Perspectives on label-free microscopy of heterogeneous and dynamic biological systems.

Significance: Advancements in label-free microscopy could provide real-time, non-invasive imaging with unique sources of contrast and automated standardized analysis to characterize heterogeneous and dynamic biological processes. These tools would overcome challenges with widely used methods that are destructive (e.g., histology, flow cytometry) or lack cellular resolution (e.g., plate-based assays, whole animal bioluminescence imaging). Aim: This perspective aims to (1) justify the need for label-free microscopy to track heterogeneous cellular functions over time and space within unperturbed systems and (2) recommend improvements regarding instrumentation, image analysis, and image interpretation to address these needs. Approach: Three key research areas (cancer research, autoimmune disease, and tissue and cell engineering) are considered to support the need for label-free microscopy to characterize heterogeneity and dynamics within biological systems. Based on the strengths (e.g., multiple sources of molecular contrast, non-invasive monitoring) and weaknesses (e.g., imaging depth, image interpretation) of several label-free microscopy modalities, improvements for future imaging systems are recommended. Conclusion: Improvements in instrumentation including strategies that increase resolution and imaging speed, standardization and centralization of image analysis tools, and robust data validation and interpretation will expand the applications of label-free microscopy to study heterogeneous and dynamic biological systems.

ChatGPT es un estudiante por encima de la media en la Facultad de Medicina de la Universidad de Zaragoza y un colaborador excelente en la elaboración de material docente / ChatGPT is an above-average student at the Faculty of Medicine of the University of Zaragoza and an excellent collaborator in the development of teaching materials

Introducción y objetivo: La inteligencia artificial se halla plenamente presente en nuestras vidas. En educación las posibilidades de su uso son infinitas, tanto para alumnos como para docentes. Material y métodos: Se ha explorado la capacidad de ChatGPT a la hora de resolver preguntas tipo test a partir del examen de la asignatura Procedimientos Diagnósticos y Terapéuticos Anatomopatológicos de la primera convocatoria del curso 2022-2023. Además de comparar su resultado con el del resto de alumnos presentados, se han evaluado las posibles causas de las respuestas incorrectas. Finalmente, se ha evaluado su capacidad para realizar preguntas de test nuevas a partir de instrucciones específicas. Resultados: ChatGPT ha acertado 47 de las 68 preguntas planteadas, obteniendo una nota superior a la de la media y mediana del curso. La mayor parte de preguntas falladas presentan enunciados negativos, utilizando las palabras «no», «falsa» o «incorrecta» en su enunciado. Tras interactuar con él, el programa es capaz de darse cuenta de su error y cambiar su respuesta inicial por la correcta. Finalmente, ChatGPT sabe elaborar nuevas preguntas a partir de un supuesto teórico o bien de una simulación clínica determinada. Conclusiones: Como docentes estamos obligados a explorar las utilidades de la inteligencia artificial, e intentar usarla en nuestro beneficio. La realización de tareas que suponen un consumo de tipo importante, como puede ser la elaboración de preguntas tipo test para evaluación de contenidos, es un buen ejemplo. (AU)

Introduction and objective: Artificial intelligence is fully present in our lives. In education, the possibilities of its use are endless, both for students and teachers. Material and methods: The capacity of ChatGPT has been explored when solving multiple choice questions based on the exam of the subject «Anatomopathological Diagnostic and Therapeutic Procedures» of the first call of the 2022-23 academic year. In addition, to comparing their results with those of the rest of the students presented the probable causes of incorrect answers have been evaluated. Finally, its ability to formulate new test questions based on specific instructions has been evaluated. Results: ChatGPT correctly answered 47 out of 68 questions, achieving a grade higher than the course average and median. Most failed questions present negative statements, using the words «no», «false» or «incorrect» in their statement. After interacting with it, the program can realize its mistake and change its initial response to the correct answer. Finally, ChatGPT can develop new questions based on a theoretical assumption or a specific clinical simulation. Conclusions: As teachers we are obliged to explore the uses of artificial intelligence and try to use it to our benefit. Carrying out tasks that involve significant consumption, such as preparing multiple-choice questions for content evaluation, is a good example. (AU)

Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

Artificial intelligence-based prescription of personalized scalp cosmetics improved the scalp condition: efficacy results from 100 participants.

