Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania

BACKGROUND

Respiratory diseases, including active tuberculosis (TB), asthma, and chronic obstructive pulmonary disease (COPD), constitute substantial global health challenges, necessitating timely and accurate diagnosis for effective treatment and management.

OBJECTIVE

This research seeks to develop and evaluate a noninvasive user-friendly artificial intelligence (AI)-powered cough audio classifier for detecting these respiratory conditions in rural Tanzania.

METHODS

This is a nonexperimental cross-sectional research with the primary objective of collection and analysis of cough sounds from patients with active TB, asthma, and COPD in outpatient clinics to generate and evaluate a noninvasive cough audio classifier. Specialized cough sound recording devices, designed to be nonintrusive and user-friendly, will facilitate the collection of diverse cough sound samples from patients attending outpatient clinics in 20 health care facilities in the Shinyanga region. The collected cough sound data will undergo rigorous analysis, using advanced AI signal processing and machine learning techniques. By comparing acoustic features and patterns associated with TB, asthma, and COPD, a robust algorithm capable of automated disease discrimination will be generated facilitating the development of a smartphone-based cough sound classifier. The classifier will be evaluated against the calculated reference standards including clinical assessments, sputum smear, GeneXpert, chest x-ray, culture and sensitivity, spirometry and peak expiratory flow, and sensitivity and predictive values.

RESULTS

This research represents a vital step toward enhancing the diagnostic capabilities available in outpatient clinics, with the potential to revolutionize the field of respiratory disease diagnosis. Findings from the 4 phases of the study will be presented as descriptions supported by relevant images, tables, and figures. The anticipated outcome of this research is the creation of a reliable, noninvasive diagnostic cough classifier that empowers health care professionals and patients themselves to identify and differentiate these respiratory diseases based on cough sound patterns.

CONCLUSIONS

Cough sound classifiers use advanced technology for early detection and management of respiratory conditions, offering a less invasive and more efficient alternative to traditional diagnostics. This technology promises to ease public health burdens, improve patient outcomes, and enhance health care access in under-resourced areas, potentially transforming respiratory disease management globally.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/54388.

Association of ulcerative colitis and acute gastroenteritis with prostate specific antigen: results from National Health and Nutrition Examination Survey from (2009 to 2010) and Mendelian randomization analyses

Background

An increasing number of studies have demonstrated that gastrointestinal inflammation may increase prostate cancer risk and raise the prostate-specific antigen (PSA) level. However, the association between ulcerative colitis (UC) and acute gastroenteritis (AGE) with PSA remains unclear and complicated. Herein, we evaluated the relationship between UC and AGE with PSA concentration using the National Health and Nutrition Examination Survey (NHANES) database and Mendelian randomization (MR) analyses.

Materials and methods

A total of 1,234 participants fit into the study after conducting the screening based on the NHANES survey conducted from 2009 to 2010. UC and AGE were the independent variables, and PSA was the dependent variable. Weighted multiple linear regressions were utilized to estimate the association of UC and AGE with PSA concentration. To detect the causal relationship between UC and AGE with PSA, a two-sample Mendelian randomized analysis was conducted.

Results

After controlling for all covariates, PSA (log2 transform) concentrations in the UC group were increased by 0.64 (0.07, 1.21). AGE was not independently associated with PSA levels after adjusting potential confounders. In patients with coronary artery disease, AGE promotes elevated PSA (log2 transform) concentrations (β = 1.20, 95% CI: 0.21-2.20, p < 0.001). Moreover, an IVW MR analysis indicated that genetically predicted UC was associated with increased PSA, and that AGE was not associated with PSA.

Conclusion

This study indicated that a positive causal association exists between UC and the PSA level. However, there is no evidence to support the relationship between AGE and the PSA level.

Associations between the muscle quality index and adult lung functions from NHANES 2011-2012

Background

The muscle quality index (MQI), as an important component of sarcopenia, is defined as the ratio of muscle strength to muscle mass. Lung function, is a clinical indicator to assess ventilation and air exchange function. This study investigated the relationship between lung function indices and MQI in the NHANES database from 2011 to 2012.

Methods

This study included 1,558 adults from the National Health and Nutrition Examination Survey from 2011 to 2012. Muscle mass and muscle strength were assessed using DXA and handgrip strength, and all participants underwent pulmonary function measurements. Multiple linear regression and multivariable logistic regression were used to assess the correlation between the MQI and lung function indices.

Results

In the adjusted model, MQI was significantly correlated with FVC% and PEF%. And, after quartiles of MQI in Q3, where FEV₁%, FVC%, and PEF% were all associated with MQI, in Q4, a lower relative risk of a restrictive spirometry pattern was linked to increased MQI. Compared to the lower age group, the relationship between the MQI and lung function indices was more significant in the higher age group.

Conclusion

There was an association between the MQI and lung function indices. Furthermore, in the middle-aged and older adult populations, lung function indicators and restrictive ventilation impairment were significantly associated with MQI. This implies that improving lung function through muscle training may be beneficial to this group.

Non-linear association between composite dietary antioxidant index and depression

Background

Growing evidence has shown that the antioxidant diet is a protective factor against depression. However, the relationship between the Composite Dietary Antioxidant Index (CDAI), an important measure of antioxidant diet, and depression has received little attention. Therefore, we investigated the relationship between CDAI and depression through a cross-sectional analysis of the National Health and Nutrition Examination Survey (NHANES) from 2007 to 2018.

