Language-based Model Research Articles

Addressing Semantic Variability in Clinical Outcome Reporting Using Large Language Models

Background/Objectives: Clinical trials frequently employ diverse terminologies and definitions to describe similar outcomes, leading to ambiguity and inconsistency in data interpretation. Addressing the variability in clinical outcome reports and integrating semantically similar outcomes is important in healthcare and clinical research. Variability in outcome reporting not only hinders the comparability of clinical trial results but also poses significant challenges in evidence synthesis, meta-analysis, and evidence-based decision-making. Methods: This study investigates variability reduction in outcome measures reporting using rule-based and large language-based models. It aims to mitigate the challenges associated with variability in outcome reporting by comparing these two models. The first approach, which is rule-based, will leverage well-known ontologies, and the second approach exploits sentence-bidirectional encoder representations from transformers (SBERT) to identify semantically similar outcomes along with Generative Pre-training Transformer (GPT) to refine the results. Results: The results show that the relatively low percentages of outcomes are linked to established rule-based ontologies. Analysis of outcomes by word count highlighted the absence of ontological linkage for three-word outcomes, which indicates potential gaps in semantic representation. Conclusions: Employing large language models (LLMs), this study demonstrates its ability to identify similar outcomes, even with more than three words, suggesting a crucial role in outcome harmonization efforts, potentially reducing redundancy and enhancing data interoperability.

ChatGPT and Its Role in Outpatient Departments

Background: ChatGPT is a language-based model built with a ‘super brain' containing a database with adequate medical knowledge used in diagnosis, investigations and management of diseases. Objectives: This study aims to explore the possibility of using ChatGPT as an assistive tool in outpatient clinics. Methods: This is a descriptive cross-sectional study. Our study targeted a population of 259 post graduate residents and consultants from reputable institutions of Punjab using convenient sampling techniques. The data collection tool was a structured questionnaire shared via google forms and distributed manually. It assessed physicians use of ChatGPT, perceived usefulness in management of patients and its role in prevention of disease and improvement of the healthcare system. Results: The responses were taken on a 5-point scale, and consisted of a greater population of female physicians 138(53.3%) as compared to males 121 (46.7%). A whopping majority of physicians found ChatGPT to be efficacious in outpatient settings (59.1%).A significant percentage of people highlighted a decrease in burn out (61%), aid in correct diagnosis (62.5%) and adequate treatment plans laid out by ChatGPT (46.7%). The responses indicated 78.4% of the participants believed that ChatGPT has a positive impact in outpatient departments Conclusion: ChatGPT shows significant potential in serving as a cognitive assistant to physicians as we inculcate it into our healthcare system. It is set to make the outpatient experience much improved for both the physicians and the patients.

Does Artificial Intelligence Speak Our Language?: A Gadamerian Assessment of Generative Language Models

The language argument is a classic argument for human distinctiveness that, for millenia, has been used to distinguish humans from non-human animals. Generative language models (GLMs) pose a challenge to traditional language-based models of human distinctiveness precisely because they can communicate and respond in a manner resembling humanity’s linguistic capabilities. This article asks: have GLMs acquired natural language? Employing Gadamer’s theory of language, I argue that they have not. While GLMs can reliably generate linguistic content that can be interpreted as “texts,” they lack the linguistically mediated reality that language provides. Missing from these models are four key features of a linguistic construction of reality: groundedness to the world, understanding, community, and tradition. I conclude with skepticism that GLMs can ever achieve natural language because they lack these characteristics in their linguistic development.

