Cardiac screening in school children: Combining auscultation and electrocardiography with a crowdsourcing model.

BACKGROUND/PURPOSE: School-based cardiac screening is useful for identifying children and adolescents with a high risk of sudden cardiac death. However, because of challenges associated with cost, distance, and human resources, cardiac screening is not widely implemented, especially in rural areas with limited medical resources. This study aims to establish a cloud-based system suitable for mass cardiac screening of schoolchildren in rural areas with limited medical resources. METHODS: Students from three schools were included. They or their guardians completed a simple questionnaire, administered in paper or electronic form. Heart sounds were recorded using an electronic stethoscope. Twelve-lead electrocardiograms (ECGs) were recorded and digitalized. The signals were transmitted through Bluetooth to a tablet computer and then uploaded to a cloud server over Wi-Fi. Crowdsourced pediatric cardiologists reviewed those data from a web-based platform and provided remote consultation. In cases in which abnormal heart sounds or ECGs were noted, the students were referred to the hospital for further evaluation. RESULTS: A total of 1004 students were enrolled in this study. Of the 138 students referred, 62 were diagnosed as having an abnormal heart condition and most had previously been undiagnosed. The interrater agreeability was high. CONCLUSION: An innovative strategy combining a cloud-based cardiac screening system with remote consultation by crowdsourced experts was established. This system allows pediatric cardiologists to provide consultation and make reliable diagnoses. Combined with crowdsourcing, the system constitutes a viable approach for mass cardiac screening in children and adolescents living in rural areas with insufficient medical resources.

Risk Factors for Traumatic Brain Injuries During Falls in Older Persons.

OBJECTIVE: To identify risk factors for traumatic brain injuries (TBIs) during falls in older Taiwanese people. PARTICIPANTS: Case patients consisted of 113 patients aged 60 years or older with a moderate/severe TBI due to a fall. Two control groups: (1) 339 older patients with a soft-tissue injury; and (2) 113 with a mild-TBI due to a fall. Proxies were required to provide information for a considerable number of patients. DESIGN: Matched case-control study. SETTINGS: The emergency departments of 3 general hospitals. MEASURES: Sociodemographic, lifestyle behavior, chronic condition, medication use, functional abilities, and fall-related characteristics. RESULTS: When patients with a soft-tissue injury were assigned to the control group, men were 2.06-fold more likely to have a moderate/severe TBI than women. Subjects who took antiarrhythmics within 4 hours of a fall were 2.59-fold more likely to have a moderate/severe TBI than those who took none. Subjects who were negotiating stairs and getting in/out of the bed/chair were 3.12-fold and 2.97-fold, respectively, more likely to have a moderate/severe TBI than those who fell while walking. Falling backward and sideways was 4.07-fold and 2.30-fold, respectively, more likely to cause a moderate/severe TBI than falling forward. When patients with a mild-TBI were assigned to the control group, results were similar, with the exception that the effect of antiarrhythmic use became nonsignificant and subjects who took 2 or more medications were 3.07-fold more likely to have a moderate/severe TBI than those who took none. CONCLUSION: Avoiding a head impact during a backward or sideways fall, reducing unnecessary use of polypharmacy and antiarrhythmics, and maintaining safety during stair negotiation and bed/chair transfer may protect an elderly person from a severe brain injury.

Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling.

Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.

Blind Monaural Source Separation on Heart and Lung Sounds Based on Periodic-Coded Deep Autoencoder.

Auscultation is the most efficient way to diagnose cardiovascular and respiratory diseases. To reach accurate diagnoses, a device must be able to recognize heart and lung sounds from various clinical situations. However, the recorded chest sounds are mixed by heart and lung sounds. Thus, effectively separating these two sounds is critical in the pre-processing stage. Recent advances in machine learning have progressed on monaural source separations, but most of the well-known techniques require paired mixed sounds and individual pure sounds for model training. As the preparation of pure heart and lung sounds is difficult, special designs must be considered to derive effective heart and lung sound separation techniques. In this study, we proposed a novel periodicity-coded deep auto-encoder (PC-DAE) approach to separate mixed heart-lung sounds in an unsupervised manner via the assumption of different periodicities between heart rate and respiration rate. The PC-DAE benefits from deep-learning-based models by extracting representative features and considers the periodicity of heart and lung sounds to carry out the separation. We evaluated PC-DAE on two datasets. The first one includes sounds from the Student Auscultation Manikin (SAM), and the second is prepared by recording chest sounds in real-world conditions. Experimental results indicate that PC-DAE outperforms several well-known separation works in terms of standardized evaluation metrics. Moreover, waveforms and spectrograms demonstrate the effectiveness of PC-DAE compared to existing approaches. It is also confirmed that by using the proposed PC-DAE as a pre-processing stage, the heart sound recognition accuracies can be notably boosted. The experimental results confirmed the effectiveness of PC-DAE and its potential to be used in clinical applications.

