Advances In Natural Language Processing Research Articles

AI-powered language learning: The role of NLP in grammar, spelling, and pronunciation feedback

Abstract. The introduction of artificial intelligence (AI) and natural language processing (NLP) in language learning has transformed the practices of education. This paper analyzes the role of AI-powered tools in English language learning with specific focus on automated essay scoring (AES), speech recognition, and advanced grammar and spelling checkers. By examining the accuracy of the most effective AES systems, it is evident that automated feedback has increased the quality of writing by providing detailed, consistent, and objective feedback on submitted essays. Speech recognition is another tool that is being used to assess pronunciation and fluency of learners. The software is constantly improving, with advances in NLP and machine learning. The technology for fluency tests is becoming more accurate, and is helping to improve learner outcomes significantly. Lastly, we examine advanced grammar and spelling checkers, which are increasingly used for correcting the contextual errors of individual learners. The AI systems adapt to the user and their needs, which make the corrections more effective. This paper offers an overview of how AI is leading to personalized and effective language learning, ultimately enhancing the educational experience of students and embracing future possibilities in education technology.

Multi-label text classification via secondary use of large clinical real-world data sets.

Procedural coding presents a taxing challenge for clinicians. However, recent advances in natural language processing offer a promising avenue for developing applications that assist clinicians, thereby alleviating their administrative burdens. This study seeks to create an application capable of predicting procedure codes by analysing clinicians' operative notes, aiming to streamline their workflow and enhance efficiency. We downstreamed an existing and a native German medical BERT model in a secondary use scenario, utilizing already coded surgery notes to model the coding procedure as a multi-label classification task. In comparison to the transformer-based architecture, we were levering the non-contextual model fastText, a convolutional neural network, a support vector machine and logistic regression for a comparative analysis of possible coding performance. About 350,000 notes were used for model adaption. By considering the top five suggested procedure codes from medBERT.de, surgeryBERT.at, fastText, a convolutional neural network, a support vector machine and a logistic regression, the mean average precision achieved was 0.880, 0.867, 0.870, 0.851, 0.870and0.805 respectively. Support vector machines performed better for surgery reports with a sequence length greater than 512, achieving a mean average precision of 0.872 in comparison to 0.840 for fastText, 0.837 for medBERT.de and 0.820 for surgeryBERT.at. A prototypical front-end application for coding support was additionally implemented. The problem of predicting procedure codes from a given operative report can be successfully modelled as a multi-label classification task, with a promising performance. Support vector machines as a classical machine learning method outperformed the non-contextual fastText approach. FastText with less demanding hardware resources has reached a similar performance to BERT-based models and has shown to be more suitable for explaining the predictions efficiently.

Advancements in Natural Language Processing for Human-Computer Interaction

• This systematic review explores the advancements in Natural Language Processing (NLP) for Human-Computer Interaction (HCI) over the period from 2010 to 2024. It highlights the significant breakthroughs achieved through deep learning models, particularly transformer architectures such as BERT and GPT, which have transformed the ability of machines to understand and generate human language. The integration of multimodal capabilities has further enriched user interactions by enabling the processing of diverse data types, including text, audio, and visual inputs. However, the review also identifies persistent challenges, including maintaining coherence in long dialogues, resolving ambiguous language, addressing bias in training data, and the need for resource-efficient models. Additionally, the paper emphasizes the importance of cross-lingual capabilities for low-resource languages and the necessity of personalized, adaptive systems. The findings underscore the need for ongoing research to overcome existing limitations and enhance the effectiveness and inclusivity of NLP technologies in HCI, ultimately contributing to a more intuitive and accessible user experience.

MultiADE: A Multi-domain benchmark for Adverse Drug Event extraction

Objective:Active adverse event surveillance monitors Adverse Drug Events (ADE) from different data sources, such as electronic health records, medical literature, social media and search engine logs. Over the years, many datasets have been created, and shared tasks have been organised to facilitate active adverse event surveillance. However, most—if not all—datasets or shared tasks focus on extracting ADEs from a particular type of text. Domain generalisation—the ability of a machine learning model to perform well on new, unseen domains (text types)—is under-explored. Given the rapid advancements in natural language processing, one unanswered question is how far we are from having a single ADE extraction model that is effective on various types of text, such as scientific literature and social media posts. Methods:We contribute to answering this question by building a multi-domain benchmark for adverse drug event extraction, which we named MultiADE. The new benchmark comprises several existing datasets sampled from different text types and our newly created dataset—CADECv2, which is an extension of CADEC (Karimi et al., 2015), covering online posts regarding more diverse drugs than CADEC. Our new dataset is carefully annotated by human annotators following detailed annotation guidelines. Conclusion:Our benchmark results show that the generalisation of the trained models is far from perfect, making it infeasible to be deployed to process different types of text. In addition, although intermediate transfer learning is a promising approach to utilising existing resources, further investigation is needed on methods of domain adaptation, particularly cost-effective methods to select useful training instances.The newly created CADECv2 and the scripts for building the benchmark are publicly available at CSIRO’s Data Portal (https://data.csiro.au/collection/csiro:62387). These resources enable the research community to further information extraction, leading to more effective active adverse drug event surveillance.

