High-Dimensional Feature Selection for Automatic Classification of Coronary Stenosis Using an Evolutionary Algorithm.

In this paper, a novel strategy to perform high-dimensional feature selection using an evolutionary algorithm for the automatic classification of coronary stenosis is introduced. The method involves a feature extraction stage to form a bank of 473 features considering different types such as intensity, texture and shape. The feature selection task is carried out on a high-dimensional feature bank, where the search space is denoted by O(2n) and n=473. The proposed evolutionary search strategy was compared in terms of the Jaccard coefficient and accuracy classification with different state-of-the-art methods. The highest feature selection rate, along with the best classification performance, was obtained with a subset of four features, representing a 99% discrimination rate. In the last stage, the feature subset was used as input to train a support vector machine using an independent testing set. The classification of coronary stenosis cases involves a binary classification type by considering positive and negative classes. The highest classification performance was obtained with the four-feature subset in terms of accuracy (0.86) and Jaccard coefficient (0.75) metrics. In addition, a second dataset containing 2788 instances was formed from a public image database, obtaining an accuracy of 0.89 and a Jaccard Coefficient of 0.80. Finally, based on the performance achieved with the four-feature subset, they can be suitable for use in a clinical decision support system.

The Effects of Introducing a Mobile App-Based Procedural Logbook on Trainee Compliance to a Central Venous Catheter Insertion Accreditation Program: Before-and-After Study.

BACKGROUND: To reduce complications associated with central venous catheter (CVC) insertions, local accreditation programs using a supervised procedural logbook are essential. To increase compliance with such a logbook, a mobile app could provide the ideal platform for training doctors in an adult intensive care unit (ICU). OBJECTIVE: The aim of this paper was to compare trainee compliance with the completion of a logbook as part of a CVC insertion accreditation program, before and after the introduction of an app-based logbook. METHODS: This is a retrospective observational study of logbook data, before and after the introduction of a purpose-built, app-based, electronic logbook to complement an existing paper-based logbook. Carried out over a 2-year period in the adult ICU of the John Hunter Hospital, Newcastle, NSW, Australia, the participants were ICU trainee medical officers completing a CVC insertion accreditation program. The primary outcome was the proportion of all CVC insertions documented in the patients' electronic medical records appearing as logbook entries. To assess logbook entry quality, we measured and compared the proportion of logbook entries that were approved by a supervisor and contained a supervisor's signature for the before and after periods. We also analyzed trainee participation before and after the intervention by comparing the total number of active logbook users, and the proportion of first-time users who logged 3 or more CVC insertions. RESULTS: Of the 2987 CVC insertions documented in the electronic medical records between April 7, 2019, and April 6, 2021, 2161 (72%) were included and separated into cohorts before and after the app's introduction. Following the introduction of the app-based logbook, the percentage of CVC insertions appearing as logbook entries increased from 3.6% (38/1059) to 20.5% (226/1102; P<.001). There was no difference in the proportion of supervisor-approved entries containing a supervisor's signature before and after the introduction of the app, with 76.3% (29/38) and 83.2% (188/226), respectively (P=.31). After the introduction of the app, there was an increase in the percentage of active logbook users from 15.3% (13/85) to 62.8% (54/86; P<.001). Adherence to one's logbook was similar in both groups with 60% (6/10) of first-time users in the before group and 79.5% (31/39) in the after group going on to log at least 3 or more CVCs during their time working in ICU. CONCLUSIONS: The addition of an electronic app-based logbook to a preexisting paper-based logbook was associated with a higher rate of logbook compliance in trainee doctors undertaking an accreditation program for CVC insertion in an adult ICU. There was a large increase in logbook use observed without a reduction in the quality of logbook entries. The overall trainee participation also improved with an observed increase in active logbook users and no reduction in the average number of entries per user following the introduction of the app. Further studies on app-based logbooks for ICU procedural accreditation programs are warranted.

3D Hermite Transform Optical Flow Estimation inLeft Ventricle CT Sequences.

