Explore the vast range of titles available.

Acute kidney injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series, requires researchers to implement classification algorithms of their own which is resource intensive and might impact study quality by introducing different interpretations of edge cases. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation. The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We constructed a standardized data model in order to ensure reproducibility. PyAKI implements the Kidney Disease: Improving Global Outcomes (KDIGO) guideline on AKI diagnosis. After implementation of the diagnostic algorithm, using both serum creatinine and urinary output data, pyAKI was tested on a subset of patients and diagnostic accuracy was compared in a comparative analysis against annotations by physicians. Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels with an accuracy of 1.0 in all categories. The pyAKI pipeline is the first open-source solution for implementing KDIGO criteria in time series data. It provides a standardized data model and a comprehensive solution for consistent AKI classification in research applications for clinicians and data scientists working with AKI data. The pipeline's high accuracy make it a valuable tool for clinical research and decision support systems. This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.

Background Acute kidney injury (AKI) and delirium are common complications in critically ill patients, both associated with adverse outcomes. Evidence suggests AKI may induce neuroinflammation and impair clearance of neurotoxic metabolites, but the clinical relationship between AKI and delirium remains incompletely characterized. We hypothesized that AKI increases the risk of delirium in a biological gradient. Methods We conducted a retrospective cohort study using two independent databases: MIMIC-IV ( n  = 15,219 patients) and a local institutional database (Reality) from University Hospital Münster ( n  = 3,461 patients). Adult ICU patients with length of stay > 12 h and validated delirium monitoring using the Confusion Assessment Method for the ICU (CAM-ICU) were included, with a positive assessment defining delirium presence. Patients with neurological/neurosurgical primary diagnoses or pre-existing cognitive impairment, as well as patient with delirium onset before AKI were excluded. AKI was classified according to KDIGO criteria. We employed landmark analysis at 24 h post-ICU admission where AKI-status was recorded as the exposure variable. Subsequent delirium was recorded as follow-up during the ICU stay. Propensity score matching, and a Fine-Gray Model were added to assess the time-based association between AKI and subsequent delirium, independently of illness severity. Results At the 24-hour landmark, AKI was present in 58.6% (MIMIC-IV) and 55.6% (Reality) of patients. Rates of subsequent delirium were significantly higher in patients with AKI compared to those without: 25.6% versus 15.7% in MIMIC-IV (OR 1.84, CI 1.68–2.04, p  < 0.001) and 12.1% versus 6.7% in Reality (OR 1.95, CI 1.44–2.64, p  < 0.001). After adjustment for confounders, AKI remained associated with delirium (adjusted-odds ratio [OR] 1.16, 95% CI 1.10–1.23 in MIMIC-IV; OR 1.20, 95% CI 1.01–1.41 in Reality). A biological gradient was observed, with delirium rates increasing progressively across AKI stages. In MIMIC-IV, adjusted-OR increased from 1.42 for Stage 1 to 4.11 for Stage 3 AKI (trend OR 1.55 per stage, p  < 0.001). The Reality cohort showed similar patterns (Stage 1 OR 1.01 and Stage 3 OR 1.92, trend OR 1.25 per stage, p  < 0.01). Propensity score matching confirmed these findings. Conclusion Acute kidney injury was associated with a higher risk of subsequent delirium in critically ill patients, with a graded association across AKI severity stages. Prospective studies are needed to determine whether interventions targeting AKI prevention or treatment can also reduce delirium burden.

Acute Kidney Injury (AKI) is a frequent complication in critically ill patients, affecting up to 50% of patients in the intensive care units. The lack of standardized and open-source tools for applying the Kidney Disease Improving Global Outcomes (KDIGO) criteria to time series data has a negative impact on workload and study quality. This project introduces pyAKI, an open-source pipeline addressing this gap by providing a comprehensive solution for consistent KDIGO criteria implementation. The pyAKI pipeline was developed and validated using a subset of the Medical Information Mart for Intensive Care (MIMIC)-IV database, a commonly used database in critical care research. We defined a standardized data model in order to ensure reproducibility. Validation against expert annotations demonstrated pyAKI's robust performance in implementing KDIGO criteria. Comparative analysis revealed its ability to surpass the quality of human labels. This work introduces pyAKI as an open-source solution for implementing the KDIGO criteria for AKI diagnosis using time series data with high accuracy and performance.

The escalating prevalence of diabetes mellitus (DM) emphasizes the critical need for early detection of diabetic retinopathy (DR). This study assesses the performance of the autonomous AI-based diagnostic system IDx-DR in detecting DR and its associated confounders in a real-world clinical setting. This prospective cross-sectional study involved 875 diabetic patients with a mean age of 52 years (range: 8–92). Retinal images were captured by trained assistants. IDx-DR results were compared with mydriatic fundus examination (gold standard) and Ophthalmologists’ image analysis. Factors impacting image acquisition or analyzability were examined. Among all patients, 10.5% yielded no image in miosis, and 26.1% were unanalyzable by IDx-DR. Confounders affecting image acquisition were examiner, pupil size, patient age and patients’ visual acuity. When good quality images were achieved, IDx-DR performed well, particularly in detection of severe DR (sensitivity 94.4%; specificity 90.5%). IDx-DR results exactly matched Ophthalmologists’ mydriatic fundoscopy gradings in 54.2% if images of sufficient quality were obtainable. Undergrading of DR severity by IDx-DR was rare (4.8%). IDx-DR shows promise in detecting DR, especially in resource-limited settings and in detecting severe DR. One remaining challenge is good image acquisition in miotic patients.