Doctor's Diagnosis Research Articles

Diabetes duration over the adult life course and associations with cardiac structure in later life

Abstract Background Type 2 diabetes mellitus (T2DM) is associated with adverse left ventricular (LV) remodelling including an increase in LV mass. With falling global age of onset of T2DM, knowing the impact of T2DM duration over the adult life course on future cardiac structure is increasingly important. Purpose We studied the association of T2DM duration over the adult life course with cardiac structure in a British birth cohort. Methods Participants in the MRC National Survey of Health and Development, (the 1946 British birth cohort) underwent comprehensive investigations including echocardiography at 60-64y. The diagnosis of T2DM and age of onset was established from self-report, doctor diagnosis and/or glycated haemoglobin. The relationship between T2DM duration (3-year intervals) and LV structure (LV mass indexed to height1.7 (LVMi), LV end-diastolic volume indexed to height1.7 (LVEDVi) and LV remodelling index (LVRI)) measured at 60-64y was investigated using multivariable linear regression models. Results Age at echocardiography was 63.2±1.10 years and 701 (47.4%) were men (Table-1). Longer T2DM duration was associated with higher LVMi (1.09 (95% CI [0.364, 1.81], g/m1.7 per 3-year; p=0.003) and was independent of confounders (model-2) (Table-2). The was no relationships with LVEDVi and LVRI. The association of T2DM with LVMi was also independent of glycaemia estimated by HbA1c at 60-64y (model-3) (Table-2). Conclusions Longer duration of T2DM is associated with elevated LVMi in later life independent of current glycaemia. Preventing or delaying the onset of T2DM may have beneficial effects on the subsequent risk of cardiovascular disease.

Multiscale feature enhanced gating network for atrial fibrillation detection.

Atrial fibrillation (AF) is a significant cause of life-threatening heart disease due to its potential to lead to stroke and heart failure. Although deep learning-assisted diagnosis of AF based on ECG holds significance in clinical settings, it remains unsatisfactory due to insufficient consideration of noise and redundant features. In this work, we propose a novel multiscale feature-enhanced gating network (MFEG Net) for AF diagnosis. The network integrates multiscale convolution, adaptive feature enhancement (FE), and dynamic temporal processing. The multiscale convolution helps capture global and local information. The FE module consists of a soft-threshold residual shrinkage component, a dilated convolution module, and a Squeeze-and-Excitation (SE) module, eliminating redundant features and emphasizing effective features. The design allows the network to focus on the most relevant AF features, thereby enhancing its robustness and accuracy in the presence of noise and irrelevant information. The dynamic temporal module helps the network learn and recognize the time dependence associated with AF. The novel design endows the model with excellent robustness to cope with random noise in real-world environments. Compared with the state-of-the-art methods, our model exhibits excellent classification performance with an accuracy of 0.930, an F1 score of 0.883, and remarkable resilience to noise interference on the PhysioNet Challenge 2017 dataset. Moreover, the model was trained on the CinC2017 database and validated on the CPSC2018 database and AFDB database, achieving accuracies of 0.908 and 0.938, respectively. The excellent classification performance of MFEG Net, coupled with its robustness in processing noisy electrocardiogram signals, makes it a powerful method for automatic atrial fibrillation detection. This method has made significant progress over state-of-the-art methods and may alleviate the burden of manual diagnosis for clinical doctors.

Association of sarcopenia with Parkinson's disease and related functional degeneration among older adults: A prospective cohort study in Europe.

Former evidence on the risk factors for Parkinson's disease (PD), especially the PD-related functional limitation and neurological outcomes was scarce. We aimed to explore the association between sarcopenia and PD along with the PD-related functional degeneration. Further, we testified the heterogeneity in the above relationships of multimorbidity severity and patterns. Data was from the Survey of Health, Ageing and Retirement in Europe (wave 4-8). PD was ascertained by self-reported doctor diagnosis. PD-related functional degeneration was defined as the coexistence of PD and functional limitation, mild cognitive impairment (MCI), and dementia. Sarcopenia status was determined by the criteria of European Working Group on Sarcopenia in Older People in 2019. Cox regression models were conducted to examine the association between sarcopenia and PD risk. Among 40,041 participants, those with sarcopenia were significantly associated with onset of PD (HR = 2.16, 95 % CI: 1.41-3.31), along with related functional limitation (HR = 2.58, 95 % CI: 1.59-4.19), MCI (HR = 2.93, 95 % CI: 1.37-5.15), and dementia (HR = 6.05, 95 % CI: 3.17-11.56). Heterogeneity of multimorbidity severity and patterns was found in the relationship of sarcopenia with PD-related functional limitation and MCI and the observed associations only existed among those with highest level of multimorbidity severity and those with complicated pattern. Sarcopenia status was correlated to PD and the related functional degeneration and the difference in the above relationships of multimorbidity patterns and severity was observed. Early screening on sarcopenia-related indicators and more emphasis on the precaution of PD among those with severe and complicated multimorbidity patterns were recommended.

