Screening children at risk for developmental disabilities based on face landmark from video data of mobile-based application: Cross-Sectional Study (Preprint)

2021 ◽  
Author(s):  
Yu Rang Park ◽  
Sang Ho Hwang ◽  
Yeonsoo Yu ◽  
Jichul Kim ◽  
Taeyeop Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Developmental Disabilities ◽  
Early Detection ◽  
Short Term Memory ◽  
Preliminary Evidence ◽  
Cross Sectional Study ◽  
Important Variable ◽  
Video Data ◽  
Classification Model ◽  
Cross Sectional

BACKGROUND Early detection and intervention of developmental disabilities (DDs) are critical for improving the long-term outcomes of the afflicted children. Mobile-based applications are easily accessible and may thus help the early identification of DDs. OBJECTIVE We aimed to identify facial expression and head pose based on face landmark data extracted from face recording videos and to differentiate the characteristics between children with DDs and those without. METHODS Eighty-nine children (DD, n=33; typically developing, n=56) were included in the analysis. Using the mobile-based application, we extracted facial landmarks and head poses from the recorded videos and performed Long Short-Term Memory(LSTM)-based DD classification. RESULTS Stratified k-fold cross-validation showed that the average values of accuracy, precision, recall, and f1-score of the LSTM based deep learning model of DD children were 88%, 91%,72%, and 80%, respectively. Through the interpretation of prediction results using SHapley Additive exPlanations (SHAP), we confirmed that the nodding head angle variable was the most important variable. All of the top 10 variables of importance had significant differences in the distribution between children with DDs and those without (p<0.05). CONCLUSIONS Our results provide preliminary evidence that the deep-learning classification model using mobile-based children’s video data could be used for the early detection of children with DDs.

scholarly journals Screening Children at Risk for Developmental Disabilities Based on Face Landmark from Video Data of Mobile-Based Application: Preliminary Cross-Sectional Study

2021 ◽  
Author(s):  
Sang Ho Hwang ◽  
Yeonsoo Yu ◽  
Jichul Kim ◽  
Taeyeop Lee ◽  
Yu Rang Park ◽  
...  
Keyword(s):  
Deep Learning ◽  
Developmental Disabilities ◽  
Early Detection ◽  
Short Term Memory ◽  
Preliminary Evidence ◽  
Cross Sectional Study ◽  
Important Variable ◽  
Video Data ◽  
Classification Model ◽  
Cross Sectional

Abstract Background Early detection and intervention of developmental disabilities (DDs) are critical for improving the long-term outcomes of the afflicted children. Mobile-based applications are easily accessible and may thus help the early identification of DDs. Objective We aimed to identify facial expression and head pose based on face landmark data extracted from face recording videos and to differentiate the characteristics between children with DDs and those without. Methods Eighty-nine children (DD, n=33; typically developing, n=56) were included in the analysis. Using the mobile-based application, we extracted facial landmarks and head poses from the recorded videos and performed Long Short-Term Memory (LSTM)-based DD classification. Results Stratified k-fold cross-validation showed that the average values of accuracy, precision, recall, and f1-score of the LSTM based deep learning model of DD children were 88%, 91%,72%, and 80%, respectively. Through the interpretation of prediction results using SHapley Additive exPlanations (SHAP), we confirmed that the nodding head angle variable was the most important variable. All of the top 10 variables of importance had significant differences in the distribution between children with DDs and those without (p<0.05). Conclusions Our results provide preliminary evidence that the deep-learning classification model using mobile-based children’s video data could be used for the early detection of children with DDs.

scholarly journals First Prospective Cross-Sectional Study on the Impact of Immigration Background and Education in Early Detection of Breast Cancer

Breast Care ◽  
2020 ◽  
pp. 1-7
Author(s):  
Elna Kuehnle ◽  
Wulf Siggelkow ◽  
Kristina Luebbe ◽  
Iris Schrader ◽  
Karl-Heinz Noeding ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Early Detection ◽  
First Generation ◽  
Participation Rate ◽  
Educational Status ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
First Generation Immigrants ◽  
Cancer Early Detection

<b><i>Background:</i></b> Although immigrant health is an important issue in national health policy, there is a serious shortage of data in many countries. Most studies lack information on educational status, which is a major limitation. This prospective cross-sectional study analyzed a real-world breast cancer population on the influence of immigration background and educational status on participation in breast cancer early detection programs in the federal state of Lower Saxony, Germany. <b><i>Methods:</i></b> Data collection was conducted from 2012 to 2016 in six certified breast cancer centers using a standardized questionnaire for patients’ interview and tumor-specific data from the patients’ medical records. <b><i>Results:</i></b> 2,145/3,047 primary breast cancer cases were analyzed. 17.5% of our patients had a history of immigration, including <i>n</i> = 202 first-generation immigrants and <i>n</i> = 168 second-generation immigrants. Most of them were citizens of EU27 member states. No significant difference was seen in age, tumor stage, histology, grading, Ki-67, Her2/neu-status, and hormone receptor status compared to the native cohort. 100% participation rate in the breast cancer early detection programs were seen in patients with no school graduation. With regards to the national mammography screening program, participation decreased significantly with educational status (<i>p</i> = 0.0003). <b><i>Conclusions:</i></b> No tumor biological differences were seen between immigrants and German natives. In first-generation immigrants, early detection programs were well accepted despite sociocultural and language differences. Participation rate decreased significantly with higher education levels irrespective of country of origin. Immigration background does not have a negative effect on the participation in breast cancer screening. This mainly relates to immigrants from EU27 member states.

