Comparing robotic and open partial nephrectomy under the prism of surgical precision: a meta-analysis of the average blood loss rate as a novel variable

Exploration of surgical precision in robotic procedures is extensive, yet lacks a unified framework for comparability. This study examines tissue handling precision by comparing the per-minute blood loss rate between robotic and open partial nephrectomy. A literature search from August 2022 to June 2024 identified 43 relevant studies providing data on estimated blood loss and procedure duration. The expected values and standard errors of these variables were used to compute the per-minute blood loss rate (Q). Meta-analytical methods estimated pooled and subgroup-level mean differences, favoring robotic surgery (MDQ = - 1.043 ml/min, CI95% = [- 1.338; - 0.747]). Subgroup analyses by publication year, patient matching, referral center count, and ROBINS-I status consistently supported this advantage. Sensitivity analyses confirmed the above benefit in studies with increased accuracy in reported results (MDQ = - 0.957 ml/min, CI95% = [- 1.269; - 0.646]), low risk of bias involving matched comparisons (MDQ = - 0.563 ml/min, CI95% = [- 0.716; - 0.410]), large sample sizes and increased statistical power (MDQ = - 0.780 ml/min, CI95% = [- 1.134; - 0.425]), and multicenter analyses with patient matching (MDQ = - 0.481 ml/min, CI95% = [- 0.698; - 0.263]). The subsequent analysis of correlation between the original variables suggested a slight reduction in the robotic advantage when the latter were proportionally related. Multilevel meta-regression at both temporal and qualitative scales consistently indicated a comparative benefit of the robotic approach. Potentially, lower per-minute blood loss compared to open surgery suggests that robotic partial nephrectomy demonstrates enhanced precision in tissue handling.

Evolution of digital twins in precision health applications: a scoping review study

An increasing amount of research is incorporating the concept of Digital twin (DT) in biomedical and health care applications. This scoping review aims to summarize existing research and identify gaps in the development and use of DTs in the health care domain. The focus of this study lies on summarizing: the different types of DTs, the techniques employed in DT development, the DT applications in health care, and the data resources used for creating DTs. We identified fifty studies, which mainly focused on creating organ- (n=15) and patient-specific twins (n=30). The research predominantly centers on cardiology, endocrinology, orthopedics, and infectious diseases. Only a few studies used real-world datasets for developing their DTs. However, there remain unresolved questions and promising directions that require further exploration. This review provides valuable reference material and insights for researchers on DTs in health care and highlights gaps and unmet needs in this field.

A methodology for planning, implementation and evaluation of skills intelligence management - results of a design science project in technology organisations

Introduction

The evolving labour market requirements amidst digital transformation necessitate robust skills intelligence for informed decision-making and adaptability. Novel technologies such as Big Data, Machine Learning, and Artificial Intelligence have significant potential for enhancing skills intelligence.

Methods

This study bridges the gap between theory and practice by designing a novel software artefact for skills intelligence management. With its systematic framework for identifying skills intelligence elements, an assessment instrument, and an implementation methodology, the artefact ensures a thorough approach to skills intelligence management.

Results

The artefact was demonstrated in 11 organisations. Feedback collected from interviews, focus group sessions, and observations (N = 19) indicated that the artefact is a feasible starting point for implementing or systematising skills intelligence management. Participants suggested improvements but concurred that the systematic approach enhances skills intelligence data collection and quality.

Discussion

The study shows that the artefact facilitates the application of advanced technologies in skills intelligence management. Additionally, it contributes a set of principles for effective skills intelligence management, fostering a broader conversation on this critical topic. Participants' feedback underscores the artefact's potential and provides a basis for further refinement and application in diverse organisational contexts.

High throughput long-read sequencing of circulating lymphocytes of the evolutionarily distant sea lamprey reveals diversity and common elements of the variable lymphocyte receptor B (VLRB) repertoire

The leucine-rich repeat-based variable lymphocyte receptor B (VLRB) antibody system of jawless vertebrates is capable of generating an antibody repertoire equal to or exceeding the diversity of antibody repertoires of jawed vertebrates. Unlike immunoglobulin-based immune repertoires, the VLRB repertoire diversity is characterized by variable lengths of VLRB encoding transcripts, rendering conventional immunoreceptor repertoire sequencing approaches unsuitable for VLRB repertoire sequencing. Here we demonstrate that long-read single-molecule real-time (SMRT) sequencing (PacBio) approaches permit the efficient large-scale assessment of the VLRB repertoire. We present a computational pipeline for sequence data processing and provide the first repertoire-based analysis of VLRB protein characteristics including properties of its subunits and regions of diversity within each structural leucine-rich repeat subunit. Our study provides a template to explore changes in the VLRB repertoire during immune responses and to establish large scale VLRB repertoire databases for computational approaches aimed at isolating monoclonal VLRB reagents for biomedical research and clinical applications.

Research progress of brain organoids in the field of diabetes

Human embryonic stem cells and human induced pluripotent stem cells may be used to create 3D tissues called brain organoids. They duplicate the physiological and pathological characteristics of human brain tissue more faithfully in terms of both structure and function, and they more precisely resemble the morphology and cellular structure of the human embryonic brain. This makes them valuable models for both drug screening and in vitro studies on the development of the human brain and associated disorders. The technical breakthroughs enabled by brain organoids have a significant impact on the research of different brain regions, brain development and sickness, the connections between the brain and other tissues and organs, and brain evolution. This article discusses the development of brain organoids, their use in diabetes research, and their progress.

Enhancing Health Literacy: Evaluating the Readability of Patient Handouts Revised by ChatGPT's Large Language Model

OBJECTIVE

To use an artificial intelligence (AI)-powered large language model (LLM) to improve readability of patient handouts.

STUDY DESIGN

Review of online material modified by AI.

SETTING

Academic center.

METHODS

Five handout materials obtained from the American Rhinologic Society (ARS) and the American Academy of Facial Plastic and Reconstructive Surgery websites were assessed using validated readability metrics. The handouts were inputted into OpenAI's ChatGPT-4 after prompting: "Rewrite the following at a 6th-grade reading level." The understandability and actionability of both native and LLM-revised versions were evaluated using the Patient Education Materials Assessment Tool (PEMAT). Results were compared using Wilcoxon rank-sum tests.

RESULTS

The mean readability scores of the standard (ARS, American Academy of Facial Plastic and Reconstructive Surgery) materials corresponded to "difficult," with reading categories ranging between high school and university grade levels. Conversely, the LLM-revised handouts had an average seventh-grade reading level. LLM-revised handouts had better readability in nearly all metrics tested: Flesch-Kincaid Reading Ease (70.8 vs 43.9; P < .05), Gunning Fog Score (10.2 vs 14.42; P < .05), Simple Measure of Gobbledygook (9.9 vs 13.1; P < .05), Coleman-Liau (8.8 vs 12.6; P < .05), and Automated Readability Index (8.2 vs 10.7; P = .06). PEMAT scores were significantly higher in the LLM-revised handouts for understandability (91 vs 74%; P < .05) with similar actionability (42 vs 34%; P = .15) when compared to the standard materials.

CONCLUSION

Patient-facing handouts can be augmented by ChatGPT with simple prompting to tailor information with improved readability. This study demonstrates the utility of LLMs to aid in rewriting patient handouts and may serve as a tool to help optimize education materials.

LEVEL OF EVIDENCE

Level VI.

Are large language models a useful resource to address common patient concerns on hallux valgus? A readability analysis

BACKGROUND

This study evaluates the accuracy and readability of Google, ChatGPT-3.5, and 4.0 (two versions of an artificial intelligence model) responses to common questions regarding bunion surgery.

METHODS

A Google search of "bunionectomy" was performed, and the first ten questions under "People Also Ask" were recorded. ChatGPT-3.5 and 4.0 were asked these ten questions individually, and their answers were analyzed using the Flesch-Kincaid Reading Ease and Gunning-Fog Level algorithms.

