Are members of marginalized communities silenced on social media when they share personal experiences of racism? Here, we investigate the role of algorithms, humans, and platform guidelines in suppressing disclosures of racial discrimination. In a field study of actual posts from a neighborhood-based social media platform, we find that when users talk about their experiences as targets of racism, their posts are disproportionately flagged for removal as toxic by five widely used moderation algorithms from major online platforms, including the most recent large language models. We show that human users disproportionately flag these disclosures for removal as well. Next, in a follow-up experiment, we demonstrate that merely witnessing such suppression negatively influences how Black Americans view the community and their place in it. Finally, to address these challenges to equity and inclusion in online spaces, we introduce a mitigation strategy: a guideline-reframing intervention that is effective at reducing silencing behavior across the political spectrum.

OBJECTIVE: To compare the performance of large language model (LLM) based Gemini and Generative Pre-trained Transformers (GPTs) in data mining and generating structured reports based on free-text PET/CT reports for breast cancer after user-defined tasks.
METHODS: Breast cancer patients (mean age, 50 years ± 11 [SD]; all female) who underwent consecutive 18F-FDG PET/CT for follow-up between July 2005 and October 2023 were retrospectively included in the study. A total of twenty reports from 10 patients were used to train user-defined text prompts for Gemini and GPTs, by which structured PET/CT reports were generated. The natural language processing (NLP) generated structured reports and the structured reports annotated by nuclear medicine physicians were compared in terms of data extraction accuracy and capacity of progress decision-making. Statistical methods, including chi-square test, McNemar test and paired samples t-test, were employed in the study.
RESULTS: The structured PET/CT reports for 131 patients were generated by using the two NLP techniques, including Gemini and GPTs. In general, GPTs exhibited superiority over Gemini in data mining in terms of primary lesion size (89.6% vs. 53.8%, p < 0.001) and metastatic lesions (96.3% vs 89.6%, p < 0.001). Moreover, GPTs outperformed Gemini in making decision for progress (p < 0.001) and semantic similarity (F1 score 0.930 vs 0.907, p < 0.001) for reports.
CONCLUSIONS: GPTs outperformed Gemini in generating structured reports based on free-text PET/CT reports, which is potentially applied in clinical practice.
METHODS: The data used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Extended reality (XR) simulations are becoming increasingly common in educational settings, particularly in medical education. Advancing XR devices to enhance these simulations is a booming field of research. This study seeks to understand the value of a novel, non-wearable mixed reality (MR) display during interactions with a simulated holographic patient, specifically in taking a medical history. Twenty-one first-year medical students at the University of North Carolina at Chapel Hill participated in the virtual patient (VP) simulations. On a five-point Likert scale, students overwhelmingly agreed with the statement that the simulations helped ensure they were progressing along learning objectives related to taking a patient history. However, they found that, at present, the simulations can only partially correct mistakes or provide clear feedback. This finding demonstrates that the novel hardware solution can help students engage in the activity, but the underlying software may need adjustment to attain sufficient pedagogical validity.

Electronic Health Records (EHRs) contain a wealth of unstructured patient data, making it challenging for physicians to do informed decisions. In this paper, we introduce a Natural Language Processing (NLP) approach for the extraction of therapies, diagnosis, and symptoms from ambulatory EHRs of patients with chronic Lupus disease. We aim to demonstrate the effort of a comprehensive pipeline where a rule-based system is combined with text segmentation, transformer-based topic analysis and clinical ontology, in order to enhance text preprocessing and automate rules\' identification. Our approach is applied on a sub-cohort of 56 patients, with a total of 750 EHRs written in Italian language, achieving an Accuracy and an F-score over 97% and 90% respectively, in the three extracted domains. This work has the potential to be integrated with EHR systems to automate information extraction, minimizing the human intervention, and providing personalized digital solutions in the chronic Lupus disease domain.