Improving Open Set Recognition via Visual Prompts Distilled from Common-Sense Knowledge

Open Set Recognition (OSR) poses significant challenges in distinguishing known from unknown classes. In OSR, the overconfidence problem has become a persistent obstacle, where visual recognition models often misclassify unknown objects as known objects with high confidence. This issue stems from the fact that visual recognition models often lack the integration of common-sense knowledge, a feature that is naturally present in language-based models but lacking in visual recognition systems. In this paper, we propose a novel approach to enhance OSR performance by distilling common-sense knowledge into visual prompts. Utilizing text prompts that embody common-sense knowledge about known classes, the proposed visual prompt is learned by extracting semantic common-sense features and aligning them with image features from visual recognition models. The unique aspect of this work is the training of individual visual prompts for each class to encapsulate this common-sense knowledge. Our methodology is model-agnostic, capable of enhancing OSR across various visual recognition models, and computationally light as it focuses solely on training the visual prompts. This research introduces a method for addressing OSR, aiming at a more systematic integration of visual recognition systems with common-sense knowledge. The obtained results indicate an enhancement in recognition accuracy, suggesting the applicability of this approach in practical settings.

An artificial neural network approach for the language learning model

The current study provides the numerical solutions of the language-based model through the artificial intelligence (AI) procedure based on the scale conjugate gradient neural network (SCJGNN). The mathematical learning language differential model is characterized into three classes, named as unknown, familiar, and mastered. A dataset is generalized by using the performance of the Adam scheme, which is used to reduce to mean square error. The AI based SCJGNN procedure works by taking the data with the ratio of testing (12%), validation (13%), and training (75%). An activation log-sigmoid function, twelve numbers of neurons, SCJG optimization, hidden and output layers are presented in this stochastic computing work for solving the learning language model. The correctness of AI based SCJGNN is noted through the overlapping of the results along with the small calculated absolute error that are around 10–06 to 10–08 for each class of the model. Moreover, the regression performances for each case of the model is performed as one that shows the perfect model. Additionally, the dependability of AI based SCJGNN is approved using the histogram, and function fitness.

Artificial Intelligence in Scoliosis Classification: An Investigation of Language-Based Models.

Open-source artificial intelligence models are finding free application in various industries, including computer science and medicine. Their clinical potential, especially in assisting diagnosis and therapy, is the subject of increasingly intensive research. Due to the growing interest in AI for diagnostics, we conducted a study evaluating the abilities of AI models, including ChatGPT, Microsoft Bing, and Scholar AI, in classifying single-curve scoliosis based on radiological descriptions. Fifty-six posturographic images depicting single-curve scoliosis were selected and assessed by two independent neurosurgery specialists, who classified them as mild, moderate, or severe based on Cobb angles. Subsequently, descriptions were developed that accurately characterized the degree of spinal deformation, based on the measured values of Cobb angles. These descriptions were then provided to AI language models to assess their proficiency in diagnosing spinal pathologies. The artificial intelligence models conducted classification using the provided data. Our study also focused on identifying specific sources of information and criteria applied in their decision-making algorithms, aiming for a deeper understanding of the determinants influencing AI decision processes in scoliosis classification. The classification quality of the predictions was evaluated using performance evaluation metrics such as sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and balanced accuracy. Our study strongly supported our hypothesis, showing that among four AI models, ChatGPT 4 and Scholar AI Premium excelled in classifying single-curve scoliosis with perfect sensitivity and specificity. These models demonstrated unmatched rater concordance and excellent performance metrics. In comparing real and AI-generated scoliosis classifications, they showed impeccable precision in all posturographic images, indicating total accuracy (1.0, MAE = 0.0) and remarkable inter-rater agreement, with a perfect Fleiss' Kappa score. This was consistent across scoliosis cases with a Cobb's angle range of 11-92 degrees. Despite high accuracy in classification, each model used an incorrect angular range for the mild stage of scoliosis. Our findings highlight the immense potential of AI in analyzing medical data sets. However, the diversity in competencies of AI models indicates the need for their further development to more effectively meet specific needs in clinical practice.

The online language of work-personal conflict

With the blurring of boundaries in this digital age, there is increasing concern around work-personal conflict. Assessing and tracking work-personal conflict is critical as it not only affects individual workers but is also a vital measure among broader well-being and economic indices. This inductive study examines the extent to which work-personal conflict corresponds to individuals’ language use on social media. We apply an open-vocabulary analysis to the posts of 2810 Facebook users who also completed a survey for an established work-personal conflict scale. It was found that the language-based model can predict personal-to-work conflict (r = 0.23) and work-to-personal conflict (r = 0.15) and provide important insights into such conflicts. Specifically, we found that high personal-to-work conflict was associated with netspeak and swearing, while low personal-to-work conflict was associated with language about work and positivity. We found that high work-to-personal conflict was associated with negative emotion and negative tone, while low work-to-personal conflict was associated with positive emotion and language about birthdays.

