AI-Driven Chatbot for Mental Health Analysis Using Transformer Models

Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner.E2E approaches utilizing pre-trained models are gaining attention for conserving training data and resources.However, most of their applications in ASR involve only one of either a pre-trained speech or a language model.This paper proposes integrating a pre-trained speech representation model and a large language model (LLM) for E2E ASR.The proposed model enables the optimization of the entire ASR process, including acoustic feature extraction and acoustic and language modeling, by combining pre-trained models with a bridge network and also enables the application of remarkable developments in LLM utilization, such as parameter-efficient domain adaptation and inference optimization.Experimental results demonstrate that the proposed model achieves a performance comparable to that of modern E2E ASR models by utilizing powerful pre-training models with the proposed integrated approach.

PurposeLarge language models (LLMs) like Generative Pre-trained Transformer 4 (GPT-4) can assist in detecting errors in radiology reports, but privacy concerns limit their clinical applicability. This study compares closed-source and privacy-compliant open-source LLMs for detecting common errors in radiology reports.Materials and methodsA total of 120 radiology reports were compiled (30 each from X-ray, ultrasound, CT, and MRI). Subsequently, 397 errors from five categories (typographical, numerical, findings-impression discrepancies, omission/insertion, interpretation) were inserted into 100 of these reports; 20 reports were left unchanged. Two open-source models (Llama 3-70b, Mixtral 8x22b) and two commercial closed-source (GPT-4, GPT-4o) were tasked with error detection using identical prompts. The Kruskall–Wallis test and paired t-test were used for statistical analysis.ResultsOpen-source LLMs required less processing time per radiology report than closed-source LLMs (6 ± 2 s vs. 13 ± 4 s; p < 0.001). Closed-source LLMs achieved higher error detection rates than open-source LLMs (GPT-4o: 88% [348/397; 95% CI: 86, 92], GPT-4: 83% [328/397; 95% CI: 80, 87], Llama 3-70b: 79% [311/397; 95% CI: 76, 83], Mixtral 8x22b: 73% [288/397; 95% CI: 68, 77]; p < 0.001). Numerical errors (88% [67/76; 95% CI: 82, 93]) were detected significantly more often than typographical errors (75% [65/86; 95% CI: 68, 82]; p = 0.02), discrepancies between findings and impression (73% [73/101; 95% CI: 67, 80]; p < 0.01), and interpretation errors (70% [50/71; 95% CI: 62, 78]; p = 0.001).ConclusionOpen-source LLMs demonstrated effective error detection, albeit with comparatively lower accuracy than commercial closed-source models, and have potential for clinical applications when deployed via privacy-compliant local hosting solutions.Key PointsQuestionCan privacy-compliant open-source large language models (LLMs) match the error-detection performance of commercial non-privacy-compliant closed-source models in radiology reports?FindingsClosed-source LLMs achieved slightly higher accuracy in detecting radiology report errors than open-source models, with Llama 3-70b yielding the best results among the open-source models.Clinical relevanceOpen-source LLMs offer a privacy-compliant alternative for automated error detection in radiology reports, improving clinical workflow efficiency while ensuring patient data confidentiality. Further refinement could enhance their accuracy, contributing to better diagnosis and patient care.Graphical

Large language models (LLMs) continue to exhibit noteworthy capabilities across a spectrum of areas, including emerging proficiencies across the health care continuum. Successful LLM implementation and adoption depend on digital readiness, modern infrastructure, a trained workforce, privacy, and an ethical regulatory landscape. These factors can vary significantly across health care ecosystems, dictating the choice of a particular LLM implementation pathway. This perspective discusses 3 LLM implementation pathways—training from scratch pathway (TSP), fine-tuned pathway (FTP), and out-of-the-box pathway (OBP)—as potential onboarding points for health systems while facilitating equitable adoption. The choice of a particular pathway is governed by needs as well as affordability. Therefore, the risks, benefits, and economics of these pathways across 4 major cloud service providers (Amazon, Microsoft, Google, and Oracle) are presented. While cost comparisons, such as on-demand and spot pricing across the cloud service providers for the 3 pathways, are presented for completeness, the usefulness of managed services and cloud enterprise tools is elucidated. Managed services can complement the traditional workforce and expertise, while enterprise tools, such as federated learning, can overcome sample size challenges when implementing LLMs using health care data. Of the 3 pathways, TSP is expected to be the most resource-intensive regarding infrastructure and workforce while providing maximum customization, enhanced transparency, and performance. Because TSP trains the LLM using enterprise health care data, it is expected to harness the digital signatures of the population served by the health care system with the potential to impact outcomes. The use of pretrained models in FTP is a limitation. It may impact its performance because the training data used in the pretrained model may have hidden bias and may not necessarily be health care–related. However, FTP provides a balance between customization, cost, and performance. While OBP can be rapidly deployed, it provides minimal customization and transparency without guaranteeing long-term availability. OBP may also present challenges in interfacing seamlessly with downstream applications in health care settings with variations in pricing and use over time. Lack of customization in OBP can significantly limit its ability to impact outcomes. Finally, potential applications of LLMs in health care, including conversational artificial intelligence, chatbots, summarization, and machine translation, are highlighted. While the 3 implementation pathways discussed in this perspective have the potential to facilitate equitable adoption and democratization of LLMs, transitions between them may be necessary as the needs of health systems evolve. Understanding the economics and trade-offs of these onboarding pathways can guide their strategic adoption and demonstrate value while impacting health care outcomes favorably.