Neurolinguistic assessments play a vital role in neurological examinations, revealing a wide range of language and communication impairments associated with developmental disorders and acquired neurological conditions. Yet, a thorough neurolinguistic assessment is time-consuming and laborious and takes valuable resources from other tasks. To empower clinicians, healthcare providers, and researchers, we have developed Open Brain AI (OBAI). The aim of this computational platform is twofold. First, it aims to provide advanced AI tools to facilitate spoken and written language analysis, automate the analysis process, and reduce the workload associated with time-consuming tasks. The platform currently incorporates multilingual tools for English, Danish, Dutch, Finnish, French, German, Greek, Italian, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, and Swedish. The tools involve models for (i) audio transcription, (ii) automatic translation, (iii) grammar error correction, (iv) transcription to the International Phonetic Alphabet, (v) readability scoring, (vi) phonology, morphology, syntax, semantic measures (e.g., counts and proportions), and lexical measures. Second, it aims to support clinicians in conducting their research and automating everyday tasks with \"OBAI Companion,\" an AI language assistant that facilitates language processing, such as structuring, summarizing, and editing texts. OBAI also provides tools for automating spelling and phonology scoring. This paper reviews OBAI\'s underlying architectures and applications and shows how OBAI can help professionals focus on higher-value activities, such as therapeutic interventions.

BACKGROUND: Medical decision-making is crucial for effective treatment, especially in psychiatry where diagnosis often relies on subjective patient reports and a lack of high-specificity symptoms. Artificial intelligence (AI), particularly Large Language Models (LLMs) like GPT, has emerged as a promising tool to enhance diagnostic accuracy in psychiatry. This comparative study explores the diagnostic capabilities of several AI models, including Aya, GPT-3.5, GPT-4, GPT-3.5 clinical assistant (CA), Nemotron, and Nemotron CA, using clinical cases from the DSM-5.
METHODS: We curated 20 clinical cases from the DSM-5 Clinical Cases book, covering a wide range of psychiatric diagnoses. Four advanced AI models (GPT-3.5 Turbo, GPT-4, Aya, Nemotron) were tested using prompts to elicit detailed diagnoses and reasoning. The models\' performances were evaluated based on accuracy and quality of reasoning, with additional analysis using the Retrieval Augmented Generation (RAG) methodology for models accessing the DSM-5 text.
RESULTS: The AI models showed varied diagnostic accuracy, with GPT-3.5 and GPT-4 performing notably better than Aya and Nemotron in terms of both accuracy and reasoning quality. While models struggled with specific disorders such as cyclothymic and disruptive mood dysregulation disorders, others excelled, particularly in diagnosing psychotic and bipolar disorders. Statistical analysis highlighted significant differences in accuracy and reasoning, emphasizing the superiority of the GPT models.
CONCLUSIONS: The application of AI in psychiatry offers potential improvements in diagnostic accuracy. The superior performance of the GPT models can be attributed to their advanced natural language processing capabilities and extensive training on diverse text data, enabling more effective interpretation of psychiatric language. However, models like Aya and Nemotron showed limitations in reasoning, indicating a need for further refinement in their training and application.
CONCLUSIONS: AI holds significant promise for enhancing psychiatric diagnostics, with certain models demonstrating high potential in interpreting complex clinical descriptions accurately. Future research should focus on expanding the dataset and integrating multimodal data to further enhance the diagnostic capabilities of AI in psychiatry.

The Languages of the Indian subcontinent are less represented in current NLP literature. To mitigate this gap, we present the IndicDialogue dataset, which contains subtitles and dialogues in 10 major Indic languages: Hindi, Bengali, Marathi, Telugu, Tamil, Urdu, Odia, Sindhi, Nepali, and Assamese. This dataset is sourced from OpenSubtitles.org, with subtitles pre-processed to remove irrelevant tags, timestamps, square brackets, and links, ensuring the retention of relevant dialogues in JSONL files. The IndicDialogue dataset comprises 7750 raw subtitle files (SRT), 11 JSONL files, 6,853,518 dialogues, and 42,188,569 words. It is designed to serve as a foundation for language model pre-training for low-resource languages, enabling a wide range of downstream tasks including word embeddings, topic modeling, conversation synthesis, neural machine translation, and text summarization.