Heart diseases are the most important causes of death in the world and over the years, thestudy of cardiac movement has been carried out mainly in two dimensions, however, it is important toconsider that the deformations due to the movement of the heart occur in a three-dimensional space.The 3D + t analysis allows to describe most of the motions of the heart, for example, the twistingmotion that takes place on every beat cycle that allows us identifying abnormalities of the heartwalls. Therefore, it is necessary to develop algorithms that help specialists understand the cardiacmovement. In this work, we developed a new approach to determine the cardiac movement inthree dimensions using a differential optical flow approach in which we use the steered Hermitetransform (SHT) which allows us to decompose cardiac volumes taking advantage of it as a model ofthe human vision system (HVS). Our proposal was tested in complete cardiac computed tomography(CT) volumes ( 3D + t), as well as its respective left ventricular segmentation. The robustness tonoise was tested with good results. The evaluation of the results was carried out through errors inforwarding reconstruction, from the volume at time t to time t + 1 using the optical flow obtained(interpolation errors). The parameters were tuned extensively. In the case of the 2D algorithm, theinterpolation errors and normalized interpolation errors are very close and below the values reportedin ground truth flows. In the case of the 3D algorithm, the results were compared with another similarmethod in 3D and the interpolation errors remained below 0.1. These results of interpolation errorsfor complete cardiac volumes and the left ventricle are shown graphically for clarity. Finally, a seriesof graphs are observed where the characteristic of contraction and dilation of the left ventricle isevident through the representation of the 3D optical flow.

Lack of Delta-Sarcoglycan (Sgcd) Results in Retinal Degeneration.

Age-related macular degeneration (AMD) is the leading cause of central vision loss and severe blindness among the elderly population. Recently, we reported on the association of the SGCD gene (encoding for δ-sarcoglycan) polymorphisms with AMD. However, the functional consequence of Sgcd alterations in retinal degeneration is not known. Herein, we characterized changes in the retina of the Sgcd knocked-out mouse (KO, Sgcd-/-). At baseline, we analyzed the retina structure of three-month-old wild-type (WT, Sgcd+/+) and Sgcd-/- mice by hematoxylin and eosin (H&E) staining, assessed the Sgcd-protein complex (α-, ß-, γ-, and ε-sarcoglycan, and sarcospan) by immunofluorescence (IF) and Western blot (WB), and performed electroretinography. Compared to the WT, Sgcd-/- mice are five times more likely to have retinal ruptures. Additionally, all the retinal layers are significantly thinner, more so in the inner plexiform layer (IPL). In addition, the number of nuclei in the KO versus the WT is ever so slightly increased. WT mice express Sgcd-protein partners in specific retinal layers, and as expected, KO mice have decreased or no protein expression, with a significant increase in the α subunit. At three months of age, there were no significant differences in the scotopic electroretinographic responses, regarding both a- and b-waves. According to our data, Sgcd-/- has a phenotype that is compatible with retinal degeneration.

A vision-based approach for fall detection using multiple cameras and convolutional neural networks: A case study using the UP-Fall detection dataset.

The automatic recognition of human falls is currently an important topic of research for the computer vision and artificial intelligence communities. In image analysis, it is common to use a vision-based approach for fall detection and classification systems due to the recent exponential increase in the use of cameras. Moreover, deep learning techniques have revolutionized vision-based approaches. These techniques are considered robust and reliable solutions for detection and classification problems, mostly using convolutional neural networks (CNNs). Recently, our research group released a public multimodal dataset for fall detection called the UP-Fall Detection dataset, and studies on modality approaches for fall detection and classification are required. Focusing only on a vision-based approach, in this paper, we present a fall detection system based on a 2D CNN inference method and multiple cameras. This approach analyzes images in fixed time windows and extracts features using an optical flow method that obtains information on the relative motion between two consecutive images. We tested this approach on our public dataset, and the results showed that our proposed multi-vision-based approach detects human falls and achieves an accuracy of 95.64% compared to state-of-the-art methods with a simple CNN network architecture.

UP-Fall Detection Dataset: A Multimodal Approach.