Advancements in Natural Language Processing: Implications, Challenges, and Future Directions

Advancements in Natural Language Processing: Implications, Challenges, and Future Directions

Addressing the risks of generative AI for the judiciary: The accountability framework(s) under the EU AI Act

The rapid advancements in natural language processing, particularly the development of generative large language models (LLMs), have renewed interest in using artificial intelligence (AI) for judicial decision-making. While these technological breakthroughs present new possibilities for legal automation, they also raise concerns about over-reliance and automation bias. Drawing insights from the COMPAS case, this paper examines the implications of deploying generative LLMs in the judicial domain. It identifies the persistent factors that contributed to an accountability gap when AI systems were previously used for judicial decision-making. To address these risks, the paper analyses the relevant provisions of the EU Artificial Intelligence Act, outlining a comprehensive accountability framework based on the regulation's risk-based approach. The paper concludes that the successful integration of generative LLMs in judicial decision-making requires a holistic approach addressing cognitive biases. By emphasising shared responsibility and the imperative of AI literacy across the AI value chain, the regulatory framework can help mitigate the risks of automation bias and preserve the rule of law.

Advancements in natural language processing: Bridging the gap between human and machine communication

Advancements in natural language processing: Bridging the gap between human and machine communication

Exploring Recent NLP Advances for Tamil: Word Vectors and Hybrid Deep Learning Architectures

The advancements of deep learning methods and the availability of large corpora and data sets have led to an exponential increase in the performance of Natural Language Processing (NLP) methods resulting in successful NLP applications for various day-to-day tasks such as Language translation, Voice to text, Grammar checking, Sentiment analysis, etc. These advancements enabled the well-resourced languages to adapt themselves to the digital era while the gap for the low-resource languages widened. This research work explores the suitability of the recent advancements in NLP for Tamil, a low-resource language spoken mainly in South India, Sri Lanka, and Malaysia. From the literature survey, it has been found that there is a lack of comprehensive study on the effect of the recent advancements of NLP for the Tamil text. To fill this gap, this research work analysed the performance of deep learning based text representation and classification approaches namely word embedding, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) for Tamil text classification tasks. Different dimensional pretrained word2Vec and FastText word vectors were built for Tamil and their effectiveness on Text classification was evaluated. The study found that the pre-trained 300- dimensional FastText word vector showed better performance than other pre-trained word vectors for Tamil text classification. Further, in this study, four simple hybrid CNN and Bi-GRU models were proposed for Tamil text classification and their performances were evaluated. The study found that hybrid CNN and Bi-GRU models perform better compared to the classical machine learning models, individual CNN and RNN models, and the Multilingual BERT model. These results confirm that the jointly learned embeddings with different deep learning architectures like CNN and RNN can achieve remarkable results for Tamil text classification, thus ensuring that the deep learning approaches can be successful for NLP on Tamil text.

Joint intent detection and slot filling with syntactic and semantic features using multichannel CNN-BiLSTM

Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU). Enhancing the NLU tasks can lead to an accurate and efficient virtual assistant thereby reducing the need for human intervention and expanding their applicability in other domains. Traditionally, these tasks have been addressed individually, but recent studies have highlighted their interconnection, suggesting better results when solved together. Recent advances in natural language processing have shown that pretrained word embeddings can enhance text representation and improve the generalization capabilities of models. However, the challenge of poor generalization in joint learning models for intent detection and slot filling remains due to limited annotated datasets. Additionally, traditional models face difficulties in capturing both the semantic and syntactic nuances of language, which are vital for accurate intent detection and slot filling. This study proposes a hybridized text representation method using a multichannel convolutional neural network with three embedding channels: non-contextual embeddings for semantic information, part-of-speech (POS) tag embeddings for syntactic features, and contextual embeddings for deeper contextual understanding. Specifically, we utilized word2vec for non-contextual embeddings, one-hot vectors for POS tags, and bidirectional encoder representations from transformers (BERT) for contextual embeddings. These embeddings are processed through a convolutional layer and a shared bidirectional long short-term memory (BiLSTM) network, followed by two softmax functions for intent detection and slot filling. Experiments on the air travel information system (ATIS) and SNIPS datasets demonstrated that our model significantly outperformed the baseline models, achieving an intent accuracy of 97.90% and slot filling F1-score of 98.86% on the ATIS dataset, and an intent accuracy of 98.88% and slot filling F1-score of 97.07% on the SNIPS dataset. These results highlight the effectiveness of our proposed approach in advancing dialogue systems, and paving the way for more accurate and efficient natural language understanding in real-world applications.