RESULTS

When compared to Google, ChatGPT-3.5 and 4.0 had a larger word count with 315 ± 39 words (p < .0001) and 294 ± 39 words (p < .0001), respectively. A significant difference was found between ChatGPT-3.5 and 4.0 compared to Google using Flesch-Kincaid Reading Ease (p < .0001).

CONCLUSIONS

Our findings demonstrate that ChatGPT provided significantly lengthier responses than Google and there was a significant difference in reading ease. Both platforms exceeded the seventh to eighth-grade reading level of the U.S.

POPULATION

LEVEL OF EVIDENCE

N/A.

Advancements in triple-negative breast cancer sub-typing, diagnosis and treatment with assistance of artificial intelligence : a focused review

Triple negative breast cancer (TNBC) is most aggressive type of breast cancer with multiple invasive sub-types and leading cause of women's death worldwide. Lack of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER-2) causes it to spread rapidly making its treatment challenging due to unresponsiveness towards anti-HER and endocrine therapy. Hence, needing advanced therapeutic treatments and strategies in order to get better recovery from TNBC. Artificial intelligence (AI) has been emerged by giving its high inputs in the automated diagnosis as well as treatment of several diseases, particularly TNBC. AI based TNBC molecular sub-typing, diagnosis as well as therapeutic treatment has become successful now days. Therefore, present review has reviewed recent advancements in the role and assistance of AI particularly focusing on molecular sub-typing, diagnosis as well as treatment of TNBC. Meanwhile, advantages, certain limitations and future implications of AI assistance in the TNBC diagnosis and treatment are also discussed in order to fully understand readers regarding this issue.

Advancing plant biology through deep learning-powered natural language processing

The application of deep learning methods, specifically the utilization of Large Language Models (LLMs), in the field of plant biology holds significant promise for generating novel knowledge on plant cell systems. The LLM framework exhibits exceptional potential, particularly with the development of Protein Language Models (PLMs), allowing for in-depth analyses of nucleic acid and protein sequences. This analytical capacity facilitates the discernment of intricate patterns and relationships within biological data, encompassing multi-scale information within DNA or protein sequences. The contribution of PLMs extends beyond mere sequence patterns and structure--function recognition; it also supports advancements in genetic improvements for agriculture. The integration of deep learning approaches into the domain of plant sciences offers opportunities for major breakthroughs in basic research across multi-scale plant traits. Consequently, the strategic application of deep learning methodologies, particularly leveraging the potential of LLMs, will undoubtedly play a pivotal role in advancing plant sciences, plant production, plant uses and propelling the trajectory toward sustainable agroecological and agro-food transitions.

The Potential Impact of Large Language Models on Doctor-Patient Communication: A Case Study in Prostate Cancer

BACKGROUND

In recent years, the integration of large language models (LLMs) into healthcare has emerged as a revolutionary approach to enhancing doctor-patient communication, particularly in the management of diseases such as prostate cancer.

METHODS

Our paper evaluated the effectiveness of three prominent LLMs-ChatGPT (3.5), Gemini (Pro), and Co-Pilot (the free version)-against the official Romanian Patient's Guide on prostate cancer. Employing a randomized and blinded method, our study engaged eight medical professionals to assess the responses of these models based on accuracy, timeliness, comprehensiveness, and user-friendliness.

RESULTS

The primary objective was to explore whether LLMs, when operating in Romanian, offer comparable or superior performance to the Patient's Guide, considering their potential to personalize communication and enhance the informational accessibility for patients. Results indicated that LLMs, particularly ChatGPT, generally provided more accurate and user-friendly information compared to the Guide.

CONCLUSIONS

The findings suggest a significant potential for LLMs to enhance healthcare communication by providing accurate and accessible information. However, variability in performance across different models underscores the need for tailored implementation strategies. We highlight the importance of integrating LLMs with a nuanced understanding of their capabilities and limitations to optimize their use in clinical settings.

Industry updates from the field of stem cell research and regenerative medicine in May 2024

Latest developments in the field of stem cell research and regenerative medicine compiled from publicly available information and press releases from non-academic institutions in May 2024.

New insights on hidradenitis suppurativa phenotypes and treatment response: An exploratory automated analysis of the SUNSHINE and SUNRISE trials

BACKGROUND

Defining hidradenitis suppurativa (HS) subtypes was previously limited by small sample sizes and poor interrater reliability; no study has investigated subtype treatment responses. The objective of this analysis was to characterize HS clusters in adult patients with moderate to severe HS and evaluate secukinumab treatment responses between clusters.

METHODS

Clusters were identified via an unsupervised machine learning clustering analysis using baseline data from the randomized, placebo-controlled SUNSHINE (NCT03713619) and SUNRISE (NCT03713632) phase 3 trials. To assess treatment responses, patients received secukinumab every 2 (SECQ2W) or 4 weeks (SECQ4W) or placebo, for 16 weeks, after which, placebo patients randomly switched to SECQ2W/SECQ4W, and SECQ2W/SECQ4W patients maintained their original treatment, until week 52. Baseline outcomes included patient characteristics, disease characteristics and severity, HS-associated comorbidities and previous treatment exposures. Treatment response was assessed via the HS clinical response (HiSCR), abscess and inflammatory nodule (AN) count, flares and NRS30 (skin pain).

RESULTS

Based on baseline data, three clusters were identified from 1084 patients (Cluster 1: 54.1%, Cluster 2: 17.8%, Cluster 3: 28.1%). Cluster 1 was predominantly female (65.4%) and was characterized by milder HS. Cluster 2 had more patients from the Asia Pacific, Middle East and Africa region (58.5%) and was characterized by moderate HS. Cluster 3 had the highest rates of previous exposure to biologics (45.9%) and prior HS-related surgeries (47.5%) and was characterized by severe HS. SECQ2W and SECQ4W demonstrated efficacy versus placebo in all clusters at week 16; SECQ2W and SECQ4W efficacy was maintained to week 52. SECQ2W treatment showed a trend for greater efficacy versus SECQ4W in Cluster 3 through week 52.

CONCLUSIONS

Three HS clusters were identified. Secukinumab demonstrated benefit over placebo in all clusters. However, patients with more severe disease may take longer to respond and more frequent secukinumab dosing may be required for these patients.

TRIAL REGISTRATION

SUNSHINE (NCT03713619) and SUNRISE (NCT03713632).

Panpsychism and dualism in the science of consciousness

A resurgence of panpsychism and dualism is a matter of ongoing debate in modern neuroscience. Although metaphysically hostile, panpsychism and dualism both persist in the science of consciousness because the former is proposed as a straightforward answer to the problem of integrating consciousness into the fabric of physical reality, whereas the latter proposes a simple solution to the problem of free will by endowing consciousness with causal power as a prerequisite for moral responsibility. I take the Integrated Information Theory (IIT) as a paradigmatic exemplar of a theory of consciousness (ToC) that makes its commitments to panpsychism and dualism within a unified framework. These features are not, however, unique for IIT. Many ToCs are implicitly prone to some degree of panpsychism whenever they strive to propose a universal definition of consciousness, associated with one or another known phenomenon. Yet, those ToCs that can be characterized as strongly emergent are at risk of being dualist. A remedy against both covert dualism and uncomfortable corollaries of panpsychism can be found in the evolutionary theory of life, called here "bioprotopsychism" and generalized in terms of autopoiesis and the free energy principle. Bioprotopsychism provides a biologically inspired basis for a minimalist approach to consciousness via the triad "chemotaxis-efference copy mechanism-counterfactual active inference" by associating the stream of weakly emergent conscious states with an amount of information (best guesses) of the brain, engaged in unconscious predictive processing.