The Role of ChatGPT in the Advancement of Diagnosis, Management, and Prognosis of Cardiovascular and Cerebrovascular Disease.

Cardiovascular and cerebrovascular disease incidence has risen mainly due to poor control of preventable risk factors and still constitutes a significant financial and health burden worldwide. ChatGPT is an artificial intelligence language-based model developed by OpenAI. Due to the model's unique cognitive capabilities beyond data processing and the production of high-quality text, there has been a surge of research interest concerning its role in the scientific community and contemporary clinical practice. To fully exploit ChatGPT's potential benefits and reduce its possible misuse, extreme caution must be taken to ensure its implications ethically and equitably. In this narrative review, we explore the language model's possible applications and limitations while emphasizing its potential value for diagnosing, managing, and prognosis of cardiovascular and cerebrovascular disease.

An explainable machine learning model of cognitive decline derived from speech.

Traditional Alzheimer's disease (AD) and mild cognitive impairment (MCI) screening lacks the sensitivity and timeliness required to detect subtle indicators of cognitive decline. Multimodal artificial intelligence technologies using only speech data promise improved detection of neurodegenerative disorders. Speech collected over the telephone from 91 older participants who were cognitively healthy (n=29) or had diagnoses of AD (n=30) or amnestic MCI (aMCI; n=32) was analyzed with multimodal natural language and speech processing methods. An explainable ensemble decision tree classifier for the multiclass prediction of cognitive decline was created. This approach was 75% accurate overall-an improvement over traditional speech-based screening tools and a unimodal language-based model. We include a dashboard for the examination of the results, allowing for novel ways of interpreting such data. This work provides a foundation for a meaningful change in medicine as clinical translation, scalability, and user friendliness were core to the methodologies. Remote assessments and artificial intelligence (AI) models allow greater access to cognitive decline screening.Speech impairments differ significantly between mild AD, amnestic mild cognitive impairment (aMCI), and healthy controls.AI predictions of cognitive decline are more accurate than experts and standard tools.The AI model was 75% accurate in classifying mild AD, aMCI, and healthy controls.

Assessing structure and disorder prediction tools for de novo emerged proteins in the age of machine learning.

Background: De novo protein coding genes emerge from scratch in the non-coding regions of the genome and have, per definition, no homology to other genes. Therefore, their encoded de novo proteins belong to the so-called "dark protein space". So far, only four de novo protein structures have been experimentally approximated. Low homology, presumed high disorder and limited structures result in low confidence structural predictions for de novo proteins in most cases. Here, we look at the most widely used structure and disorder predictors and assess their applicability for de novo emerged proteins. Since AlphaFold2 is based on the generation of multiple sequence alignments and was trained on solved structures of largely conserved and globular proteins, its performance on de novo proteins remains unknown. More recently, natural language models of proteins have been used for alignment-free structure predictions, potentially making them more suitable for de novo proteins than AlphaFold2. Methods: We applied different disorder predictors (IUPred3 short/long, flDPnn) and structure predictors, AlphaFold2 on the one hand and language-based models (Omegafold, ESMfold, RGN2) on the other hand, to four de novo proteins with experimental evidence on structure. We compared the resulting predictions between the different predictors as well as to the existing experimental evidence. Results: Results from IUPred, the most widely used disorder predictor, depend heavily on the choice of parameters and differ significantly from flDPnn which has been found to outperform most other predictors in a comparative assessment study recently. Similarly, different structure predictors yielded varying results and confidence scores for de novo proteins. Conclusions: We suggest that, while in some cases protein language model based approaches might be more accurate than AlphaFold2, the structure prediction of de novo emerged proteins remains a difficult task for any predictor, be it disorder or structure.

