RESUMEN

Cardiovascular diseases, particularly arrhythmias, remain a leading cause of mortality worldwide. Electrocardiogram (ECG) analysis plays a pivotal role in cardiovascular disease diagnosis. Although previous studies have focused on waveform analysis and model training, integrating additional clinical information, especially demographic data, remains challenging. In this study, we present an innovative approach to ECG classification by incorporating demographic information from patients' medical histories through a colorization technique. Our proposed method maps demographic features onto the (R, G, B) color space through normalized scaling. Each demographic feature corresponds to a distinct color, allowing for different ECG leads to be colored. This approach preserves the relationships between data by maintaining the color correlations in the statistical features, enhancing ECG analytics and supporting precision medicine. We conducted experiments with PTB-XL dataset and achieved 1%-6% improvements in the area under the receiving operator characteristic curve performance compared with other methods for various classification problems. Notably, our method excelled in multiclass and challenging classification tasks. The combined use of color features and the original waveform shape features enhanced prediction accuracy for various deep learning models. Our findings suggest that colorization is a promising avenue for advancing ECG classification and diagnosis, contributing to improved prediction and diagnosis of cardiovascular diseases and ultimately enhancing clinical outcomes.

Asunto(s)

RESUMEN

Background: The incidence of thyroid tumor is increasing, and preoperative diagnosis of hyalinizing trabecular tumor (HTT) is difficult. Aim: To investigate the cytological features of HTT of the thyroid gland. Settings and Design: A retrospective observational study. Materials and Methods: Ultrasonography, preoperative needle aspiration cytology, postoperative histopathology, immunohistochemistry, and BRAF V600E gene test were performed in five patients with HTT to analyze the pathological characteristics of the patients and review the relevant literature. Results: Four female and one male patients with HTT were recruited. Fine-needle aspiration cytology (FNAC) showed bloodstained background tumor cells with multiple morphologies. The tumor cells exhibited ovoid nuclei, abundant cytoplasm, fine chromatin, nuclear crowding and overlapping, and small nucleoli. Focal nuclear pseudoinclusions and grooves were present. No papillary structures or psammoma bodies were observed. In all cases, tumor cells were radially distributed around the eosinophilic extracellular matrix. In 40% (2 in 5) of cases, trabecular patterns of elongated tumor cells were present, with their nuclei staggered along the longitudinal axis of tumor cells in the trabeculae. FNAC suggested two cases of HTT and three cases of papillary thyroid cancer. Post-operational biopsy indicated they were HTT cases. Conclusion: HTT is a rare thyroid tumor with non-specific clinical manifestations. It can be misinterpreted as papillary thyroid carcinoma by FNAC. However, its cytomorphological traits are helpful in the diagnosis. In combination with FNAC, immunohistochemistry, and molecular testing, HTT can be accurately diagnosed.

Asunto(s)

RESUMEN

BACKGROUND: Elevated levels of executive function and physical fitness play a pivotal role in shaping future quality of life. However, few studies have examined the collaborative influences of physical and mental health on academic achievement. This study aims to investigate the key factors that collaboratively influence primary school students' academic achievement from executive function, physical fitness, and demographic factors. Additionally, ensemble learning methods are employed to predict academic achievement, and their predictive performance is compared with individual learners. METHODS: A cluster sampling method was utilized to select 353 primary school students from Huai'an, China, who underwent assessments for executive function, physical fitness, and academic achievement. The recursive feature elimination cross-validation method was employed to identify key factors that collaboratively influence academic achievement. Ensemble learning models, utilizing eXtreme Gradient Boosting and Random Forest algorithms, were constructed based on Bagging and Boosting methods. Individual learners were developed using Support Vector Machine, Decision Tree, Logistic Regression, and Linear Discriminant Analysis algorithms, followed by the establishment of a Stacking ensemble learning model. RESULTS: Our findings revealed that sex, body mass index, muscle strength, cardiorespiratory function, inhibition, working memory, and shifting were key factors influencing the academic achievement of primary school students. Moreover, ensemble learning models demonstrated superior predictive performance compared to individual learners in predicting academic achievement among primary school students. CONCLUSIONS: Our results suggest that recognizing sex differences and emphasizing the simultaneous development of cognition and physical well-being can positively impact the academic development of primary school students. Ensemble learning methods warrant further attention, as they enable the establishment of an accurate academic early warning system for primary school students.