Falls, especially in elderly persons, are an important health problem worldwide. Reliable fall detection systems can mitigate negative consequences of falls. Among the important challenges and issues reported in literature is the difficulty of fair comparison between fall detection systems and machine learning techniques for detection. In this paper, we present UP-Fall Detection Dataset. The dataset comprises raw and feature sets retrieved from 17 healthy young individuals without any impairment that performed 11 activities and falls, with three attempts each. The dataset also summarizes more than 850 GB of information from wearable sensors, ambient sensors and vision devices. Two experimental use cases were shown. The aim of our dataset is to help human activity recognition and machine learning research communities to fairly compare their fall detection solutions. It also provides many experimental possibilities for the signal recognition, vision, and machine learning community.

Communication with Families Regarding Organ and Tissue Donation after Death in Intensive Care (COMFORT): a multicentre before-and-after study.

OBJECTIVE: To implement a best-practice intervention offering deceased organ donation, testing whether it increased family consent rates. DESIGN: A multicentre before-and-after study of a prospective cohort compared with pre-intervention controls. SETTING: Nine Australian intensive care units. PARTICIPANTS: Families and health care professionals caring for donor-eligible patients without registered donation preferences or aged ≤ 16 years. INTERVENTION: A multicomponent intervention including offers of deceased organ donation from specially trained designated requesters using a structured conversation separate to end-of-life discussions. MAIN OUTCOME MEASURE: Proportion of families consenting to organ donation. RESULTS: Consent was obtained in 87/164 cases (53%) during the intervention period compared with 14/25 cases (56%) pre-intervention (P = 0.83). The odds ratio (OR) of obtaining consent during the intervention period relative to preintervention was 1.13 (95% CI, 0.48-2.63; P = 0.78). During the intervention period, designated requesters obtained consent in 55/98 cases (56%), compared with 32/66 cases (48%) in which the medical team managing patient care raised donation (P = 0.34). Factors independently associated with increased consent were: family-raised organ donation (OR, 4.34; 95% CI, 1.79-10.52; P = 0.001), presence of an independent designated requester (OR, 3.84; 95% CI, 1.35- 10.98; P = 0.012), and multiple donation conversations per case (OR, 3.35; 95% CI, 1.93-5.81; P < 0.001). Consent decreased when patients were of non-Christian religion (OR, 0.18; 95% CI, 0.04-0.91; P = 0.038) and end-of-life and donation meetings were separate (OR, 0.38; 95% CI, 0.16-0.89; P = 0.026). CONCLUSION: Implementation of a multicomponent intervention did not increase consent rates for organ donation, although some components of the intervention exerted significant effect. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry: ACTRN12613000815763. ClinicalTrials.gov: NCT01922310.

Heart Rate Estimation using Hermite Transform Video Magnification and Deep Learning.

Monitoring of heart rate can be used in many medical and sports applications. Lack of portability and connection problems make traditional monitoring methods difficult to use outside of clinical environments. The computer vision techniques have been shown that some physiological variables as heart rate can be measured without contact. Video magnification is one of these approach used for the detection of the pulse signal. In this paper we propose a new strategy to magnify motion in a video sequence using the Hermite transform. In addition a deep learning technique is implemented to estimate the beat by beat pulse signal. We trained the system and validated our results using an electronic pulse monitoring device. Our approach is compared with the classical video magnification using a Gaussian pyramid. The results show a better enhancement of spectral information from the colour changes allowing an accurate estimation of the instantaneous beat by beat pulse than the Gaussian approach.

A Novel Artificial Organic Control System for Mobile Robot Navigation in Assisted Living Using Vision- and Neural-Based Strategies.

Robots in assisted living (RAL) are an alternative to support families and professional caregivers with a wide range of possibilities to take care of elderly people. Navigation of mobile robots is a challenging problem due to the uncertainty and dynamics of environments found in the context of places for elderly. To accomplish this goal, the navigation system tries to replicate such a complicated process inspired on the perception and judgment of human beings. In this work, we propose a novel nature-inspired control system for mobile RAL navigation using an artificial organic controller enhanced with vision-based strategies such as Hermite optical flow (OF) and convolutional neural networks (CNNs). Particularly, the Hermite OF is employed for obstacle motion detection while CNNs are occupied for obstacle distance estimation. We train the CNN using OF visual features guided by ultrasonic sensor-based measures in a 3D scenario. Our application is oriented to avoid mobile and fixed obstacles using a monocular camera in a simulated environment. For the experiments, we use the robot simulator V-REP, which is an integrated development environment into a distributed control architecture. Security and smoothness metrics as well as quantitative evaluation are computed and analyzed. Results showed that the proposed method works successfully in simulation conditions.

