Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 13,511 to 13,520 of 211,153 articles

Robustness of Healthcare ML Under Data Quality Degradation: A Dimension-Wise Analysis on MIMIC-IV.

Studies in health technology and informatics
Using the MIMIC-IV database (1,500-7,000 patients), we assess the robustness of healthcare machine learning models under controlled data quality (DQ) degradations applied to training or test data across five dimensions. Model performance declined wit... read more 

Extending Grad-CAM to DualNet.

Studies in health technology and informatics
The machine learning architecture DualNet was introduced for analysing both frontal and lateral X-rays of a patient for disease classification. Since the model lacks explainability methods, we extended the pytorch-grad-cam package for the application... read more 

Automated Segmentation of Tissue Zones in Distraction Osteogenesis.

Studies in health technology and informatics
Automated analysis of histological sections in distraction osteogenesis can reduce manual effort and subjectivity in histological assessment. A 2D nnU-Net was trained to segment three characteristic tissue zones in sections of rat tibial distraction ... read more 

Norovirus in the UK Biobank: Silver-Standard Labels, Semi-Supervised Models.

Studies in health technology and informatics
Researching norovirus gastroenteritis retrospectively is challenging, since the absence of a disease record does not imply the absence of that disease. We compared three classification approaches in the UK Biobank: silver-standard labeled controls on... read more 

Temporal Query Answering for the Scheduling of Multiple Clinical Guidelines.

Studies in health technology and informatics
Clinical guidelines are widely used in the medical practice. Temporal constraints-such as durations, intervals, and delays-are an intrinsic component of most guidelines. Existing approaches to computerized clinical guidelines (CIGs) typically include... read more 

A Comparison of Different Models to Recommend Variables for Research Data Requests to German Cancer Registries.

Studies in health technology and informatics
Cancer registry data is an important resource in cancer research, e.g. to formulate hypotheses for new interventions, to identify recruitment potentials for clinical trials or to evaluate side effects of new interventions on a large population, but r... read more 

Reuse of EUCAIM Ontology for Prescreening Use Case.

Studies in health technology and informatics
Implementing patient-trial matching during Clinical Trials (CT) execution requires a time consuming and usually manual processing of eligibility criteria (EC) focusing on those that are both the most relevant at the pre-inclusion step and the most co... read more 

Bridging Expertise with Algorithms: Evaluation of Generative AI in Nursing Decisions.

Studies in health technology and informatics
Integrating generative artificial intelligence (GenAI) into nursing clinical decision-making (CDM) offers potential to bridge expertise gaps. This randomized, double-blind simulation (n=69) compared nurses' perceptions of GenAI-generated clinical adv... read more 

Can LLMs Turn French PET/CT Narrative Reports into Structured Knowledge?

Studies in health technology and informatics
This study evaluates large language models (LLMs) for information extraction from French PET/CT reports related to cognitive impairment, focusing on descriptive patterns of cerebral metabolism, perfusion and uptake for three radiotracers, as well as ... read more 

Distribution Shift Analysis in Generalizable Modelling: Intensive Care Time-Series Data.

Studies in health technology and informatics
In this paper, we investigate how distribution shift affects model generalizability in medical time-series from intensive care. We define clinically relevant domain adaptation scenarios for predicting hypotension and hypoxemia using the MIMIC-III Mat... read more