scholarly journals Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning

2021 ◽  
Vol 9 ◽  
Author(s):  
Martin G. Frasch ◽  
Shadrian B. Strong ◽  
David Nilosek ◽  
Joshua Leaverton ◽  
Barry S. Schifrin
Keyword(s):  
Deep Learning ◽  
Fetal Monitoring ◽  
Fetal Distress ◽  
Well Being ◽  
Adverse Outcomes ◽  
Care Providers ◽  
Learning Framework ◽  
Uterine Contractions ◽  
Neuroprotective Treatment ◽  
Pattern Information

Despite broad application during labor and delivery, there remains considerable debate about the value of electronic fetal monitoring (EFM). EFM includes the surveillance of fetal heart rate (FHR) patterns in conjunction with the mother's uterine contractions, providing a wealth of data about fetal behavior and the threat of diminished oxygenation and cerebral perfusion. Adverse outcomes universally associate a fetal injury with the failure to timely respond to FHR pattern information. Historically, the EFM data, stored digitally, are available only as rasterized pdf images for contemporary or historical discussion and examination. In reality, however, they are rarely reviewed systematically or purposefully. Using a unique archive of EFM collected over 50 years of practice in conjunction with adverse outcomes, we present a deep learning framework for training and detection of incipient or past fetal injury. We report 94% accuracy in identifying early, preventable fetal injury intrapartum. This framework is suited for automating an early warning and decision support system for maintaining fetal well-being during the stresses of labor. Ultimately, such a system could enable obstetrical care providers to timely respond during labor and prevent both urgent intervention and adverse outcomes. When adverse outcomes cannot be avoided, they can provide guidance to the early neuroprotective treatment of the newborn.

scholarly journals Maternal Exercise Uncovers Placental Insufficiency in Diabetic Mothers

2019 ◽  
pp. 91-93
Author(s):  
Petrikovsky BM ◽  
Zharov EV ◽  
Plotkin D ◽  
Petrikovsky E
Keyword(s):  
Gestational Diabetes ◽  
Apgar Score ◽  
Neonatal Intensive Care ◽  
Fetal Monitoring ◽  
Well Being ◽  
Adverse Outcomes ◽  
Exercise Regimen ◽  
Maternal Exercise ◽  
Nicu Admission ◽  
Diabetic Mothers

Regular physical activity during pregnancy improves or maintains physical fitness, helps with weight management, reduces the risk of gestational diabetes, and enhances patient’s psychological well-being. We studied the possibility to use maternal exercise to test placental reserves in diabetic mothers. We used a motorized treadmill in a moderate exercise regimen (15-minute fast walk at a speed of 3 mph with an incline of 15-25 degrees). Fetal monitoring was provided by using standard Phillips equipment (Avalon CTS and FM40). Adverse fetal outcomes were considered if one or more of the following were present: Category III Fetal Heart Rate (FHR) tracing, 5-minute Apgar score of less than 7, admission to the neonatal intensive care nursery, fetal growth restriction, and fetal and early neonatal death. A total of 819 fetal assessments were performed: 160 patients had gestational diabetes, 80 had pregestational diabetes. The most common complication in fetuses with positive prenatal test results was abnormal FHR in labor (36%) followed by low Apgar score (21%) and need for NICU admission (19%). Most of the adverse outcomes had good correlation with positive results of the exercise test. In conclusion, it appears that maternal exercise causes changes in FHR, which may be used to assess placental and fetal reserves.

scholarly journals Labor Admission Test

2011 ◽  
Vol 2 (3) ◽  
pp. 89-95 ◽  
Author(s):  
Sabaratnam Arulkumaran ◽  
Vikram Sinai Talaulikar
Keyword(s):  
Systematic Reviews ◽  
Well Being ◽  
Adverse Outcomes ◽  
Current Evidence ◽  
Cochrane Library ◽  
Amniotic Fluid Index ◽  
Uterine Contractions ◽  
Active Labor ◽  
Admission Test ◽  
Adequate Sample Size

ABSTRACT Labor admission test (LAT) is performed at the onset of labor to establish fetal well-being in low-risk pregnancies and identify those fetuses who either may be hypoxic, needing delivery or at risk of developing hypoxia during labor so that additional measures of fetal surveillance can be instituted to prevent adverse outcomes. We searched the literature in Medline, Cochrane Library and PubMed using the words— cardiotocograph, cardiotocogram, nonstress test, vibroacoustic stimulus (VAS), amniotic fluid index (AFI), Doppler, labor admission test, labor admission cardiotocography (CTG) and reviewed four randomized controlled trials (RCTs) and three systematic reviews to summarize the current evidence regarding use of LAT. Although the existing RCTs and systematic reviews do not favor admission testing, we have critically reviewed the methodology used in some of these major studies. There is a need for robust RCTs with adequate sample size to evaluate the effectiveness of LAT. In clinical practice, while a normal admission CTG reassures the mother and the clinician about the health of the baby, an admission CTG with nonreassuring FHR pattern leads to careful review which may reveal a growth restricted or compromised fetus before onset of active labor when the risk of fetal hypoxia is higher with increasing frequency and duration of uterine contractions. Like in other obstetric interventions, the woman should be offered the choice of LAT after providing appropriate information and her informed decision should be respected.

scholarly journals Deep learning framework for subject-independent emotion detection using wireless signals

