Large language models in psychiatry: Opportunities and challenges.

The ability of Large Language Models (LLMs) to analyze and respond to freely written text is causing increasing excitement in the field of psychiatry; the application of such models presents unique opportunities and challenges for psychiatric applications. This review article seeks to offer a comprehensive overview of LLMs in psychiatry, their model architecture, potential use cases, and clinical considerations. LLM frameworks such as ChatGPT/GPT-4 are trained on huge amounts of text data that are sometimes fine-tuned for specific tasks. This opens up a wide range of possible psychiatric applications, such as accurately predicting individual patient risk factors for specific disorders, engaging in therapeutic intervention, and analyzing therapeutic material, to name a few. However, adoption in the psychiatric setting presents many challenges, including inherent limitations and biases in LLMs, concerns about explainability and privacy, and the potential damage resulting from produced misinformation. This review covers potential opportunities and limitations and highlights potential considerations when these models are applied in a real-world psychiatric context.

Can large language models understand molecules?

PURPOSE: Large Language Models (LLMs) like Generative Pre-trained Transformer (GPT) from OpenAI and LLaMA (Large Language Model Meta AI) from Meta AI are increasingly recognized for their potential in the field of cheminformatics, particularly in understanding Simplified Molecular Input Line Entry System (SMILES), a standard method for representing chemical structures. These LLMs also have the ability to decode SMILES strings into vector representations. METHOD: We investigate the performance of GPT and LLaMA compared to pre-trained models on SMILES in embedding SMILES strings on downstream tasks, focusing on two key applications: molecular property prediction and drug-drug interaction prediction. RESULTS: We find that SMILES embeddings generated using LLaMA outperform those from GPT in both molecular property and DDI prediction tasks. Notably, LLaMA-based SMILES embeddings show results comparable to pre-trained models on SMILES in molecular prediction tasks and outperform the pre-trained models for the DDI prediction tasks. CONCLUSION: The performance of LLMs in generating SMILES embeddings shows great potential for further investigation of these models for molecular embedding. We hope our study bridges the gap between LLMs and molecular embedding, motivating additional research into the potential of LLMs in the molecular representation field. GitHub: https://github.com/sshaghayeghs/LLaMA-VS-GPT .

Fine-tuning large language models for rare disease concept normalization.

OBJECTIVE: We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO). METHODS: We developed an in-house template-based script to generate two corpora for fine-tuning. The first (NAME) contains standardized HPO names, sourced from the HPO vocabularies, along with their corresponding identifiers. The second (NAME+SYN) includes HPO names and half of the concept's synonyms as well as identifiers. Subsequently, we fine-tuned Llama 2 (Llama2-7B) for each sentence set and conducted an evaluation using a range of sentence prompts and various phenotype terms. RESULTS: When the phenotype terms for normalization were included in the fine-tuning corpora, both models demonstrated nearly perfect performance, averaging over 99% accuracy. In comparison, ChatGPT-3.5 has only ∼20% accuracy in identifying HPO IDs for phenotype terms. When single-character typos were introduced in the phenotype terms, the accuracy of NAME and NAME+SYN is 10.2% and 36.1%, respectively, but increases to 61.8% (NAME+SYN) with additional typo-specific fine-tuning. For terms sourced from HPO vocabularies as unseen synonyms, the NAME model achieved 11.2% accuracy, while the NAME+SYN model achieved 92.7% accuracy. CONCLUSION: Our fine-tuned models demonstrate ability to normalize phenotype terms unseen in the fine-tuning corpus, including misspellings, synonyms, terms from other ontologies, and laymen's terms. Our approach provides a solution for the use of LLMs to identify named medical entities from clinical narratives, while successfully normalizing them to standard concepts in a controlled vocabulary.

Applying generative AI with retrieval augmented generation to summarize and extract key clinical information from electronic health records.

