporates DenseNet121, MobileNet, and Xception as backbones for both video- and image-based models. We used data from 3907 patients to train and evaluate the models, which were tested using video- and image-based methods, as well as reader studies with human experts.

RESULTS

This study evaluated 3907 female patients aged 22 to 86 years. The results indicated that the MobileNet video model achieved an AUROC of 0.961 in prospective data testing, surpassing the DenseNet121 video model. In real-world data testing, it demonstrated an accuracy of 92.59%, outperforming both the DenseNet121 and Xception video models, and exceeding the 76.00% to 85.60% accuracy range of human experts. Additionally, the MobileNet video model exceeded the performance of image models and other video models across all evaluation metrics, including accuracy, sensitivity, specificity, F1 score, and AUC. Its exceptional performance, particularly suitable for resource-limited clinical settings, demonstrates its potential for clinical application in breast cancer screening.

CONCLUSIONS

The level of expertise reached by the video models was greater than that achieved by image-based models. We have developed an artificial intelligence framework based on videos that may be able to aid breast cancer diagnosis and alleviate the shortage of experienced experts.

Artificial intelligence and machine learning trends in kidney care

BACKGROUND

The integration of artificial intelligence (AI) and machine learning (ML) in kidney care has seen a significant rise in recent years. This study specifically analyzed AI and ML research publications related to kidney care to identify leading authors, institutions, and countries in this area. It aimed to examine publication trends and patterns, and to explore the impact of collaborative efforts on citation metrics.

METHODS

The study used the Science Citation Index Expanded (SCI-EXPANDED) of Clarivate Analytics Web of Science Core Collection to search for AI and machine learning publications related to nephrology from 1992 to 2021. The authors used quotation marks and Boolean operator "or" to search for keywords in the title, abstract, author keywords, and Keywords Plus. In addition, the 'front page' filter was applied. A total of 5425 documents were identified and analyzed.

RESULTS

The results showed that articles represent 75% of the analyzed documents, with an average author to publications ratio of 7.4 and an average number of citations per publication in 2021 of 18. English articles had a higher citation rate than non-English articles. The USA dominated in all publication indicators, followed by China. Notably, the research also showed that collaborative efforts tend to result in higher citation rates. A significant portion of the publications were found in urology journals, emphasizing the broader scope of kidney care beyond traditional nephrology.

CONCLUSIONS

The findings underscore the importance of AI and ML in enhancing kidney care, offering a roadmap for future research and implementation in this expanding field.

Review of applications of artificial intelligence (AI) methods in crop research

Sophisticated and modern crop improvement techniques can bridge the gap for feeding the ever-increasing population. Artificial intelligence (AI) refers to the simulation of human intelligence in machines, which refers to the application of computational algorithms, machine learning (ML) and deep learning (DL) techniques. This is aimed to generalise patterns and relationships from historical data, employing various mathematical optimisation techniques thus making prediction models for facilitating selection of superior genotypes. These techniques are less resource intensive and can solve the problem based on the analysis of large-scale phenotypic datasets. ML for genomic selection (GS) uses high-throughput genotyping technologies to gather genetic information on a large number of markers across the genome. The prediction of GS models is based on the mathematical relation between genotypic and phenotypic data from the training population. ML techniques have emerged as powerful tools for genome editing through analysing large-scale genomic data and facilitating the development of accurate prediction models. Precise phenotyping is a prerequisite to advance crop breeding for solving agricultural production-related issues. ML algorithms can solve this problem through generating predictive models, based on the analysis of large-scale phenotypic datasets. DL models also have the potential reliability of precise phenotyping. This review provides a comprehensive overview on various ML and DL models, their applications, potential to enhance the efficiency, specificity and safety towards advanced crop improvement protocols such as genomic selection, genome editing, along with phenotypic prediction to promote accelerated breeding.

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.

Computational limits to the legibility of the imaged human brain

Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal. Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging. We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05). Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.

A cross-sectional comparative study: ChatGPT 3.5 versus diverse levels of medical experts in the diagnosis of ENT diseases

PURPOSE

With recent advances in artificial intelligence (AI), it has become crucial to thoroughly evaluate its applicability in healthcare. This study aimed to assess the accuracy of ChatGPT in diagnosing ear, nose, and throat (ENT) pathology, and comparing its performance to that of medical experts.

METHODS

We conducted a cross-sectional comparative study where 32 ENT cases were presented to ChatGPT 3.5, ENT physicians, ENT residents, family medicine (FM) specialists, second-year medical students (Med2), and third-year medical students (Med3). Each participant provided three differential diagnoses. The study analyzed diagnostic accuracy rates and inter-rater agreement within and between participant groups and ChatGPT.