Large language models and their applications in bioinformatics

Recent advancements in Natural Language Processing (NLP) have been significantly driven by the development of Large Language Models (LLMs), representing a substantial leap in language-based technology capabilities. These models, built on sophisticated deep learning architectures, typically transformers, are characterized by billions of parameters and extensive training data, enabling them to achieve high accuracy across various tasks. The transformer architecture of LLMs allows them to effectively handle context and sequential information, which is crucial for understanding and generating human language. Beyond traditional NLP applications, LLMs have shown significant promise in bioinformatics, transforming the field by addressing challenges associated with large and complex biological datasets. In genomics, proteomics, and personalized medicine, LLMs facilitate identifying patterns, predicting protein structures, or understanding genetic variations. This capability is crucial, e.g., for advancing drug discovery, where accurate prediction of molecular interactions is essential. This review discusses the current trends in LLMs research and their potential to revolutionize the field of bioinformatics and accelerate novel discoveries in the life sciences.

Need of retrieval augmented generation for conversational assistants for government social welfare scheme popularization

Governments allocate substantial resources to uplift under-privileged communities through various assistance schemes. Despite these efforts, the effectiveness of such initiatives often fails due to variety of reasons including cryptic nature of information available, lack of awareness to the needy people and or lack of transparency. In India, a vast and diverse developing democracy, these challenges are exacerbated by disparities in access to information. To address these issues, we explored the use of conversational AI technologies, including chatbots, which have seen successful application in many developed nations. Conversational AI agents often get challenged to a variety of factual inaccuracies and other types of hallucinations. Our study compares the accuracy of responses across different architectures: Our architectures integrate advancements in natural language processing, such as large language models (LLMs) and retrieval-augmented generation (RAG), along with automatic speech recognition (ASR), knowledge distillation, hybrid retrieval strategies, and text-to-speech systems. Overall this research experiments demonstrate that leveraging retrieval augmented generation using the same model embeddings substantially improves the quality of the output, its similarity to desired responses. This also reduces hallucinations. We also notice that larger models perform better than smaller parameter models.

Comparison of Gemini Advanced and ChatGPT 4.0's Performances on the Ophthalmology Resident Ophthalmic Knowledge Assessment Program (OKAP) Examination Review Question Banks.