Multi-omics integration analysis: Tools and applications in environmental toxicology

Nowadays, traditional single-omics study is not enough to explain the causality between molecular alterations and toxicity endpoints for environmental pollutants. With the development of high-throughput sequencing technology and high-resolution mass spectrometry technology, the integrative analysis of multi-omics has become an efficient strategy to understand holistic biological mechanisms and to uncover the regulation network in specific biological processes. This review summarized sample preparation methods, integration analysis tools and the application of multi-omics integration analyses in environmental toxicology field. Currently, omics methods have been widely applied being as the sensitivity of early biological response, especially for low-dose and long-term exposure to environmental pollutants. Integrative omics can reveal the overall changes of genes, proteins, and/or metabolites in the cells, tissues or organisms, which provide new insights into revealing the overall toxicity effects, screening the toxic targets, and exploring the underlying molecular mechanism of pollutants.

Patient-Representing Population's Perceptions of GPT-Generated Versus Standard Emergency Department Discharge Instructions: Randomized Blind Survey Assessment

BACKGROUND

Discharge instructions are a key form of documentation and patient communication in the time of transition from the emergency department (ED) to home. Discharge instructions are time-consuming and often underprioritized, especially in the ED, leading to discharge delays and possibly impersonal patient instructions. Generative artificial intelligence and large language models (LLMs) offer promising methods of creating high-quality and personalized discharge instructions; however, there exists a gap in understanding patient perspectives of LLM-generated discharge instructions.

OBJECTIVE

We aimed to assess the use of LLMs such as ChatGPT in synthesizing accurate and patient-accessible discharge instructions in the ED.

METHODS

We synthesized 5 unique, fictional ED encounters to emulate real ED encounters that included a diverse set of clinician history, physical notes, and nursing notes. These were passed to GPT-4 in Azure OpenAI Service (Microsoft) to generate LLM-generated discharge instructions. Standard discharge instructions were also generated for each of the 5 unique ED encounters. All GPT-generated and standard discharge instructions were then formatted into standardized after-visit summary documents. These after-visit summaries containing either GPT-generated or standard discharge instructions were randomly and blindly administered to Amazon MTurk respondents representing patient populations through Amazon MTurk Survey Distribution. Discharge instructions were assessed based on metrics of interpretability of significance, understandability, and satisfaction.

RESULTS

Our findings revealed that survey respondents' perspectives regarding GPT-generated and standard discharge instructions were significantly (P=.01) more favorable toward GPT-generated return precautions, and all other sections were considered noninferior to standard discharge instructions. Of the 156 survey respondents, GPT-generated discharge instructions were assigned favorable ratings, "agree" and "strongly agree," more frequently along the metric of interpretability of significance in discharge instruction subsections regarding diagnosis, procedures, treatment, post-ED medications or any changes to medications, and return precautions. Survey respondents found GPT-generated instructions to be more understandable when rating procedures, treatment, post-ED medications or medication changes, post-ED follow-up, and return precautions. Satisfaction with GPT-generated discharge instruction subsections was the most favorable in procedures, treatment, post-ED medications or medication changes, and return precautions. Wilcoxon rank-sum test of Likert responses revealed significant differences (P=.01) in the interpretability of significant return precautions in GPT-generated discharge instructions compared to standard discharge instructions but not for other evaluation metrics and discharge instruction subsections.

CONCLUSIONS

This study demonstrates the potential for LLMs such as ChatGPT to act as a method of augmenting current documentation workflows in the ED to reduce the documentation burden of physicians. The ability of LLMs to provide tailored instructions for patients by improving readability and making instructions more applicable to patients could improve upon the methods of communication that currently exist.

Artificial intelligence integration in the drug lifecycle and in regulatory science: policy implications, challenges and opportunities

Artificial intelligence tools promise transformative impacts in drug development. Regulatory agencies face challenges in integrating AI while ensuring reliability and safety in clinical trial approvals, drug marketing authorizations, and post-market surveillance. Incorporating these technologies into the existing regulatory framework and agency practices poses notable challenges, particularly in evaluating the data and models employed for these purposes. Rapid adaptation of regulations and internal processes is essential for agencies to keep pace with innovation, though achieving this requires collective stakeholder collaboration. This article thus delves into the need for adaptations of regulations throughout the drug development lifecycle, as well as the utilization of AI within internal processes of medicine agencies.

Continuous remote monitoring of neurophysiologic Immersion accurately predicts mood

Mental health professionals have relied primarily on clinical evaluations to identify in vivo pathology. As a result, mental health is largely reactive rather than proactive. In an effort to proactively assess mood, we collected continuous neurophysiologic data for ambulatory individuals 8-10 h a day at 1 Hz for 3 weeks (N = 24). Data were obtained using a commercial neuroscience platform (Immersion Neuroscience) that quantifies the neural value of social-emotional experiences. These data were related to self-reported mood and energy to assess their predictive accuracy. Statistical analyses quantified neurophysiologic troughs by the length and depth of social-emotional events with low values and neurophysiologic peaks as the complement. Participants in the study had an average of 2.25 (SD = 3.70, Min = 0, Max = 25) neurophysiologic troughs per day and 3.28 (SD = 3.97, Min = 0, Max = 25) peaks. The number of troughs and peaks predicted daily mood with 90% accuracy using least squares regressions and machine learning models. The analysis also showed that women were more prone to low mood compared to men. Our approach demonstrates that a simple count variable derived from a commercially-available platform is a viable way to assess low mood and low energy in populations vulnerable to mood disorders. In addition, peak Immersion events, which are mood-enhancing, may be an effective measure of thriving in adults.

Effect of homophily on coupled behavior-disease dynamics near a tipping point

Understanding the interplay between social activities and disease dynamics is crucial for effective public health interventions. Recent studies using coupled behavior-disease models assumed homogeneous populations. However, heterogeneity in population, such as different social groups, cannot be ignored. In this study, we divided the population into social media users and non-users, and investigated the impact of homophily (the tendency for individuals to associate with others similar to themselves) and online events on disease dynamics. Our results reveal that homophily hinders the adoption of vaccinating strategies, hastening the approach to a tipping point after which the population converges to an endemic equilibrium with no vaccine uptake. Furthermore, we find that online events can significantly influence disease dynamics, with early discussions on social media platforms serving as an early warning signal of potential disease outbreaks. Our model provides insights into the mechanisms underlying these phenomena and underscores the importance of considering homophily in disease modeling and public health strategies.

Quality assurance for cancer patient safety: Clinical assessment for precise angles in linac during radiation therapy

PURPOSE

Quality assurance for stereotactic body radiation treatment requires that isocentric verification be ensured during gantry rotation at various angles. This study examined statistical parameters on Winston-Lutz tests to distinguish the deviation of angles from isocenter during gantry rotation using machine learning.

METHOD

The Varian TrueBeam linac was aligned with the marked lines on the Ruby phantom. Eight images were captured while the gantry was rotating at a 45° shift. The statistical features were derived from IsoCheck EPID software. The decision tree model was applied to these Winston-Lutz tests to cluster data into two groups: precise and error angles.

RESULTS

At 90° and 270° angles, the gantry exhibits isocentric stability compared to other angles. In these angles, the most statistical features were inside the range. Most variations were observed at 0° and 180° angles. In most tests, the angles 45°, 135°, 225°, and 315° showed reasonable performance and with less variation.

CONCLUSION

The comprehensive statistical analyses for gantry rotation of angles assists expert radiotherapists in determining the contribution of each feature that highly affects gantry movement at specific angles. Misalignment between radiation isocenter and imaging isocenter, tuning of the beam at each angle, or a slight change in the position of the Ruby phantom can further improve the inaccuracy that causes the most variations. Better precision can effectively increase patient safety and quality during cancer treatment.

Robust Visual Question Answering: Datasets, Methods, and Future Challenges

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Third, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.

Machine Learning Models for Pancreatic Cancer Risk Prediction Using Electronic Health Record Data-A Systematic Review and Assessment

INTRODUCTION

Accurate risk prediction can facilitate screening and early detection of pancreatic cancer (PC). We conducted a systematic review to critically evaluate effectiveness of machine learning (ML) and artificial intelligence (AI) techniques applied to electronic health records (EHR) for PC risk prediction.