BACKGROUND: Malnutrition is a prevalent issue in aged care facilities (RACFs), leading to adverse health outcomes. The ability to efficiently extract key clinical information from a large volume of data in electronic health records (EHR) can improve understanding about the extent of the problem and developing effective interventions. This research aimed to test the efficacy of zero-shot prompt engineering applied to generative artificial intelligence (AI) models on their own and in combination with retrieval augmented generation (RAG), for the automating tasks of summarizing both structured and unstructured data in EHR and extracting important malnutrition information. METHODOLOGY: We utilized Llama 2 13B model with zero-shot prompting. The dataset comprises unstructured and structured EHRs related to malnutrition management in 40 Australian RACFs. We employed zero-shot learning to the model alone first, then combined it with RAG to accomplish two tasks: generate structured summaries about the nutritional status of a client and extract key information about malnutrition risk factors. We utilized 25 notes in the first task and 1,399 in the second task. We evaluated the model's output of each task manually against a gold standard dataset. RESULT: The evaluation outcomes indicated that zero-shot learning applied to generative AI model is highly effective in summarizing and extracting information about nutritional status of RACFs' clients. The generated summaries provided concise and accurate representation of the original data with an overall accuracy of 93.25%. The addition of RAG improved the summarization process, leading to a 6% increase and achieving an accuracy of 99.25%. The model also proved its capability in extracting risk factors with an accuracy of 90%. However, adding RAG did not further improve accuracy in this task. Overall, the model has shown a robust performance when information was explicitly stated in the notes; however, it could encounter hallucination limitations, particularly when details were not explicitly provided. CONCLUSION: This study demonstrates the high performance and limitations of applying zero-shot learning to generative AI models to automatic generation of structured summarization of EHRs data and extracting key clinical information. The inclusion of the RAG approach improved the model performance and mitigated the hallucination problem.

Ultrapotent Broadly Neutralizing Human-llama Bispecific Antibodies against HIV-1.

Broadly neutralizing antibodies are proposed as therapeutic and prophylactic agents against HIV-1, but their potency and breadth are less than optimal. This study describes the immunization of a llama with the prefusion-stabilized HIV-1 envelope (Env) trimer, BG505 DS-SOSIP, and the identification and improvement of potent neutralizing nanobodies recognizing the CD4-binding site (CD4bs) of vulnerability. Two of the vaccine-elicited CD4bs-targeting nanobodies, G36 and R27, when engineered into a triple tandem format with llama IgG2a-hinge region and human IgG1-constant region (G36×3-IgG2a and R27×3-IgG2a), neutralized 96% of a multiclade 208-strain panel at geometric mean IC80s of 0.314 and 0.033 µg mL-1, respectively. Cryo-EM structures of these nanobodies in complex with Env trimer revealed the two nanobodies to neutralize HIV-1 by mimicking the recognition of the CD4 receptor. To enhance their neutralizing potency and breadth, nanobodies are linked to the light chain of the V2-apex-targeting broadly neutralizing antibody, CAP256V2LS. The resultant human-llama bispecific antibody CAP256L-R27×3LS exhibited ultrapotent neutralization and breadth exceeding other published HIV-1 broadly neutralizing antibodies, with pharmacokinetics determined in FcRn-Fc mice similar to the parent CAP256V2LS. Vaccine-elicited llama nanobodies, when combined with V2-apex broadly neutralizing antibodies, may therefore be able to fulfill anti-HIV-1 therapeutic and prophylactic clinical goals.

Distilling large language models for matching patients to clinical trials.

OBJECTIVE: The objective of this study is to systematically examine the efficacy of both proprietary (GPT-3.5, GPT-4) and open-source large language models (LLMs) (LLAMA 7B, 13B, 70B) in the context of matching patients to clinical trials in healthcare. MATERIALS AND METHODS: The study employs a multifaceted evaluation framework, incorporating extensive automated and human-centric assessments along with a detailed error analysis for each model, and assesses LLMs' capabilities in analyzing patient eligibility against clinical trial's inclusion and exclusion criteria. To improve the adaptability of open-source LLMs, a specialized synthetic dataset was created using GPT-4, facilitating effective fine-tuning under constrained data conditions. RESULTS: The findings indicate that open-source LLMs, when fine-tuned on this limited and synthetic dataset, achieve performance parity with their proprietary counterparts, such as GPT-3.5. DISCUSSION: This study highlights the recent success of LLMs in the high-stakes domain of healthcare, specifically in patient-trial matching. The research demonstrates the potential of open-source models to match the performance of proprietary models when fine-tuned appropriately, addressing challenges like cost, privacy, and reproducibility concerns associated with closed-source proprietary LLMs. CONCLUSION: The study underscores the opportunity for open-source LLMs in patient-trial matching. To encourage further research and applications in this field, the annotated evaluation dataset and the fine-tuned LLM, Trial-LLAMA, are released for public use.