Background With advancements in natural language processing, tools such as Chat Generative Pre-Trained Transformers (ChatGPT) version 4.0 and Google Bard's Gemini Advanced are being increasingly evaluated for their potential in various medical applications. The objective of this study was to systematically assess the performance of these language learning models (LLMs) on both image and non-image-based questions within the specialized field of Ophthalmology. We used a review question bank for the Ophthalmic Knowledge Assessment Program (OKAP) used by ophthalmology residents nationally to prepare for the Ophthalmology Board Exam to assess the accuracy and performance of ChatGPT and Gemini Advanced. Methodology A total of 260 randomly generated multiple-choice questions from the OphthoQuestions question bank were run through ChatGPT and Gemini Advanced. A simulated 260-question OKAP examination was created at random from the bank. Question-specific data were analyzed, including overall percent correct, subspecialty accuracy, whether the question was "high yield," difficulty (1-4), and question type (e.g., image, text). To compare the performance of ChatGPT-4 and Gemini on the difficulty of questions, we utilized the standard deviation of user answer choices to determine question difficulty. In this study, a statistical analysis of Google Sheets was conducted using two-tailed t-tests with unequal variance to compare the performance of ChatGPT-4.0 and Google's Gemini Advanced across various question types, subspecialties, and difficulty levels. Results In total, 259 of the 260 questions were included in the study as one question used a video that any form of ChatGPT could not interpret as of May 1, 2024. For text-only questions, ChatGPT-4.0.0 correctly answered 57.14% (148/259, p < 0.018), and Gemini Advanced correctly answered 46.72% (121/259, p < 0.018). Both versions answered most questions without a prompt and would have received a below-average score on the OKAP. Moreover, there were 27 questions utilizing a secondary prompt in ChatGPT-4.0 compared to 67 questions in Gemini Advanced. ChatGPT-4.0 performed 68.99% on easier questions (<2 on a scale from 1-4) and 44.96% on harder questions (>2 on a scale from 1-4). On the other hand, Gemini Advanced performed 49.61% on easier questions (<2 on a scale from 1-4) and 44.19% on harder questions (>2 on a scale from 1-4). There was a statistically significant difference in accuracy between ChatGPT-4.0 and Gemini Advanced for easy (p < 0.0015) but not for hard (p < 0.55) questions. For image-only questions, ChatGPT-4.0 correctly answered 39.58% (19/48, p < 0.013), and Gemini Advanced correctly answered 33.33% (16/48, p < 0.022), resulting in a statistically insignificant difference in accuracy between ChatGPT-4.0 and Gemini Advanced (p < 0.530). A comparison against text-only and image-based questions demonstrated a statistically significant difference in accuracy for both ChatGPT-4.0 (p < 0.013) and Gemini Advanced (p < 0.022). Conclusions This study provides evidence that ChatGPT-4.0 performs better on the OKAP-style exams and is improved compared to Gemini Advanced within the context of ophthalmic multiple-choice questions. This may show an opportunity for increased worth for ChatGPT in ophthalmic medical education. While showing promise within medical education, caution should be used as a more detailed evaluation of reliability is needed.

Decomposing maintenance actions into sub-tasks using natural language processing: A case study in an Italian automotive company

Industry 4.0 has led to a huge increase in data coming from machine maintenance. At the same time, advances in Natural Language Processing (NLP) and Large Language Models provide new ways to analyse this data. In our research, we use NLP to analyse maintenance work orders, and specifically the descriptions of failures and the corresponding repair actions. Many NLP studies have focused on failure descriptions for categorising them, extracting specific information about failure, or supporting failure analysis methodologies (such as FMEA). Whereas, the analysis of repair actions and its relationship with failure remains underexplored. Addressing this gap, our study makes three significant contributions. Firstly, we focused on the Italian language, which presents additional challenges due to the dominance of NLP systems that are mainly designed for English. Secondly, it proposes a method for automatically subdividing a repair action into a set of sub-tasks. Lastly, it introduces an approach that employs association rule mining to recommend sub-tasks to maintainers when addressing failures. We tested our approach with a case study from an automotive company in Italy. The case study provides insights into the current barriers faced by NLP applications in maintenance, offering a glimpse into the future opportunities for smart maintenance systems.

Analysing Psychological Sentiment Prediction Across Modalities: Harnessing Emotion Datasets within Natural Language Processing (NLP)

Studying human emotions and feelings is a crucial element in the field of psychology, having significant implications such as evaluating mental health and improving human-computer interactions. Recently, there has been a rise in interest in examining how psychological sentiment can be predicted through various mediums, including text, audio, video, and physiological signals. By utilizing advancements in Natural Language Processing (NLP) and analysing multimodal data, this research delves into incorporating emotion datasets into NLP frameworks to improve psychological sentiment prediction. This presents present an applicability of some of the NLP techniques to predicts the Psychological Sentiment such as Deep Generating adversarial networks (D-GANs), Long short-term memory (LSTM) and gated recurrent unit (GRU). The sentimental analysis performed by the considered algorithms are implemented in python and the parameters which are considered for the results evaluation are model loss, confusion matrix, accuracy, precision, recall and f1-score. Our goal with this analysis is to offer a deeper understanding of the existing methodologies and future scope of growth in psychological sentiment prediction of research in the field of NLP.

Detecting schizophrenia, bipolar disorder, psychosis vulnerability and major depressive disorder from 5 minutes of online-collected speech.