Background: Scalp-related symptoms such as dandruff and itching are common with diverse underlying etiologies. We previously proposed a novel classification and scoring system for scalp conditions, called the scalp photographic index (SPI); it grades five scalp features using trichoscopic images with good reliability. However, it requires trained evaluators.Aim: To develop artificial intelligence (AI) algorithms for assessment of scalp conditions and to assess the feasibility of AI-based recommendations on personalized scalp cosmetics.Methods: Using EfficientNet, convolutional neural network (CNN) models (SPI-AI) ofeach scalp feature were established. 101,027 magnified scalp images graded according to the SPI scoring were used for training, validation, and testing the model Adults with scalp discomfort were prescribed shampoos and scalp serums personalized according to their SPI-AI-defined scalp types. Using the SPI, the scalp conditions were evaluated at baseline and at weeks 4, 8, and 12 of treatment.Results: The accuracies of the SPI-AI for dryness, oiliness, erythema, folliculitis, and dandruff were 91.3%, 90.5%, 89.6%, 87.3%, and 95.2%, respectively. Overall, 100 individuals completed the 4-week study; 43 of these participated in an extension study until week 12. The total SPI score decreased from 32.70 ± 7.40 at baseline to 15.97 ± 4.68 at week 4 (p < 0.001). The efficacy was maintained throughout 12 weeks.Conclusions: SPI-AI accurately assessed the scalp condition. AI-based prescription of tailored scalp cosmetics could significantly improve scalp health.

Advancements in Barrett's esophagus detection: The role of artificial intelligence and its implications.

Artificial intelligence (AI) is making significant strides in revolutionizing the detection of Barrett's esophagus (BE), a precursor to esophageal adenocarcinoma. In the research article by Tsai et al, researchers utilized endoscopic images to train an AI model, challenging the traditional distinction between endoscopic and histological BE. This approach yielded remarkable results, with the AI system achieving an accuracy of 94.37%, sensitivity of 94.29%, and specificity of 94.44%. The study's extensive dataset enhances the AI model's practicality, offering valuable support to endoscopists by minimizing unnecessary biopsies. However, questions about the applicability to different endoscopic systems remain. The study underscores the potential of AI in BE detection while highlighting the need for further research to assess its adaptability to diverse clinical settings.

Advancements in technology for characterizing the tumor immune microenvironment.

Immunotherapy plays a key role in cancer treatment, however, responses are limited to a small number of patients. The biological basis for the success of immunotherapy is the complex interaction between tumor cells and tumor immune microenvironment (TIME). Historically, research on tumor immune constitution was limited to the analysis of one or two markers, more novel technologies are needed to interpret the complex interactions between tumor cells and TIME. In recent years, major advances have already been made in depicting TIME at a considerably elevated degree of throughput, dimensionality and resolution, allowing dozens of markers to be labeled simultaneously, and analyzing the heterogeneity of tumour-immune infiltrates in detail at the single cell level, depicting the spatial landscape of the entire microenvironment, as well as applying artificial intelligence (AI) to interpret a large amount of complex data from TIME. In this review, we summarized emerging technologies that have made contributions to the field of TIME, and provided prospects for future research.

Managing Risk and Quality of AI in Healthcare: Are Hospitals Ready for Implementation?

Artificial intelligence (AI) provides a unique opportunity to help meet the demands of the future healthcare system. However, hospitals may not be well equipped to handle safe and effective development and/or procurement of AI systems. Furthermore, upcoming regulations such as the EU AI Act may enforce the need to establish new management systems, quality assurance and control mechanisms, novel to healthcare organizations. This paper discusses challenges in AI implementation, particularly potential gaps in current management systems (MS), by reviewing the harmonized standard for AI MS, ISO 42001, as part of a gap analysis of a tertiary acute hospital with ongoing AI activities. Examination of the industry agnostic ISO 42001 reveals a technical debt within healthcare, aligning with previous research on digitalization and AI implementation. To successfully implement AI with quality assurance in mind, emphasis should be put on the foundation and structure of the healthcare organizations, including both workforce and data infrastructure.

Review of approaches to the use of unmanned aerial vehicles, remote sensing and geographic information systems in humanitarian demining: Ukrainian case.

