Delirium in older hospitalized patients-A prospective analysis of the detailed course of delirium in geriatric inpatients.

BACKGROUND: Delirium in older hospitalized patients (> 65) is a common clinical syndrome, which is frequently unrecognized. AIMS: We aimed to describe the detailed clinical course of delirium and related cognitive functioning in geriatric patients in a mainly non-postoperative setting in association with demographic and clinical parameters and additionally to identify risk factors for delirium in this common setting. METHODS: Inpatients of a geriatric ward were screened for delirium and in the case of presence of delirium included into the study. Patients received three assessments including Mini-Mental-Status-Examination (MMSE) and the Delirium Rating Scale Revised 98 (DRS-R-98). We conducted correlation and linear mixed-effects model analyses to detect associations. RESULTS: Overall 31 patients (82 years (mean)) met the criteria for delirium and were included in the prospective observational study. Within one week of treatment, mean delirium symptom severity fell below the predefined cut-off. While overall cognitive functioning improved over time, short- and long-term memory deficits remained. Neuroradiological conspicuities were associated with cognitive deficits, but not with delirium severity. DISCUSSION: The temporal stability of some delirium symptoms (short-/long-term memory, language) on the one hand and on the other hand decrease in others (hallucinations, orientation) shown in our study visualizes the heterogeneity of symptoms attributed to delirium and their different courses, which complicates the differentiation between delirium and a preexisting cognitive decline. The recovery from delirium seems to be independent of preclinical cognitive status. CONCLUSION: Treatment of the acute medical condition is associated with a fast decrease in delirium severity. Given the high incidence and prevalence of delirium in hospitalized older patients and its detrimental impact on cognition, abilities and personal independence further research needs to be done.

Patient Embeddings From Diagnosis Codes for Health Care Prediction Tasks: Pat2Vec Machine Learning Framework.

BACKGROUND: In health care, diagnosis codes in claims data and electronic health records (EHRs) play an important role in data-driven decision making. Any analysis that uses a patient's diagnosis codes to predict future outcomes or describe morbidity requires a numerical representation of this diagnosis profile made up of string-based diagnosis codes. These numerical representations are especially important for machine learning models. Most commonly, binary-encoded representations have been used, usually for a subset of diagnoses. In real-world health care applications, several issues arise: patient profiles show high variability even when the underlying diseases are the same, they may have gaps and not contain all available information, and a large number of appropriate diagnoses must be considered. OBJECTIVE: We herein present Pat2Vec, a self-supervised machine learning framework inspired by neural network-based natural language processing that embeds complete diagnosis profiles into a small real-valued numerical vector. METHODS: Based on German outpatient claims data with diagnosis codes according to the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10), we discovered an optimal vectorization embedding model for patient diagnosis profiles with Bayesian optimization for the hyperparameters. The calibration process ensured a robust embedding model for health care-relevant tasks by aggregating the metrics of different regression and classification tasks using different machine learning algorithms (linear and logistic regression as well as gradient-boosted trees). The models were tested against a baseline model that binary encodes the most common diagnoses. The study used diagnosis profiles and supplementary data from more than 10 million patients from 2016 to 2019 and was based on the largest German ambulatory claims data set. To describe subpopulations in health care, we identified clusters (via density-based clustering) and visualized patient vectors in 2D (via dimensionality reduction with uniform manifold approximation). Furthermore, we applied our vectorization model to predict prospective drug prescription costs based on patients' diagnoses. RESULTS: Our final models outperform the baseline model (binary encoding) with equal dimensions. They are more robust to missing data and show large performance gains, particularly in lower dimensions, demonstrating the embedding model's compression of nonlinear information. In the future, other sources of health care data can be integrated into the current diagnosis-based framework. Other researchers can apply our publicly shared embedding model to their own diagnosis data. CONCLUSIONS: We envision a wide range of applications for Pat2Vec that will improve health care quality, including personalized prevention and signal detection in patient surveillance as well as health care resource planning based on subcohorts identified by our data-driven machine learning framework.

Interrupting chains of respiratory infections via remote patient monitoring in ambulatory care - a randomized controlled trial during the 2020/21 infection season.

Aim of the study: The aim of the study was to investigate patient satisfaction, saving of time and the possible reduction of visits to medical practices that use Remote Patient Monitoring (RPM) during treatment compared to usual care. Methods: In a randomized controlled trial between October 2020 and May 2021, the participating medical practices were randomized into three groups (two different RPM systems, one control). Doctors were required to enroll patients ≥18 years with acute respiratory infection in possession of a web-enabled device, such as a laptop, tablet or computer. After a three-month study phase, doctors were asked to describe the treatment of their patients via online survey. Patients were also questioned. The analysis was carried out descriptively and through group comparisons. Results: 51 practices with 121 patients were included. Overall, the results generally show a positive assessment of digital care on the patient side. As for the doctors, handling and integrating the systems into established practice routines seem to be a challenge. Further, the number of patient visits to the medical practice was not reduced by using the systems. Doctors did not save time, but the relationship to the patients was intensified. Conclusion: While there was no indication for an increase in efficiency by using RPM systems, participating doctors indicated their potential for an enhanced interaction between doctor and patient. In particular, intensified interaction contact with patients with chronic diseases (e. g. COPD, long-COVID) could be of long-term interest and importance for doctors in ambulatory care.Trial Registration: DRKS00023553.

Causal graph analysis of COVID-19 observational data in German districts reveals effects of determining factors on reported case numbers.

Several determinants are suspected to be causal drivers for new cases of COVID-19 infection. Correcting for possible confounders, we estimated the effects of the most prominent determining factors on reported case numbers. To this end, we used a directed acyclic graph (DAG) as a graphical representation of the hypothesized causal effects of the determinants on new reported cases of COVID-19. Based on this, we computed valid adjustment sets of the possible confounding factors. We collected data for Germany from publicly available sources (e.g. Robert Koch Institute, Germany's National Meteorological Service, Google) for 401 German districts over the period of 15 February to 8 July 2020, and estimated total causal effects based on our DAG analysis by negative binomial regression. Our analysis revealed favorable effects of increasing temperature, increased public mobility for essential shopping (grocery and pharmacy) or within residential areas, and awareness measured by COVID-19 burden, all of them reducing the outcome of newly reported COVID-19 cases. Conversely, we saw adverse effects leading to an increase in new COVID-19 cases for public mobility in retail and recreational areas or workplaces, awareness measured by searches for "corona" in Google, higher rainfall, and some socio-demographic factors. Non-pharmaceutical interventions were found to be effective in reducing case numbers. This comprehensive causal graph analysis of a variety of determinants affecting COVID-19 progression gives strong evidence for the driving forces of mobility, public awareness, and temperature, whose implications need to be taken into account for future decisions regarding pandemic management.