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0242946
Author(s):  
Ahsan Noor Khan ◽  
Achintha Avin Ihalage ◽  
Yihan Ma ◽  
Baiyang Liu ◽  
Yujie Liu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Sequence Data ◽  
Well Being ◽  
The Body ◽  
Superior Performance ◽  
Learning Approaches ◽  
Emotion Detection ◽  
Ecg Signals ◽  
Learning Framework ◽  
Proposed Model

Emotion states recognition using wireless signals is an emerging area of research that has an impact on neuroscientific studies of human behaviour and well-being monitoring. Currently, standoff emotion detection is mostly reliant on the analysis of facial expressions and/or eye movements acquired from optical or video cameras. Meanwhile, although they have been widely accepted for recognizing human emotions from the multimodal data, machine learning approaches have been mostly restricted to subject dependent analyses which lack of generality. In this paper, we report an experimental study which collects heartbeat and breathing signals of 15 participants from radio frequency (RF) reflections off the body followed by novel noise filtering techniques. We propose a novel deep neural network (DNN) architecture based on the fusion of raw RF data and the processed RF signal for classifying and visualising various emotion states. The proposed model achieves high classification accuracy of 71.67% for independent subjects with 0.71, 0.72 and 0.71 precision, recall and F1-score values respectively. We have compared our results with those obtained from five different classical ML algorithms and it is established that deep learning offers a superior performance even with limited amount of raw RF and post processed time-sequence data. The deep learning model has also been validated by comparing our results with those from ECG signals. Our results indicate that using wireless signals for stand-by emotion state detection is a better alternative to other technologies with high accuracy and have much wider applications in future studies of behavioural sciences.

scholarly journals Facilitators and barriers to using telepresence robots in aged care settings: a scoping review protocol

BMJ Open ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. e051769
Author(s):  
Chelsea Smith ◽  
Mario Gregorio ◽  
Lillian Hung
Keyword(s):  
Older People ◽  
Social Isolation ◽  
Scoping Review ◽  
Well Being ◽  
Aged Care ◽  
Adverse Outcomes ◽  
Care Providers ◽  
Term Care ◽  
Review Team ◽  
Telepresence Robots

IntroductionSocial isolation is a significant issue in aged care settings (eg, long-term care (LTC) and hospital) and is associated with adverse outcomes such as reduced well-being and loneliness. Loneliness is linked with depression, anxiety, cognitive decline, weakened immune system, poor physical health, poor quality of life and mortality. The use of robotic assistance may help mitigate social isolation and loneliness. Although telepresence robots have been used in healthcare settings, a comprehensive review of studies focusing on their use in aged care for reducing social isolation requires further investigation. This scoping review will focus on the use of telepresence robots to support social connection of older people in care settings.Methods and analysisThis scoping review will follow Joanna Briggs Institute scoping review methodology. The review team consists of patient partners and family partners, a nurse researcher and a group of students. In the scoping review, we will search the following databases: MEDLINE (Ovid), CINAHL, PsycINFO (EBSCO), Web of Science and ProQuest Dissertations & Theses Global. Google and Google Scholar will be used to search for additional literature. A handsearch will be conducted using the reference lists of included studies to identify additional relevant articles. The scoping review will consider studies of using a telepresence robotic technology with older adults in care settings (ie, LTC and hospital), published in English.Ethics and disseminationSince the methodology of the study consists of collecting data from publicly available articles, it does not require ethics approval. By examining the current state of using telepresence to support older people in care settings, this scoping review can offer useful insight into users’ needs (eg, patients’ and care providers’ needs) and inform future research and practice. We will share the scoping review results through conference presentations and an open access publication in a peer-reviewed journal.

Organizational Justice enhances Subjective Well-being

2016 ◽  
Vol 3 (3) ◽  
Author(s):  
Ms. Anjali Sahai ◽  
Prof. (Dr). Abha Singh
Keyword(s):  
Organizational Justice ◽  
Satisfaction With Life ◽  
Interactional Justice ◽  
Well Being ◽  
Adverse Outcomes ◽  
Satisfaction With Life Scale ◽  
Subjective Well Being ◽  
Negative Experience ◽  
Life Scale ◽  
The Relationship

Organizational Justice has the potential to create major impact on organizations and employees alike. These include greater commitment, trust, enhanced job performance, more citizenship behaviors and less number of conflicts. It has been reported that employees seem to have a universal concern for Justice that transcends the self and that many are subject to biases at various point of time in their work life. Sometimes these biases lead to adverse outcomes including decreased level of subjective well-being. Subjective well-being is a broad category that includes life satisfaction, positive affect, and low negative affect, such as anger, sadness and fear. Thus to study the relationship between Organizational justice and subjective well-being, a sample of 88 employees working in Private Universities of NCR region were examined. For this purpose, the Organizational Justice scales consisting of Measure of Procedural & Interactional Justice and Distributive Justice Index scale by Moorman, Blakely & Niehoff (1998) and Subjective Wellbeing Scales inclusive of the Satisfaction with Life Scale(SWLS),Scale of Positive and Negative Experience(SPANE) and Flourishing Scale (FS) by Ed Diener (2004)were used. Results indicate significant relationship between the three types of Organizational justice and subjective well-being of employees.

A Deep Learning Framework for Prediction of Retinal Disorders

2020 ◽  
Author(s):  
Raniyaharini R ◽  
Madhumitha K ◽  
Mishaa S ◽  
Virajaravi R
Keyword(s):  
Deep Learning ◽  
Learning Framework ◽  
Retinal Disorders

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

Sign in / Sign up

Export Citation Format

Share Document