The history of the use of mines dates back almost two centuries. The geography of their use and the associated social harm have made them, without exaggeration, a global problem. At the same time, searches were underway for safe methods of their neutralization using various technical means. In so doing, until now, none of the existing methods provides a 100% guarantee of cleaning the territory, which determines the purpose of finding innovative methods and the possibility of combining them with existing ones. Unmanned aerial vehicles (UAVs) are becoming a real modern breakthrough in the field of intellectual achievements. Obtaining optimal results when solving a wide range of different problems, together with the development of composite materials, software, and the latest navigation equipment, make the tasks assigned to them and the expected results more and more difficult. UAVs allow people not to be in life-threatening conditions, to conduct activities beyond their physiological and psychophysiological abilities. The combination of the ability to collect spatial data during flight in various ranges of remote sensing with the possibility of carrying variants of useful equipment opens up prospects for their use in the field of demining territories. Supplementing UAV technologies with modern information systems for processing and analysis of information (expert systems, machine learning, computational intelligence, distributed artificial intelligence, neural networks, etc.), including spatial geographic information systems (GIS), opens up great prospects in the field of humanitarian demining of territories.

Now you see me, now you don't: an exploration of religious exnomination in DALL-E.

Artificial intelligence (AI) systems are increasingly being used not only to classify and analyze but also to generate images and text. As recent work on the content produced by text and image Generative AIs has shown (e.g., Cheong et al., 2024, Acerbi & Stubbersfield, 2023), there is a risk that harms of representation and bias, already documented in prior AI and natural language processing (NLP) algorithms may also be present in generative models. These harms relate to protected categories such as gender, race, age, and religion. There are several kinds of harms of representation to consider in this context, including stereotyping, lack of recognition, denigration, under-representation, and many others (Crawford in Soundings 41:45-55, 2009; in: Barocas et al., SIGCIS Conference, 2017). Whereas the bulk of researchers' attention thus far has been given to stereotyping and denigration, in this study we examine 'exnomination', as conceived by Roland Barthes (1972), of religious groups. Our case study is DALL-E, a tool that generates images from natural language prompts. Using DALL-E mini, we generate images from generic prompts such as "religious person." We then examine whether the generated images are recognizably members of a nominated group. Thus, we assess whether the generated images normalize some religions while neglecting others. We hypothesize that Christianity will be recognizably represented more frequently than other religious groups. Our results partially support this hypothesis but introduce further complexities, which we then explore.

Quantitative analysis of mandibular cortical morphology using artificial intelligence-based computer assisted diagnosis for panoramic radiography on underlying diseases and dental status in women over 20 years of age.

Background/purpose: Recently, an artificial intelligence-based computer-assisted diagnosis (AI-CAD) for panoramic radiography was developed to scan the inferior margin of the mandible and automatically evaluate mandibular cortical morphology. The aim of this study was to analyze quantitatively the mandibular cortical morphology using the AI-CAD, especially focusing on underlying diseases and dental status in women over 20 years of age. Materials and methods: 419 patients in women over 20 years of age who underwent panoramic radiography were included in this study. The mandibular cortical morphology was analyzed with an AI-CAD that evaluated the degree of deformation of the mandibular inferior cortex (MIC) and mandibular cortical index (MCI) automatically. Those were analyzed in relation to underlying diseases, such as diabetes, hypertension, dyslipidemia, rheumatism and osteoporosis, and dental status, such as the number of teeth present in the maxilla and mandible. Results: The degree of deformation of MIC in women under 51 years of age (21-50 years; n = 229, 16.0 ± 12.7) was significantly lower than those of over 50 years of age (51-90 years; n = 190, 45.1 ± 23.0), and the MCI was a significant difference for the different age group. Regarding the degree of deformation of MIC and MCI in women over 50 years of age, osteoporosis and number of total teeth present in the maxilla and mandible were significant differences. Conclusion: The results of this study indicated that the mandibular cortical morphology using the AI-CAD is significantly related to osteoporosis and dental status in women over 50 years of age.

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.

Generative Artificial Intelligence Performs at a Second-Year Orthopedic Resident Level.

