OBJECTIVES: Mapping clinical classification systems, such as the International Classification of Diseases (ICD), is essential yet challenging. While the manual mapping method remains labor-intensive and lacks scalability, existing embedding-based automatic mapping methods, particularly those leveraging transformer-based pretrained encoders, encounter 2 persistent challenges: (1) linguistic variation and (2) varying granular details in clinical conditions. MATERIALS AND METHODS: We introduce an automatic mapping method that combines the representational power of pretrained encoders with the reasoning capability of large language models (LLMs). For each ICD code, we generate: (1) hierarchy-augmented (HA) and (2) LLM-generated (LG) descriptions to capture rich semantic nuances, addressing linguistic variation. Furthermore, we introduced a prompting framework (PR) that leverages LLM reasoning to handle granularity mismatches, including source-to-parent mappings. RESULTS: Chapterwise mappings were performed between ICD versions (ICD-9-CM↔ICD-10-CM and ICD-10-AM↔ICD-11) using multiple LLMs. The proposed approach consistently outperformed the baseline across all ICD pairs and chapters. For example, combining HA descriptions with Qwen3-8B-generated descriptions yielded an average top-1 accuracy improvement of 6.5% (0.065) across the mapping cases. A small-scale pilot study further indicated that HA+LG remains effective in more challenging one-to-many mappings. CONCLUSIONS: Our findings demonstrate that integrating the representational power of pretrained encoders with LLM reasoning offers a robust, scalable strategy for automatic ICD mapping.

OBJECTIVE: We study the use of speech recognition and information extraction to generate drafts of Australian nursing-handover documents. METHODS: Speech recognition correctness and clinicians' preferences were evaluated using 15 recorder-microphone combinations, six documents, three speakers, Dragon Medical 11, and five survey/interview participants. Information extraction correctness evaluation used 260 documents, six-class classification for each word, two annotators, and the CRF++ conditional random field toolkit. RESULTS: A noise-cancelling lapel-microphone with a digital voice recorder gave the best correctness (79%). This microphone was also the most preferred option by all but one participant. Although the participants liked the small size of this recorder, their preference was for tablets that can also be used for document proofing and sign-off, among other tasks. Accented speech was harder to recognize than native language and a male speaker was detected better than a female speaker. Information extraction was excellent in filtering out irrelevant text (85% F1) and identifying text relevant to two classes (87% and 70% F1). Similarly to the annotators' disagreements, there was confusion between the remaining three classes, which explains the modest 62% macro-averaged F1. DISCUSSION: We present evidence for the feasibility of speech recognition and information extraction to support clinicians' in entering text and unlock its content for computerized decision-making and surveillance in healthcare. CONCLUSIONS: The benefits of this automation include storing all information; making the drafts available and accessible almost instantly to everyone with authorized access; and avoiding information loss, delays, and misinterpretations inherent to using a ward clerk or transcription services.

Telehealth is the provision of health services at a distance. Typically, this occurs in unsupervised or remote environments, such as a patient's home. We describe one such telehealth system and the integration of extracted clinical measurement parameters with a decision-support system (DSS). An enterprise application-server framework, combined with a rules engine and statistical analysis tools, is used to analyze the acquired telehealth data, searching for trends and shifts in parameter values, as well as identifying individual measurements that exceed predetermined or adaptive thresholds. An overarching business process engine is used to manage the core DSS knowledge base and coordinate workflow outputs of the DSS. The primary role for such a DSS is to provide an effective means to reduce the data overload and to provide a means of health risk stratification to allow appropriate targeting of clinical resources to best manage the health of the patient. In this way, the system may ultimately influence changes in workflow by targeting scarce clinical resources to patients of most need. A single case study extracted from an initial pilot trial of the system, in patients with chronic obstructive pulmonary disease and chronic heart failure, will be reviewed to illustrate the potential benefit of integrating telehealth and decision support in the management of both acute and chronic disease.