Psychosis poses substantial social and healthcare burdens. The analysis of speech is a promising approach for the diagnosis and monitoring of psychosis, capturing symptoms like thought disorder and flattened affect. Recent advancements in Natural Language Processing (NLP) methodologies enable the automated extraction of informative speech features, which has been leveraged for early psychosis detection and assessment of symptomology. However, critical gaps persist, including the absence of standardized sample collection protocols, small sample sizes, and a lack of multi-illness classification, limiting clinical applicability. Our study aimed to (1) identify an optimal assessment approach for the online and remote collection of speech, in the context of assessing the psychosis spectrum and evaluate whether a fully automated, speech-based machine learning (ML) pipeline can discriminate among different conditions on the schizophrenia-bipolar spectrum (SSD-BD-SPE), help-seeking comparison subjects (MDD), and healthy controls (HC) at varying layers of analysis and diagnostic complexity. We adopted online data collection methods to collect 20 minutes of speech and demographic information from individuals. Participants were categorized as "healthy" help-seekers (HC), having a schizophrenia-spectrum disorder (SSD), bipolar disorder (BD), major depressive disorder (MDD), or being on the psychosis spectrum with sub-clinical psychotic experiences (SPE). SPE status was determined based on self-reported clinical diagnosis and responses to the PHQ-8 and PQ-16 screening questionnaires, while other diagnoses were determined based on self-report from participants. Linguistic and paralinguistic features were extracted and ensemble learning algorithms (e.g., XGBoost) were used to train models. A 70%-30% train-test split and 30-fold cross-validation was used to validate the model performance. The final analysis sample included 1140 individuals and 22,650 minutes of speech. Using 5-minutes of speech, our model could discriminate between HC and those with a serious mental illness (SSD or BD) with 86% accuracy (AUC = 0.91, Recall = 0.7, Precision = 0.98). Furthermore, our model could discern among HC, SPE, BD and SSD groups with 86% accuracy (F1 macro = 0.855, Recall Macro = 0.86, Precision Macro = 0.86). Finally, in a 5-class discrimination task including individuals with MDD, our model had 76% accuracy (F1 macro = 0.757, Recall Macro = 0.758, Precision Macro = 0.766). Our ML pipeline demonstrated disorder-specific learning, achieving excellent or good accuracy across several classification tasks. We demonstrated that the screening of mental disorders is possible via a fully automated, remote speech assessment pipeline. We tested our model on relatively high number conditions (5 classes) in the literature and in a stratified sample of psychosis spectrum, including HC, SPE, SSD and BD (4 classes). We tested our model on a large sample (N = 1150) and demonstrated best-in-class accuracy with remotely collected speech data in the psychosis spectrum, however, further clinical validation is needed to test the reliability of model performance.

Extracting lung cancer staging descriptors from pathology reports: A generative language model approach

BackgroundIn oncology, electronic health records contain textual key information for the diagnosis, staging, and treatment planning of patients with cancer. However, text data processing requires a lot of time and effort, which limits the utilization of these data. Recent advances in natural language processing (NLP) technology, including large language models, can be applied to cancer research. Particularly, extracting the information required for the pathological stage from surgical pathology reports can be utilized to update cancer staging according to the latest cancer staging guidelines. ObjectivesThis study has two main objectives. The first objective is to evaluate the performance of extracting information from text-based surgical pathology reports and determining pathological stages based on the extracted information using fine-tuned generative language models (GLMs) for patients with lung cancer. The second objective is to determine the feasibility of utilizing relatively small GLMs for information extraction in a resource-constrained computing environment. MethodsLung cancer surgical pathology reports were collected from the Common Data Model database of Seoul National University Bundang Hospital (SNUBH), a tertiary hospital in Korea. We selected 42 descriptors necessary for tumor-node (TN) classification based on these reports and created a gold standard with validation by two clinical experts. The pathology reports and gold standard were used to generate prompt-response pairs for training and evaluating GLMs which then were used to extract information required for staging from pathology reports. ResultsWe evaluated the information extraction performance of six trained models as well as their performance in TN classification using the extracted information. The Deductive Mistral-7B model, which was pre-trained with the deductive dataset, showed the best performance overall, with an exact match ratio of 92.24% in the information extraction problem and an accuracy of 0.9876 (predicting T and N classification concurrently) in classification. ConclusionThis study demonstrated that training GLMs with deductive datasets can improve information extraction performance, and GLMs with a relatively small number of parameters at approximately seven billion can achieve high performance in this problem. The proposed GLM-based information extraction method is expected to be useful in clinical decision-making support, lung cancer staging and research.

CODEX

Project Codex is an advanced artificial intelligence (AI) system designed to provide human-like conversational capabilities. Built on the GPT-3.5 architecture, Codex is a revolutionary project developed by OpenAI. It combines state-of-the-art language models and deep learning techniques to generate responses and engage in meaningful conversations with users. Codex is an innovative project that pushes the boundaries of conversational artificial intelligence (AI) through the development of a sophisticated chatbot built on the GPT (Generative Pre-trained Transformer) framework. Inspired by the remarkable advancements in natural language processing, Codex aims to create an AI system capable of engaging in human-like conversations, providing users with a seamless and intelligent chat experience.

