Signals, in order.

Published intelligence from the original source record.

Source: ClinicalTrials.gov

This research examines whether women experience more changes in melanocytic nevi during and after pregnancy compared to age‑matched non‑pregnant women. It also evaluates the psychological impact of using total body mapping and dermoscopic examination supported by artificial intelligence during pregnancy.

Source: ClinicalTrials.gov

The PANIC study is a research project based in the United States that seeks to develop a machine‑learning application for accurately predicting which patients are at risk of anastomotic insufficiency following colon and colorectal surgery. The goal is to provide a preoperative risk assessment tool to improve surgical outcomes.

Source: ClinicalTrials.gov

The study analyzes driving behavior of individuals under the influence of alcohol using a validated research driving simulator. Based on the simulator’s driving variables, the investigators aim to establish algorithms capable of discriminating sober and drunk driving patterns using deep machine learning classifiers.

Source: ClinicalTrials.gov

This research compares 2D and 3D imaging techniques with routine clinical care for early melanoma detection in a prospective, large-scale real‑world dataset collected in Switzerland. The study evaluates the effectiveness of VECTRA imaging technology in improving diagnostic accuracy. Data were gathered from a real-world clinical setting across Switzerland.

Source: ClinicalTrials.gov

The project at Inselspital Bern will develop a clinical decision support system that uses self‑learning AI to analyze cardiotocography traces from 10,000–15,000 maternity records. CSEM will design, develop, and validate multiple machine‑learning architectures to predict the optimal fetal extraction time during labor, providing a superhuman support tool for obstetricians. The system will be trained on existing clinical outcomes to improve decision‑making accuracy.

Source: ClinicalTrials.gov

Asthma is a chronic inflammatory airway disease affecting 8% of school‑aged children and 30% of preschoolers, with frequent exacerbations that are difficult for parents and patients to assess. Current assessment tools include the Pediatric Respiratory Assessment Measure (PRAM) score and lung function tests such as spirometry, but these require patient cooperation and are limited in young children. Digital stethoscopes that record and transmit auscultation data up to 20‑20,000 Hz, combined with advanced signal processing and unsupervised AI learning, offer a promising objective method to evalu…

Source: ClinicalTrials.gov

This research aims to develop a wearable-based ICU prediction algorithm for inpatients with SARS-CoV-2. Participants include inpatients with suspected or confirmed COVID-19, who will wear a smartwatch that gathers physiological data throughout their stay. The study seeks to predict clinical trajectories using this data.

Source: ClinicalTrials.gov

This multi-center observational case-control study in ICU patients aims to identify novel biomarkers for early recognition of severe community acquired pneumonia-associated sepsis and to predict sepsis-related mortality. Patients with sCAP will be profiled over time and compared with controls, using modern omics technologies to explore mechanisms and influencing factors. The resulting data will be analyzed with machine learning algorithms and multi-dimensional mathematical models.

Source: ClinicalTrials.gov

A prospective non‑interventional study will enroll 400 early AMD patients (600 untreated early AMD eyes) in Vienna, Austria, and follow them for at least one year. Patients will undergo Optical Coherence Tomography every four months; when the Vienna Reading Center detects focal changes, a targeted follow‑up schedule will be initiated to investigate the progression at those sites.

Source: ClinicalTrials.gov