Asunto(s)

RESUMEN

Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive approach to examining abnormal brain connectivity associated with brain disorders. Graph neural network (GNN) gains popularity in fMRI representation learning and brain disorder analysis with powerful graph representation capabilities. Training a general GNN often necessitates a large-scale dataset from multiple imaging centers/sites, but centralizing multi-site data generally faces inherent challenges related to data privacy, security, and storage burden. Federated Learning (FL) enables collaborative model training without centralized multi-site fMRI data. Unfortunately, previous FL approaches for fMRI analysis often ignore site-specificity, including demographic factors such as age, gender, and education level. To this end, we propose a specificity-aware federated graph learning (SFGL) framework for rs-fMRI analysis and automated brain disorder identification, with a server and multiple clients/sites for federated model aggregation and prediction. At each client, our model consists of a shared and a personalized branch, where parameters of the shared branch are sent to the server while those of the personalized branch remain local. This can facilitate knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-temporal attention graph isomorphism network to learn dynamic fMRI representations. In the personalized branch, we integrate vectorized demographic information (i.e., age, gender, and education years) and functional connectivity networks to preserve site-specific characteristics. Representations generated by the two branches are then fused for classification. Experimental results on two fMRI datasets with a total of 1218 subjects suggest that SFGL outperforms several state-of-the-art approaches.

Asunto(s)

RESUMEN

The current study aims to identify meaningful psychotic patients' profiles by examining certain combinations of patient's demographic and socio-economic variables (sex, age, marital status, number of children, cohabitant and level of education). Moreover, we aim to assess whether there is any significant effect of class membership (profile) on negative symptoms, health state, and quality of life among psychotic patients. A convenience sample of 103 patients (age: M = 22, SD = 1.75), was drawn from the clinical populations of Kosovo. Demographic and socio-economic data was obtained through individual interviews, meanwhile a battery of questionnaires was used to assess negative symptoms, mental health, and quality of life of patients. The 4-class solution was selected as the best fitting model and used in subsequent analyses. Results indicated a significant effect of class membership on health state, quality of life and negative symptoms. Practical implications are discussed.

RESUMEN

Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced machine learning techniques to facilitate automated diagnosis using laryngeal images and achieved promising results. The diagnostic performance can be improved when patients' demographic information is incorporated into models. However, the manual entry of patient data is time-consuming for clinicians. In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve the detector model's performance. The overall accuracy for gender, smoking history, and age was 85.5%, 65.2%, and 75.9%, respectively. We also created a new laryngoscopic image set for the machine learning study and benchmarked the performance of eight classical deep learning models based on CNNs and Transformers. The results can be integrated into current learning models to improve their performance by incorporating the patient's demographic information.

RESUMEN

OBJECTIVE Aimed to analyze the demographic,anthropometric,severity,and common comorbidities of individuals with suspected obstructive sleep apnea(OSA)referred to the OSA diagnosis and treatment center of the Sixth People's Hospital affiliated with Shanghai Jiao Tong University School of Medicine from 2012 to 2021.METHODS Data of subjects with suspected OSA who underwent polysomnography(PSG)from January 2012 to December 2021 were collected.Subjects were categorized into five groups based on the PSG study date with a two-year interval.Clinical characteristics trends were compared across groups,focusing on the comparison between 2020-2021 and 2018-2019 to explore changes after COVID-19 epidemic.RESULTS 1.A total of 5870 subjects were included from 2012 to 2019[age(43.2±12.7)years,21.7％females].OSA prevalence was 84.8％.Over the two-year intervals,age,female proportion,OSA severity,and other indicators showed no significant changes.Body mass index(median 26.8kg/m2 to 26.0kg/m2)and overweight rates(78.1％to 73.4％)decreased yearly,as did the proportions of subjects who smoked(38.1％to 27.8％)and consumed alcohol(13.5％to 6.4％).The prevalence of hypertension increased yearly(40.3％to 51.8％),while awareness rates gradually decreased(70.3％to 59.4％).Diabetes prevalence remained relatively stable(9.4％to 9.7％),with increased awareness(49.5％to 66.2％).Dyslipidemia prevalence remained high(76.7％to 78.3％),with low awareness rates(20.8％to 28.7％).2.A total of 805 subjects were included from 2020 to 2021.Compared with 2018-2019,the proportion of females decreased(14.9％vs.22.0％),and OSA severity increased(apnea-hypopnea index 40.4 times/h vs.29.2 times/h).Prevalence rates of hypertension,diabetes,dyslipidemia(47.1％,6.9％,62.1％)and awareness rates(52.4％,57.7％,17.8％)were lower than those from 2018-2019.3.Compared with subjects with known their comorbidities,unknown subjects had significantly higher levels of systolic blood pressure(141 mmHg vs.134 mmHg),diastolic blood pressure(93 mmHg vs.85 mmHg),fasting blood glucose(7.87 mmol/L vs.6.07 mmol/L),and low-density lipoprotein(3.08 mmol/L vs.2.91 mmol/L)(P＜0.05).CONCLUSION From 2012 to 2021,individuals with suspected OSA referred for PSG test showed a tendency toward younger age,lower proportion of females,fewer comorbidities,but increased OSA severity.The awareness rate of comorbidities needs improvement,emphasizing the importance of a multidisciplinary approach to the diagnosis and treatment of OSA.