Insulin hesitancy: A language-based model.

Psychological insulin resistance is a well known entity. This communication proposes the term 'insulin hesitancy' to describe the hesitation that a person living with diabetes experiences, when advised to take insulin. It approaches hesitancy through a triage model, based upon the language used by the patient. By identifying the predominant adverb, "will not", "shall not", or "cannot" in the patient's speech, the diabetes care professional can assess the degree of insulin hesitancy, and tailor his or her conversation towards overcoming it.

A study on the relevance of semantic features extracted using BERT-based language models for enhancing the performance of software defect classifiers

In the context of new research in the software defect prediction (SDP) task using pre-trained language models, the present study aims to analyze the relevance of semantic features extracted using BERT-based language models for the detection of defective source codes. RoBERTa and CodeBERT-MLM language models are used to generate source code embeddings that capture semantic and contextual features which help in solving language understanding tasks such as SDP. The learned representations are then fed to a neural network-based SDP classifier in order to decide which of the learned code embeddings are more informative in discriminating between faulty and non-faulty software entities. Extensive experiments are conducted in a cross-version SDP scenario for Apache Calcite, an open-source framework for data management. The evaluation results of the defect classifiers show a statistically significant improvement when the code representations are learned by the pre-trained models compared with the semantic representations provided by other natural language-based models, doc2vec and LSI.

Integrating Verbal Short-Term Memory Into the Assessment and Treatment of Aphasia

Purpose:Verbal short-term memory (STM) impairment is ubiquitous in people with aphasia, and its severity generally parallels the severity of word processing impairment. In language-based models of STM, verbal STM arises from the activation and maintenance of linguistic representations. Measures of verbal STM can provide insight into the nature of language processing deficits in aphasia and should be a component of comprehensive assessment and treatment plans. Although verbal STM impairment in aphasia is widely studied in the research community, inclusion of verbal STM assessment and treatment in clinical practice remains limited.Method:This tutorial presents a description of language-based models of verbal STM and factors that contribute to performance in verbal STM tasks. We outline a model of verbal STM assessment and intervention that considers two levels of linguistic processing deficits (i.e., semantic vs. phonological), temporal variability in performance and access to representations (activation transmission vs. maintenance), and the effects of memory load. This tutorial presents a practical framework for the integration of measures of verbal STM in both assessment and treatment. Case studies are included to facilitate learning.Conclusions:This tutorial provides clinicians with the theoretical background and practical framework for integration of verbal STM in both treatment and assessment. While the assessment and treatment of verbal STM deficits in aphasia is in the beginning stages of implementation in the clinical setting, it offers a promising avenue for aphasia rehabilitation.

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery.

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

Harvest – a System for Creating Structured Rate Filing Data from Filing PDFs

We present a machine-learning-guided process that can efficiently extract factor tables from unstructured rate filing documents. Our approach combines multiple deep-learning-based models that work in tandem to create structured representations of tabular data present in unstructured documents such as pdf files. This process combines CNN's to detect tables, language-based models to extract table metadata and conventional computer vision techniques to improve the accuracy of tabular data on the machine-learning side. The extracted tabular data is validated through an intuitive user interface. This process, which we call Harvest, significantly reduces the time needed to extract tabular information from PDF files, enabling analysis of such data at a speed and scale that was previously unattainable.

An Information Theoretic Approach to Symbolic Learning in Synthetic Languages.

An important aspect of using entropy-based models and proposed “synthetic languages”, is the seemingly simple task of knowing how to identify the probabilistic symbols. If the system has discrete features, then this task may be trivial; however, for observed analog behaviors described by continuous values, this raises the question of how we should determine such symbols. This task of symbolization extends the concept of scalar and vector quantization to consider explicit linguistic properties. Unlike previous quantization algorithms where the aim is primarily data compression and fidelity, the goal in this case is to produce a symbolic output sequence which incorporates some linguistic properties and hence is useful in forming language-based models. Hence, in this paper, we present methods for symbolization which take into account such properties in the form of probabilistic constraints. In particular, we propose new symbolization algorithms which constrain the symbols to have a Zipf–Mandelbrot–Li distribution which approximates the behavior of language elements. We introduce a novel constrained EM algorithm which is shown to effectively learn to produce symbols which approximate a Zipfian distribution. We demonstrate the efficacy of the proposed approaches on some examples using real world data in different tasks, including the translation of animal behavior into a possible human language understandable equivalent.