Introduction Artificial intelligence (AI) models using large language models (LLMs) and non-specific domains have gained attention for their innovative information processing. As AI advances, it's essential to regularly evaluate these tools' competency to maintain high standards, prevent errors or biases, and avoid flawed reasoning or misinformation that could harm patients or spread inaccuracies. Our study aimed to determine the performance of Chat Generative Pre-trained Transformer (ChatGPT) by OpenAI and Google BARD (BARD) in orthopedic surgery, assess performance based on question types, contrast performance between different AIs and compare AI performance to orthopedic residents. Methods We administered ChatGPT and BARD 757 Orthopedic In-Training Examination (OITE) questions. After excluding image-related questions, the AIs answered 390 multiple choice questions, all categorized within 10 sub-specialties (basic science, trauma, sports medicine, spine, hip and knee, pediatrics, oncology, shoulder and elbow, hand, and food and ankle) and three taxonomy classes (recall, interpretation, and application of knowledge). Statistical analysis was performed to analyze the number of questions answered correctly by each AI model, the performance returned by each AI model within the categorized question sub-specialty designation, and the performance of each AI model in comparison to the results returned by orthopedic residents classified by their respective post-graduate year (PGY) level. Results BARD answered more overall questions correctly (58% vs 54%, p<0.001). ChatGPT performed better in sports medicine and basic science and worse in hand surgery, while BARD performed better in basic science (p<0.05). The AIs performed better in recall questions compared to the application of knowledge (p<0.05). Based on previous data, it ranked in the 42nd-96th percentile for post-graduate year ones (PGY1s), 27th-58th for PGY2s, 3rd-29th for PGY3s, 1st-21st for PGY4s, and 1st-17th for PGY5s. Discussion ChatGPT excelled in sports medicine but fell short in hand surgery, while both AIs performed well in the basic science sub-specialty but performed poorly in the application of knowledge-based taxonomy questions. BARD performed better than ChatGPT overall. Although the AI reached the second-year PGY orthopedic resident level, it fell short of passing the American Board of Orthopedic Surgery (ABOS). Its strengths in recall-based inquiries highlight its potential as an orthopedic learning and educational tool.

Performance of ChatGPT vs. HuggingChat on OB-GYN Topics.

Background While large language models show potential as beneficial tools in medicine, their reliability, especially in the realm of obstetrics and gynecology (OB-GYN), is not fully comprehended. This study seeks to measure and contrast the performance of ChatGPT and HuggingChat in addressing OB-GYN-related medical examination questions, offering insights into their effectiveness in this specialized field. Methods ChatGPT and HuggingChat were subjected to two standardized multiple-choice question banks: Test 1, developed by the National Board of Medical Examiners (NBME), and Test 2, gathered from the Association of Professors of Gynecology & Obstetrics (APGO) Web-Based Interactive Self-Evaluation (uWISE). Responses were analyzed and compared for correctness. Results The two-proportion z-test revealed no statistically significant difference in performance between ChatGPT and HuggingChat on both medical examinations. For Test 1, ChatGPT scored 90%, while HuggingChat scored 85% (p = 0.6). For Test 2, ChatGPT correctly answered 70% of questions, while HuggingChat correctly answered 62% of questions (p = 0.4). Conclusion Awareness of the strengths and weaknesses of artificial intelligence allows for the proper and effective use of its knowledge. Our findings indicate that there is no statistically significant difference in performance between ChatGPT and HuggingChat in addressing medical inquiries. Nonetheless, both platforms demonstrate considerable promise for applications within the medical domain.

Folk psychological attributions of consciousness to large language models.

Technological advances raise new puzzles and challenges for cognitive science and the study of how humans think about and interact with artificial intelligence (AI). For example, the advent of large language models and their human-like linguistic abilities has raised substantial debate regarding whether or not AI could be conscious. Here, we consider the question of whether AI could have subjective experiences such as feelings and sensations ('phenomenal consciousness'). While experts from many fields have weighed in on this issue in academic and public discourse, it remains unknown whether and how the general population attributes phenomenal consciousness to AI. We surveyed a sample of US residents (n = 300) and found that a majority of participants were willing to attribute some possibility of phenomenal consciousness to large language models. These attributions were robust, as they predicted attributions of mental states typically associated with phenomenality-but also flexible, as they were sensitive to individual differences such as usage frequency. Overall, these results show how folk intuitions about AI consciousness can diverge from expert intuitions-with potential implications for the legal and ethical status of AI.

Application of AI in Sepsis: Citation Network Analysis and Evidence Synthesis.

