Natural language processing for chest X‐ray reports in the transformer era: BERT‐like encoders for comprehension and GPT‐like decoders for generation

iRadiology, Год журнала: 2025, Номер unknown

Опубликована: Янв. 6, 2025

We conducted a comprehensive literature search in PubMed to illustrate the current landscape of transformer-based tools from perspective transformer's two integral components: encoder exemplified by BERT and decoder characterized GPT. Also, we discussed adoption barriers potential solutions terms computational burdens, interpretability concerns, ethical issues, hallucination problems, malpractice, legal liabilities. hope that this commentary will serve as foundational introduction for radiologists seeking explore evolving technical chest X-ray report analysis transformer era. Natural language processing (NLP) has gained widespread use computer-assisted (CXR) analysis, particularly since renaissance deep learning (DL) 2012 ImageNet challenge. While early endeavors predominantly employed recurrent neural networks (RNN) convolutional (CNN) [1], revolution is brought [2] its success can be attributed three key factors [3]. First, self-attention mechanism enables simultaneous multiple parts an input sequence, offering significantly greater efficiency compared earlier models such RNN [4]. Second, architecture exhibits exceptional scalability, supporting with over 100 billion parameters capture intricate linguistic relationships human [5]. Third, availability vast internet-based corpus advances power have made pre-training fine-tuning large-scale feasible [6]. The development resolution previously intractable problems achieves expert-level performance across broad range CXR analytical tasks, name entity recognition, question answering, extractive summarization [7]. In commentary, (Figure 1) landscape, barriers, handling comprehension managing generation. As our primary focus NLP, classification criteria or was based on text modules excluded research purely focusing vision transformers (ViT). Literature pipeline identify relevant articles published June 12, 2017, when model first introduced, October 4, 2024. followed previous systematic reviews [3, 8, 9] design groups keywords: (1) "transformer"; (2) "clinical notes", reports", narratives", text", "medical text"; (3) "natural processing", "text mining", "information extraction"; (4) "radiography", "chest film", radiograph", "radiograph", "X-rays". means communication between referring physicians, reports contain high-density information patients' conditions [10]. Much like physicians interpreting reports, step NLP understanding content important application explicitly converting it into format suitable subsequent tasks. One notable [11], which stands bidirectional representations transformers. contrast predecessors rely large amounts expert annotations supervised [12], undergoes self-supervised training unlabeled datasets understand patterns subsequently fine-tuned small set target task [12, 13], yielding superior [14], recognition [15], [16], semantics optimization [17]. context healthcare, Olthof et al. [18] built evaluate varying complexities, disease prevalence, sample sizes, demonstrating statistically outperformed conventional DL CNN, area under curve F1-score, t-test p-values less than 0.05. Beyond models, adapting domain-specific further enhance effectiveness various Yan [19] adapted four BERT-like encoders using millions radiology tackle tasks: identifying sentences describe abnormal findings, assigning diagnostic codes, extracting summarize reports. Their results demonstrated adaptation yielded significant improvements accuracy, ROUGE metrics all Most BERT-relevant studies sentence-, paragraph-, report-level predictions, while are also well-suited word-level pattern recognition. Chambon [20] leveraged [21], biomedical-specific BERT, probability individual tokens containing protected health information, replaced identified sensitive synthetic surrogates ensure privacy preservation. Similarly, Weng [22] developed system utilizing ALBERT [23], lite reduced parameters, keywords unrelated thereby reducing false-positive alarms outperforming regular expression-, syntactic grammar-, DL-based baselines. BERT-derived labels applied develop targeting other modalities 13]. Nowak [24] systematically explored utility BERT-generated silver linked them corresponding radiographs image classifiers. Compared trained exclusively radiologist-annotated gold labels, integrating led improved discriminability. macro-averaged synchronous proved effective settings limited whereas silver, better cases abundant labels. Zhang [25] introduced novel approach more generalizable classifiers, rather relying predefined categories: first, they used extract entities relationships; second, constructed knowledge graph these extractions; third, refined their domain expertise. Unlike traditional multiclass established not only categorized each but revealed interpretable categories, those linking anatomical regions signs. addition deriving advanced capabilities unprecedented innovation: direct supervision pixel-level segmentation medical [26]. Li [26] proposed text-augmented lesion paradigm integrated BERT-based textual compensate deficiency radiograph quality refine pseudo semi-supervision. These highlight strength comprehending healthcare-related annotation systems multi-modality beyond text. Meanwhile, researchers failures complex clinical Sushil [27] implementations inference achieved test accuracy 0.778. adaptations textbooks 0.833, still fell short experts. Potential limitations lie relatively modest parameter size, although larger reliance inadequate corpora, books, Wikipedia, selected databases [28]. Consequently, ability learn remains