RESUMEN

【Objective】 To explore the status and characteristics of voluntary blood donors in rural areas of Dali Bai Autonomous Prefecture (referred as Dali), and to provide basis for scientific and effective voluntary blood donation in rural population in regions inhabited by ethnic groups. 【Methods】 The data of rural blood donors who donated blood in Dali from 2010 to 2019 were collected, including demographic data as nationality, gender, age, educational background, as well as the blood donation frequency and blood infection screening (index) results. The above data of urban blood donors who donated blood in Dali during the same period were selected to investigate the increasing trend of blood donation rate. SPSS26.0 was used for statistical analysis of the collected data of rural and urban blood donation population. 【Results】 From 2010 to 2019,the number of blood donors in Dali increased from 13 949 to 19 479,with an increasing rate of 39.64%. The number of rural blood donors increased from 2 623 to 8 727,among which the number of ethnic minority groups increased from 1 779 to 5 059.The ratio of male to female blood donors was 70.30% (1 844/2 623) vs 29.70% (779/2 623) in 2010,56.37% (4 919/8 727) vs 43.63%(3 808/8 727) in 2019. Those with educational level of junior middle school or below were the most, accounted for 43.97%(38 443/85 836),with ethnic donors of 24.47%(23 583/85 836). The proportion of donors aged between 36 and 45 was the highest[40.73% (30 477/74 827) ], with ethnic donors of [28.56% (21 374/74 827), and the proportion of repeated blood donors was 54.87%(35 279/64 299),with ethnic donors of 49.89%(18 080/36 240) [the proportion of repeated blood donors in urban donors in the same period was 48.13% (55 677/115 675) ] (P0.05). 【Conclusion】 It is of great significance to explore the characteristics of blood donors in rural areas (especially regions inhabited by ethnic groups) and the reasons for disqualification, in order to scientifically carry out the recruitment of voluntary blood donors and further promote blood donation for rural residents

RESUMEN

BACKGROUND: Before the COVID-19 pandemic, Guinea has been the epicenter of the huge West Africa Ebola outbreak (2014-2016), that impact heavily the health system. Demographic information is one of the most basic data sources for health systems and services delivery, and yet can be very difficult to obtain with any accuracy. The objectives were to contribute among other to: (i) a determination of the catchment area (health coverage area and responsibility) of the Kirikilan health facility (PCM); (ii) geocoded mapping to find out exactly where these populations per sector of Kirikilan neighborhood lives; (iii) an approach for regular and systematic annual demographic follow up of target populations. METHODS: The study was a 3-year community-based survey with annual follow up of the population within the quartier of Kirikilan in Dubreka Prefecture in Guinea. It was an exhaustive enumeration of the population, sector by sector of the quartier, then there was no sampling size neither estimation. RESULTS: In October 2017 as a baseline of the study, the enumeration showed the total population was 8824 persons, 936 compounds, 1435 households, and the breakdown by sub quartier (sector) has been performed. It's showed the interest of the mapping of the target populations with geo-referenced localization. The annual follow up by demographic enumerus showed a dramatic increase of the size of the population, including strong migration of the evicted population due to urbanization purpose in some districts of Conakry, the capital. CONCLUSION: The study showed the importance of the enumeration and follow up of the target populations, but also of the setting up community data based to improve the district health information system (DHIS 2) in Guinea. The approach has a best practice could be an importunity to improve data sharing, mapping, health quality access, and affordability for a sustainable health toward universal health coverage.