An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing: Algorithm Development and Validation Study.

BACKGROUND: Large language models (LLMs) have shown remarkable capabilities in natural language processing (NLP), especially in domains where labeled data are scarce or expensive, such as the clinical domain. However, to unlock the clinical knowledge hidden in these LLMs, we need to design effective prompts that can guide them to perform specific clinical NLP tasks without any task-specific training data. This is known as in-context learning, which is an art and science that requires understanding the strengths and weaknesses of different LLMs and prompt engineering approaches. OBJECTIVE: The objective of this study is to assess the effectiveness of various prompt engineering techniques, including 2 newly introduced types-heuristic and ensemble prompts, for zero-shot and few-shot clinical information extraction using pretrained language models. METHODS: This comprehensive experimental study evaluated different prompt types (simple prefix, simple cloze, chain of thought, anticipatory, heuristic, and ensemble) across 5 clinical NLP tasks: clinical sense disambiguation, biomedical evidence extraction, coreference resolution, medication status extraction, and medication attribute extraction. The performance of these prompts was assessed using 3 state-of-the-art language models: GPT-3.5 (OpenAI), Gemini (Google), and LLaMA-2 (Meta). The study contrasted zero-shot with few-shot prompting and explored the effectiveness of ensemble approaches. RESULTS: The study revealed that task-specific prompt tailoring is vital for the high performance of LLMs for zero-shot clinical NLP. In clinical sense disambiguation, GPT-3.5 achieved an accuracy of 0.96 with heuristic prompts and 0.94 in biomedical evidence extraction. Heuristic prompts, alongside chain of thought prompts, were highly effective across tasks. Few-shot prompting improved performance in complex scenarios, and ensemble approaches capitalized on multiple prompt strengths. GPT-3.5 consistently outperformed Gemini and LLaMA-2 across tasks and prompt types. CONCLUSIONS: This study provides a rigorous evaluation of prompt engineering methodologies and introduces innovative techniques for clinical information extraction, demonstrating the potential of in-context learning in the clinical domain. These findings offer clear guidelines for future prompt-based clinical NLP research, facilitating engagement by non-NLP experts in clinical NLP advancements. To the best of our knowledge, this is one of the first works on the empirical evaluation of different prompt engineering approaches for clinical NLP in this era of generative artificial intelligence, and we hope that it will inspire and inform future research in this area.

Applications of Large Language Models in Pathology.

Large language models (LLMs) are transformer-based neural networks that can provide human-like responses to questions and instructions. LLMs can generate educational material, summarize text, extract structured data from free text, create reports, write programs, and potentially assist in case sign-out. LLMs combined with vision models can assist in interpreting histopathology images. LLMs have immense potential in transforming pathology practice and education, but these models are not infallible, so any artificial intelligence generated content must be verified with reputable sources. Caution must be exercised on how these models are integrated into clinical practice, as these models can produce hallucinations and incorrect results, and an over-reliance on artificial intelligence may lead to de-skilling and automation bias. This review paper provides a brief history of LLMs and highlights several use cases for LLMs in the field of pathology.

Pathological findings in South American camelids presented at a farm animal clinic in Northern Germany (2005-2021).

To expand the knowledge about common diseases in llamas and alpacas in Germany, a screening of the cases of South American camelids presented at the Clinic for Swine and Small Ruminants of the University of Veterinary Medicine Hannover, Germany from 2005 to the end of November 2021 was performed. A retrospective evaluation of necropsy reports from this period was conducted. Overall, necropsy reports were evaluated from 187 alpacas, 35 llamas and one vicuña (n = 223). A total of 50.2% of the dissected animals were thin or cachectic. Pathological alterations of the gastrointestinal tract were the most common findings (44.8%). In addition, liver changes were recorded, most frequently in adult animals. In contrast, diseases of the respiratory tract and the nervous system were found more frequently in juvenile animals. This study provides an overview of common pathologies in South American camelids in Germany and thus may help to recognise different disease symptoms at an early stage.

AlpaPICO: Extraction of PICO frames from clinical trial documents using LLMs.

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. More specifically, both of the proposed frameworks utilize AlpaCare as base LLM which employs both few-shot in-context learning and instruction tuning techniques to extract PICO-related terms from the clinical trial reports. We applied these approaches to the widely used coarse-grained datasets such as EBM-NLP, EBM-COMET and fine-grained datasets such as EBM-NLPrev and EBM-NLPh. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at https://github.com/shrimonmuke0202/AlpaPICO.git.