BACKGROUND: Artificial intelligence (AI) has garnered considerable attention in the context of sepsis research, particularly in personalized diagnosis and treatment. Conducting a bibliometric analysis of existing publications can offer a broad overview of the field and identify current research trends and future research directions. OBJECTIVE: The objective of this study is to leverage bibliometric data to provide a comprehensive overview of the application of AI in sepsis. METHODS: We conducted a search in the Web of Science Core Collection database to identify relevant articles published in English until August 31, 2023. A predefined search strategy was used, evaluating titles, abstracts, and full texts as needed. We used the Bibliometrix and VOSviewer tools to visualize networks showcasing the co-occurrence of authors, research institutions, countries, citations, and keywords. RESULTS: A total of 259 relevant articles published between 2014 and 2023 (until August) were identified. Over the past decade, the annual publication count has consistently risen. Leading journals in this domain include Critical Care Medicine (17/259, 6.6%), Frontiers in Medicine (17/259, 6.6%), and Scientific Reports (11/259, 4.2%). The United States (103/259, 39.8%), China (83/259, 32%), United Kingdom (14/259, 5.4%), and Taiwan (12/259, 4.6%) emerged as the most prolific countries in terms of publications. Notable institutions in this field include the University of California System, Emory University, and Harvard University. The key researchers working in this area include Ritankar Das, Chris Barton, and Rishikesan Kamaleswaran. Although the initial period witnessed a relatively low number of articles focused on AI applications for sepsis, there has been a significant surge in research within this area in recent years (2014-2023). CONCLUSIONS: This comprehensive analysis provides valuable insights into AI-related research conducted in the field of sepsis, aiding health care policy makers and researchers in understanding the potential of AI and formulating effective research plans. Such analysis serves as a valuable resource for determining the advantages, sustainability, scope, and potential impact of AI models in sepsis.

AI-powered COVID-19 forecasting: a comprehensive comparison of advanced deep learning methods.

Objectives: The coronavirus disease 2019 (COVID-19) pandemic continues to pose significant challenges to the public health sector, including that of the United Arab Emirates (UAE). The objective of this study was to assess the efficiency and accuracy of various deep-learning models in forecasting COVID-19 cases within the UAE, thereby aiding the nation's public health authorities in informed decision-making. Methods: This study utilized a comprehensive dataset encompassing confirmed COVID-19 cases, demographic statistics, and socioeconomic indicators. Several advanced deep learning models, including long short-term memory (LSTM), bidirectional LSTM, convolutional neural network (CNN), CNN-LSTM, multilayer perceptron, and recurrent neural network (RNN) models, were trained and evaluated. Bayesian optimization was also implemented to fine-tune these models. Results: The evaluation framework revealed that each model exhibited different levels of predictive accuracy and precision. Specifically, the RNN model outperformed the other architectures even without optimization. Comprehensive predictive and perspective analytics were conducted to scrutinize the COVID-19 dataset. Conclusion: This study transcends academic boundaries by offering critical insights that enable public health authorities in the UAE to deploy targeted data-driven interventions. The RNN model, which was identified as the most reliable and accurate for this specific context, can significantly influence public health decisions. Moreover, the broader implications of this research validate the capability of deep learning techniques in handling complex datasets, thus offering the transformative potential for predictive accuracy in the public health and healthcare sectors.

Constructing synthetic datasets with generative artificial intelligence to train large language models to classify acute renal failure from clinical notes.

OBJECTIVES: To compare performances of a classifier that leverages language models when trained on synthetic versus authentic clinical notes. MATERIALS AND METHODS: A classifier using language models was developed to identify acute renal failure. Four types of training data were compared: (1) notes from MIMIC-III; and (2, 3, and 4) synthetic notes generated by ChatGPT of varied text lengths of 15 (GPT-15 sentences), 30 (GPT-30 sentences), and 45 (GPT-45 sentences) sentences, respectively. The area under the receiver operating characteristics curve (AUC) was calculated from a test set from MIMIC-III. RESULTS: With RoBERTa, the AUCs were 0.84, 0.80, 0.84, and 0.76 for the MIMIC-III, GPT-15, GPT-30- and GPT-45 sentences training sets, respectively. DISCUSSION: Training language models to detect acute renal failure from clinical notes resulted in similar performances when using synthetic versus authentic training data. CONCLUSION: The use of training data derived from protected health information may not be needed.

Performance of ChatGPT on Factual Knowledge Questions Regarding Clinical Pharmacy.

ChatGPT is a language model that was trained on a large dataset including medical literature. Several studies have described the performance of ChatGPT on medical exams. In this study, we examine its performance in answering factual knowledge questions regarding clinical pharmacy. Questions were obtained from a Dutch application that features multiple-choice questions to maintain a basic knowledge level for clinical pharmacists. In total, 264 clinical pharmacy-related questions were presented to ChatGPT and responses were evaluated for accuracy, concordance, quality of the substantiation, and reproducibility. Accuracy was defined as the correctness of the answer, and results were compared to the overall score by pharmacists over 2022. Responses were marked concordant if no contradictions were present. The quality of the substantiation was graded by two independent pharmacists using a 4-point scale. Reproducibility was established by presenting questions multiple times and on various days. ChatGPT yielded accurate responses for 79% of the questions, surpassing pharmacists' accuracy of 66%. Concordance was 95%, and the quality of the substantiation was deemed good or excellent for 73% of the questions. Reproducibility was consistently high, both within day and between days (>92%), as well as across different users. ChatGPT demonstrated a higher accuracy and reproducibility to factual knowledge questions related to clinical pharmacy practice than pharmacists. Consequently, we posit that ChatGPT could serve as a valuable resource to pharmacists. We hope the technology will further improve, which may lead to enhanced future performance.

