The Impact of Delirium on Recovery in Geriatric Rehabilitation after Acute Infection.

OBJECTIVES: Delirium is common during acute infection in older patients and is associated with functional decline. Geriatric rehabilitation (GR) can help older patients to return to their premorbid functional level. It is unknown whether delirium affects GR outcomes in patients with acute infection. We evaluated whether delirium affects trajectories of activities of daily living (ADL) and quality of life (QoL) recovery in GR after COVID-19 infection. DESIGN: This study was part of the EU-COGER study, a multicenter cohort study conducted between October 2020 and October 2021. SETTING AND PARTICIPANTS: Participants were recruited after COVID-19 infection from 59 GR centers in 10 European countries. METHODS: Data were collected at GR admission, discharge, and at the 6-week and 6-month follow-ups. Trajectories of ADL [using the Barthel index (BI)] and QoL [using the EuroQol-5 Dimensions-5 Level (EQ-5D-5L)] recovery were examined using linear mixed models. RESULTS: Of the 723 patients included (mean age 75.5 ± 9.9 years; 52.4% male), 28.9% had delirium before or during GR admission. Participants with delirium recovered in ADL at approximately the same rate as those without (linear slope effect = -0.13, SE 0.16, P = .427) up to an estimated BI score of 16.1 at 6 months. Similarly, participants with delirium recovered in QoL at approximately the same rate as those without (linear slope effect = -0.017, SE 0.015, P = .248), up to an estimated EQ-5D-5L score of 0.8 at 6 months. CONCLUSIONS AND IMPLICATIONS: Presence of delirium during the acute phase of infection or subsequent GR did not influence the recovery trajectory of ADL functioning and QoL.

What is the ecotoxicity of a given chemical for a given aquatic species? Predicting interactions between species and chemicals using recommender system techniques.

Ecotoxicological safety assessment of chemicals requires toxicity data on multiple species, despite the general desire of minimizing animal testing. Predictive models, specifically machine learning (ML) methods, are one of the tools capable of solving this apparent contradiction as they allow to generalize toxicity patterns across chemicals and species. However, despite the availability of large public toxicity datasets, the data is highly sparse, complicating model development. The aim of this study is to provide insights into how ML can predict toxicity using a large but sparse dataset. We developed models to predict LC50-values, based on experimental LC50-data covering 2431 organic chemicals and 1506 aquatic species from the ECOTOX-database. Several well-known ML techniques were evaluated and a new ML model was developed, inspired by recommender systems. This new model involves a simple linear model that learns low-rank interactions between species and chemicals using factorization machines. We evaluated the predictive performances of the developed models based on two validation settings: 1) predicting unseen chemical-species pairs, and 2) predicting unseen chemicals. The results of this study show that ML models can accurately predict LC50-values in both validation settings. Moreover, we show that the novel factorization machine approach can match well-tuned, complex, ML approaches.

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning.

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network-based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

Time domain diffuse correlation spectroscopy with a high coherence pulsed source: in vivo and phantom results.

Diffuse correlation spectroscopy (DCS), combined with time-resolved reflectance spectroscopy (TRS) or frequency domain spectroscopy, aims at path length (i.e. depth) resolved, non-invasive and simultaneous assessment of tissue composition and blood flow. However, while TRS provides a path length resolved data, the standard DCS does not. Recently, a time domain DCS experiment showed path length resolved measurements for improved quantification with respect to classical DCS, but was limited to phantoms and small animal studies. Here, we demonstrate time domain DCS for in vivo studies on the adult forehead and the arm. We achieve path length resolved DCS by means of an actively mode-locked Ti:Sapphire laser that allows high coherence pulses, thus enabling adequate signal-to-noise ratio in relatively fast (~1 s) temporal resolution. This work paves the way to the translation of this approach to practical in vivo use.