Food Allergy and Mental Health in Children and Adolescents-The Role of Shared Familial Environment.

Evidence suggests a link between food allergy and poor mental health, however, this may be explained by shared genetic and environmental factors. We aimed to investigate the association between food allergy of different severity and mental health in children, and the role of familial factors. This population-based, longitudinal cohort study is based on the Child and Adolescent Twin Study in Sweden with questionnaire data reported by parents and/or children. Food allergy 'ever' and doctor's diagnosis were reported at age 9-12 years, and ≥ 1 recent dispensation of adrenaline was used as a marker for current severe food allergy. Outcomes were identified using validated questionnaires for anxiety; Screen for Child Anxiety Related Disorders (SCARED); Strength and Difficulties Questionnaire (SDQ) and depression; Short Mood and Feelings Questionnaire (SMFQ), Center for Epidemiological Studies Depression Scale (CES-D) and Diagnostic and Statistical manual of Mental Disorders (DSM-IV-MDE) and reported at 9-12, 15 and 18 years of age. Multivariate linear and logistic modelling was applied to the whole cohort and a co-twin control approach to remove confounding by familial factors. In total, 3039 (8.9%) children had a parent-reported food allergy. Among these, 1292 (43.5%) had non-severe food allergy without diagnosis, 1490 (49%) had non-severe food allergy with diagnosis and 257 (8.5%) had severe food allergy. Compared to children with no food allergy, non-severe food allergy with diagnosis by 9-12 years was associated with parent-reported anxiety/depression; SCARED (adjOR 2.10, 95% CI 1.48-2.98), SMFQ (adjOR 1.92, 95% CI 1.19-3.10) at 9-12 years and SDQ (adjβ 0.2, 95% CI 0.0-0.4) at 15 years. All other associations were null including for those with severe food allergy. All positive estimates in the full cohort were attenuated using co-twin controls. Evidence associating paediatric food allergy severity and poor mental health was weak, and positive associations observed were likely due to familial confounding.

Heterogeneity of reduced FEV1 in early adulthood: A looking forward, looking backwards analysis.

Some individuals never achieve normal peak FEV1 in early adulthood. It is unknown if this is due to airflow limitation and/or lung restriction. To investigate this, we: (1) looked forward in 19,791 participants in the Dutch Lifelines general population cohort aged 25-35 years with 5-year follow-up; and (2) looked backwards in 2032 participants in the Swedish BAMSE birth cohort with spirometry at 24 years of age but also at 16 and/or 8 years. (1) In Lifelines 8.5% of participants had reduced FEV1 at 25-35 years, 68% due to Preserved Ratio Impaired Spirometry ('PRISm') and 32% to airflow limitation ('low-limited'); besides, 3.8% participants with normal FEV1 showed airflow-limitation ('normal-limited'). Low-limited and normal-limited, but not PRISm, reported higher smoking exposures and asthma diagnosis than normal (p < 0.05). At 5-year follow-up, 91.2% of participants remained in the same group, and FEV1 decline was similar in normal and normal-limited participants, but statistically smaller (p < 0.05) in PRISm and low-limited; (2) these observations were largely reproduced in BAMSE at 24 years of age; and, (3) in BAMSE, low-limited or PRISm individuals were already identifiable at 8-16 years of age. Low peak FEV1 in early adulthood is most often due to PRISm and results in a significant burden of respiratory symptoms. Only low-limited and normal-limited, but not PRISm, associate with a doctor diagnosis of asthma, and FEV1 decline was statistically different in PRISm indicating a need for differentiated clinical approaches. These spirometric abnormalities can be already identified in childhood and adolescence.

The relationship between the early life gastrointestinal microbiome and childhood nocturnal cough.