METHODS

Ovid MEDLINE(R), Ovid EMBASE, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, Scopus, and Web of Science were searched for articles that utilized ML/AI techniques to predict PC, published between January 1, 2012, and February 1, 2024. Study selection and data extraction were conducted by 2 independent reviewers. Critical appraisal and data extraction were performed using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies checklist. Risk of bias and applicability were examined using prediction model risk of bias assessment tool.

RESULTS

Thirty studies including 169,149 PC cases were identified. Logistic regression was the most frequent modeling method. Twenty studies utilized a curated set of known PC risk predictors or those identified by clinical experts. ML model discrimination performance (C-index) ranged from 0.57 to 1.0. Missing data were underreported, and most studies did not implement explainable-AI techniques or report exclusion time intervals.

DISCUSSION

AI/ML models for PC risk prediction using known risk factors perform reasonably well and may have near-term applications in identifying cohorts for targeted PC screening if validated in real-world data sets. The combined use of structured and unstructured EHR data using emerging AI models while incorporating explainable-AI techniques has the potential to identify novel PC risk factors, and this approach merits further study.

Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer

PURPOSE

The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer.

METHODS

A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers.

RESULTS

The PQM score was 40.7 ± 13.1 for manual plans and 40.8 ± 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 ± 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 ± 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 ± 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 ± 20.0 min and 97.4 ± 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200).

CONCLUSIONS

The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.

Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration

Predictions of gradient degree of lenition of voiceless and voiced stops in a corpus of Argentine Spanish are evaluated using three acoustic measures (minimum and maximum intensity velocity and duration) and two recurrent neural network (Phonet) measures (posterior probabilities of sonorant and continuant phonological features). While mixed and inconsistent predictions were obtained across the acoustic metrics, sonorant and continuant probability values were consistently in the direction predicted by known factors of a stop's lenition with respect to its voicing, place of articulation, and surrounding contexts. The results suggest the effectiveness of Phonet as an additional or alternative method of lenition measurement. Furthermore, this study has enhanced the accessibility of Phonet by releasing the trained Spanish Phonet model used in this study and a pipeline with step-by-step instructions for training and inferencing new models.

Poor performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal dysfunction

PURPOSE

Clinical decision support systems (CDSS) are used to identify drugs with potential need for dose modification in patients with renal impairment. ChatGPT holds the potential to be integrated in the electronic health record (EHR) system to give such dosing advices. In this study, we aim to evaluate the performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal impairment.

METHODS

This cross-sectional study was performed at Tergooi Medical Center, the Netherlands. CDSS alerts regarding renal dysfunction were collected from the electronic health record (EHR) during a 2-week period and were presented to ChatGPT and an expert panel. Alerts were presented with and without patient variables. To evaluate the performance, suggested medication interventions were compared.

RESULTS

In total, 172 CDDS alerts were generated for 80 patients. Indecisive responses by ChatGPT to alerts were excluded. For alerts presented without patient variables, ChatGPT provided "correct and identical" responses to 19.9%, "correct and different" responses to 26.7%, and "incorrect responses to 53.4% of the alerts. For alerts including patient variables, ChatGPT provided "correct and identical" responses to 16.7%, "correct and different" responses to 16.0%, and "incorrect responses to 67.3% of the alerts. Accuracy was better for newer drugs such as direct oral anticoagulants.

CONCLUSION

The performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal dysfunction was poor. Based on these results, we conclude that ChatGPT, in its current state, is not appropriate for automatic integration into our EHR to handle CDSS alerts related to renal dysfunction.

Multi-institution single geometry plan complexity characteristics based on IROC phantoms

BACKGROUND

Clinical intensity modulated radiation therapy plans have been described using various complexity metrics to help identify problematic radiotherapy plans. Most previous studies related to the quantification of plan complexity and their utility have relied on institution-specific plans which can be highly variable depending on the machines, planning techniques, delivery modalities, and measurement devices used. In this work, 1723 plans treating one of only four standardized geometries were simultaneously analyzed to investigate how radiation plan complexity metrics vary across four different sets of common objectives.

PURPOSE

To assess the treatment plan complexity characteristics of plans developed for Imaging and Radiation Oncology Core (IROC) phantoms. Specifically, to understand the variability in plan complexity between institutions for a common plan objective, and to evaluate how various complexity metrics differentiate relevant groups of plans.

METHODS

1723 plans treating one of four standardized IROC phantom geometries representing four different anatomical sites of treatment were analyzed. For each plan, 22 MLC-descriptive plan complexity metrics were calculated, and principal component analysis (PCA) was applied to the 22 metrics in order to evaluate differences in plan complexity between groups. Across all metrics, pairwise comparisons of the IROC phantom data were made for the following classifications of the data: anatomical phantom treated, treatment planning system (TPS), and the combination of MLC model and treatment planning system. An objective k-means clustering algorithm was also applied to the data to determine if any meaningful distinctions could be made between different subgroups. The IROC phantom database was also compared to a clinical database from the University of Wisconsin-Madison (UW) which included plans treating the same four anatomical sites as the IROC phantoms using a TrueBeam™ STx and Pinnacle3 TPS.

RESULTS

The IROC head and neck and spine plans were distinct from the prostate and lung plans based on comparison of the 22 metrics. All IROC phantom plan group complexity metric distributions were highly variable despite all plans being designed for identical geometries and plan objectives. The clusters determined by the k-means algorithm further supported that the IROC head and neck and spine plans involved similar amounts of complexity and were largely distinct from the prostate and lung plans, but no further distinctions could be made. Plan complexity in the head and neck and spine IROC phantom plans were similar to the complexity encountered in the UW clinical plans.

CONCLUSIONS

There is substantial variability in plan complexity between institutions when planning for the same objective. For each IROC anatomical phantom treated, the magnitude of variability in plan complexity between institutions is similar to the variability in plan complexity encountered within a single institution database containing several hundred unique clinical plans treating corresponding anatomies in actual patients.

Lung CT harmonization of paired reconstruction kernel images using generative adversarial networks

BACKGROUND

The kernel used in CT image reconstruction is an important factor that determines the texture of the CT image. Consistency of reconstruction kernel choice is important for quantitative CT-based assessment as kernel differences can lead to substantial shifts in measurements unrelated to underlying anatomical structures.

PURPOSE

In this study, we investigate kernel harmonization in a multi-vendor low-dose CT lung cancer screening cohort and evaluate our approach's validity in quantitative CT-based assessments.

METHODS

Using the National Lung Screening Trial, we identified CT scan pairs of the same sessions with one reconstructed from a soft tissue kernel and one from a hard kernel. In total, 1000 pairs of five different paired kernel types (200 each) were identified. We adopt the pix2pix architecture to train models for kernel conversion. Each model was trained on 100 pairs and evaluated on 100 withheld pairs. A total of 10 models were implemented. We evaluated the efficacy of kernel conversion based on image similarity metrics including root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) as well as the capability of the models to reduce measurement shifts in quantitative emphysema and body composition measurements. Additionally, we study the reproducibility of standard radiomic features for all kernel pairs before and after harmonization.

RESULTS

Our approach effectively converts CT images from one kernel to another in all paired kernel types, as indicated by the reduction in RMSE (p < 0.05) and an increase in the PSNR (p < 0.05) and SSIM (p < 0.05) for both directions of conversion for all pair types. In addition, there is an increase in the agreement for percent emphysema, skeletal muscle area, and subcutaneous adipose tissue (SAT) area for both directions of conversion. Furthermore, radiomic features were reproducible when compared with the ground truth features.

CONCLUSIONS

Kernel conversion using deep learning reduces measurement variation in percent emphysema, muscle area, and SAT area.