Evaluating the Potential of AI Chatbots in Treatment Decision-making for Acquired Bilateral Vocal Fold Paralysis in Adults.

OBJECTIVES: The development of artificial intelligence-powered language models, such as Chatbot Generative Pre-trained Transformer (ChatGPT) or Large Language Model Meta AI (Llama), is emerging in medicine. Patients and practitioners have full access to chatbots that may provide medical information. The aim of this study was to explore the performance and accuracy of ChatGPT and Llama in treatment decision-making for bilateral vocal fold paralysis (BVFP). METHODS: Data of 20 clinical cases, treated between 2018 and 2023, were retrospectively collected from four tertiary laryngology centers in Europe. The cases were defined as the most common or most challenging scenarios regarding BVFP treatment. The treatment proposals were discussed in their local multidisciplinary teams (MDT). Each case was presented to ChatGPT-4.0 and Llama Chat-2.0, and potential treatment strategies were requested. The Artificial Intelligence Performance Instrument (AIPI) treatment subscore was used to compare both Chatbots' performances to MDT treatment proposal. RESULTS: Most common etiology of BVFP was thyroid surgery. A form of partial arytenoidectomy with or without posterior transverse cordotomy was the MDT proposal for most cases. The accuracy of both Chatbots was very low regarding their treatment proposals, with a maximum AIPI treatment score in 5% of the cases. In most cases even harmful assertions were made, including the suggestion of vocal fold medialisation to treat patients with stridor and dyspnea. ChatGPT-4.0 performed significantly better in suggesting the correct treatment as part of the treatment proposal (50%) compared to Llama Chat-2.0 (15%). CONCLUSION: ChatGPT and Llama are judged as inaccurate in proposing correct treatment for BVFP. ChatGPT significantly outperformed Llama. Treatment decision-making for a complex condition such as BVFP is clearly beyond the Chatbot's knowledge expertise. This study highlights the complexity and heterogeneity of BVFP treatment, and the need for further guidelines dedicated to the management of BVFP.

Can large language models reason about medical questions?

Although large language models often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate whether closed- and open-source models (GPT-3.5, Llama 2, etc.) can be applied to answer and reason about difficult real-world-based questions. We focus on three popular medical benchmarks (MedQA-US Medical Licensing Examination [USMLE], MedMCQA, and PubMedQA) and multiple prompting scenarios: chain of thought (CoT; think step by step), few shot, and retrieval augmentation. Based on an expert annotation of the generated CoTs, we found that InstructGPT can often read, reason, and recall expert knowledge. Last, by leveraging advances in prompt engineering (few-shot and ensemble methods), we demonstrated that GPT-3.5 not only yields calibrated predictive distributions but also reaches the passing score on three datasets: MedQA-USMLE (60.2%), MedMCQA (62.7%), and PubMedQA (78.2%). Open-source models are closing the gap: Llama 2 70B also passed the MedQA-USMLE with 62.5% accuracy.

A comprehensive evaluation of large Language models on benchmark biomedical text processing tasks.

Recently, Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated their capability in the biomedical domain yet. To this end, this paper aims to evaluate the performance of LLMs on benchmark biomedical tasks. For this purpose, a comprehensive evaluation of 4 popular LLMs in 6 diverse biomedical tasks across 26 datasets has been conducted. To the best of our knowledge, this is the first work that conducts an extensive evaluation and comparison of various LLMs in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot LLMs even outperform the current state-of-the-art models when they were fine-tuned only on the training set of these datasets. This suggests that pre-training on large text corpora makes LLMs quite specialized even in the biomedical domain. We also find that not a single LLM can outperform other LLMs in all tasks, with the performance of different LLMs may vary depending on the task. While their performance is still quite poor in comparison to the biomedical models that were fine-tuned on large training sets, our findings demonstrate that LLMs have the potential to be a valuable tool for various biomedical tasks that lack large annotated data.

The potential and limitations of large language models in identification of the states of motivations for facilitating health behavior change.