Nocturnal cough affects approximately 1 in 3 children, can negatively impact child health, and is often attributable to asthma. The association of the gut microbiome with nocturnal cough has not been investigated. To investigate the association between early-life gut microbiome composition and nocturnal cough overall and in the context of asthma. Gut microbiota 1-month (neonate) and 6-month (infant) specimens from 512 children in the Wayne County, Health, Environment, Allergy, and Asthma Longitudinal Study were profiled using 16S rRNA V4 sequencing. Nocturnal cough (parental-report) and asthma (parental-reported doctor diagnosis) were assessed at age 4 years. Microbiome Regression-Based Kernel Association Tests were used to assess the relationship between gut microbiota composition and nocturnal cough overall and in the context of asthma. Operational taxonomic unit (OTU) associations were conducted using negative binomial regression, adjusting for multiple comparisons using the false discovery rate (FDR). Stool microbial composition differences during infancy were associated with nocturnal cough (Weighted Unifrac p=0.045). 78 OTUs were significantly associated with nocturnal cough overall (FDR<0.05). 110 OTUs were significantly associated with nocturnal cough and differed by asthma status (interaction FDR<0.05), with predominance of Lachnospiraceae Blautia and Dorea. 32 OTU were identified as having both overall effects and differences by asthma status. Among OTUs with significant nocturnal cough-by-asthma interactions, 84 retained significance in children with asthma, with 45 exclusive to those with asthma (predominance of Bacteroidaceae Bacteroides and Lachnospiraceae Dorea). Infantile gut microbiome development is associated with nocturnal cough and differed by asthma status by age 4 years. Further studies are needed to determine if the gut microbiome may provide additional information for the early identification of children at risk for nocturnal cough, with and without asthma.

Supervised Learning based Chest Disease Prediction with IOT from Xray Images

New WHO research indicates that there are an increasing number of chest-related illnesses. This results in the deaths of 17.9 million people annually. It gets harder to identify problems and start therapy at an early age as the population grows. However, new developments in technology, such as deep learning and machine learning methods, have sped up research in the medical profession. The creation of a machine learning and deep learning model for heart disease prediction based on pertinent features is the goal of this study. The chest's X-ray images are kept in the cloud for public access in the suggested method. The images retrieved from the cloud via the internet are analyzed for prediction using machine learning methods such as K Nearest Neighbor and Random Forest and deep learning algorithms such as Convolutional Neural Network and ResNet. Results are further stored in the cloud. Doctors, users, and patients can access the saved findings on cloud servers for diagnosis and treatment. We used a benchmark dataset from UCI Chest Disease Prediction for this research study. The proposed method classified X-ray images into normal and chest disease as cardiomegaly, aortic enlargement, and enlarged cardioment. Results are updated in the cloud for doctor diagnosis purposes. From experimental analysis, ResNet produced better results compared to other methods.

Long-Term Oral Health Effects of Traumatic Events Among World Trade Center Health Registry Enrolees, 2003-2020.

Posttraumatic stress disorder (PTSD) is a disabling mental health condition arising from experiencing serious traumatic events. This study investigated if PTSD secondary to the World Trade Center terrorist attack on 11 September 2001 (9/11) is associated with self-reported doctor's diagnosis of periodontitis and count of missing teeth. Data from the World Trade Center Health Registry, 2003-2020 (n = 20 826) were used to prospectively examine the rate of periodontitis and cross-sectionally the odds of missing teeth among enrolees with/without PTSD post-9/11 using a modified Poisson regression and generalised logit model, respectively, adjusted for covariates. Approximately 17% reported a doctor's diagnosis of PTSD post-9/11 and 7.4% a doctor's diagnosis of periodontitis. There were 355 new cases of periodontitis (incidence rate = 7.6 per 1000 person-years) among those with PTSD and a rate of 4.3 per 1000 person-years among those without PTSD. The covariate-adjusted rate ratio for periodontitis comparing those with and without PTSD = 1.52 (95% CI: 1.33, 1.74). The adjusted odds ratio (OR) (95% CI) comparing those with and without PTSD were, respectively, OR = 1.15 (95% CI: 1.05, 1.25) and OR = 1.41 (95% CI: 1.09, 1.83) for missing 1-5 teeth and all teeth missing, respectively, as compared to no missing teeth. PTSD post-9/11 appears to be associated with poorer oral health outcomes, underscoring the far-reaching consequences of traumatic events on oral health.

