OBJECTIVES: This study aims to evaluate the utility of large language models (LLMs) in healthcare, focusing on their applications in enhancing patient care through improved diagnostic, decision-making processes, and as ancillary tools for healthcare professionals. MATERIALS AND METHODS: We evaluated ChatGPT, GPT-4, and LLaMA in identifying patients with specific diseases using gold-labeled Electronic Health Records (EHRs) from the MIMIC-III database, covering three prevalent diseases-Chronic Obstructive Pulmonary Disease (COPD), Chronic Kidney Disease (CKD)-along with the rare condition, Primary Biliary Cirrhosis (PBC), and the hard-to-diagnose condition Cancer Cachexia. RESULTS: In patient identification, GPT-4 had near similar or better performance compared to the corresponding disease-specific Machine Learning models (F1-score ≥ 85%) on COPD, CKD, and PBC. GPT-4 excelled in the PBC use case, achieving a 4.23% higher F1-score compared to disease-specific "Traditional Machine Learning" models. ChatGPT and LLaMA3 demonstrated lower performance than GPT-4 across all diseases and almost all metrics. Few-shot prompts also help ChatGPT, GPT-4, and LLaMA3 achieve higher precision and specificity but lower sensitivity and Negative Predictive Value. DISCUSSION: The study highlights the potential and limitations of LLMs in healthcare. Issues with errors, explanatory limitations and ethical concerns like data privacy and model transparency suggest that these models would be supplementary tools in clinical settings. Future studies should improve training datasets and model designs for LLMs to gain better utility in healthcare. CONCLUSION: The study shows that LLMs have the potential to assist clinicians for tasks such as patient identification but false positives and false negatives must be mitigated before LLMs are adequate for real-world clinical assistance.

Search has become an integral part of Adobe products and users rely on it to learn about tool usage, shortcuts, quick links, and ways to add creative effects and to find assets such as backgrounds, templates, and fonts. Within applications such as Photoshop and Illustrator, users express domain-specific search intents via short text queries. In this work, we leverage sentence-BERT models fine-tuned on Adobe's HelpX data to perform multi-lingual semantic search on help and tutorial documents. We used behavioral data (queries, clicks, and impressions) and additional annotated data to train several BERT-based models for scoring query-document pairs for semantic similarity. We benchmarked the keyword-based production system against semantic search. Subsequent AB tests demonstrate that this approach improves engagement for longer queries while reducing null results significantly.

In order to optimally support learning, help should be given at an appropriate level: providing the users with new information, relevant to and needed for their task. This paper discusses the design and evaluation of such a help system, applied in the Radiology domain.

We report on the development of a knowledge representation model, which is based on the SHARED object model reported in Shared Workspaces for Computer-Aided Collaborative Engineering (Wong, A. and Sriram, D., Technical Report, IESL 93-06, Intelligent Engineering Systems Laboratory, Department of Civil Engineering, MIT, March, 1993) and Research in Engineering Design (Wong, A. and Sriram, D., SHARED: An Information Model for Cooperative Product Development, 1993, Fall, 21-39). Our current model is implemented as a layered scheme, that incorporates both an evolving artifact and its associated design process. To represent artifacts as they evolve, we define objects recursively without a pre-defined granularity on this recursive decomposition. This eliminates the need for translations between levels of abstraction in the design process. The SHARED model extends traditional OOP in three ways: by allowing explicit relationship classes with inheritance hierarchies; by permitting constraints to be associated with objects and relationships; and by comparing `similar' objects at three different levels (form, function and behavior).