Highlighting the role of CD44 in cervical cancer progression: immunotherapy's potential in inhibiting metastasis and chemoresistance

Cervical cancer affects thousands of women globally with recurring high-risk HPV infections being at the centre of cervical pathology. Oncological treatment strategies are continually challenged by both chemoresistance and metastasis within patients. Although both work hand-in-hand, targeting their individual mechanisms could prove highly beneficial for treatment outcomes. Such targets include the metastatic-promoting stem cell marker, CD44, which is abundant in cervical cancer cells and is common to both chemoresistance and metastatic mechanisms. Seeing that many existing advanced-stage cervical cancer treatment regimes, such as platinum-based chemotherapy regimens, remain limited and are rarely curative, alternative treatment options within the field of immunology are being considered. The use of immune checkpoint inhibition therapy, which targets immune checkpoints, CTLA-4 and PD-1/PD-L1, has shown promise as an alternate standard of care for patients suffering from advanced-stage cervical cancer. Therefore, this review aims to assess whether immune checkpoint inhibition can mitigate the pathological effects of CD44-induced EMT, metastasis, and chemoresistance in cervical cancer patients.

EDA-Graph: Graph Signal Processing of Electrodermal Activity for Emotional States Detection

The continuous detection of emotional states has many applications in mental health, marketing, human-computer interaction, and assistive robotics. Electrodermal activity (EDA), a signal modulated by sympathetic nervous system activity, provides continuous insight into emotional states. However, EDA possesses intricate nonstationary and nonlinear characteristics, making the extraction of emotion-relevant information challenging. We propose a novel graph signal processing (GSP) approach to model EDA signals as graphical networks, termed EDA-graph. The GSP leverages graph theory concepts to capture complex relationships in time-series data. To test the usefulness of EDA-graphs to detect emotions, we processed EDA recordings from the CASE emotion dataset using GSP by quantizing and linking values based on the Euclidean distance between the nearest neighbors. From these EDA-graphs, we computed the features of graph analysis, including total load centrality (TLC), total harmonic centrality (THC), number of cliques (GNC), diameter, and graph radius, and compared those features with features obtained using traditional EDA processing techniques. EDA-graph features encompassing TLC, THC, GNC, diameter, and radius demonstrated significant differences (p < 0.05) between five emotional states (Neutral, Amused, Bored, Relaxed, and Scared). Using machine learning models for classifying emotional states evaluated using leave-one-subject-out cross-validation, we achieved a five-class F1 score of up to 0.68.

Computerized diagnostic decision support systems - a comparative performance study of Isabel Pro vs. ChatGPT4

OBJECTIVES

Validate the diagnostic accuracy of the Artificial Intelligence Large Language Model ChatGPT4 by comparing diagnosis lists produced by ChatGPT4 to Isabel Pro.

METHODS

This study used 201 cases, comparing ChatGPT4 to Isabel Pro. Systems inputs were identical. Mean Reciprocal Rank (MRR) compares the correct diagnosis's rank between systems. Isabel Pro ranks by the frequency with which the symptoms appear in the reference dataset. The mechanism ChatGPT4 uses to rank the diagnoses is unknown. A Wilcoxon Signed Rank Sum test failed to reject the null hypothesis.

RESULTS

Both systems produced comprehensive differential diagnosis lists. Isabel Pro's list appears immediately upon submission, while ChatGPT4 takes several minutes. Isabel Pro produced 175 (87.1 %) correct diagnoses and ChatGPT4 165 (82.1 %). The MRR for ChatGPT4 was 0.428 (rank 2.31), and Isabel Pro was 0.389 (rank 2.57), an average rank of three for each. ChatGPT4 outperformed on Recall at Rank 1, 5, and 10, with Isabel Pro outperforming at 20, 30, and 40. The Wilcoxon Signed Rank Sum Test confirmed that the sample size was inadequate to conclude that the systems are equivalent. ChatGPT4 fabricated citations and DOIs, producing 145 correct references (87.9 %) but only 52 correct DOIs (31.5 %).

CONCLUSIONS

This study validates the promise of Clinical Diagnostic Decision Support Systems, including the Large Language Model form of artificial intelligence (AI). Until the issue of hallucination of references and, perhaps diagnoses, is resolved in favor of absolute accuracy, clinicians will make cautious use of Large Language Model systems in diagnosis, if at all.

The policies on the use of large language models in radiological journals are lacking: a meta-research study

OBJECTIVE

To evaluate whether and how the radiological journals present their policies on the use of large language models (LLMs), and identify the journal characteristic variables that are associated with the presence.

METHODS

In this meta-research study, we screened Journals from the Radiology, Nuclear Medicine and Medical Imaging Category, 2022 Journal Citation Reports, excluding journals in non-English languages and relevant documents unavailable. We assessed their LLM use policies: (1) whether the policy is present; (2) whether the policy for the authors, the reviewers, and the editors is present; and (3) whether the policy asks the author to report the usage of LLMs, the name of LLMs, the section that used LLMs, the role of LLMs, the verification of LLMs, and the potential influence of LLMs. The association between the presence of policies and journal characteristic variables was evaluated.

RESULTS

The LLM use policies were presented in 43.9% (83/189) of journals, and those for the authors, the reviewers, and the editor were presented in 43.4% (82/189), 29.6% (56/189) and 25.9% (49/189) of journals, respectively. Many journals mentioned the aspects of the usage (43.4%, 82/189), the name (34.9%, 66/189), the verification (33.3%, 63/189), and the role (31.7%, 60/189) of LLMs, while the potential influence of LLMs (4.2%, 8/189), and the section that used LLMs (1.6%, 3/189) were seldomly touched. The publisher is related to the presence of LLM use policies (p < 0.001).

CONCLUSION

The presence of LLM use policies is suboptimal in radiological journals. A reporting guideline is encouraged to facilitate reporting quality and transparency.

CRITICAL RELEVANCE STATEMENT

It may facilitate the quality and transparency of the use of LLMs in scientific writing if a shared complete reporting guideline is developed by stakeholders and then endorsed by journals.

KEY POINTS

The policies on LLM use in radiological journals are unexplored. Some of the radiological journals presented policies on LLM use. A shared complete reporting guideline for LLM use is desired.

Machine Learning Predicts Patients With New-onset Diabetes at Risk of Pancreatic Cancer

BACKGROUND

New-onset diabetes represent a high-risk cohort to screen for pancreatic cancer.

GOALS

Develop a machine model to predict pancreatic cancer among patients with new-onset diabetes.

STUDY

A retrospective cohort of patients with new-onset diabetes was assembled from multiple health care networks in the United States. An XGBoost machine learning model was designed from a portion of this cohort (the training set) and tested on the remaining part of the cohort (the test set). Shapley values were used to explain the XGBoost's model features. Model performance was compared with 2 contemporary models designed to predict pancreatic cancer among patients with new-onset diabetes.

RESULTS

In the test set, the XGBoost model had an area under the curve of 0.80 (0.76 to 0.85) compared with 0.63 and 0.68 for other models. Using cutoffs based on the Youden index, the sensitivity of the XGBoost model was 75%, the specificity was 70%, the accuracy was 70%, the positive predictive value was 1.2%, and the negative predictive value was >99%. The XGBoost model obtained a positive predictive value of at least 2.5% with a sensitivity of 38%. The XGBoost model was the only model that detected at least 50% of patients with cancer one year after the onset of diabetes. All 3 models had similar features that predicted pancreatic cancer, including older age, weight loss, and the rapid destabilization of glucose homeostasis.

CONCLUSION

Machine learning models isolate a high-risk cohort from those with new-onset diabetes at risk for pancreatic cancer.

Artificial Intelligence Readiness, Perceptions, and Educational Needs Among Dental Students: A Cross-Sectional Study

OBJECTIVES

With Artificial Intelligence (AI) profoundly affecting education, ensuring that students in health disciplines are ready to embrace AI is essential for their future workforce integration. This study aims to explore dental students' readiness to use AI, perceptions about AI in health education and healthcare, and their AI-related educational needs.