Analysis and Prediction of Risk Factors for Heart Failure

Abstract. Heart failure is a grave and progressive illness. It is associated with multiple risk factors such as age and other possible factors. Accurately identifying and quantifying these risk factors is critical to developing personalized prevention and treatment strategies. However, it is difficult for common patients to predict heart failure without the professional diagnosis of doctors, and relying on human resources to predict heart failure is more subjective. This study proposes a method to evaluate and predict the factors related to heart failure based on multiple body indicators by using random forest algorithm. The random forest prediction model was applied to assess the correlation between multiple medical indicators such as creatinine phosphokinase (CPK), serum creatinine (SCR), ejection fraction (EF), age and heart failure. CPK was found to be the most associated with heart failure. In addition, increasing follow-up period can also effectively monitor heart failure progression in patients. In this high dimension prediction problem, the prediction effect of random forest is better, and the overall accuracy is higher. The approach used in this research is important for forecasting the risk of heart failure, enhancing the survival rates of patients, and alleviating the burden on healthcare systems.

Abstract 4136294: Carbohydrate intakes and cardiovascular disease risk factors in South Asians: Results from 56,024 participants in Bangladesh, India, Pakistan, and Sri Lanka

Background: Evidence on effects of carbohydrate intake with cardiovascular disease risk factors is inconsistent and has limited generalizability to diverse populations such as South Asians, whose carbohydrate intakes are typically high. Aims: We examined the association of the quantity and types of carbohydrate intake with two risk factors for major cardiovascular events– hypertension (HT) and hypercholesterolemia (HC). Methods: We analyzed cross-sectional data from participants aged ≥18 years in the South Asia Biobank in Bangladesh, India, Pakistan, and Sri Lanka. Using dietary data assessed with interviewer-led 24h diet recalls, we calculated intakes of total and subtypes of carbohydrates and several indices of carbohydrate quality. Primary outcomes were HT and HC, defined by medication use, doctor diagnosis, blood pressure and blood lipid levels. With mixed effects Poisson regression, HT and HC was regressed on quantiles of carbohydrate intakes by country to estimate prevalence ratios (PR) and 95% confidence intervals (CI), followed by meta-analysis pooling country-specific estimates. We examined interactions by diabetes status and adiposity. Results: Of 56,024 adults, 36.6% had HT, 16.1% had HC. In pooled multivariable analyses comparing extreme quantiles, total carbohydrate intake was not associated with HT or HC prevalence. Fructose, free sugar and free sugar-to-fiber ratio were associated with higher prevalence of HT (PRs Q5vsQ1 : 1.03-1.15). Higher intakes of cereal fiber (PR Q4vsQ1 : 0.96, 95% CI: 0.95-0.98) and legume fiber (PR Q4vsQ1 : 0.98, 95% CI: 0.97-0.98) were associated with lower prevalence of HT and higher cereal fiber intake with lower HC prevalence (PR Q5vsQ1 : 0.80, 95% CI: 0.75-0.85). Diabetes and adiposity were observed as effect-modifiers (p&lt;0.001). There were null associations in adults with diabetes but in non-diabetic adults, free sugar intake was related positively with HT (PR Q5vsQ1 : 1.07, 95% CI: 1.05-1.09) while fiber intake was inversely related (PR Q5vsQ1 : 0.98, 0.95-0.97). Starch, sugar and free sugar intake were associated positively with HT prevalence in adults with high body fat (≥20% for men; ≥30% for women) and visceral fat (≥10%) levels (PRs Q5vsQ1 : 1.03-1.20); associations were null for low body and visceral fat levels. Associations varied by country (between-country heterogeneity I 2 &gt;60%). Conclusion: Associations of dietary carbohydrates with HT and HC depended on the quality and type of intake in South Asians.

Research on Sleep Staging Based on Support Vector Machine and Extreme Gradient Boosting Algorithm.