scholarly journals Frequent neurocognitive deficits after recovery from mild COVID-19

2020 ◽  
Vol 2 (2) ◽  
Author(s):  
Marcel S Woo ◽  
Jakob Malsy ◽  
Jana Pöttgen ◽  
Susan Seddiq Zai ◽  
Friederike Ufer ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Telephone Interview ◽  
Acute Infection ◽  
Young Patients ◽  
Cross Sectional Study ◽  
Cognitive Status ◽  
Neurocognitive Deficits ◽  
Cross Sectional ◽  
Neuropsychiatric Complications ◽  
Moderate Disease

Abstract Neuropsychiatric complications associated with coronavirus disease 2019 caused by the Coronavirus SARS-CoV-2 (COVID-19) are increasingly appreciated. While most studies have focussed on severely affected individuals during acute infection, it remains unclear whether mild COVID-19 results in neurocognitive deficits in young patients. Here, we established a screening approach to detect cognitive deficiencies in post-COVID-19 patients. In this cross-sectional study, we recruited 18 mostly young patients 20–105 days (median, 85 days) after recovery from mild to moderate disease who visited our outpatient clinic for post-COVID-19 care. Notably, 14 (78%) patients reported sustained mild cognitive deficits and performed worse in the Modified Telephone Interview for Cognitive Status screening test for mild cognitive impairment compared to 10 age-matched healthy controls. While short-term memory, attention and concentration were particularly affected by COVID-19, screening results did not correlate with hospitalization, treatment, viremia or acute inflammation. Additionally, Modified Telephone Interview for Cognitive Status scores did not correlate with depressed mood or fatigue. In two severely affected patients, we excluded structural or other inflammatory causes by magnetic resonance imaging, serum and cerebrospinal fluid analyses. Together, our results demonstrate that sustained sub-clinical cognitive impairments might be a common complication after recovery from COVID-19 in young adults, regardless of clinical course that were unmasked by our diagnostic approach.

scholarly journals Prostate cancer awareness and attitude toward early detection among male soldiers in Ghana: a cross-sectional study

2019 ◽  
Vol 25 (1) ◽  
Author(s):  
Juliana Gyasi Necku ◽  
Emmanuel Anongeba Anaba ◽  
Aaron Asibi Abuosi
Keyword(s):  
Prostate Cancer ◽  
Early Detection ◽  
Cross Sectional Study ◽  
Health Interventions ◽  
Effective Management ◽  
Sectional Study ◽  
Cancer Awareness ◽  
Cross Sectional ◽  
Knowledge And Attitudes ◽  
Positive Attitudes

Abstract Background Prostate cancer (PC) is the leading cause of cancer deaths among men in Ghana. This poses a public health threat, especially among the Ghana Armed Force (GAF) where the majority are males. This study aimed to assess male soldiers’ awareness, knowledge and attitudes toward early detection of prostate cancer. Results It was found that 58.3% of the soldiers were less aware of PC and 76.0% had low or neutral knowledge regarding risk factors and symptoms of PC. The soldiers had positive attitudes toward early detection but had low intentions of getting tested. Awareness was significantly associated with education, rank, haven received PC information from a health worker and being knowledgeable of signs of PC. Conclusion We recommend that management of the GAF should liaise with the Ministry of Health to sensitize and educate soldiers on prostate cancer, and if possible, organize periodic screening activities for the soldiers to aid in early detection and effective management of the disease. The findings of this study provide valuable information for health interventions in Ghana.

scholarly journals Psychopathology and Somatic Complaints: A Cross-Sectional Study with Portuguese Adults

Healthcare ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 478
Author(s):  
Joana Proença Becker ◽  
Rui Paixão ◽  
Manuel João Quartilho
Keyword(s):  
Early Detection ◽  
Short Form ◽  
Female Gender ◽  
Cross Sectional Study ◽  
Physical Symptoms ◽  
Brief Symptom Inventory ◽  
Cross Sectional ◽  
Psychopathological Symptoms ◽  
Patient Health ◽  
The Impact