RESULTS

The accuracy rate of ChatGPT was 70.8%, being not significantly different from ENT physicians or ENT residents. However, a significant difference in correctness rate existed between ChatGPT and FM specialists (49.8%, p < 0.001), and between ChatGPT and medical students (Med2 47.5%, p < 0.001; Med3 47%, p < 0.001). Inter-rater agreement for the differential diagnosis between ChatGPT and each participant group was either poor or fair. In 68.75% of cases, ChatGPT failed to mention the most critical diagnosis.

CONCLUSIONS

ChatGPT demonstrated accuracy comparable to that of ENT physicians and ENT residents in diagnosing ENT pathology, outperforming FM specialists, Med2 and Med3. However, it showed limitations in identifying the most critical diagnosis.

Using Artificial Intelligence to Label Free-Text Operative and Ultrasound Reports for Grading Pediatric Appendicitis

PURPOSE

Data science approaches personalizing pediatric appendicitis management are hampered by small datasets and unstructured electronic medical records (EMR). Artificial intelligence (AI) chatbots based on large language models can structure free-text EMR data. We compare data extraction quality between ChatGPT-4 and human data collectors.

METHODS

To train AI models to grade pediatric appendicitis preoperatively, several data collectors extracted detailed preoperative and operative data from 2100 children operated for acute appendicitis. Collectors were trained for the task based on satisfactory Kappa scores. ChatGPT-4 was prompted to structure free text from 103 random anonymized ultrasound and operative records in the dataset using the set variables and coding options, and to estimate appendicitis severity grade from the operative report. A pediatric surgeon then adjudicated all data, identifying errors in each method.

RESULTS

Within the 44 ultrasound (42.7%) and 32 operative reports (31.1%) discordant in at least one field, 98% of the errors were found in the manual data extraction. The appendicitis grade was erroneously assigned manually in 29 patients (28.2%), and by ChatGPT-4 in 3 (2.9%). Across datasets, the use of the AI chatbot was able to avoid misclassification in 59.2% of the records including both reports and extracted data approximately 40 times faster.

CONCLUSION

AI chatbot significantly outperformed manual data extraction in accuracy for ultrasound and operative reports, and correctly assigned the appendicitis grade. While wider validation is required and data safety concerns must be addressed, these AI tools show significant promise in improving the accuracy and efficiency of research data collection.

LEVELS OF EVIDENCE

Level III.

Content analysis of AI-generated (ChatGPT) responses concerning orthodontic clear aligners

OBJECTIVES

To assess the accuracy of ChatGPT answers concerning orthodontic clear aligners.

MATERIALS AND METHODS

A cross-sectional content analysis of ChatGPT generated responses to queries related to clear aligner treatment (CAT) was undertaken. A total of 111 questions were generated by three orthodontists based on a set of predefined domains and subdomains. The artificial intelligence (AI)-generated (ChatGPT) answers were extracted and their accuracy was determined independently by five orthodontists. The accuracy of answers was assessed using a prepiloted four-point scale scoring rubric. Descriptive statistics were performed.

RESULTS

The total mean accuracy score for the entire set was 2.6 ± 1.1. It was noted that 58% of the AI-generated answers were scored as objectively true, 18% were selected facts, 9% were minimal facts, and 15% were false. False claims included the ability of CAT to reduce the need for orthognathic surgery (4.0 ± 0.0), improve airway function (3.8 ± 0.5), achieve root parallelism (3.6 ± 0.5), alleviate sleep apnea (3.8 ± 0.5), and produce more stable results compared to fixed appliances (3.8 ± 0.5).

CONCLUSIONS

The overall level of accuracy of ChatGPT responses to questions concerning CAT was suboptimal and lacked citations to relevant literature. Ability of the software to offer current and precise information was limited. Therefore, clinicians and patients must be mindful of false claims and relevant facts omitted in the answers generated by ChatGPT.

A framework enabling LLMs into regulatory environment for transparency and trustworthiness and its application to drug labeling document

Regulatory agencies consistently deal with extensive document reviews, ranging from product submissions to both internal and external communications. Large Language Models (LLMs) like ChatGPT can be invaluable tools for these tasks, however present several challenges, particularly the proprietary information, combining customized function with specific review needs, and transparency and explainability of the model's output. Hence, a localized and customized solution is imperative. To tackle these challenges, we formulated a framework named askFDALabel on FDA drug labeling documents that is a crucial resource in the FDA drug review process. AskFDALabel operates within a secure IT environment and comprises two key modules: a semantic search and a Q&A/text-generation module. The Module S built on word embeddings to enable comprehensive semantic queries within labeling documents. The Module T utilizes a tuned LLM to generate responses based on references from Module S. As the result, our framework enabled small LLMs to perform comparably to ChatGPT with as a computationally inexpensive solution for regulatory application. To conclude, through AskFDALabel, we have showcased a pathway that harnesses LLMs to support agency operations within a secure environment, offering tailored functions for the needs of regulatory research.