ATTENTION BASED IMAGE CAPTIONING USING DEEP LEARNING

The process of deriving written descriptions from a picture based on the items and behaviours portrayed is known as image caption generation. The resulting description will represent what is in the image and the interactions among the objects. However, like with any other image processing challenge, recreating this characteristic in an artificial system is a difficult feat, and so the adoption Deep Learning procedures can help to tackle the problem. The main goal of this project is to generate an image captioning model that can provide a concise and relatable description of the picture by incorporating an attention mechanism. Ideally, the model can be separated into two components – one is called Encoder and the other is a Decoder. The encoder used here is a Google InceptionV3 pre-trained model. And the decoder is a language-based model, Gated Recurrent Unit (GRU) to translate the characteristics and objects provided by the encoder into natural sentences. Furthermore, the model's effectiveness is aided by the attention mechanism. To conclude, the model is trained on a subset of the MS COCO dataset, which contains about 80,000 pictures with at least five descriptions each and evaluated based on the BLEU score. To reduce the loss, the model weights are tuned using the categorical cross-entropy loss function. The results of the model are promising and competitive.

ACTION RESEARCH ON USING SHORT STORIES TO BOOST EFL LEARNERS’ PERFORMANCE: A SYSTEMATIC REVIEW

Various conceptual and empirical research has revealed that short stories are effective learning tools teachers can use to boost English as a foreign language (EFL) learning performances. However, most EFL teachers are still find using short stories in EFL classrooms challenging. To solve the problem, conducting action research on using short stories in EFL teaching seems to be the best option. This study aims at reviewing action research on using short story use to increase EFL students’ learning achievement. Employing four inclusion and three exclusion criteria, 12 action research articles indexed in Google Scholar and published in 2011-2020 were selected. Data were analyzed using the constant comparative method. The results showed that the use of short stories employing the Before-During-After reading strategy, language-based model, and literature as content model managed to attain the intended outcomes in 2 to 3 cycles. This review is ended by highlighting some research gaps for future action research and future review as well.

Sentiment Analysis of Nepali COVID19 Tweets Using NB, SVM AND LSTM

The government's months-long total lockdown in response to the COVID19 outbreak has resulted in a lack of physical connection with others. This resulted in a massive increase in social media communication. Twitter has become one of the most popular places for people to communicate their thoughts and opinions. As a result, massive amounts of data are created every day. These data can assist businesses in making better judgments. In the case of Nepal, there has been relatively little investigation into the text's analysis. Because few researchers are working in the field, development is slow. In this study, Four language-based models for sentiment analysis of Nepali covid19 tweets are designed and evaluated. Because the number of individuals using social media is expected to skyrocket in the next few days, companies will benefit from an AI-based sentiment analysis system. It will greatly assist firms in adapting to the changing climate.

Object representations in the human brain reflect the co-occurrence statistics of vision and language

A central regularity of visual perception is the co-occurrence of objects in the natural environment. Here we use machine learning and fMRI to test the hypothesis that object co-occurrence statistics are encoded in the human visual system and elicited by the perception of individual objects. We identified low-dimensional representations that capture the latent statistical structure of object co-occurrence in real-world scenes, and we mapped these statistical representations onto voxel-wise fMRI responses during object viewing. We found that cortical responses to single objects were predicted by the statistical ensembles in which they typically occur, and that this link between objects and their visual contexts was made most strongly in parahippocampal cortex, overlapping with the anterior portion of scene-selective parahippocampal place area. In contrast, a language-based statistical model of the co-occurrence of object names in written text predicted responses in neighboring regions of object-selective visual cortex. Together, these findings show that the sensory coding of objects in the human brain reflects the latent statistics of object context in visual and linguistic experience.