Towards safe and reliable deep learning for lung nodule malignancy estimation using out-of-distribution detection.

Artificial Intelligence (AI) models may fail or suffer from reduced performance when applied to unseen data that differs from the training data distribution, referred to as dataset shift. Automatic detection of out-of-distribution (OOD) data contributes to safe and reliable clinical implementation of AI models. In this study, we propose a recognized OOD detection method that utilizes the Mahalanobis distance (MD) and compare its performance to widely known classical methods.

Evaluation of participation in a former rehabilitation population: a comparison between USER-Participation Restriction and Satisfaction subscales and PROMIS Ability to Participate and PROMIS Satisfaction with participation 8-item short forms in a cross-sectional multicentre study.

Background: Several Patient Reported Outcome Measurements (PROMs) can be used to quantify participation in rehabilitation patients, yet there is limited comparative research on their content and psychometric properties to make an informed decision between them.

Objective: To compare the content and several psychometric properties of the Restriction and Satisfaction subscales of the Utrecht Scale for Evaluation of Rehabilitation - Participation (USER-P) with the Patient-Reported Outcomes Measurement Information System Ability to Participate in Social Roles and Activities (PROMIS-APS) and Satisfaction with Social Roles and Activities (PROMIS-SPS) v2.0 8-item short forms.

How bulk liquid viscosity shapes capillary suspensions.

Hypothesis: Capillary suspensions offer a new approach to generate novel materials. They are ternary liquid-liquid-solid systems characterized by particles connected by liquid bridges of one fluid suspended in a second immiscible bulk fluid. The viscosity of the bulk liquid can be modulated to customize the structure and rheological properties of capillary suspensions.

Psychological screening of significant others during spinal cord injury rehabilitation.

Design: Retrospective cohort study.

Objective: Determine the course of burden and psychological distress of significant others (SOs) during initial spinal cord injury (SCI) rehabilitation and to predict the caregiver's burden at discharge with characteristics of SOs and persons with SCI (PSCIs) at the start of rehabilitation.

Setting: Rehabilitation center Sint Maartenskliniek, Nijmegen, The Netherlands.

Texture of emulsion-filled pea protein-potato starch gels: Effect of processing conditions and composition.

From a physicochemical perspective, foods like vegan cheese and meat analogues are complex multicomponent gels. The aim of this study was to investigate the effect of processing conditions and composition on the textural properties of multicomponent gels containing starch, pea protein isolate (PPI) and emulsion droplets. Mechanical properties were measured, and structural analysis was carried with CLSM and SEM.

Favorable resuscitation characteristics in patients undergoing extracorporeal cardiopulmonary resuscitation: A secondary analysis of the INCEPTION-trial.

Introduction: Extracorporeal cardiopulmonary resuscitation (ECPR) is increasingly used as a supportive treatment for refractory out-of-hospital cardiac arrest (OHCA). Still, there is a paucity of data evaluating favorable and unfavorable prognostic characteristics in patients considered for ECPR.

Methods: We performed a previously unplanned post-hoc analysis of the multicenter randomized controlled INCEPTION-trial.

Exploring patients' experience using PROMs within routine post-discharge follow-up assessment after stroke: a mixed methods approach.

Background: Patient Reported Outcomes Measures (PROMs) are being used increasingly to measure health problems in stroke clinical practice. However, the implementation of these PROMs in routine stroke care is still in its infancy. To understand the value of PROMs used in ischemic stroke care, we explored the patients' experience with PROMs and with the consultation at routine post-discharge follow-up after stroke.

Cost-effectiveness of extracorporeal cardiopulmonary resuscitation vs. conventional cardiopulmonary resuscitation in out-of-hospital cardiac arrest: a pre-planned, trial-based economic evaluation.

Aims: When out-of-hospital cardiac arrest (OHCA) becomes refractory, extracorporeal cardiopulmonary resuscitation (ECPR) is a potential option to restore circulation and improve the patient's outcome. However, ECPR requires specific materials and highly skilled personnel, and it is unclear whether increased survival and health-related quality of life (HRQOL) justify these costs.

Methods And Results: This cost-effectiveness study was part of the INCEPTION study, a multi-centre, pragmatic randomized trial comparing hospital-based ECPR to conventional CPR (CCPR) in patients with refractory OHCA in 10 cardiosurgical centres in the Netherlands.

A national multi centre pre-hospital ECPR stepped wedge study; design and rationale of the ON-SCENE study.

Background: The likelihood of return of spontaneous circulation with conventional advanced life support is known to have an exponential decline and therefore neurological outcome after 20 min in patients with a cardiac arrest is poor. Initiation of venoarterial ExtraCorporeal Membrane Oxygenation (ECMO) during resuscitation might improve outcomes if used in time and in a selected patient category. However, previous studies have failed to significantly reduce the time from cardiac arrest to ECMO flow to less than 60 min.

Enhancing a deep learning model for pulmonary nodule malignancy risk estimation in chest CT with uncertainty estimation.

Objective: To investigate the effect of uncertainty estimation on the performance of a Deep Learning (DL) algorithm for estimating malignancy risk of pulmonary nodules.