COMmunication with Families regarding ORgan and Tissue donation after death in intensive care (COMFORT): protocol for an intervention study.

BACKGROUND: Discussing deceased organ donation can be difficult not only for families but for health professionals who initiate and manage the conversations. It is well recognised that the methods of communication and communication skills of health professionals are key influences on decisions made by families regarding organ donation. METHODS: This multicentre study is being performed in nine intensive care units with follow-up conducted by the Organ and Tissue Donation Service in New South Wales (NSW) Australia. The control condition is pre-intervention usual practice for at least six months before each site implements the intervention. The COMFORT intervention consists of six elements: family conversations regarding offers for organ donation to be led by a "designated requester"; family offers for donation are deferred to the designated requester; the offer of donation is separated from the end-of-life discussion that death is inevitable; it takes place within a structured family donation conversation using a "balanced" approach. Designated requesters may be intensivists, critical care nurses or social workers prepared by attending the three-day national "Family Donation Conversation" workshops, and the half-day NSW Simulation Program. The design is pre-post intervention to compare rates of family consent for organ donation six months before and under the intervention. Each ICU crosses from using the control to intervention condition after the site initiation visit. The primary endpoint is the consent rate for deceased organ donation calculated from 140 eligible next of kin families. Secondary endpoints are health professionals' adherence rates to core elements of the intervention; identification of predictors of family donation decision; and the proportion of families who regret their final donation decision at 90 days. DISCUSSION: The pragmatic design of this study may identify 'what works' in usual clinical settings when requesting organ donation in critical care areas, both in terms of changes in practice healthcare professionals are willing and able to adopt, and the effect this may have on desired outcomes. The findings of this study will be indicative of the potential benefits of the intervention and be relevant and transferrable to clinical settings in other states and countries. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR): ACTRN12613000815763 (24 July 2013). ClinicalTrials.gov: NCT01922310 (14 August 2013) (retrospectively registered).

Segmentation and optical flow estimation in cardiac CT sequences based on a spatiotemporal PDM with a correction scheme and the Hermite transform.

PURPOSE: The left ventricle and the myocardium are two of the most important parts of the heart used for cardiac evaluation. In this work a novel framework that combines two methods to isolate and display functional characteristics of the heart using sequences of cardiac computed tomography (CT) is proposed. A shape extraction method, which includes a new segmentation correction scheme, is performed jointly with a motion estimation approach. METHODS: For the segmentation task we built a Spatiotemporal Point Distribution Model (STPDM) that encodes spatial and temporal variability of the heart structures. Intensity and gradient information guide the STPDM. We present a novel method to correct segmentation errors obtained with the STPDM. It consists of a deformable scheme that combines three types of image features: local histograms, gradients and binary patterns. A bio-inspired image representation model based on the Hermite transform is used for motion estimation. The segmentation allows isolating the structure of interest while the motion estimation can be used to characterize the movement of the complete heart muscle. RESULTS: The work is evaluated with several sequences of cardiac CT. The left ventricle was used for evaluation. Several metrics were used to validate the proposed framework. The efficiency of our method is also demonstrated by comparing with other techniques. CONCLUSION: The implemented tool can enable physicians to better identify mechanical problems. The new correction scheme substantially improves the segmentation performance. Reported results demonstrate that this work is a promising technique for heart mechanical assessment.

Prediction of death in less than 60 minutes after withdrawal of cardiorespiratory support in potential organ donors after circulatory death.