Soil Organic Carbon Estimation via Remote Sensing and Machine Learning Techniques: Global Topic Modeling and Research Trend Exploration

Understanding and monitoring soil organic carbon (SOC) stocks is crucial for ecosystem carbon cycling, services, and addressing global environmental challenges. This study employs the BERTopic model and bibliometric trend analysis exploration to comprehensively analyze global SOC estimates. BERTopic, a topic modeling technique based on BERT (bidirectional encoder representatives from transformers), integrates recent advances in natural language processing. The research analyzed 1761 papers on SOC and remote sensing (RS), in addition to 490 related papers on machine learning (ML) techniques. BERTopic modeling identified nine research themes for SOC estimation using RS, emphasizing spectral prediction models, carbon cycle dynamics, and agricultural impacts on SOC. In contrast, for the literature on RS and ML it identified five thematic clusters: spatial forestry analysis, hyperspectral soil analysis, agricultural deep learning, the multitemporal imaging of farmland SOC, and RS platforms (Sentinel-2 and synthetic aperture radar, SAR). From 1991 to 2023, research on SOC estimation using RS and ML has evolved from basic mapping to topics like carbon sequestration and modeling with Sentinel-2A and big data. In summary, this study traces the historical growth and thematic evolution of SOC research, identifying synergies between RS and ML and focusing on SOC estimation with advanced ML techniques. These findings are critical to global ecosystem SOC assessments and environmental policy formulation.

Automated Speech Analysis in Bipolar Disorder: The CALIBER Study Protocol and Preliminary Results.

Background: Bipolar disorder (BD) involves significant mood and energy shifts reflected in speech patterns. Detecting these patterns is crucial for diagnosis and monitoring, currently assessed subjectively. Advances in natural language processing offer opportunities to objectively analyze them. Aims: To (i) correlate speech features with manic-depressive symptom severity in BD, (ii) develop predictive models for diagnostic and treatment outcomes, and (iii) determine the most relevant speech features and tasks for these analyses. Methods: This naturalistic, observational study involved longitudinal audio recordings of BD patients at euthymia, during acute manic/depressive phases, and after-response. Patients participated in clinical evaluations, cognitive tasks, standard text readings, and storytelling. After automatic diarization and transcription, speech features, including acoustics, content, formal aspects, and emotionality, will be extracted. Statistical analyses will (i) correlate speech features with clinical scales, (ii) use lasso logistic regression to develop predictive models, and (iii) identify relevant speech features. Results: Audio recordings from 76 patients (24 manic, 21 depressed, 31 euthymic) were collected. The mean age was 46.0 ± 14.4 years, with 63.2% female. The mean YMRS score for manic patients was 22.9 ± 7.1, reducing to 5.3 ± 5.3 post-response. Depressed patients had a mean HDRS-17 score of 17.1 ± 4.4, decreasing to 3.3 ± 2.8 post-response. Euthymic patients had mean YMRS and HDRS-17 scores of 0.97 ± 1.4 and 3.9 ± 2.9, respectively. Following data pre-processing, including noise reduction and feature extraction, comprehensive statistical analyses will be conducted to explore correlations and develop predictive models. Conclusions: Automated speech analysis in BD could provide objective markers for psychopathological alterations, improving diagnosis, monitoring, and response prediction. This technology could identify subtle alterations, signaling early signs of relapse. Establishing standardized protocols is crucial for creating a global speech cohort, fostering collaboration, and advancing BD understanding.

Unlocking the Potential of Free Text in Electronic Health Records with Large Language Models (LLM): Enhancing Patient Safety and Consultation Interactions.

Computer-mediated clinical consultation, involving clinicians, electronic health record (EHR) systems, and patients, yield rich narrative data. Despite advancements in Natural Language Processing (NLP), these narratives remain underutilised. Free text recording in EHRs allows expressivity, complements structured data from clinical coding systems, and facilitates collaborative care. Large language models (LLMs) excel in understanding and generating natural language, enabling complex dialogue processing. Integrating LLM tools into consultations could harness the untapped potential of free text to identify patient safety concerns, support diagnosis and provide content to enhance clinical-patient interactions. Tailoring LLMs for specific consultation tasks through pre-training and fine-tuning is viable. This paper outlines approaches for adopting LLMs in primary care and suggests that using fine-tuned LLMs with prompt engineering could enhance computer-mediated clinical consultation cost-effectively.