(1) Background: Functional somatic symptoms (FSS) are physical symptoms that cannot be fully explained by medical diagnosis, injuries, and medication intake. More than the presence of unexplained symptoms, this condition is associated with functional disabilities, psychological distress, increased use of health services, and it has been linked to depressive and anxiety disorders. Recognizing the difficulty of diagnosing individuals with FSS and the impact on public health systems, this study aimed to verify the concomitant incidence of psychopathological symptoms and FSS in Portugal. (2) Methods: For this purpose, 93 psychosomatic outpatients (91.4% women with a mean age of 53.9 years old) and 101 subjects from the general population (74.3% women with 37.8 years old) were evaluated. The survey questionnaire included the 15-item Patient Health Questionnaire, the 20-Item Short Form Survey, the Brief Symptom Inventory, the Depression, Anxiety and Stress Scale, and questions on sociodemographic and clinical characteristics. (3) Results: Increases in FSS severity were correlated with higher rates of depression, anxiety, and stress symptoms. The findings also suggest that increased rates of FSS are associated with lower educational level and female gender. (4) Conclusion: Being aware of the relationship between FSS and psychopathological symptoms and the need to explore psychosocial issues during clinical interviews may favor early detection of these cases. The early detection of mental disorders is essential for individuals’ adherence to treatments, reflecting on healthcare costs.

scholarly journals Perceptions and Impact of the 2017 Canadian Guideline for Opioid Therapy and Chronic Noncancer Pain: A Cross-Sectional Study of Canadian Physicians

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Jason W. Busse ◽  
Joyce Douglas ◽  
Tara S. Chauhan ◽  
Bilal Kobeissi ◽  
Jeff Blackmer
Keyword(s):  
Online Survey ◽  
Preliminary Evidence ◽  
Opioid Therapy ◽  
Cross Sectional Study ◽  
High Dose ◽  
Cross Sectional ◽  
Chronic Noncancer Pain ◽  
Canadian Guideline ◽  
Opioid Tapering ◽  
Noncancer Pain

Background. Physician adherence to guideline recommendations for the use of opioids to manage chronic pain is often limited. Objective. In February 2018, we administered a 28-item online survey to explore perceptions of the 2017 Canadian guideline for opioid therapy and chronic noncancer pain and if physicians had altered practices in response to recommendations. Results. We invited 34,322 Canadian physicians to complete our survey, and 1,128 responded for a response rate of 3%; 687 respondents indicated they prescribed opioids for noncancer pain and answered survey questions about the guideline and their practice. Almost all were aware of the guideline, 94% had read the document, and 89% endorsed the clarity as good or excellent. The majority (86%) felt the guideline was feasible to implement, but 66% highlighted resistance by patients, and 63% the lack of access to effective nonopioid treatment as barriers. Thirty-six percent of respondents mistakenly believed the guideline recommended mandatory tapering for patients using high-dose opioid therapy (≥90 mg morphine equivalent per day), and 58% felt they would benefit from support for opioid tapering. Seventy percent of respondents had changed practices to align with guideline recommendations, with 51% engaging some high-dose patients in opioid tapering and 43% reducing the number of new opioid starts. Conclusion. There was high awareness of the 2017 Canadian opioid guideline among respondents, and preliminary evidence that recommendations have changed practice to better align with the evidence. Ongoing education is required to avoid the misunderstanding that opioid tapering is mandatory, and research to identify effective strategies to manage chronic noncancer pain is urgently needed.

scholarly journals Could Emotional Intelligence Ability Predict Salary? A Cross-Sectional Study in a Multioccupational Sample

2021 ◽  
Vol 18 (3) ◽  
pp. 1322
Author(s):  
Martin Sanchez-Gomez ◽  
Edgar Breso ◽  
Gabriele Giorgi
Keyword(s):  
Emotional Intelligence ◽  
Interpersonal Relationships ◽  
Work Experience ◽  
Ad Hoc ◽  
Preliminary Evidence ◽  
Cross Sectional Study ◽  
Cross Sectional ◽  
Repair Capacity ◽  
Relevant Variable ◽  
Correlation And Regression Analysis

The study of emotional intelligence (EI) in work environments is a trending topic. However, few studies have examined the relationship between EI and salary. Therefore, the presented research aims to analyze the influence of EI on salary using a multioccupational sample. The participants were 785 subjects aged between 18 and 58 years (M = 39.41; SD = 10.95). EI ability was measured using the Mobile Emotional Intelligence Test (MEIT), while the salary was collected together with other sociodemographic variables in a questionnaire created ad hoc. After controlling for the age, gender, social class, educational level, and work experience variables, the results of correlation and regression analysis showed that participants with higher EI and emotional-repair capacity generally have higher salary. These findings provide preliminary evidence that EI is a relevant variable in achieving career success. The ability to channel and manage emotions could help employees develop stronger interpersonal relationships, leading to higher positions and greater financial compensation.

scholarly journals Are surface and deep learning approaches associated with study patterns and choices among medical students? A cross-sectional study

2018 ◽  
Vol 136 (5) ◽  
pp. 414-420 ◽  
Author(s):  
Álvaro Henrique de Almeida Delgado ◽  
João Paulo Rodrigues Almeida ◽  
Larissa Souza Borowski Mendes ◽  
Isabella Noceli de Oliveira ◽  
Oscarina da Silva Ezequiel ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Students ◽  
Cross Sectional Study ◽  
Learning Approaches ◽  
Sectional Study ◽  
Cross Sectional
Sign in / Sign up

Export Citation Format

Share Document