Maritime operations are increasingly reliant on sensor data to drive efficiency and enhance decision-making. However, despite rapid advances in large language models, including expanded context windows and stronger generative capabilities, critical industrial settings still require secure, role-constrained access to enterprise data and explicit limitation of model context. Retrieval-Augmented Generation (RAG) remains essential to enforce data minimization, preserve privacy, support verifiability, and meet regulatory obligations by retrieving only permissioned, provenance-tracked slices of information at query time. However, current RAG solutions lack robust validation protocols for numerical accuracy for high-stakes industrial applications. This paper introduces Lighthouse Bot, a novel Agentic RAG system specifically designed to provide natural-language access to complex maritime sensor data, including time-series and relational sensor data. The system addresses a critical need for verifiable autonomous data analysis within the Artificial Intelligence of Things (AIoT) domain, which we explore through a case study on optimizing ferry operations. We present a detailed architecture that integrates a Large Language Model with a specialized database and coding agents to transform natural language into executable tasks, enabling core AIoT capabilities such as generating Python code for time-series analysis, executing complex SQL queries on relational sensor databases, and automating workflows, while keeping sensitive data outside the prompt and ensuring auditable, policy-aligned tool use. To evaluate performance, we designed a test suite of 24 questions with ground-truth answers, categorized by query complexity (simple, moderate, complex) and data interaction type (retrieval, aggregation, analysis). Our results show robust, controlled data access with high factual fidelity: the proprietary Claude 3.7 achieved close to 90% overall factual correctness, while the open-source Qwen 72B achieved 66% overall and 99% on simple retrieval and aggregation queries. These findings underscore the need for a secure limited-context RAG in maritime AIoT and the potential for cost-effective automation of routine exploratory analyses.

The purpose of this study was to compare manual assessment of corneal nerve fiber length (CNFL) and dendritic cell (DC) density with an automated assessment method utilizing deep learning segmentation to perform rule-based density estimation. Corneal images were acquired using in vivo confocal microscopy (IVCM) from 100 participants with persistent ocular symptoms after mild COVID-19 (Group 1) and 30 controls without symptoms (Group 2). In total, 1,300 IVCM images were selected and manually annotated for CNFL, and 1,300 for DCs (with dendrites and without dendrites), using FIJI tools. The between-method difference in mean CNFL density was 0.2  (95% CI: [0.09, 0.23]) for Group 1 and −0.2  (95% CI: [−0.34, −0.10]) for Group 2. For Group 1, the mean difference for DCs with dendrites was −1.1  (95% CI: [−1.78, −0.39]), and for DCs without dendrites it was −3.1  (95% CI: [−5.1, −1.0]). For Group 2, the mean difference for DCs with dendrites was −1.0  (95% CI: [−1.79, −0.27]), and for DCs without dendrites it was 0.3  (95% CI: [−1.93, 2.60]). Both manual and automated methods showed significant between-group differences for CNFL (p=0.012 and p=0.034, respectively) and DC densities (p=0.005 and p=0.010). The automated approach performed comparably to manual assessment, supporting its potential for reliable, scalable analysis of CNFL and DC in IVCM images.

Maintaining mobility is vital for older adults. However, standardized functional tests often overlook crucial qualitative aspects, and expert assessments (EA) are costly and lack standardization. This project aims to develop an AI-based movement screening tool (SAT-Movement Analysis) utilizing the low-cost Skeleton Avatar Technique (SAT) and standardized Observational Movement Analysis (OMA) to detect deviations in daily movement. The initial phase automated expert assessments to establish a reliable foundation for machine learning. Five participants (ages 35–57) performed Sit-To-Stand, Stand-To-Sit, and One-Leg Stance, assessed by three physiotherapists using a modified IRAF protocol. Results demonstrated correspondence between automatically aggregated expert scores and consensus scores across all aggregation levels (Pearson’s r = 0.90–0.97, ICC = 0.91–0.98, = 0.78–1.00). These findings motivate continued development of an AI-trained screening tool providing accurate movement quality feedback based on 2D smartphone video, supporting early detection and personalized intervention.

Monitoring adverse drug events (ADEs) is critical for pharmacovigilance and patient safety. However, identifying ADEs remains challenging, as suspected or confirmed side effects are often documented solely in the unstructured text of electronic health records (EHRs). Manually reviewing clinical notes to detect ADEs is labor-intensive and time-consuming, highlighting the need for automated methods capable of analyzing and extracting ADE-related information from clinical documentation. In this short communication, we describe our ongoing research on fine-tuning and evaluating a large language model (LLM) for the detection of ADEs in clinical notes. Preliminary descriptive result of this study indicates that ADEs are poorly documented in discharge notes, with less than 15% explicitly linking ADEs to specific drugs, which highlights the need for improved reporting practices.

Potential adverse drug events can be signaled in Clinical Decision Support Systems (CDSSs). This study validated a Swedish CDSS (Janusmed Risk Profile) by investigating associations between calculated risk classifications of drugs with QT-prolonging potential and registered related clinical outcomes. Subjects living in Kalmar County, Sweden, between 2011 and 2020 exposed to risk drugs (risk level I: somewhat increased risk, II: moderate increased risk, III: significant increased risk) were extracted from regional electronic health records and matched to controls (risk level 0: no known increased risk) by age, sex, and index date. Ventricular arrhythmia (VA), Torsade de Pointes, cardiac arrest and death were outcomes followed for one year. Logistic regression analysis was performed adjusted for age, sex, number of drugs, days in hospital and previous diagnosis. Among the 188,453 subjects, a higher proportion of those classified by the CDSS as having a risk of QT prolongation experienced VA compared to controls (risk level I = 0.26%, II = 0.34%, III = 0.71% vs risk level 0 = 0.17%). When adjusting for other risk factors, the association decreased, but risk level III remained significant with OR 2.1 (95% CI 1.6-2.9) compared to controls. Similar results were seen for the other outcomes. Although there was an association between CDSS risk classifications and clinical outcomes, only a few subjects are affected, and other factors, such as previous diagnosis, play an important role. The need for multifactorial CDSS algorithms is thus crucial to better guide prescribers in finding high-risk patients.