BackgroundIt has been validated that dementia can be alleviated by talk therapy. While general large language models (LLMs) have the potential for talk therapy and dementia treatment, customized LLMs resembling a mental‐health therapist can be more professional and powerful. We introduced an LLM solution designed for tailored mental health support for future dementia care. By employing GPT self‐generated data, encompassing a diverse range of mental health scenarios, we've significantly enhanced the model’s ability to understand and engage with complex emotional and psychological queries from patients. This advancement in LLMs paves the way for more efficient and effective delivery of talk therapy, shedding light for future dementia care and treatment.MethodWe fine‐tuned five open‐source LLMs to enhance their capabilities in the context of mental health counseling. The fine‐tuning process was conducted using the quantized Low‐Rank Adapters (QLoRA) method on an A40 GPU. We generated 10,000 question‐answer pairs as the training data using GPT‐3.5‐Turbo, designed to simulate interactions between mental health counselors and patients. This dataset encompassed a broad spectrum of mental health issues, including but not limited to depression, anxiety, and sleep disorders. Post fine‐tuning, the performance of these models in test data gathered from the Mental Health Forum and Quora (Fig. 2) was judged comprehensively by GPT‐4 Turbo. This evaluation was structured around six mental health metrics (Fig. 1) to ensure precise and relevant assessment in the context of mental health therapy.ResultThe top‐performing model, “Mixtral‐8×7B‐v0.1‐qlora,” achieved a remarkable average score of 7.83 (Tab. 1), highlighting its superior capability over the base model in handling complex mental health interactions. Other fine‐tuned models, such as “Zephyr‐7b‐gpt” and “Vicuna‐7b‐gpt,” also showcased exceptional performance over their base models, scoring 7.82 and 7.78 respectively. These results underscore the efficacy of fine‐tuning in enhancing the empathetic and contextual responsiveness of LLMs in mental health settings, particularly in dementia care.ConclusionThe study’s results showcased the effectiveness of fine‐tuned large language models (LLMs) suffixed by “QLoRA” in enhancing talk therapy. The leading model, “Mistral‐7B‐Instruct‐v0.2‐QLoRA,” demonstrated superior empathy and understanding over the base model in complex dementia interactions by leveraging domain‐specific data.

Accurate genomic prediction of complex phenotypes is crucial for accelerating genetic progress in swine breeding. However, conventional methods like Genomic Best Linear Unbiased Prediction (GBLUP) face limitations in capturing complex non-additive effects that contribute significantly to phenotypic variation, restricting the potential accuracy of phenotype prediction. To address this challenge, we introduce a novel framework based on a self-supervised, pre-trained encoder-only Transformer model. Its core novelty lies in tokenizing SNP sequences into non-overlapping 6-mers (sequences of 6 SNPs), enabling the model to directly learn local haplotype patterns instead of treating SNPs as independent markers. The model first undergoes self-supervised pre-training on the unlabeled version of the same SNP dataset used for subsequent fine-tuning, learning intrinsic genomic representations through a masked 6-mer prediction task. Subsequently, the pre-trained model is fine-tuned on labeled data to predict phenotypic values for specific economic traits. Experimental validation demonstrates that our proposed model consistently outperforms baseline methods, including GBLUP and a Transformer of the same architecture trained from scratch (without pre-training), in prediction accuracy across key economic traits. This outperformance suggests the model's capacity to capture non-linear genetic signals missed by linear models. This research contributes not only a new, more accurate methodology for genomic phenotype prediction but also validates the potential of self-supervised learning to decipher complex genomic patterns for direct application in breeding programs. Ultimately, this approach offers a powerful new tool to enhance the rate of genetic gain in swine production by enabling more precise selection based on predicted phenotypes.