MATERIAL AND METHODS

A cross-sectional survey was conducted among dental students at the College of Dental Medicine, Qatar University. The survey assessed readiness for AI using the Medical Artificial Intelligence Readiness Scale (MAIRS). Students' perceptions of AI in healthcare and health education and their educational needs were also explored.

RESULTS

A total of 94 students responded to the survey. AI readiness scores were average (3.3 ± 0.64 out of 5); while participants appeared more ready for the vision and ethics domains of MAIRS, they showed less readiness regarding cognition and ability. Participants scored average on AI perceptions (3.35 ± 0.45 out of 5), with concerns regarding AI risks and disadvantages. They expressed a high need for knowledge and skills related to AI use in healthcare (84%), AI for health-related research (81.9%), and AI in radiology and imaging procedures (79.8%). Student readiness had a significant correlation with AI perceptions and perceived level of AI knowledge.

CONCLUSIONS

This is the first study in Qatar exploring dental students' AI readiness, perceptions, and educational needs regarding AI applications in education and healthcare. The perceived AI knowledge gaps could inform future curricular AI integration. Advancing AI skills and deepening AI comprehension can empower future dental professionals through anticipated advances in the AI-driven healthcare landscape.

Predictive models and applicability of artificial intelligence-based approaches in drug allergy

PURPOSE OF REVIEW

Drug allergy is responsible for a huge burden on public healthcare systems, representing in some instances a threat for patient's life. Diagnosis is complex due to the heterogeneity of clinical phenotypes and mechanisms involved, the limitations of in vitro tests, and the associated risk to in vivo tests. Predictive models, including those using recent advances in artificial intelligence, may circumvent these drawbacks, leading to an appropriate classification of patients and improving their management in clinical settings.

RECENT FINDINGS

Scores and predictive models to assess drug allergy development, including patient risk stratification, are scarce and usually apply logistic regression analysis. Over recent years, different methods encompassed under the general umbrella of artificial intelligence, including machine and deep learning, and artificial neural networks, are emerging as powerful tools to provide reliable and optimal models for clinical diagnosis, prediction, and precision medicine in different types of drug allergy.

SUMMARY

This review provides general concepts and current evidence supporting the potential utility of predictive models and artificial intelligence branches in drug allergy diagnosis.

Are Virtual Assistants Trustworthy for Medicare Information: An Examination of Accuracy and Reliability

BACKGROUND AND OBJECTIVES

Advances in artificial intelligence (AI)-based virtual assistants provide a potential opportunity for older adults to use this technology in the context of health information-seeking. Meta-analysis on trust in AI shows that users are influenced by the accuracy and reliability of the AI trustee. We evaluated these dimensions for responses to Medicare queries.

RESEARCH DESIGN AND METHODS

During the summer of 2023, we assessed the accuracy and reliability of Alexa, Google Assistant, Bard, and ChatGPT-4 on Medicare terminology and general content from a large, standardized question set. We compared the accuracy of these AI systems to that of a large representative sample of Medicare beneficiaries who were queried twenty years prior.

RESULTS

Alexa and Google Assistant were found to be highly inaccurate when compared to beneficiaries' mean accuracy of 68.4% on terminology queries and 53.0% on general Medicare content. Bard and ChatGPT-4 answered Medicare terminology queries perfectly and performed much better on general Medicare content queries (Bard = 96.3%, ChatGPT-4 = 92.6%) than the average Medicare beneficiary. About one month to a month-and-a-half later, we found that Bard and Alexa's accuracy stayed the same, whereas ChatGPT-4's performance nominally decreased, and Google Assistant's performance nominally increased.

DISCUSSION AND IMPLICATIONS

LLM-based assistants generate trustworthy information in response to carefully phrased queries about Medicare, in contrast to Alexa and Google Assistant. Further studies will be needed to determine what factors beyond accuracy and reliability influence the adoption and use of such technology for Medicare decision-making.

Ethical Considerations and Fundamental Principles of Large Language Models in Medical Education: Viewpoint

This viewpoint article first explores the ethical challenges associated with the future application of large language models (LLMs) in the context of medical education. These challenges include not only ethical concerns related to the development of LLMs, such as artificial intelligence (AI) hallucinations, information bias, privacy and data risks, and deficiencies in terms of transparency and interpretability but also issues concerning the application of LLMs, including deficiencies in emotional intelligence, educational inequities, problems with academic integrity, and questions of responsibility and copyright ownership. This paper then analyzes existing AI-related legal and ethical frameworks and highlights their limitations with regard to the application of LLMs in the context of medical education. To ensure that LLMs are integrated in a responsible and safe manner, the authors recommend the development of a unified ethical framework that is specifically tailored for LLMs in this field. This framework should be based on 8 fundamental principles: quality control and supervision mechanisms; privacy and data protection; transparency and interpretability; fairness and equal treatment; academic integrity and moral norms; accountability and traceability; protection and respect for intellectual property; and the promotion of educational research and innovation. The authors further discuss specific measures that can be taken to implement these principles, thereby laying a solid foundation for the development of a comprehensive and actionable ethical framework. Such a unified ethical framework based on these 8 fundamental principles can provide clear guidance and support for the application of LLMs in the context of medical education. This approach can help establish a balance between technological advancement and ethical safeguards, thereby ensuring that medical education can progress without compromising the principles of fairness, justice, or patient safety and establishing a more equitable, safer, and more efficient environment for medical education.

Biomedical Data Science, Artificial Intelligence, and Ethics: Navigating Challenges in the Face of Explosive Growth

Advances in biomedical data science and artificial intelligence (AI) are profoundly changing the landscape of healthcare. This article reviews the ethical issues that arise with the development of AI technologies, including threats to privacy, data security, consent, and justice, as they relate to donors of tissue and data. It also considers broader societal obligations, including the importance of assessing the unintended consequences of AI research in biomedicine. In addition, this article highlights the challenge of rapid AI development against the backdrop of disparate regulatory frameworks, calling for a global approach to address concerns around data misuse, unintended surveillance, and the equitable distribution of AI's benefits and burdens. Finally, a number of potential solutions to these ethical quandaries are offered. Namely, the merits of advocating for a collaborative, informed, and flexible regulatory approach that balances innovation with individual rights and public welfare, fostering a trustworthy AI-driven healthcare ecosystem, are discussed.

Automatic Segmentation and Alignment of Uterine Shapes from 3D Ultrasound Data

BACKGROUND

The uterus is the most important organ in the female reproductive system. Its shape plays a critical role in fertility and pregnancy outcomes. Advances in medical imaging, such as 3D ultrasound, have significantly improved the exploration of the female genital tract, thereby enhancing gynecological healthcare. Despite well-documented data for organs like the liver and heart, large-scale studies on the uterus are lacking. Existing classifications, such as VCUAM and ESHRE/ESGE, provide different definitions for normal uterine shapes but are not based on real-world measurements. Moreover, the lack of comprehensive datasets significantly hinders research in this area. Our research, part of the larger NURSE study, aims to fill this gap by establishing the shape of a normal uterus using real-world 3D vaginal ultrasound scans. This will facilitate research into uterine shape abnormalities associated with infertility and recurrent miscarriages.

METHODS

We developed an automated system for the segmentation and alignment of uterine shapes from 3D ultrasound data, which consists of two steps: automatic segmentation of the uteri in 3D ultrasound scans using deep learning techniques, and alignment of the resulting shapes with standard geometrical approaches, enabling the extraction of the normal shape for future analysis. The system was trained and validated on a comprehensive dataset of 3D ultrasound images from multiple medical centers. Its performance was evaluated by comparing the automated results with manual annotations provided by expert clinicians.

RESULTS

The presented approach demonstrated high accuracy in segmenting and aligning uterine shapes from 3D ultrasound data. The segmentation achieved an average Dice similarity coefficient (DSC) of 0.90. Our method for aligning uterine shapes showed minimal translation and rotation errors compared to traditional methods, with the preliminary average shape exhibiting characteristics consistent with expert findings of a normal uterus.