To develop a sleep-staging algorithm based on support vector machine (SVM) and extreme gradient boosting model (XB Boost) and evaluate its performance. In this study, data features were extracted based on physiological significance, feature dimension reduction was performed through appropriate methods, and XG Boost classifier and SVM were used for classification. One hundred and twenty training sets and 80 test sets were randomly composed of the first 200 groups of data from the SHH1 database. The polysomnography (PSG) data of 20 real individuals in the clinic were selected as the experimental data. The C3 electroencephalogram (EEG), left and right electrooculogram (EOG), electromyogram (EMG), and other signals were analyzed. Finally, the stages were adjusted based on human sleep laws. The standard staging of the database and the doctor's diagnosis staging was used as the standard. The SHHS1 database test results were as follows: the average accuracy was 83.24%, the precision and recall of Stage Wake and Stage 2 NREM sleep (N2) were over 80%, and the precision, F1-Score and recall of Stage 3 NREM sleep (N3) and Rapid Eye Movement (REM) were more than 70%. The clinical data test results were as follows: the average accuracy rate was 76.37%; for Wake and N3, the precision reached 85%; for Wake, N2, and REM, the recall rate reached over 70%; for Wake, the F-1 Score reached over 90%. This study shows that the sleep staging results of the algorithm for the database and clinical data were similar. The staging results meet the requirements at the medical level.

Asian birth cohort studies on allergic diseases: The A2BC network initiative.

The Asia Allergy Birth Cohort (A2BC) network consolidates data from multiple independently established birth cohorts across Asia to enhance research on host-environment interactions in allergic diseases. These cohorts, established at different times with various methodologies, are reliable data sources. Our aim is to introduce the content, variables, and outcomes of these cohorts while highlighting their differences, laying the groundwork for future collaborative research. The A2BC network includes 10 cohort studies on allergic diseases from six Asian countries. Enrollment criteria, study aims, and an initial inventory were discussed and confirmed through five business meetings. A common database was developed to assess the study characteristics of these observational cohorts on allergic diseases, though harmonization efforts are retrospective. Five studies collected data on specific immunoglobulin E responses to various inhalant and food allergens, while six cohorts conducted skin prick tests. Lung function measurements were included in some studies, but without standardized procedures across cohorts. Asthma and allergic rhinitis were primarily assessed using questionnaires or doctor diagnoses, while assessments of eczema and food allergies varied across studies. The A2BC network also examines early-life environmental factors such as delivery mode, antibiotic usage, diet, and air pollutants, although these exposures were measured differently across the cohorts. Despite differences in the origins, methods, and objectives of each cohort, pooling data and conducting joint analyses offer valuable insights into the relationship between environmental exposures and allergic disease outcomes in Asian children. This approach can serve as a foundation for future collaborative research.

Nepal Family Cohort study: a study protocol

IntroductionThe Nepal Family Cohort study uses a life course epidemiological approach to collect comprehensive data on children’s and their parents’ environmental, behavioural and metabolic risk factors. These factors can affect...

Income level is associated with differences in primary and secondary stroke prevention in China.

The aim of this study was to assess differences in the effects of income level on the primary and secondary prevention of stroke in the Chinese population. This was a population-based study using data from a China Kadoorie Biobank survey that began in 2004 in 10 geographical regions. Community residents (n = 512,715) aged 30-79 years were recruited. Stroke was determined by the self-reporting of a doctor's diagnosis, and participants with a high risk of stroke were identified using the model developed in the Prediction for ASCVD Risk in China study. The final numbers of people included in this study were 8,884 with stroke and 218,972 with a high risk of stroke. The participants' income level was positively associated with high levels of physical activity and the consumption of a healthy diet, but negatively associated with the control of alcohol consumption (all p < 0.05). In addition, positive associations were observed between the control of smoking and the use of antiplatelet and antihypertensive medication for primary prevention (all p < 0.05), but there was a negative association with the control of blood pressure (p < 0.001). Low-income individuals were less likely to control smoking and their diet and use preventive medications, while high-income individuals were less likely to control their alcohol consumption and blood pressure. Moreover, medication use was low for both primary and secondary prevention in high-income individuals.

A cross-sectional study on utilization and barriers of eSanjeevani telemedicine services in rural areas of South India: Curing at a distance