Text summarization plays a pivotal role in condensing crucial information from huge volumes of text. This study investigates the utilization of pre-trained transformer models within the domain of text summarization, with a specific emphasis on extreme summarization. It delves into the effectiveness of two prominent models, text-to-text transfer transformers and bidirectional and auto-regressive transformers, when applied to the task of summarization, providing a comparative analysis of their capabilities. The experiments conducted in this study involve the utilization of the XSum and SciTLDR datasets. While fine-tuning T5 and BART on summarization tasks is a standard approach, we delve into the performance of these models without fine-tuning. Additionally, we explore the potential of other pretrained models, such as PREGASUS and distilBART, in generating concise and coherent summaries. This study contributes to the understanding of how pre-trained transformer models can be harnessed effectively for text summarization, especially in extreme summarization scenarios. The findings shed light on the performance, challenges, and potential of these models, opening avenues for further research in the field of automatic text summarization.

Continuous professional development of science teachers is closely related to their ability to reflect on their science lessons. For teachers to effectively reflect on their lesson, they need opportunities to make meaningful teaching-related experiences and receive guiding feedback for their reflections during initial teacher education. A sensible means to provide reflection opportunities for teachers is through written reflection assignments. However, assessing written reflections is conceptually challenging and resource-intensive. Recent developments suggest that artificial intelligence (AI) might provide novel opportunities for science teacher education and assessing written reflections. Consequently, we investigate ways in which AI in the form of a large language model can be utilized in a specific science teacher training program. The potential of AI for the use in higher education have been highlighted in recent years. However, it is noted that large language models oftentimes are too generic to be useful in specific science teacher education contexts. To address this issue, we used a pre-trained large language model and fine-tuned it to provide individualized feedback for pre-service physics teachers’ written reflection and investigated to which degree contextual factors impact the classification accuracy. Our results show that the pre-trained language model allowed a sufficient classification and that the classification accuracy can be improved by context specification. Our study highlights opportunities and challenges when utilizing AI, in particular large language models, for reflective writing analytics in science education.

Mental health diagnoses possess unique challenges that often lead to nuanced difficulties in managing an individual’s well-being and daily functioning. Self-report questionnaires are a common practice in clinical settings to help mitigate the challenges involved in mental health disorder screening. However, these questionnaires rely on an individual’s subjective response which can be influenced by various factors. Despite the advancements of Large Language Models (LLMs), quantifying self-reported experiences with natural language processing has resulted in imperfect accuracy. This project aims to demonstrate the effectiveness of zero-shot learning LLMs for screening and assessing item scales for depression using LLMs. The DAIC-WOZ is a publicly available mental health dataset that contains textual data from clinical interviews and self-report questionnaires with relevant mental health disorder labels. The RISEN prompt engineering framework was utilized to evaluate LLMs’ effectiveness in predicting depression symptoms based on individual PHQ-8 items. Various LLMs, including GPT models, Llama3_8B, Cohere, and Gemini were assessed based on performance. The GPT models, especially GPT-4o, were consistently better than other LLMs (Llama3_8B, Cohere, Gemini) across all eight items of the PHQ-8 scale in accuracy (M = 75.9%), and F1 score (0.74). GPT models were able to predict PHQ-8 items related to emotional and cognitive states. Llama 3_8B demonstrated superior detection of anhedonia-related symptoms and the Cohere LLM’s strength was identifying and predicting psychomotor activity symptoms. This study provides a novel outlook on the potential of LLMs for predicting self-reported questionnaire scores from textual interview data. The promising preliminary performance of the various models indicates there is potential that these models could effectively assist in the screening of depression. Further research is needed to establish a framework for which LLM can be used for specific mental health symptoms and other disorders. As well, analysis of additional datasets while fine-tuning models should be explored.

The use of Natural Language Processing (NLP) in the field of engineering seems complex with many applications which require calculations and engineering judgements. Large Language Models (LLM) have been successfully presented to be one of the most effective solutions in many specific fields such as arts and literature, to finance, to even software development. However, the use of LLM in the field of Civil Engineering and specifically in Geotechnical Engineering has not been discussed often compared to the other fields of expertise that utilize the functionalities of Application Programming Interfaces (API) of OpenAI. This paper aims to cover the details of the framework and breakdown of how LLMs can be used to train a domain-specific dataset, specifically related to settlement analysis, ground improvement, to slope stability analysis and provide results that are generated from a fine-tuned model with the dataset of research papers and technical documents provided by geotechnical engineers. The paper presents three folds: introduction for LLM models with pre-trained models, and choice of the models used. Then, the paper discusses the fine-tuning process of the LLM model with a domain-specific database. The paper provides benchmarks and metrics for performance of the model using the technique called Recall-Oriented Understudy for Gisting Evaluation (ROGUE) for validation of the outputs by comparing the result with prompt-completion pairs. With sufficient data for the prompt-completion pairs from the experts in the field and also from the scientific literature and localized technical documents, the LLM model trained with data related to the geotechnical engineering domain provides reasonable responses that otherwise would not have been achieved with the original ChatGPT LLM model. This paper introduces innovative way to manage current database of geotechnical documents and literature that can be optimized to be used with LLMs. The paper provides discussion of the comparative results and the future potential capabilities of its fine-tuned model.