constrained. shortcomings being alleviated GPT-like decoders, incorporate hundreds billions internet-scale corpora [29]. Following advent encoders, generative pre-trained (GPT) [30], next groundbreaking leap, breaks enabling non-experts perform tasks through freely conversational without any coding. CvT2DistilGPT2 [31], prominent generator era, utilizes ViT GPT-2 decoder. experiments indicated CNN GPT surpassed encoder–decoder architectures specific generation applications, state-of-the-art methods integrate decoders. TranSQ [32] framework. emulates reasoning process generating reports: formulating hypothesis embeddings represent implicit intentions, querying visual features extracted synthesizing semantic cross-modality fusion, transforming candidate DistilGPT [33]. Finally, attained BLEU-4 score 0.205 0.409. comparison, best-performing baseline among 17 retrieval 0.188 0.383, highlighting capability unified multi-modality. Though decoders dominated general domain, family long short-term memory (LSTM) [34] good partially because highly templated characteristics [32]. Kaur Mittal [35] classical architectures, feature extraction, LSTM token They modules, generate numerical inputs prior shortlist disease-relevant afterward. Results presented solution 0.767 0.897, suggesting approaches remain viable backbone scenarios. quantitative comparing outputs ground truth model-generated should supplemented evaluation Boag [36] study automated generation, divergence accuracy. A discrepancy readability been reported [37]. Accordingly, emphasize involvement rating correctness readability. sections, reviewed applications Although remarkable well-established, face problems. Some integration specialized expertise [31, 38], others necessitate resolution. demands era substantial. For example, version contains 334 million GPT-3 175 billion. contrast, support vector machines [39] random forests [40], require few hundred thousand parameters. result, many healthcare providers cannot afford costs tailoring scratch. To address this, offer several recommendations. development, suggest leverage open-access building fine-tuning, considering scales, recommend parameter-efficient technique updates subset model's leaving majority weights unchanged [41]. An exemplificative Taylor [42] empirically validated techniques within domain. advocate prompt engineering techniques, retrieval-augmented crafting informative instructive guide decoders' output changing [43]. Ranjit [44] method retrieve most contextual prompts concise accurate retaining critical entities. Last least, obtaining approval ethics committees share anonymous data facilitate collaboration external partners, helping alleviate resource burdens. including both where decisions directly impact lives. often regarded black-box simple render explainable modern layers neurons dissected visualized, providing insights functionality [45-48]. behavior challenge due complexity associated exponential scaling neuron numbers [49]. though internal activations challenging interpret, preliminary analyzing influence high degree alignment assessments [50, 51]. lies flexibility align instructions. This allows users obtain expected request explanations outputs, fostering enhanced usability [52, 53]. readers overview detailed insights, surveys [54-56]. considerations paramount transformers, given powerful nuanced datasets. concerns pressing private representative population. patient privacy, anonymizing during deployment stages neither learned [57] nor inadvertently disclosed certain [58]. Dataset representativeness issue, underrepresentation minority exacerbate disparities perpetuate inequities [59]. mitigate risk, developers prioritize inclusivity collection, maintainers continuously monitor equitable outcomes [60]. Fourth, coherent responses diverse user solving wide [61], predictive internet instead radiological well-defined logic [62]. Therefore, continue suffer hallucinations, phenomenon appears plausible factually incorrect, nonsensical, users' [63]. Current efforts broadly post-training stages. During training, strategies include in-house reinforcement guided radiologists' feedback 64]. Post-training encompass detection, knowledge, multi-agent collaboration, radiologist-in-the-loop frameworks [62, 65]. Due space constraints, encourage refer 66-68] strategies. Lastly, even after refinements, may present risks potentially leading errors liabilities [69]. Errors arise sources, inaccurate clinician nonadherence correct recommendations, poor workflows [70]. determining responsibility adverse issue stakeholders, software developers, maintenance teams, departments, [71]. European Commission focuses safety liability implications artificial intelligence, applies device laws demonstrates generally falls civil product Civil typically pertains developers. However, stops strict definitive framework inherent ambiguity algorithms questions surrounding likely addressed courts case law. Under existing frameworks, follow standard care, supplementary confirmatory substitutes practice beneficial stakeholders Additionally, departments implement tools, involve radiologists, throughout entire cycle [72], prepare in-depth programs familiarize differ routine statistical tests black boxes resist full interpretation [73]. Moreover, expectations important: unrealistic optimism, seen replacement expertise, undue pessimism, perceived no utility, avoided [74-77]. Han Yuan: Conceptualization; curation; formal analysis; investigation; project administration; validation; visualization; writing—original draft; writing—review editing. None. author declares he conflicts interest. exempt review committee does participants, animal subjects, collection. Not applicable. Data sharing apply were generated analyzed.