IMPORTANCE: The study highlights the potential and limitations of the Large Language Models (LLMs) in recognizing different states of motivation to provide appropriate information for behavior change. Following the Transtheoretical Model (TTM), we identified the major gap of LLMs in responding to certain states of motivation through validated scenario studies, suggesting future directions of LLMs research for health promotion. OBJECTIVES: The LLMs-based generative conversational agents (GAs) have shown success in identifying user intents semantically. Little is known about its capabilities to identify motivation states and provide appropriate information to facilitate behavior change progression. MATERIALS AND METHODS: We evaluated 3 GAs, ChatGPT, Google Bard, and Llama 2 in identifying motivation states following the TTM stages of change. GAs were evaluated using 25 validated scenarios with 5 health topics across 5 TTM stages. The relevance and completeness of the responses to cover the TTM processes to proceed to the next stage of change were assessed. RESULTS: 3 GAs identified the motivation states in the preparation stage providing sufficient information to proceed to the action stage. The responses to the motivation states in the action and maintenance stages were good enough covering partial processes for individuals to initiate and maintain their changes in behavior. However, the GAs were not able to identify users' motivation states in the precontemplation and contemplation stages providing irrelevant information, covering about 20%-30% of the processes. DISCUSSION: GAs are able to identify users' motivation states and provide relevant information when individuals have established goals and commitments to take and maintain an action. However, individuals who are hesitant or ambivalent about behavior change are unlikely to receive sufficient and relevant guidance to proceed to the next stage of change. CONCLUSION: The current GAs effectively identify motivation states of individuals with established goals but may lack support for those ambivalent towards behavior change.

Comparison of atlantoaxial and lumbosacral cerebrospinal fluid centesis techniques in South American camelids.

BACKGROUND: Iatrogenic blood contamination during cerebrospinal fluid (CSF) centesis is common, which can limit the diagnostic usefulness of the sample. A novel ultrasound-guided CSF collection technique is described in horses, by which CSF is obtained from the atlantoaxial (AA) space. HYPOTHESIS/OBJECTIVES: To compare ultrasound-guided AA centesis with lumbosacral (LS) centesis in South American camelids (SAC). The hypotheses were that AA centesis would yield samples with less blood contamination although being technically more challenging than LS centesis. ANIMALS: Eight clinically healthy adult SAC from a university-owned teaching herd. METHODS: Single-blinded, randomized, 4-way, 4-period crossover study in which 2 veterinarians each performed both centesis techniques on each animal once. Cytological sample analysis was performed, and the technical difficulty of sample acquisition was assessed. RESULTS: The CSF was collected successfully and without complications by either technique during all collection attempts. Aspects of technical difficulty and concentrations of CSF analytes did not vary significantly between techniques. Median total nucleated cell and red blood cell counts were 1/µL and 0.5/µL and 167.5/µL and 155/µL for AA and LS techniques, respectively. The median total protein concentration was 32.9 mg/dL and 38 mg/dL for AA and LS centeses. A median of 1 attempt was necessary for both centesis techniques and the median number of needle repositioning events was 1 for AA and 0 for LS. CONCLUSION AND CLINICAL IMPORTANCE: Depending on clinical circumstances, ultrasound-guided AA centesis appears to be an acceptable alternative to other techniques for collection of CSF from SAC.

Fine-tuning Large Language Models for Rare Disease Concept Normalization.

Objective: We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO). Methods: We developed an in-house template-based script to generate two corpora for fine-tuning. The first (NAME) contains standardized HPO names, sourced from the HPO vocabularies, along with their corresponding identifiers. The second (NAME+SYN) includes HPO names and half of the concept's synonyms as well as identifiers. Subsequently, we fine-tuned Llama2 (Llama2-7B) for each sentence set and conducted an evaluation using a range of sentence prompts and various phenotype terms. Results: When the phenotype terms for normalization were included in the fine-tuning corpora, both models demonstrated nearly perfect performance, averaging over 99% accuracy. In comparison, ChatGPT-3.5 has only ~20% accuracy in identifying HPO IDs for phenotype terms. When single-character typos were introduced in the phenotype terms, the accuracy of NAME and NAME+SYN is 10.2% and 36.1%, respectively, but increases to 61.8% (NAME+SYN) with additional typo-specific fine-tuning. For terms sourced from HPO vocabularies as unseen synonyms, the NAME model achieved 11.2% accuracy, while the NAME+SYN model achieved 92.7% accuracy. Conclusion: Our fine-tuned models demonstrate ability to normalize phenotype terms unseen in the fine-tuning corpus, including misspellings, synonyms, terms from other ontologies, and laymen's terms. Our approach provides a solution for the use of LLM to identify named medical entities from the clinical narratives, while successfully normalizing them to standard concepts in a controlled vocabulary.