Methods And Materials: In this retrospective study, we integrated an uncertainty estimation method into a previously developed DL algorithm for nodule malignancy risk estimation. Uncertainty thresholds were developed using CT data from the Danish Lung Cancer Screening Trial (DLCST), containing 883 nodules (65 malignant) collected between 2004 and 2010.

Nodule Detection and Generation on Chest X-Rays: NODE21 Challenge.

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task.

The role of membrane components on the oleosome lubrication properties.

Hypothesis: Oleosomes are natural oil droplets with a unique phospholipid/protein membrane, abundant in plant seeds, from which they can be extracted and used in emulsion-based materials, such as foods, cosmetics and pharmaceutics. The lubrication properties of such materials are essential, on one hand, due to the importance of the in-mouth creaminess for the consumed products or the importance of spreading the topical creams. Therefore, here, we will evaluate the lubrication properties of oleosomes, and how these properties are affected by the components at the oleosome membrane.

Health-related quality of life in early onset scoliosis patients treated with the spring distraction system: what to expect in the first 2 years after surgery.

Purpose: The Spring Distraction System (SDS) is a novel "growth-friendly" implant for the treatment of Early-Onset Scoliosis (EOS). This prospective study aims to determine the evolution of the "24-Item Early-Onset Scoliosis Questionnaire" (EOSQ-24) scores during 2-year follow-up after SDS surgery. Secondary aims include investigating the relation between EOSQ-24 scores and EOS etiology, and evaluating the impact of an unplanned return to the operating room (UPROR) on HRQoL.

Deep learning for the detection of benign and malignant pulmonary nodules in non-screening chest CT scans.

Background: Outside a screening program, early-stage lung cancer is generally diagnosed after the detection of incidental nodules in clinically ordered chest CT scans. Despite the advances in artificial intelligence (AI) systems for lung cancer detection, clinical validation of these systems is lacking in a non-screening setting.

Method: We developed a deep learning-based AI system and assessed its performance for the detection of actionable benign nodules (requiring follow-up), small lung cancers, and pulmonary metastases in CT scans acquired in two Dutch hospitals (internal and external validation).

Changes in bladder emptying during inpatient rehabilitation after spinal cord injury and predicting factors: data from the Dutch Spinal Cord Injury Database.

Study Design: Secondary analysis of multicentre prospective observational data.

Objectives: To describe methods of bladder emptying at admission and discharge in patients with recently acquired spinal cord injury (SCI) and to describe predictors of bladder emptying methods at discharge.

Setting: First inpatient rehabilitation in specialised rehabilitation centres in the Netherlands.

The effect of cations and epigallocatechin gallate on in vitro salivary lubrication.

Ionic valency influences oral processing by changing salivary behavior and merits more attention since little is known. In this study, the influence of three ionic valences (monovalent, divalent and trivalent), ionic strength and epigallocatechin gallate (EGCG) on lubricating properties of saliva were investigated. Tribological measurements were used to characterize the lubrication response of KCl, MgCl, FeCl, and AlCl in combination with EGCG to the ex vivo salivary pellicle.

Prior CT Improves Deep Learning for Malignancy Risk Estimation of Screening-detected Pulmonary Nodules.

Background Prior chest CT provides valuable temporal information (eg, changes in nodule size or appearance) to accurately estimate malignancy risk. Purpose To develop a deep learning (DL) algorithm that uses a current and prior low-dose CT examination to estimate 3-year malignancy risk of pulmonary nodules. Materials and Methods In this retrospective study, the algorithm was trained using National Lung Screening Trial data (collected from 2002 to 2004), wherein patients were imaged at most 2 years apart, and evaluated with two external test sets from the Danish Lung Cancer Screening Trial (DLCST) and the Multicentric Italian Lung Detection Trial (MILD), collected in 2004-2010 and 2005-2014, respectively.

Role of polysaccharide structure in the rheological, physical and sensory properties of low-fat ice cream.

Polysaccharides can be used as fat replacers in ice cream, as they contribute to an increase of viscosity. However, no research has clarified the exact role of viscosity from that of the structure of the polysaccharides on the properties of ice cream. In this study, the effect of polysaccharide structure on different properties of low-fat ice cream was investigated.

Trends in the incidence of pulmonary nodules in chest computed tomography: 10-year results from two Dutch hospitals.

Objective: To study trends in the incidence of reported pulmonary nodules and stage I lung cancer in chest CT.

Methods: We analyzed the trends in the incidence of detected pulmonary nodules and stage I lung cancer in chest CT scans in the period between 2008 and 2019. Imaging metadata and radiology reports from all chest CT studies were collected from two large Dutch hospitals.

Development of the self-regulation assessment and content validation using cognitive interviews in a multicultural post-rehabilitation population.

Aim: Self-regulation is one of the main goals of medical rehabilitation. Four themes of self-regulation were identified by former patients and rehabilitation physicians in a previous study. Based on these themes, a measure for self-regulation, the self-regulation assessment (SeRA), was developed.