Suitability of the Quality of Life after Brain Injury Instrument for Older People with Traumatic Brain Injury.

We prospectively investigated the psychometric properties of the Quality of Life after Brain Injury (QOLIBRI) instrument among older patients with traumatic brain injury (TBI). The 37-item QOLIBRI comprises six domains (cognition, self, daily life and autonomy, social relationships, emotions, and physical problems). We recruited 333 patients ≥60 years of age with TBI from the neurosurgery clinics and emergency departments of three hospitals in Taipei, Taiwan. The ceiling and floor values for most QOLIBRI domains were <5%, and the internal consistency and test-retest reliability ranged from 0.84 to 0.97 and 0.83 to 0.96, respectively. For the known-groups validity, patients with TBI attained lower scores for all QOLIBRI domains, except physical problems, compared with those with soft-tissue injuries. Patients with intact cognition who had higher levels on the Glasgow Outcome Scale Extended (GOSE) and the Glasgow Coma Scale, fewer limitations in activities of daily living, and fewer chronic conditions obtained higher scores for almost all the QOLIBRI domains, compared with their counterparts. For convergent validity, the correlation coefficients for the QOLIBRI domains and the selected functional measures conceptually related to that domain were all ≥0.4. A confirmatory factor analysis revealed that the original six-domain structure fit the data with a comparative fit index of ≥0.9. Effect sizes for changes in the GOSE over a 6-month follow-up period were clinically meaningful (≥ 0.2) for all the QOLIBRI domains except emotions. For older people with TBI, the use of the QOLIBRI is generally appropriate, and adding the domain of environment to the scale would be beneficial.

Comparisons of Different Screening Tools for Identifying Fracture/Osteoporosis Risk Among Community-Dwelling Older People.

A prospective study was conducted to compare criterion, predictive, and construct validities of 9 fracture/osteoporosis assessment tools, including calcaneal quantitative ultrasonography (QUS), Age Bulk One or Never Estrogens (ABONE), body weight criterion (BWC), Fracture Risk Assessment Tool (FRAX), Garvan fracture risk calculator (GARVAN), Osteoporosis Risk Assessment Instrument (ORAI), Osteoporosis Index of Risk (OSIRIS), Osteoporosis Self-Assessment Tool for Asians (OSTA), and Simple Calculated Osteoporosis Risk Estimation (SCORE), among older men and women in Taiwan.Using the femoral neck dual-energy x-ray absorptiometry (DXA) T-score as an external criterion, the sensitivity, specificity, positive and negative predictive values, positive and negative likelihood ratios, and the area under the receiver operating characteristic curve (AUC) for each tool were calculated. The ability of these tools to predict injurious falls was examined. A principal component analysis was applied to understand whether these tools were measuring the same underlying construct.The FRAX, BWC, ORAI, OSIRIS, OSTA, and SCORE had AUCs of ≥0.8 in men, while the GARVAN, OSIRIS, OSTA, and SCORE had AUCs of ≥0.8 in women. The sensitivity, negative predictive value, and likelihood ratio of the ABONE, BWC, ORAI, OSIRIS, OSTA, and SCORE tools in both men and women were 100%, ≥90%, and 0.0, respectively; the specificity and positive predictive value and likelihood ratio were far from satisfactory. The GARVAN displayed the best predictive ability of a fall in both men (AUCs, 0.653-0.686) and women (AUCs, 0.560-0.567), despite being smaller in women. The 9 screening tools and 2 central DXA measurements assessed 5 different factors, while the ABONE, BWC, ORAI, OSIRIS, OSTA, and SCORE measured the same one.Simple self-assessment tools can serve as initial screening instruments to rule out persons who have osteoporosis; however, these tools may measure a different construct other than fracture/osteoporosis risk.