Язык: Английский

---

Exploring instructional designers' utilization and perspectives on generative AI tools: A mixed methods study

Educational Technology Research and Development, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 25, 2024

Abstract The emergence of generative artificial intelligence (GenAI) has caused significant disruptions on a global scale in various workplace settings, including the field instructional design (ID). Given paucity research investigating impact GenAI ID work, we conducted mixed methods study to understand designers (IDs)’ perceptions and experiences utilizing across spectrum tasks. A total 70 IDs completed an online survey, 13 them participated semi-structured interviews. survey results indicated IDs’ familiarity with perceived usability tools performing responsibilities their specific contexts. Qualitative findings further explained that often utilized (1) brainstorming ideas, (2) handling low-stake tasks, (3) streamlining process, (4) enhancing collaborations. Participants also expressed concerns challenges while using ID, quality concerns, data security privacy over authorship, ownership plagiarism, amongst others. Implications recommendations are discussed inform future practices research.

Язык: Английский

---

A Systematic Review and Comprehensive Analysis of Pioneering AI Chatbot Models from Education to Healthcare: ChatGPT, Bard, Llama, Ernie and Grok

Future Internet, Год журнала: 2024, Номер 16(7), С. 219 - 219

Опубликована: Июнь 22, 2024

AI chatbots have emerged as powerful tools for providing text-based solutions to a wide range of everyday challenges. Selecting the appropriate chatbot is crucial optimising outcomes. This paper presents comprehensive comparative analysis five leading chatbots: ChatGPT, Bard, Llama, Ernie, and Grok. The based on systematic review 28 scholarly articles. indicates that developed by OpenAI, excels in educational, medical, humanities, writing applications but struggles with real-time data accuracy lacks open-source flexibility. powered Google, leverages internet problem solving shows potential competitive quiz environments, albeit performance variability inconsistencies responses. an model from Meta, demonstrates significant promise medical contexts, natural language processing, personalised educational tools, yet it requires substantial computational resources. Baidu, specialises Chinese tasks, thus localised advantages may not extend globally due restrictive policies. Grok, Xai still its early stages, engaging, interactions, humour, mathematical reasoning capabilities, full remains be evaluated through further development empirical testing. findings underscore context-dependent utility each absence singularly superior chatbot. Future research should expand include wider fields, explore practical applications, address concerns related privacy, ethics, security, responsible deployment these technologies.

Язык: Английский

---

Mental Health Applications of Generative AI and Large Language Modeling in the United States

International Journal of Environmental Research and Public Health, Год журнала: 2024, Номер 21(7), С. 910 - 910

Опубликована: Июль 12, 2024

(1) Background: Artificial intelligence (AI) has flourished in recent years. More specifically, generative AI had broad applications many disciplines. While mental illness is on the rise, proven valuable aiding diagnosis and treatment of disorders. However, there little to no research about precisely how much interest technology. (2) Methods: We performed a Google Trends search for “AI health” compared relative volume (RSV) indices “AI”, Depression”, anxiety”. This time series study employed Box–Jenkins modeling forecast long-term through end 2024. (3) Results: Within United States, steadily increased throughout 2023, with some anomalies due media reporting. Through predictive models, we found that this trend predicted increase 114% year 2024, public being rise. (4) Conclusions: According our study, awareness drastically especially health. demonstrates increasing health AI, making advocacy education technology paramount importance.

Язык: Английский

---

Information Security, Ethics, and Integrity in LLM Agent Interaction

Journal of Information Security, Год журнала: 2025, Номер 16(01), С. 184 - 196

Опубликована: Янв. 1, 2025

Язык: Английский

---

AI Safety in Computer-Assisted Language Learning

Опубликована: Янв. 1, 2025

Язык: Английский

---

Ethical Challenges in AI-Driven Strategic Communication: Identification and Mitigation Strategies

Опубликована: Янв. 1, 2025

Язык: Английский

---

Leveraging generative AI synthetic and social media data for content generalizability to overcome data constraints in vision deep learning

Artificial Intelligence Review, Год журнала: 2025, Номер 58(5)

Опубликована: Фев. 24, 2025

Язык: Английский

---

AI for cyber-security risk: harnessing AI for automatic generation of company-specific cybersecurity risk profiles

Information and Computer Security, Год журнала: 2025, Номер unknown

Опубликована: Фев. 26, 2025

Purpose In the modern digital realm, artificial intelligence (AI) technologies create unprecedented opportunities and enhance tactical security operations. This study aims to address gap in using AI strategically produce holistic cybersecurity risk profiles. Design/methodology/approach paper uses a rigorous AI-powered method conduct profiles tailored individual enterprises, investigating sources of threat guiding defense strategies. built real working demo application based on databases used it build company-specific Findings demonstrated robust, automated process for developing three case studies across different industries. The produced coherent outputs, validated by experts as accurate. Research limitations/implications lays groundwork further research, allowing refinement integrating additional resources, such near-real-time alerts from external or internal sources. Practical implications escalating landscape highlights need organizations adopt management, leveraging tools that assist defining refining measures. Social Using AI-generated supports efforts safer environment organizations, their employees customers, aligning with growing reliance daily life. Originality/value Unlike most papers, this an contemporary challenges creating holistic, non-tactical can be refined contextualized while achieving automation key processes multiple resources.

Язык: Английский

---

“Thus spoke Socrates”: enhancing ethical inquiry, decision, and reflection through

AI and Ethics, Год журнала: 2025, Номер unknown

Опубликована: Март 7, 2025

Язык: Английский

---