Asunto(s)

RESUMEN

Objective: The epidemiological characteristics of patients with antibody-medicated autoimmune encephalitis in China remain unclear, and a large-scale epidemiological survey is necessary. Methods: A multiple-center retrospective study was performed. We collected 1,047 patients with suspected autoimmune encephalitis and ultimately enrolled 778 defined patients across centers in China. All patients were positive for serum [or cerebrospinal fluid (CSF)] antibodies. Demographic information and clinical data from January 2014 to January 2019 from 22 centers in China were reviewed. Results: A total of 778 patients with autoimmune encephalitis were enrolled in the study. In general, the ratio of males to females was ~1.2:1. The main subtypes of autoimmune encephalitis were NMDAR-AE (61.35%), LGI-1-AE (20.61%), and GABAbR-AE (12.40%). According to the characteristics of age of onset, the incidence of autoimmune encephalitis showed a "double peak" distribution entailing a 20-year-old age group and a 60-year-old age group. We next analyzed the proportion of patients with tumors in this cohort. More specifically, there were 34 patients with tumors and 85 with tumor marker positivity. Relapse occurred in 81 patients within at least 1 year's follow up study: 52 with NMDAR-AE (18.2%); 19 with LGI-1-AE (16.8%); 5 with GABAbR-AE (9%); and 3 with CASPR2-AE. Interpretation: Due to the vast differences in demographic features, the incidence of cancer and the genetic characteristics between the populations in China and Western countries, the demographics, sex distribution, concomitant tumor rate, clinical features, and relapse characteristics associated with autoimmune encephalitis in China shows a similar profile with Western countries with some minor differences.

Asunto(s)

RESUMEN

Introduction. Demographic information is one of the key parameters that organizations utilize to modify their practices in order to respond to the existing risk within work environments. The present article aims to assess the level of safety climate factors as well as to evaluate the influence of personal factors on safety climate in two different-sized industries. Methods. A total of 216 employees in two large and three small and medium-sized chemical manufacturing industries responded to a questionnaire. Descriptive statistics were used to measure the safety climate level; a two-independent-sample Mann-Whitney U test and a Kruskal-Wallis test were run to compare the difference in safety climate scores among different demographic variables. Results. The lower level of safety climate in small and medium-sized industries revealed lower understanding and performance of management and non-management with regard to safety climate compared to the large industries. Additionally, significant mean differences on some safety climate factors among demographic variables were detected in both sizes of industries, emphasizing the important role of the employees' demographic variables on the plants' safety climate. Conclusion. Improving organization-level and group-level safety climates is recommended to improve employees' level of safety climate and control their personal factors.

Asunto(s)

RESUMEN

India's Adivasi scheduled tribe population is disproportionately affected by undernutrition and anemia, thereby prevailing in the poorest wealth deciles denominated as socially and economically vulnerable. This study was designed to assess the extent of child undernutrition (conventional and composite index of anthropometric failure (CIAF) classification), as well as the burden of anemia in children and its independent nutrition specific and sensitive drivers, moreover to reflect the living conditions of Santal Adivasis. The research survey was conducted in 21 Santal villages, Birbhum District, West Bengal, in 2015. An overall 307 children (aged 6-39 months) and their mothers (n = 288) were assessed for their hemoglobin (Hb) levels (HemoCue Hb201+) and anthropometric indices such as height/length, weight and mid-upper arm circumference (MUAC). Moreover, socio-demographic household characteristics were surveyed. The study confirmed Adivasi children lagging behind national average with a high prevalence of undernutrition (height-for-age z-score (HAZ) 51.9%, weight-for-age z-score (WAZ) 49.2%, weight-for-height z-score WHZ 19.0% and CIAF 61.6%) and of moderate and severe anemia (Hb < 10 g/dL, 73.3% altogether). Child's age <24 months, low WAZ scores, morbidity (any fever, diarrhea or respiratory infection) on the checkup day or during previous week, low maternal Hb level, and lack of dietary diversification were identified as predictors for anemia, thereby warrant targeted interventions to decrease the high anemia rates assessed in the study site.

Asunto(s)

RESUMEN

The aim of this study was to determine the prevalence of mental disorders among offenders admitted at the health establishments in Bizzah Makhathe Correctional Centre, South Africa. Structured psychiatric interviews were conducted to elicit the information. The majority of the participants were young male Africans with low educational levels and poor socio-economic status. Crimes against human beings were the most common ones committed by the offenders. The lifetime prevalence of mental disorders was 54.7%. Personality disorders, followed by substance and addictive disorders, were the most prominent disorders among the study sample. Other psychiatric disorders noted were depressive disorders, schizophrenia, intellectual disabilities and neurocognitive disorders. The results show that mental disorders in prisons go undetected and untreated, meaning that competency to stand trial and criminal responsibility are not always observed. There is a need to conduct more empirical studies on the prevalence and incidences of mental disorders in South African prisons.