BACKGROUND: Given the stable number of potential organ donors after brain death, donors after circulatory death have been an increasing source of organs procured for transplant. Among the most important considerations for donation after circulatory death (DCD) is the prediction that death will occur within a reasonable period of time after the withdrawal of cardiorespiratory support (WCRS). Accurate prediction of time to death is necessary for the procurement process. We aimed to develop simple predictive rules for death in less than 60 min and test the accuracy of these rules in a pool of potential DCD donors. METHODS: A multicenter prospective longitudinal cohort design of DCD eligible patients (n=318), with the primary binary outcome being death in less than 60 min after withdrawal of cardiorespiratory support conducted in 28 accredited intensive care units (ICUs) in Australia. We used a random split-half method to produce two samples, first to develop the predictive classification rules and then to estimate accuracy in an independent sample. RESULTS: The best classification model used only three simple classification rules to produce an overall efficiency of 0.79 (0.72-0.85), sensitivity of 0.82 (0.73-0.90), and a positive predictive value of 0.80 (0.70-0.87) in the independent sample. Using only intensive care unit specialist prediction (a single classification rule) produced comparable efficiency 0.80 (0.73-0.86), sensitivity 0.87 (0.78-0.93), and positive predictive value 0.78 (0.68-0.86). CONCLUSION: This best predictive model missed only 18% of all potential donors. A positive prediction would be incorrect on only 20% of occasions, meaning there is an acceptable level of lost opportunity costs involved in the unnecessary assembly of transplantation teams and theatres.

Prediction of death in less than 60 minutes following withdrawal of cardiorespiratory support in ICUs.

OBJECTIVES: Half of all ICU patients die within 60 minutes of withdrawal of cardiorespiratory support. Prediction of which patients die before and after 60 minutes would allow changes in service organization to improve patient palliation, family grieving, and allocation of ICU beds. This study tested various predictors of death within 60 minutes and explored which clinical variables ICU specialists used to make their prediction. DESIGN AND SETTINGS: Prospective longitudinal cohort design (n = 765) of consecutive adult patients having withdrawal of cardiorespiratory support, in 28 ICUs in Australia. Primary outcome was death within 60 minutes following withdrawal of cardiorespiratory support. A random split-half method was used to make two independent samples for development and testing of the predictive indices. The secondary outcome was ICU Specialist prediction of death within 60 minutes. MEASUREMENTS AND MAIN RESULTS: Death within 60 minutes of withdrawal of cardiorespiratory support occurred in 377 (49.3%). ICU specialist opinion was the best individual predictor, with an unadjusted odds ratio of 15.42 (95% CI, 9.33-25.49) and an adjusted odds ratio of 8.44 (4.30-16.58). A predictive index incorporating the ICU specialist opinion and clinical variables had an area under the curve of 0.89 (0.86-0.92) and 0.84 (0.80-0.88) in the development and test sets, respectively; and a second index using only clinical variables had an area under the curve of 0.86 (0.82-0.89) and 0.78 (0.73-0.83). The ICU specialist prediction of death within 60 minutes was independently associated with five clinical variables: pH, Glasgow Coma Scale, spontaneous respiratory rate, positive end-expiratory pressure, and systolic blood pressure. CONCLUSION: ICU specialist opinion is probably the current clinical standard for predicting death within 60 minutes of withdrawal of cardiorespiratory support. This approach is supported by this study, although predictive indices restricted to clinical variables are only marginally inferior. Either approach has a clinically useful level of prediction that would allow ICU service organization to be modified to improve care for patients and families and use ICU beds more efficiently.

Withholding and withdrawal of life-sustaining therapies in intensive care: an Australian experience.

OBJECTIVES: Withholding and withdrawal of treatment in intensive care is currently widely accepted, but little has been published about Australian practice. DESIGN AND SETTING: Retrospective audit of all deaths in two major tertiary intensive care units in the Hunter New England Area Health Service during 2008. Patients who died were classified as "no limitations" (died while receiving full treatment), "treatments withheld" (specific treatment limitations) or "withdrawal of life-sustaining treatment" (WLST). RESULTS: Of 1950 patients admitted to an ICU, 283 died (14.5%). Of these 283, 54 (19%) died despite all therapeutic efforts; 97 (34%) had treatments withheld, and 132 (47%) had WLST. There were no statistically significant differences in length of stay between the three groups. Patients who died despite all therapeutic efforts were younger than those who died after treatments were withheld or WLST (mean age [SD], 58.7 [21.1] v 73.1 [12.5] v 69.3 [13.5]; P = 0.001). APACHE II score was higher in the group who died than in the total ICU group (mean [SD], 25.5 [8.3] v 17.7 [8.7], P = 0.001). CONCLUSIONS: In this population of critically ill patients, most deaths occurred after discussion of end-of-life decisions and withholding or withdrawal of treatment.