Evaluating gpt-4 for zero-shot classification of bleeding and clotting events: Can large language models serve as second reviewers?

Adverse drug event (ADE) detection in social media texts poses significant challenges due to the informal nature of the text and the limited availability of annotations. The scarcity of ADE named entity recognition (NER) datasets for social media hinders the development of robust ADE detection models for this type of corpus. In this paper, we leveraged the generative capabilities of large language models (LLMs) to create synthetic data, addressing this dataset gap. Specifically, we generated 17,000 tweets with ADE annotations and pre-trained NER models on this synthetic data. Our evaluations on an out-of-sample collection of 915 manually annotated tweets revealed that these models outperform state-of-the-art lexico-based and massively pre-trained open NER models. We also show that fine-tuning our synthetically pre-trained models on human-annotated data surpasses the current state-of-the-art in ADE detection on tweets. These findings suggest that synthetic data generated by LLMs can enhance ADE detection performance, offering a promising avenue to explore in response to the scarcity of annotated ADE datasets. The synthetic dataset is available at https://huggingface.co/datasets/anthonyyazdaniml/synthetic-ner-ade-tweets-v1.

Automatic quantitative stroke severity assessment based on Chinese clinical named entity recognition with domain-adaptive pre-trained large language model

BackgroundArtificial intelligence (AI) has rapidly permeated various sectors, including healthcare, highlighting its potential to facilitate mental health assessments. This study explores the underexplored domain of AI’s role in evaluating prognosis...

In the field of confidentiality management, secret point recognition serves as an accurate and highly efficient approach. Due to the strict confidentiality requirements imposed on training data and the limited scope of data access, secret point recognition based on machine learning faces challenges in achieving good recognition results because of insufficient training data. This paper presents a secret point recognition algorithm using test-time augmentation (TTA) based on large language models. During training, a small amount of data was used to finetune the pretrained model. During inference, a large language model is used to paraphrase the input text, generating multiple expressions with different styles but the same meaning. These expressions are used as augmented data and are classified using a fine-tuned pre-trained classification model. The classification results were aggregated through an aggregation strategy to obtain the final prediction. To verify the effectiveness of the proposed method, we conducted experiments using simulated data. In the experiments, the ERNIE model was fine-tuned with a small amount of data. On this basis, TTA based on large language model was applied, and compared it with the BiLSTM and TextCNN methods. The experimental results demonstrate that this method can effectively improve the accuracy by 4.2 percent.

Embodied AI has notably advanced the autonomy of physical agents such as robots, vehicles, and AAVs, expanding their application scope. However, existing systems are predominantly data-driven, relying on static programming and pre-trained models. This limits their adaptability to dynamic and unforeseen scenarios. Additionally, the high computational cost of training large-scale models locally hinders their practical deployment. One promising solution lies in integrating Large Language Models (LLMs) into Embodied AI frameworks. Although LLMs excel in reasoning, coding, and perception, most existing frameworks adopt a single-LLM architecture, which restricts their effectiveness in addressing complex, multimodal tasks. The diverse strengths of individual LLMs, ranging from natural language understanding, visual processing to code generation, are seldom utilized in a collaborative and structured manner. To address these challenges, we propose a knowledge-driven framework, called EUF, that incorporates multi-LLMs into the Embodied AI architecture for AAV-as-a-Service in Intelligent Transportation Systems. Each LLM is dedicated to a specific stage of the AAV task, including user intent interpretation, adaptive path planning with code generation, and error-feedback mechanisms. Our research explores both One-shot and Segmented Code Generation approaches using various LLM-driven models to identify the optimal strategy. We conduct an in-depth analysis of different code errors to evaluate the strengths and limitations of each approach, including the feedback capabilities of the LLM-driven models. Experiments conducted in the AirSim environment demonstrate the framework’s robustness and accuracy in complex AAV path planning tasks, highlighting its practical potential for real-world ITS deployments.