Characterizing subtle cognitive changes in preclinical Alzheimer’s disease (AD) is difficult using traditional neuropsychological assessments. Remote and unsupervised digital assessments can improve scalability, measurement reliability, and ecological validity, enabling the capture of subtle changes….
Continue Reading
Large-language models (LLMs) show promise for clinical note information extraction, but deployment challenges include high computational costs and privacy concerns. We used synthetic data distillation to fine-tune smaller, open-source LLMs to achieve performance comparable…
Continue Reading
Clinical validation studies are important to translate artificial intelligence (AI) technology in healthcare but may be underperformed in Otolaryngology – Head & Neck Surgery (OHNS). This scoping review examined deep learning publications in OHNS…
Continue Reading
Commissioning of innovations in healthcare is a complex socio-technical process, ideally informed by high quality evidence. However, evidence is not always prepared and presented in a format usable for commissioning decisions. Agile methodology, combined…
Continue Reading
Accurate medical decision-making is critical for both patients and clinicians. Patients often struggle to interpret their symptoms, determine their severity, and select the right specialist. Simultaneously, clinicians face challenges in integrating complex patient data…
Continue Reading
Mixed reality (MR) technology is increasingly used in surgical procedures, particularly in pediatric oncological surgery. The CarnaLife Holo system (MedApp S.A., Poland) converts medical imaging data into interactive 3D holograms for preoperative planning and…
Continue Reading
Speech dysarthria is a key symptom of neurological conditions like ALS, yet existing AI models designed to analyze it from audio signal rely on handcrafted features with limited inference performance. Deep learning approaches improve…
Continue Reading
AI cancer detection models require calibration to attain the desired balance between cancer detection rate (CDR) and false positive rate. In this study, we simulate the impact of six types of mismatches between the…
Continue Reading
Large language models progressively result in improved ways of patient engagement and access to healthcare, reaching both an exciting and concerning time, as they no longer serve solely as a guide to clinicians, but,…
Continue Reading
Critical findings in radiology reports are life threatening conditions that need to be communicated promptly to physicians for timely management of patients. Although challenging, advancements in natural language processing (NLP), particularly large language models…
Continue Reading