Prediction of death after withdrawal of life-sustaining treatments.

OBJECTIVE: To assess the predictive value of respiratory and haemodynamic variables and opinion of the intensivist for determining how soon death occurs after withdrawal of life-sustaining treatments (WLST). DESIGN: Multicentre prospective observational study. PARTICIPANTS AND SETTING: 83 consecutive adult intensive care patients at John Hunter and Calvary Mater Hospitals, Newcastle, New South Wales, for whom a decision was made to withdraw life-sustaining treatment between March 2007 and March 2008. MAIN OUTCOME MEASURES: Data were collected before initiation of palliation. Primary outcome was to recognise in a multivariate analysis the parameters associated with a time to death < or = 60 minutes after WLST. RESULTS: 81 patients underwent WLST: 79 died, and two survived to be discharged from hospital. Thirty-six patients (45%) died within 60 minutes of WLST, and 45 (55%) survived 60 minutes or longer. Mean ICU stay before WLST was 4.8 days (range, 1-85 days). Mean time from WLST to death was 6:31 h (range, 1 minute to 31 days). A modified University of Wisconsin assessment tool showed no statistical association with the time from WLST to death (P = 0.09). The adapted United Network for Organ Sharing tool, systolic blood pressure, APACHE II score, ventilatory dependence, oxygen disruption, Glasgow Coma Scale (GCS) score and staff specialist opinion all showed a statistically significant association with time from WLST to death (P < 0.05). CONCLUSIONS: It is possible to predict the time from WLST to death accurately using a tool that combines GCS, respiratory and haemodynamic parameters and intensivist opinion. These results require validation in a large multicentre study.

Cyclophosphamide-induced acute respiratory distress syndrome.

Cyclophosphamide is widely used in neoplastic and inflammatory diseases. Although several adverse events have been described with its use, acute and subacute interstitial pneumonitis leading to pulmonary fibrosis is rare and potentially fatal. This case report describes a 64-year-old man who, after the fifth chemotherapy cycle, developed a severe ARDS leading to pulmonary fibrosis in just 30 days.

Nongenomic actions of glucocorticosteroids on the airway vasculature in asthma.

Inhaled glucocorticosteroids (corticosteroids) continue to be the standard treatment for nonexacerbated asthma because of their anti-inflammatory actions. These include effects on the airway vasculature, which participates in the inflammatory process. Corticosteroids are now known to have genomic as well as nongenomic effects that involve different mechanisms of action. The genomic vascular effects of inhaled corticosteroids include a decrease in airway wall hypervascularity (inhibition of angiogenesis), reversal of the increased airway blood flow, and inhibition of vascular hyperpermeability and leukocyte recruitment. In addition, inhaled corticosteroids decrease airway blood flow acutely (within minutes) and reversibly through a nongenomic action that involves noradrenergic neurotransmission. This effect is likely related to the binding of inhaled corticosteroids to the plasma membrane of and the inhibition of the extraneuronal monoamine transporter on airway vascular smooth muscle cells, thereby increasing norepinephrine concentrations at alpha(1)-adrenoceptors and causing airway vascular smooth muscle contraction and a decrease in airway blood flow. Inasmuch as vascular hyperperfusion is a manifestation of airway inflammation, the acute vasoconstriction could also be considered an anti-inflammatory effect of inhaled corticosteroids.

String matching techniques for high-level primitive formation in 2-D vascular imaging.

This paper deals with a so-called "intermediate" description, in other words, the formation of high-level primitives in angiographies. The method is based on an attributed string matching technique capable to capture the shape similarities between low-level primitives (i.e., vessel contours and centerlines). After designing a multiparametric cost function, we propose a multiline pairing algorithm. In order to objectively evaluate its performances, results are first provided on simulated data and then on a set of coronarographic images, where it is shown that anatomically coherent entities like vessel segments and branches can be built, "objects" that can be further individually analyzed for clinical purpose.