CONCLUSION

We have presented an approach to automatically segment and align uterine shapes from 3D ultrasound data. We trained a deep learning nnU-Net model that achieved high accuracy and proposed an alignment method using a combination of standard geometrical techniques. Additionally, we have created a publicly available dataset of 3D transvaginal ultrasound volumes with manual annotations of uterine cavities to support further research and development in this field. The dataset and the trained models are available at https://github.com/UL-FRI-LGM/UterUS.

Towards equitable AI in oncology

Artificial intelligence (AI) stands at the threshold of revolutionizing clinical oncology, with considerable potential to improve early cancer detection and risk assessment, and to enable more accurate personalized treatment recommendations. However, a notable imbalance exists in the distribution of the benefits of AI, which disproportionately favour those living in specific geographical locations and in specific populations. In this Perspective, we discuss the need to foster the development of equitable AI tools that are both accurate in and accessible to a diverse range of patient populations, including those in low-income to middle-income countries. We also discuss some of the challenges and potential solutions in attaining equitable AI, including addressing the historically limited representation of diverse populations in existing clinical datasets and the use of inadequate clinical validation methods. Additionally, we focus on extant sources of inequity including the type of model approach (such as deep learning, and feature engineering-based methods), the implications of dataset curation strategies, the need for rigorous validation across a variety of populations and settings, and the risk of introducing contextual bias that comes with developing tools predominantly in high-income countries.

Assessing ChatGPT's Potential in HIV Prevention Communication: A Comprehensive Evaluation of Accuracy, Completeness, and Inclusivity

With the advancement of artificial intelligence(AI), platforms like ChatGPT have gained traction in different fields, including Medicine. This study aims to evaluate the potential of ChatGPT in addressing questions related to HIV prevention and to assess its accuracy, completeness, and inclusivity. A team consisting of 15 physicians, six members from HIV communities, and three experts in gender and queer studies designed an assessment of ChatGPT. Queries were categorized into five thematic groups: general HIV information, behaviors increasing HIV acquisition risk, HIV and pregnancy, HIV testing, and the prophylaxis use. A team of medical doctors was in charge of developing questions to be submitted to ChatGPT. The other members critically assessed the generated responses regarding level of expertise, accuracy, completeness, and inclusivity. The median accuracy score was 5.5 out of 6, with 88.4% of responses achieving a score ≥ 5. Completeness had a median of 3 out of 3, while the median for inclusivity was 2 out of 3. Some thematic groups, like behaviors associated with HIV transmission and prophylaxis, exhibited higher accuracy, indicating variable performance across different topics. Issues of inclusivity were identified, notably the use of outdated terms and a lack of representation for some communities. ChatGPT demonstrates significant potential in providing accurate information on HIV-related topics. However, while responses were often scientifically accurate, they sometimes lacked the socio-political context and inclusivity essential for effective health communication. This underlines the importance of aligning AI-driven platforms with contemporary health communication strategies and ensuring the balance of accuracy and inclusivity.

Adequacy of prostate cancer prevention and screening recommendations provided by an artificial intelligence-powered large language model

PURPOSE

We aimed to assess the appropriateness of ChatGPT in providing answers related to prostate cancer (PCa) screening, comparing GPT-3.5 and GPT-4.

METHODS

A committee of five reviewers designed 30 questions related to PCa screening, categorized into three difficulty levels. The questions were formulated identically for both GPTs three times, varying the prompts. Each reviewer assigned a score for accuracy, clarity, and conciseness. The readability was assessed by the Flesch Kincaid Grade (FKG) and Flesch Reading Ease (FRE). The mean scores were extracted and compared using the Wilcoxon test. We compared the readability across the three different prompts by ANOVA.

RESULTS

In GPT-3.5 the mean score (SD) for accuracy, clarity, and conciseness was 1.5 (0.59), 1.7 (0.45), 1.7 (0.49), respectively for easy questions; 1.3 (0.67), 1.6 (0.69), 1.3 (0.65) for medium; 1.3 (0.62), 1.6 (0.56), 1.4 (0.56) for hard. In GPT-4 was 2.0 (0), 2.0 (0), 2.0 (0.14), respectively for easy questions; 1.7 (0.66), 1.8 (0.61), 1.7 (0.64) for medium; 2.0 (0.24), 1.8 (0.37), 1.9 (0.27) for hard. GPT-4 performed better for all three qualities and difficulty levels than GPT-3.5. The FKG mean for GPT-3.5 and GPT-4 answers were 12.8 (1.75) and 10.8 (1.72), respectively; the FRE for GPT-3.5 and GPT-4 was 37.3 (9.65) and 47.6 (9.88), respectively. The 2nd prompt has achieved better results in terms of clarity (all p < 0.05).

CONCLUSIONS

GPT-4 displayed superior accuracy, clarity, conciseness, and readability than GPT-3.5. Though prompts influenced the quality response in both GPTs, their impact was significant only for clarity.

Cloze probability, predictability ratings, and computational estimates for 205 English sentences, aligned with existing EEG and reading time data

We release a database of cloze probability values, predictability ratings, and computational estimates for a sample of 205 English sentences (1726 words), aligned with previously released word-by-word reading time data (both self-paced reading and eye-movement records; Frank et al., Behavior Research Methods, 45(4), 1182-1190. 2013) and EEG responses (Frank et al., Brain and Language, 140, 1-11. 2015). Our analyses show that predictability ratings are the best predictors of the EEG signal (N400, P600, LAN) self-paced reading times, and eye movement patterns, when spillover effects are taken into account. The computational estimates are particularly effective at explaining variance in the eye-tracking data without spillover. Cloze probability estimates have decent overall psychometric accuracy and are the best predictors of early fixation patterns (first fixation duration). Our results indicate that the choice of the best measurement of word predictability in context critically depends on the processing index being considered.

Artificial intelligence in maxillofacial and facial plastic and reconstructive surgery

PURPOSE OF REVIEW

To provide a current review of artificial intelligence and its subtypes in maxillofacial and facial plastic surgery including a discussion of implications and ethical concerns.

RECENT FINDINGS

Artificial intelligence has gained popularity in recent years due to technological advancements. The current literature has begun to explore the use of artificial intelligence in various medical fields, but there is limited contribution to maxillofacial and facial plastic surgery due to the wide variance in anatomical facial features as well as subjective influences. In this review article, we found artificial intelligence's roles, so far, are to automatically update patient records, produce 3D models for preoperative planning, perform cephalometric analyses, and provide diagnostic evaluation of oropharyngeal malignancies.

SUMMARY

Artificial intelligence has solidified a role in maxillofacial and facial plastic surgery within the past few years. As high-quality databases expand with more patients, the role for artificial intelligence to assist in more complicated and unique cases becomes apparent. Despite its potential, ethical questions have been raised that should be noted as artificial intelligence continues to thrive. These questions include concerns such as compromise of the physician-patient relationship and healthcare justice.

A review of self-supervised, generative, and few-shot deep learning methods for data-limited magnetic resonance imaging segmentation

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical-level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state-of-the-art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self-supervised learning, generative models, few-shot learning, and semi-supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field-including emerging algorithms, such as contrastive language-image pretraining, and potential combinations across the methods discussed-that can further increase the efficacy of image segmentation with limited labels.

The Role of Artificial Intelligence in Medical Education: A Systematic Review

BACKGROUND

To examine the artificial intelligence (AI) tools currently being studied in modern medical education, and critically evaluate the level of validation and the quality of evidence presented in each individual study.

METHODS

This review (PROSPERO ID: CRD42023410752) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. A database search was conducted using PubMed, Embase, and Cochrane Library. Articles written in the English language between 2000 and March 2023 were reviewed retrospectively using the MeSH Terms "AI" and "medical education" A total of 4642 potentially relevant studies were found.