Enhancing IEP Goal Development for Preschoolers with Autism: A Preliminary Study on ChatGPT Integration.

PURPOSE: The impact of well-crafted IEP goals on student outcomes is well-documented, but creating high-quality goals can be a challenging task for many special education teachers. This study aims to investigate potential effectiveness of using ChatGPT, an AI technology, in supporting development of high-quality, individualized IEP goals for preschool children with autism. METHODS: Thirty special education teachers working with preschool children with autism were randomly assigned to either the ChatGPT or control groups. Both groups received written guidelines on how to write SMART IEP goals, but only the ChatGPT group was given handout on how to use ChatGPT during IEP goal writing process. Quality of IEP goals written by the two groups was compared using a two-sample t-test, and categorization of goals by developmental domains was reported using frequency counts. RESULTS: Results indicate that using ChatGPT significantly improved the quality of IEP goals developed by special education teachers compared to those who did not use the technology. Teachers in the ChatGPT group had a higher proportion of goals targeting communication, social skills, motor/sensory, and self-care skills, while teachers in the control group had a higher proportion of goals targeting preacademic skills and behaviors. CONCLUSION: The potential of ChatGPT as an effective tool for supporting special education teachers in developing high-quality IEP goals suggests promising implications for improving outcomes for preschool children with autism. Its integration may offer valuable assistance in tailoring individualized goals to meet the diverse needs of students in special education settings.

Advocating for population health: The role of public health practitioners in the age of artificial intelligence.

Over the past decade, artificial intelligence (AI) has begun to transform Canadian organizations, driven by the promise of improved efficiency, better decision-making, and enhanced client experience. While AI holds great opportunities, there are also near-term impacts on the determinants of health and population health equity that are already emerging. If adoption is unregulated, there is a substantial risk that health inequities could be exacerbated through intended or unintended biases embedded in AI systems. New economic opportunities could be disproportionately leveraged by already privileged workers and owners of AI systems, reinforcing prevailing power dynamics. AI could also detrimentally affect population well-being by replacing human interactions rather than fostering social connectedness. Furthermore, AI-powered health misinformation could undermine effective public health communication. To respond to these challenges, public health must assess and report on the health equity impacts of AI, inform implementation to reduce health inequities, and facilitate intersectoral partnerships to foster development of policies and regulatory frameworks to mitigate risks. This commentary highlights AI's near-term risks for population health to inform a public health response.

RéSUMé: Au cours de la dernière décennie, l'intelligence artificielle (IA) a commencé à transformer les organismes canadiens en leur promettant une plus grande efficience, de meilleurs processus décisionnels et une expérience client enrichie. Bien qu'elle recèle d'immenses possibilités, l'IA aura des effets à court terme ­ qui se font d'ailleurs déjà sentir ­ sur les déterminants de la santé et sur l'équité en santé des populations. Si son adoption n'est pas réglementée, il se peut très bien que les iniquités en santé continuent d'être exacerbées par les préjugés, intentionnels ou non, ancrés dans les systèmes d'IA. Les nouvelles possibilités économiques pourraient être démesurément exploitées par les travailleurs et les travailleuses déjà privilégiés et par les propriétaires des systèmes d'IA, renforçant ainsi la dynamique de pouvoir existante. L'IA pourrait aussi nuire au bien-être des populations en remplaçant les interactions humaines au lieu de favoriser la connexité sociale. De plus, la mésinformation sur la santé alimentée par l'IA pourrait réduire l'efficacité des messages de santé publique. Pour relever ces défis, la santé publique devra évaluer et communiquer les effets de l'IA sur l'équité en santé, en modérer la mise en œuvre pour réduire les iniquités en santé, et faciliter des partenariats intersectoriels pour éclairer l'élaboration de politiques et de cadres réglementaires d'atténuation des risques. Le présent commentaire fait ressortir les risques à court terme de l'IA pour la santé des populations afin d'éclairer la riposte de la santé publique.