Background: Telemedicine services are essential in a country like India, where the doctor-to-patient ratio and hospital-topopulation ratio are lower than the World Health Organization (WHO)-recommended ratio. To prevent the long waiting time for doctor appointments, diagnosis, and treatment plans in person, an alternative system such as eSanjeevani telemedicine is necessary to tackle medical emergencies in a populated country like India. Objectives: To assess the utilization and barriers affecting the utilization of eSanjeevani services among residents of rural areas in Karnataka. Materials and Methods: A Cross sectional community study was conducted in the rural areas of south India, using a pre-tested semi-structured interview schedule. Multistage cluster sampling method was used to select 400 households. The collected data has been expressed in terms of frequencies and percentages. Results: The study identified that most of the study participants were from lower middle class as per the modified Kuppuswamy Scale. Only 34.8% were aware of the eSanjeevani services and among them 22% utilized eSanjeevani services in which General medicine services (86.3%) were used the most. Major barriers for utilization included network issues (29%) followed by no room for queries/questions (20%). Conclusion: Telemedicine has the potential to enhance the availability and accessibility of healthcare to everyone. At the moment, lack of awareness, low network connectivity, and inherent technological limits pose major challenges for accessing telemedicine. Utilization of telemedicine can be increased by making people aware about the advantages of using it through strong Information, Education and Communication and media publicity

Associations of polysomnographic measures of obstructive sleep apnea, and nocturnal oxygen saturation with incident type 2 diabetes mellitus in middle-aged and older men.

Obstructive sleep apnea (OSA) has been associated with incident type 2 diabetes mellitus (T2DM); however, few prospective epidemiological studies have accounted for important T2DM predictors including pre-diabetes status and testosterone. Participants in the longitudinal Men Androgens Inflammation Lifestyles Environment and Stress (MAILES) study, who underwent eight-channel home-based polysomnography (PSG) in 2010-2011 (n = 824) and were free of diabetes at baseline were included in the analysis (n = 682). From 2015 to 2021, 78.6% (n = 536) completed at least one follow-up assessment. Incident T2DM was determined by self-reported doctor diagnosis, diabetes medications, plasma glucose (fasting ≥7.0 mmol/L or random ≥11.0 mmol/L) or glycated haemoglobin ≥6.5%. Conservative hierarchical Poisson regression models adjusted associations of PSG metrics (categorical and continuous) for age, waist circumference, baseline fasting glucose and testosterone concentrations. In all, 52 men (9.7%) developed T2DM over a mean (range) of 8.3 (3.5-10.5) years. Significant age- and waist circumference-adjusted association of incident T2DM with rapid eye movement (REM) sleep apnea-hypopnea index (AHI) ≥20 events/h (incidence rate ratio [IRR] 1.5, 95% confidence interval [CI] 0.8-2.8; p = 0.23] and highest quartile of delta index (IRR 2.1, 95% CI 0.95-4.6; p = 0.066) were attenuated after adjustment for baseline glucose and testosterone, and the association with the lowest quartile of mean oxygen saturation persisted (IRR 4.2, 95% CI 1.7-10.3; p = 0.029). Categorical measures of AHI severity, oxygen desaturation index, and hypoxia burden index (HBI) were not independently associated with incident T2DM. Associations with T2DM were similar when continuous PSG variables were used; however, HBI was significant (IRR 1.015, 95% CI 1.006-1.024; p = 0.007). In a sub-sample with OSA treatment data (n = 479), these significant associations persisted after excluding adequately treated OSA (n = 32). Understanding underlying OSA endotypes generating hypoxaemia may identify opportunities for diabetes prevention.

Abstract P129: Assessing the impact of serum lead levels on kidney function Among hypertensive population: NHANES 2017-2020

Purpose: Hypertension and chronic kidney disease is known adverse effects of lead poisoning. However, there is limited evidence on the magnitude of the relationship between blood lead levels and kidney function, especially on a national scale. This study investigates the association of serum lead levels (Pb-S) with estimated glomerular filtration rate (eGFR). Method: A national study of 6,789 adults, using NHANES 2017-2020 data, analyzed the correlation between Pb-S and eGFR. Participants were categorized into non-hypertension and hypertension groups based on self-reported for doctor diagnosis, with three linear regression models employed. Results: In our population, 35.6% have been diagnosed with hypertension, with 36.1% in males and 35.2% in females. The average SBP and DBP were 130.7 ± 17.8 mmHg and 77.6 ± 12.7 mmHg, respectively. The average Pb-S level was 1.04 ± 0.68 µg/dL, with 1.16 ± 0.72 µg/dL for males and 0.94 ± 0.63 µg/dL for females (mean difference 0.22 ± 0.02, P&lt;0.001). Individuals with hypertension had higher mean Pb-S levels compared to those without hypertension (1.15 ± 0.70 vs. 0.98 ± 0.66 µg/dL; mean difference 0.17 ± 0.02, P&lt;0.001). In the final adjusted model, eGFR declined by -1.28 (95% CI: -2.16 to -0.39) in the total group, by -0.35 (95% CI: -1.50 to 0.80) in the non-hypertension group, and by -2.50 (95% CI: -3.90 to -1.11) in the hypertension group, respectively (Fig 1). Conclusion: The Pb-S is inversely associated with kidney function in adult hypertensive population in the United States Testing for Pb-S may be considered to especially in hypertensive patients with declined kidney function who are at risk for lead exposure or toxicity.