RESULTS

After a thorough screening process, 36 studies were included in the final analysis. These studies consisted of 26 quantitative studies and 10 studies investigated the development and validation of AI tools. When examining the results of studies in which Support vector machines (SVMs) were employed, it has demonstrated high accuracy in assessing students' experiences, diagnosing acute abdominal pain, classifying skilled and novice participants, and evaluating surgical training levels. Particularly in the comparison of surgical skill levels, it has achieved an accuracy rate of over 92%.

CONCLUSION

AI tools demonstrated effectiveness in improving practical skills, diagnosing diseases, and evaluating student performance. However, further research with rigorous validation is required to identify the most effective AI tools for medical education.

Relationship Between Nonsmoothness in Adversarial Training, Constraints of Attacks, and Flatness in the Input Space

Adversarial training (AT) is a promising method to improve the robustness against adversarial attacks. However, its performance is not still satisfactory in practice compared with standard training. To reveal the cause of the difficulty of AT, we analyze the smoothness of the loss function in AT, which determines the training performance. We reveal that nonsmoothness is caused by the constraint of adversarial attacks and depends on the type of constraint. Specifically, the L∞ constraint can cause nonsmoothness more than the L2 constraint. In addition, we found an interesting property for AT: the flatter loss surface in the input space tends to have the less smooth adversarial loss surface in the parameter space. To confirm that the nonsmoothness causes the poor performance of AT, we theoretically and experimentally show that smooth adversarial loss by EntropySGD (EnSGD) improves the performance of AT.

Enhanced analysis of large-scale news text data using the bidirectional-Kmeans-LSTM-CNN model

Traditional methods may be inefficient when processing large-scale data in the field of text mining, often struggling to identify and cluster relevant information accurately and efficiently. Additionally, capturing nuanced sentiment and emotional context within news text is challenging with conventional techniques. To address these issues, this article introduces an improved bidirectional-Kmeans-long short-term memory network-convolutional neural network (BiK-LSTM-CNN) model that incorporates emotional semantic analysis for high-dimensional news text visual extraction and media hotspot mining. The BiK-LSTM-CNN model comprises four modules: news text preprocessing, news text clustering, sentiment semantic analysis, and the BiK-LSTM-CNN model itself. By combining these components, the model effectively identifies common features within the input data, clusters similar news articles, and accurately analyzes the emotional semantics of the text. This comprehensive approach enhances both the accuracy and efficiency of visual extraction and hotspot mining. Experimental results demonstrate that compared to models such as Transformer, AdvLSTM, and NewRNN, BiK-LSTM-CNN achieves improvements in macro accuracy by 0.50%, 0.91%, and 1.34%, respectively. Similarly, macro recall rates increase by 0.51%, 1.24%, and 1.26%, while macro F1 scores improve by 0.52%, 1.23%, and 1.92%. Additionally, the BiK-LSTM-CNN model shows significant improvements in time efficiency, further establishing its potential as a more effective approach for processing and analyzing large-scale text data.

Applied artificial intelligence for global child health: Addressing biases and barriers

Given the potential benefits of artificial intelligence and machine learning (AI/ML) within healthcare, it is critical to consider how these technologies can be deployed in pediatric research and practice. Currently, healthcare AI/ML has not yet adapted to the specific technical considerations related to pediatric data nor adequately addressed the specific vulnerabilities of children and young people (CYP) in relation to AI. While the greatest burden of disease in CYP is firmly concentrated in lower and middle-income countries (LMICs), existing applied pediatric AI/ML efforts are concentrated in a small number of high-income countries (HICs). In LMICs, use-cases remain primarily in the proof-of-concept stage. This narrative review identifies a number of intersecting challenges that pose barriers to effective AI/ML for CYP globally and explores the shifts needed to make progress across multiple domains. Child-specific technical considerations throughout the AI/ML lifecycle have been largely overlooked thus far, yet these can be critical to model effectiveness. Governance concerns are paramount, with suitable national and international frameworks and guidance required to enable the safe and responsible deployment of advanced technologies impacting the care of CYP and using their data. An ambitious vision for child health demands that the potential benefits of AI/Ml are realized universally through greater international collaboration, capacity building, strong oversight, and ultimately diffusing the AI/ML locus of power to empower researchers and clinicians globally. In order that AI/ML systems that do not exacerbate inequalities in pediatric care, teams researching and developing these technologies in LMICs must ensure that AI/ML research is inclusive of the needs and concerns of CYP and their caregivers. A broad, interdisciplinary, and human-centered approach to AI/ML is essential for developing tools for healthcare workers delivering care, such that the creation and deployment of ML is grounded in local systems, cultures, and clinical practice. Decisions to invest in developing and testing pediatric AI/ML in resource-constrained settings must always be part of a broader evaluation of the overall needs of a healthcare system, considering the critical building blocks underpinning effective, sustainable, and cost-efficient healthcare delivery for CYP.

Deep survival analysis for interpretable time-varying prediction of preeclampsia risk

OBJECTIVE

Survival analysis is widely utilized in healthcare to predict the timing of disease onset. Traditional methods of survival analysis are usually based on Cox Proportional Hazards model and assume proportional risk for all subjects. However, this assumption is rarely true for most diseases, as the underlying factors have complex, non-linear, and time-varying relationships. This concern is especially relevant for pregnancy, where the risk for pregnancy-related complications, such as preeclampsia, varies across gestation. Recently, deep learning survival models have shown promise in addressing the limitations of classical models, as the novel models allow for non-proportional risk handling, capturing nonlinear relationships, and navigating complex temporal dynamics.

METHODS

We present a methodology to model the temporal risk of preeclampsia during pregnancy and investigate the associated clinical risk factors. We utilized a retrospective dataset including 66,425 pregnant individuals who delivered in two tertiary care centers from 2015 to 2023. We modeled the preeclampsia risk by modifying DeepHit, a deep survival model, which leverages neural network architecture to capture time-varying relationships between covariates in pregnancy. We applied time series k-means clustering to DeepHit's normalized output and investigated interpretability using Shapley values.

RESULTS

We demonstrate that DeepHit can effectively handle high-dimensional data and evolving risk hazards over time with performance similar to the Cox Proportional Hazards model, achieving an area under the curve (AUC) of 0.78 for both models. The deep survival model outperformed traditional methodology by identifying time-varied risk trajectories for preeclampsia, providing insights for early and individualized intervention. K-means clustering resulted in patients delineating into low-risk, early-onset, and late-onset preeclampsia groups-notably, each of those has distinct risk factors.

CONCLUSION

This work demonstrates a novel application of deep survival analysis in time-varying prediction of preeclampsia risk. Our results highlight the advantage of deep survival models compared to Cox Proportional Hazards models in providing personalized risk trajectory and demonstrating the potential of deep survival models to generate interpretable and meaningful clinical applications in medicine.

Attention-Aware Non-Rigid Image Registration for Accelerated MR Imaging

Accurate motion estimation at high acceleration factors enables rapid motion-compensated reconstruction in Magnetic Resonance Imaging (MRI) without compromising the diagnostic image quality. In this work, we introduce an attention-aware deep learning-based framework that can perform non-rigid pairwise registration for fully sampled and accelerated MRI. We extract local visual representations to build similarity maps between the registered image pairs at multiple resolution levels and additionally leverage long-range contextual information using a transformer-based module to alleviate ambiguities in the presence of artifacts caused by undersampling. We combine local and global dependencies to perform simultaneous coarse and fine motion estimation. The proposed method was evaluated on in-house acquired fully sampled and accelerated data of 101 patients and 62 healthy subjects undergoing cardiac and thoracic MRI. The impact of motion estimation accuracy on the downstream task of motion-compensated reconstruction was analyzed. We demonstrate that our model derives reliable and consistent motion fields across different sampling trajectories (Cartesian and radial) and acceleration factors of up to 16x for cardiac motion and 30x for respiratory motion and achieves superior image quality in motion-compensated reconstruction qualitatively and quantitatively compared to conventional and recent deep learning-based approaches. The code is publicly available at https://github.com/lab-midas/GMARAFT.