RESUMEN

BACKGROUND AND PURPOSE: The purpose of this study was to review the methods used to analyze the kinematics of upper limbs (ULs) of healthy and poststroke adults, namely specificities of sampling and motor tasks. SUMMARY OF REVIEW: A database of articles published in the last decade was compiled using the following search terms combinations: ("upper extremity" OR "upper limb" OR arm) AND (kinematics OR motion OR movement) AND (analysis OR assessment OR measurement). The articles included in this review (1) had the purpose to analyze objectively a three-dimension kinematics of ULs, (2) studied functional movements or activities of daily living (ADL) involving uppers limbs, and (3) studied healthy and/or poststroke adults. Fourteen articles were included (four studied a healthy sample, three analyzed poststroke patients, and seven examined both poststroke and healthy participants). CONCLUSION: Most of the recommended demographic and stroke information, such as some preexisting conditions to stroke, initial stroke severity, and stroke location, were not collected by all or most of the articles. Time poststroke onset was presented in all articles but showed great variability. Few articles identified anthropometric characteristics and adjusted task environment to them. Most of the samples were composed mainly by males and had a low mean age, which does not represent poststroke population. Most articles analyzed "functional movements", namely simulations of ADL. Implication of key findings: Future research should identify the recommended information to allow an adequate stratification. Acute phase after stroke, real ADL with different complexities, and ipsilesional UL should be studied.

Asunto(s)

RESUMEN

Exchanges between diabetic patients on discussion fora permit to study their understanding of their disorder, their behavior and needs when facing health problems. When analyzing these exchanges and behavior, it is necessary to collect information on user profile. We present an approach combining lexicon and super-vised classifiers for the identification of age and gender of contributors, their disorders and relation between contributor and patient. According to parameters of the method, precision is between 100% for gender and 53.48% for disorders.

Asunto(s)

RESUMEN

Alzheimer's disease (AD) remains to be a grand challenge for the international community despite over a century of exploration. A key factor likely accounting for such a situation is the vast heterogeneity in the disease etiology, which involves very complex and divergent pathways. Therefore, intervention strategies shall be tailored for subgroups of AD patients. Both demographic and in-depth information is needed for patient stratification. The demographic information includes primarily APOE genotype, age, gender, education, environmental exposure, life style, and medical history, whereas in-depth information stems from genome sequencing, brain imaging, peripheral biomarkers, and even functional assays on neurons derived from patient-specific induced pluripotent cells (iPSCs). Comprehensive information collection, better understanding of the disease mechanisms, and diversified strategies of drug development would help with more effective intervention in the foreseeable future.

Asunto(s)

RESUMEN

AIMS: To describe the data collected by the Chinese methadone maintenance treatment (MMT) system and the characteristics of clients entering the programme. DESIGN: Descriptive study using routinely collected data from the MMT data management system for the period March 2004 and March 2010. SETTING: All MMT clinics in China. PARTICIPANTS: Clients who enrolled for services between March 2004 and March 2010. MEASUREMENTS: Routinely collected data included: demographic information; drug use, sexual and criminal behaviours; status of infection with human immunodeficiency virus (HIV), hepatitis C virus (HCV) and syphilis; random urine-opiate test results; and the daily methadone dose received. Differences among clients by year were examined. FINDINGS: During the period examined, there were 251,974 clients attending 684 clinics in 27 provinces. Overall, the mean age was 34.4 years, 83.8% were male, 70.2% were unemployed, 75% had ever injected drugs, 17% had shared needles and 7.4% were HIV-positive. The profile of clients changed over time, with fewer HIV-positive individuals, fewer injecting drug users, fewer needle-sharers, fewer females and fewer unemployed. Half the clients dropped out within 6 months. The average final dose received was 49.4 mg. The estimated probability of interrupting treatment before 6 months was 52.5%. CONCLUSIONS: The profile of clients enrolling in methadone maintenance treatment in China is continually changing and appears to be associated with reduced risk of HIV. High dropout in the programme may limit its effectiveness. The availability of a centralized, real-time data system was extremely useful for monitoring the progress of the Chinese methadone maintenance treatment programme.

Asunto(s)