Background:  Medications are essential for health care but can cause adverse drug events (ADEs), which are harmful and sometimes fatal. Detecting ADEs is a challenging task because they are often not documented in the structured data of electronic health records (EHRs) . There is a need for automatically extracting ADE-related information from clinical notes, as manual review is labor-intensive and time-consuming.

Objectives: This study aims to fine-tune the pre-trained clinical language model, SweDeClin-BERT, for medical named entity recognition (NER) and relation extraction (RE) tasks, and to implement an integrated NER-RE approach to more effectively identify ADEs in clinical notes from clinical units in Sweden. The performance of this approach is compared to our previous machine learning method, which utilized conditional random fields (CRFs) and Random Forest (RF).

Data Sources: A subset of clinical notes from the Stockholm EPR (Electronic Patient Record) Corpus, dated 2009-2010, containing suspected ADEs based on ICD-10 codes in the A.1/A.2 categories was randomly sampled. These notes were annotated by a physician with ADE-related entities and relations following the ADE annotation guidelines.

Methods: We fine-tuned the SweDeClin-BERT model for the NER and RE tasks and implemented an integrated NER-RE pipeline to extract entities and relationships from clinical notes. The models were evaluated using 395 clinical notes from clinical units in Sweden. The NER-RE pipeline was then applied to classify the clinical notes as containing or not containing ADEs. Additionally, we conducted an error analysis to better understand the model’s behavior and to identify potential areas for improvement.

Results: In total 62% of notes contained an explicit description of an ADE, indicating that an ADE-related ICD-10 code alone does not ensure detailed event documentation. The fine-tuned SweDeClin-BERT model achieved an F1-score of 0.845 for NER and 0.81 for RE task, outperforming the baseline models (CRFs for NER and Random Forests for RE). In particular, the RE task showed a 53% improvement in macro-average F1-score compared to the baseline. The integrated NER-RE pipeline achieved an overall F1-score of 0.81.

Conclusions: Utilizing a domain-specific language model like SweDeClin-BERT for detecting ADEs in clinical notes demonstrates improved classification performance (0.77 in strict and 0.81 in relaxed mode) compared to conventional machine learning models like CRFs and RF. The proposed fine-tuned ADE model requires further refinement and evaluation on annotated clinical notes from another hospital to evaluate the model’s generalizability. In addition, the annotation guidelines should be revised, as there is an overlap of words between the Finding and Disorder entity categories, which were not consistently distinguished by the annotators. Furthermore, future work should address the handling of compound words and split entities to better capture context in the Swedish language.  

Acanthamoeba are ubiquitous microorganisms found in the air, soil, tap and drinking water, swimming pools, and in both saltwater and freshwater environments [1].They can cause corneal infections that lead to Acanthamoeba keratitis (AK), which is serious medical condition accompanied by intense eye pain, sensitivity to light, and severely impaired vision. AK is commonly associated with contact lens use, particularly in developed countries, where up to 90% of cases are linked to contact lens wear [2]. Timely identification and diagnosis of AK are critical to preventing vision loss. Corneal culture is the gold standard for diagnosing AK, but its low sensitivity and slow turnaround can delay treatment and worsen infection [3]. A complementary method uses non-invasive clinical imaging such as in-vivo confocal microscopy (IVCM) [4,5]. Despite several advantages such as high-resolution imaging, rapid diagnosis, and the ability to monitor disease progression, IVCM has limitations, including the large volume of images generated and the needs for identifying informative/useful images and experienced interpretation. While previous approaches have primarily focused on building models to detect AK in pre- selected images, our decision support system [6], IVCMAssist, automates the entire diagnostic workflow—from processing raw IVCM images and removing artifacts, to sorting images by corneal layer, to identifying informative images, and to detecting AK signs such as cysts in informative images. It enhances the AK diagnosis process by reducing the time spent on image sorting and pre-selection of informative images (non-overlapped images with detected AK cysts), while enabling experienced observers to correct model errors through a human-in-the-loop AI approach.

One approach to preventing adverse drug events (ADEs), such as harmful drug interactions, is the implementation of clinical decision support systems (CDSS). In an ongoing project, we are investigating the accuracy of the rule-based CDSS currently utilized in Swedish healthcare for predicting ADEs and exploring whether machine learning (ML) can improve these predictions. By analyzing real-world healthcare data from a Swedish region spanning a 10-year period, we show that ML has potential to improve ADE predictions compared to existing rule-based CDSS.

What constitutes 'world archaeology'?

Visualize the subject of archaeological publications by geographic region location over time.

Antiquity Journal was founded as a journal of world archaeology in 1927, continuously publishing peer-reviewed research through to the present day. This tool takes the place names listed in Antiquity abstracts from 1927 to 2015, attributes them to a geographic region, and allows the user to view and manipulate the resulting graph. Below, users may also generate visualizations of specific time periods for individual regions.