Suggestions from Experience and AI Tools to Teach Evidence Based Practice to Nurses.

Hospital librarians receive invites to teach thinking and searching in an evidence-based way and critical appraisal of the literature to nurses. With these invitations, the hospital librarians play a central role in establishing an evidence-based culture in the hospital and contribute to the nursing staff feeling competent and confident in fulfilling evidence-based competencies. This author just prepared a 17-minute online talk as part of an international nursing webinar on "searching nursing literature in an evidence-based way." Using this experience, remembering other teaching and presentation experiences, and some "help" from AI tools, this experienced hospital librarian suggests decision points for colleagues to create a meaningful, practical information session for nurses and introduce to some AI tools along the way.

ChatGPT in healthcare: A taxonomy and systematic review.

The recent release of ChatGPT, a chat bot research project/product of natural language processing (NLP) by OpenAI, stirs up a sensation among both the general public and medical professionals, amassing a phenomenally large user base in a short time. This is a typical example of the 'productization' of cutting-edge technologies, which allows the general public without a technical background to gain firsthand experience in artificial intelligence (AI), similar to the AI hype created by AlphaGo (DeepMind Technologies, UK) and self-driving cars (Google, Tesla, etc.). However, it is crucial, especially for healthcare researchers, to remain prudent amidst the hype. This work provides a systematic review of existing publications on the use of ChatGPT in healthcare, elucidating the 'status quo' of ChatGPT in medical applications, for general readers, healthcare professionals as well as NLP scientists. The large biomedical literature database PubMed is used to retrieve published works on this topic using the keyword 'ChatGPT'. An inclusion criterion and a taxonomy are further proposed to filter the search results and categorize the selected publications, respectively. It is found through the review that the current release of ChatGPT has achieved only moderate or 'passing' performance in a variety of tests, and is unreliable for actual clinical deployment, since it is not intended for clinical applications by design. We conclude that specialized NLP models trained on (bio)medical datasets still represent the right direction to pursue for critical clinical applications.

Anaemia in South American camelids - an overview of clinical and laboratory diagnostics.

South American camelids (SACs) play an increasing role in veterinary care in Europe. Many alpacas or llamas presented to veterinarians suffer from anaemia, regularly with a packed cell volume (PCV) below 0.10 l/l, which is a life-threatening condition for the animals. This review article presents clinical and laboratory diagnostic tools for the diagnosis of anaemia in SACs. Clinical identification of anaemic animals can be performed by assessing the FAMACHA© score and the Body Condition Score (BCS), since anaemia in alpacas and llamas correlates with pale mucous membranes and a lowered BCS. Haematological examination of a blood sample can provide a more differentiated diagnosis of anaemia in SACs. A common finding is regenerative anaemia with an increased number of reticulocytes that is often caused by blood loss due to Haemonchus contortus. Changes in a blood smear from an alpaca or llama with regenerative anaemia may include normoblasts (nucleated red blood cells), anisocytosis, poikilocytosis, polychromasia, Howell-Jolly bodies or basophilic stippling. Furthermore, non-regenerative anaemia, often caused by trace element deficiency or cachexia, can also occur.

Middle East respiratory coronavirus (MERS-CoV) internalized by llama alveolar macrophages does not result in virus replication or induction of pro-inflammatory cytokines.

Severe Middle East respiratory syndrome (MERS) is characterized by massive infiltration of immune cells in lungs. MERS-coronavirus (MERS-CoV) replicates in vitro in human macrophages, inducing high pro-inflammatory responses. In contrast, camelids, the main reservoir for MERS-CoV, are asymptomatic carriers. Although limited infiltration of leukocytes has been observed in the lower respiratory tract of camelids, their role during infection remains unknown. Here we studied whether llama alveolar macrophages (LAMs) are susceptible to MERS-CoV infection and can elicit pro-inflammatory responses. MERS-CoV did not replicate in LAMs; however, they effectively capture and degrade viral particles. Moreover, transcriptomic analyses showed that LAMs do not induce pro-inflammatory cytokines upon MERS-CoV sensing.