BACKGROUND: Despite the significance and prevalence of acute respiratory distress syndrome (ARDS), its detection remains highly variable and inconsistent. In this work, we aim to develop an algorithm (ARDSFlag) to automate the diagnosis of ARDS based on the Berlin definition. We also aim to develop a visualization tool that helps clinicians efficiently assess ARDS criteria.
METHODS: ARDSFlag applies machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria by incorporating structured and unstructured data in an electronic health record (EHR) system. The study cohort includes 19,534 ICU admissions in the Medical Information Mart for Intensive Care III (MIMIC-III) database. The output is the ARDS diagnosis, onset time, and severity.
RESULTS: ARDSFlag includes separate text classifiers trained using large training sets to find evidence of bilateral infiltrates in radiology reports (accuracy of 91.9%±0.5%) and heart failure/fluid overload in radiology reports (accuracy 86.1%±0.5%) and echocardiogram notes (accuracy 98.4%±0.3%). A test set of 300 cases, which was blindly and independently labeled for ARDS by two groups of clinicians, shows that ARDSFlag generates an overall accuracy of 89.0% (specificity = 91.7%, recall = 80.3%, and precision = 75.0%) in detecting ARDS cases.
CONCLUSIONS: To our best knowledge, this is the first study to focus on developing a method to automate the detection of ARDS. Some studies have developed and used other methods to answer other research questions. Expectedly, ARDSFlag generates a significantly higher performance in all accuracy measures compared to those methods.

Background Clinical trial matching, essential for advancing medical research, involves detailed screening of potential participants to ensure alignment with specific trial requirements. Research staff face challenges due to the high volume of eligible patients and the complexity of varying eligibility criteria. The traditional manual process, both time-consuming and error-prone, often leads to missed opportunities. Recently, large language models (LLMs), specifically generative pre-trained transformers (GPTs), have become impressive and impactful tools. Utilizing such tools from artificial intelligence (AI) and natural language processing (NLP) may enhance the accuracy and efficiency of this process through automated patient screening against established criteria. Methods Utilizing data from the National NLP Clinical Challenges (n2c2) 2018 Challenge, we utilized 202 longitudinal patient records. These records were annotated by medical professionals and evaluated against 13 selection criteria encompassing various health assessments. Our approach involved embedding medical documents into a vector database to determine relevant document sections and then using an LLM (OpenAI\'s GPT-3.5 Turbo and GPT-4) in tandem with structured and chain-of-thought prompting techniques for systematic document assessment against the criteria. Misclassified criteria were also examined to identify classification challenges. Results This study achieved an accuracy of 0.81, sensitivity of 0.80, specificity of 0.82, and a micro F1 score of 0.79 using GPT-3.5 Turbo, and an accuracy of 0.87, sensitivity of 0.85, specificity of 0.89, and micro F1 score of 0.86 using GPT-4. Notably, some criteria in the ground truth appeared mislabeled, an issue we couldn\'t explore further due to insufficient label generation guidelines on the website. Conclusion Our findings underscore the potential of AI and NLP technologies, including LLMs, in the clinical trial matching process. The study demonstrated strong capabilities in identifying eligible patients and minimizing false inclusions. Such automated systems promise to alleviate the workload of research staff and improve clinical trial enrollment, thus accelerating the process and enhancing the overall feasibility of clinical research. Further work is needed to determine the potential of this approach when implemented on real clinical data.

UNASSIGNED: Individuals at clinical high risk (CHR) for psychosis experience subtle emotional disturbances that are traditionally difficult to assess, but natural language processing (NLP) methods may provide novel insight into these symptoms. We predicted that CHR individuals would express more negative emotionality and less emotional language when compared to controls. We also examined associations with symptomatology.
UNASSIGNED: Participants included 49 CHR individuals and 42 healthy controls who completed a semi-structured narrative interview. Interview transcripts were analyzed using Linguistic Inquiry and Word Count (LIWC) to assess the emotional tone of the language (tone -the ratio of negative to positive language) and count positive/negative words used. Participants also completed clinical symptom assessments to determine CHR status and characterize symptoms (i.e., positive and negative symptom domains).
UNASSIGNED: The CHR group had more negative emotional tone compared to healthy controls (t=2.676, p=.009), which related to more severe positive symptoms (r2=.323, p=.013). The percentages of positive and negative words did not differ between groups (p\'s>.05).
UNASSIGNED: Language analyses provided accessible, ecologically valid insight into affective dysfunction and psychosis risk symptoms. Natural language processing analyses unmasked differences in language for CHR that captured language tendencies that were more nuanced than the words that are chosen.