Patients' Expectations of Doctors' Clinical Competencies in the Digital Health Care Era: Qualitative Semistructured Interview Study Among Patients.

Digital technologies have impacted health care delivery globally, and are increasingly being deployed in clinical practice. However, there is limited research on patients' expectations of doctors' clinical competencies when using digital health care technologies (DHTs) in medical care. Understanding these expectations can reveal competency gaps, enhance patient confidence, and contribute to digital innovation initiatives. This study explores patients' perceptions of doctors' use of DHTs in clinical care. Using Singapore as a case study, it examines patients' expectations regarding doctors' communication, diagnosis, and treatment skills when using telemedicine, health apps, wearable devices, electronic health records, and artificial intelligence. Findings were drawn from individual semistructured interviews with patients from outpatient clinics. Participants were recruited using purposive sampling. Data were analyzed qualitatively using thematic analysis. Twenty-five participants from different backgrounds and with various chronic conditions participated in the study. They expected doctors to be adept in handling medical data from apps and wearable devices. For telemedicine, participants expected a level of assessment of their medical conditions akin to in-person consultations. In addition, they valued doctors recognizing when a physical examination was necessary. Interestingly, eye contact was appreciated but deemed nonessential by participants across all age bands when electronic health records were used, as they valued the doctor's efficiency more than eye contact. Nonetheless, participants emphasized the need for empathy throughout the clinical encounter regardless of DHT use. Furthermore, younger participants had a greater expectation for DHT use among doctors compared to older ones, who preferred DHTs as a complement rather than a replacement for clinical skills. The former expected doctors to be knowledgeable about the algorithms, principles, and purposes of DHTs such as artificial intelligence technologies to better assist them in diagnosis and treatment. By identifying patients' expectations of doctors amid increasing health care digitalization, this study highlights that while basic clinical skills remain crucial in the digital age, the role of clinicians needs to evolve with the introduction of DHTs. It has also provided insights into how DHTs can be integrated effectively into clinical settings, aligning with patients' expectations and preferences. Overall, the findings offer a framework for high-income countries to harness DHTs in enhancing health care delivery in the digital era.

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

AN INTELLIGENT MODEL FOR BENIGN AND MALIGNANT PULMONARY NODULE ANALYSIS USING U-NET NETWORKS AND MULTILEVEL ATTENTION MECHANISMS

A key study area throughout the medical sector for image processing and analysis is medical image segmentation. The diagnosis and treatment strategies of doctors may have a solid foundation owing to accurate and effective medical image segmentation. Conventional approaches in this field rely on manual feature extraction, which makes segmentation complex, costs doctors’ time and energy, and involves a subjective evaluation that is readily susceptible to diagnostic errors. Researchers have applied convolutional neural network-based deep learning techniques to the segmentation of medical images as a result of their impressive advancements and successes in the field of computer vision. The research described here uses the U-Net network’s outstanding feature learning capabilities and end-to-end processing mode for lung CT image segmentation via fully convolutional network (FCN) research. However, focusing on valuable, crucial information aspects in the U-Net network is challenging. This study employed multilevel attention mechanisms on the basis of U-Net networks to enhance the model’s accuracy in lung CT image segmentation. These mechanisms were inspired by attention mechanisms. By improving the segmentation accuracy and optimizing the segmentation effect, the new model embeds a self-attention module in front of each upsampling layer in the U-Net model. This module provides more detailed information by stitching the self-attention module of the original image and then suppresses irrelevant and redundant information by using the effect of feature extraction of the upsampling layer. Several additional comparative experiments were conducted on the 2019nCoVR dataset. The outcomes demonstrate the efficacy of the optimized model described in this paper and its application results in improved segmentation effects in lung CT images. Additionally, the new model has distinct advantages over existing approaches that are typical of medical image segmentation, which represent its higher level of lung CT image segmentation.