Methods

The association between CDAI and depression was investigated using a weighted multiple logistic regression model with subgroup analysis. Non-linear correlations were explored using fitted smoothing curves. And we used a recursive method to figure out the turning point and build a weighted two-piece linear regression model.

Results

In the multivariate logistic regression model with full adjustment for confounding variables, the ORs (95% CI) for the association between CDAI and depression were 0.83 (0.78, 0.88). Moreover, a non-linear association was found, with 0.16 being the inflection point. Before the inflection point, each unit increase in CDAI was associated with a 30% decrease in the risk of depression. After the inflection point, the risk of depression was found to be reduced by 11% for each unit increase. None of the interactions in all subgroup analyses were statistically significant.

Conclusions

Our study highlighted a negative non-linear association between CDAI and depression in a nationally representative sample of US adults. Further clinical and basic research is needed to explore their association better.

Association of the serum uric acid to creatinine ratio with metabolic syndrome in the middle age and older population in China

BACKGROUND

Metabolic syndrome (MetS) has attracted great interest, with an increasing prevalence. Recent studies have shown that the serum uric acid-to-creatinine ratio (SUACr) might be an excellent biomarker for MetS risk prediction in diabetic patients and postmenopausal women. However, the relationship between SUACr and MetS in a middle-aged and older population remains unclear.

METHODS

A total of 1277 participants were included in this cross-sectional study. Logistic regression modelling was performed to assess the association between SUACr and MetS in the total population. The dose-response relationship of SUACr and MetS was further assessed by a restricted cubic spline model (RCS). Furthermore, to explore the relationships between the levels of SUACr and the number of metabolic components, analysis of covariance (ANCOVA) was applied.

RESULTS

The levels of SUACr were lower in the non-MetS participants (OR 1.60, 95% CI 1.36 to 1.89; P<0.001),. Positive and dose-response relationships were further confirmed by the RCS model. We also found that, with increased number of components, the SUACr tended to increase. Moreover, values of SUACr were strongly related to levels of triglycerides (TGs), body mass index (BMI), blood glucose levels, systolic blood pressure/diastolic blood pressure (SBP/DBP), and hypertension. In addition, the positive association between SUACr and MetS also occurred in those patients with normal uric acid levels.

CONCLUSION

Elevated values of SUACr were strongly associated with an increased risk of MetS; this positive relationship remained in those individuals with normal uric acid levels.

Impact of sense of coherence, resilience and loneliness on quality of life amongst older adults in long-term care: A correlational study using the salutogenic model

AIMS

This study aimed to identify the predicting factors of quality of life (QoL) from a set of psychosocial, sociodemographic and clinical variables amongst older adults in a long-term care setting.

DESIGN

A cross-sectional, descriptive correlational study.

METHOD

The study was conducted in a nursing home and a day care centre from July to December 2019. Two hundred older adults were recruited. Guided by the salutogenic model, the sense of coherence (SOC) scale, Connor-Davidson resilience scale, de Jong Gierveld loneliness scale and World Health Organization quality of life instrument-older adults (WHOQOL-OLD) were used. The sociodemographic and clinical profiles of participants were collected. Descriptive statistics, Pearson product-moment correlation coefficient, independent-samples t test, one-way analysis of variance and stepwise regression were utilised in the analysis.

RESULTS

The mean score for WHOQOL-OLD was 94.42 ± 19.55. The highest mean score was observed in the "Death and Dying" facet, while the lowest mean scores were reflected in the "Autonomy" and "Intimacy" facets of QoL. Regardless of resident type, most QoL scores were similar across different variables. Based on the stepwise regression, higher manageability and meaningfulness in SOC, higher resilience, lower social loneliness, lower emotional loneliness and hearing impairments are significantly associated with higher QoL.

CONCLUSION

Manageability, meaningfulness and resilience should be enhanced while ameliorating feelings of loneliness to improve the QoL amongst older adults receiving long-term care. Age, marital status, educational level, care arrangement, body mass index, performance in activities of daily living, comorbidities and hearing and mobility impairments could influence QoL and thus warrant more attention.

IMPACT

Future interventions can be conducted in group sessions to facilitate social interaction and alleviate loneliness. More resources should be allocated to enhance older adults' care arrangements and coping mechanisms to provide them with the support, as they face challenges in daily life due to mobility impairment and other restrictions.

Prevalence and factors associated with depression, anxiety, and stress symptoms among older adults: A cross-sectional population-based study

Despite population aging and the increase in mental health problems, studies on the mental health of older people in developing countries are lacking. This population-based cross-sectional study estimated the prevalence and associated factors for depression, anxiety and stress symptoms among older adults in Nepal. Community-dwelling older adults (N = 794) were interviewed using a questionnaire which consisted of the 21-item Depression Anxiety Stress Scales; and a wide range of sociodemographic, health-related, and lifestyle characteristics; functional ability, social support, participation in social activities, and adverse life events. The prevalence of symptoms was 15.4% for depression, 18.1% for anxiety, and 12.1% for stress. Risk factors for symptoms included female gender, working in agriculture, lower household wealth, perceived poor health, smoking, chronic conditions, migration of adult children, and exposure to adverse life events. Receiving an allowance, physical exercise, functional ability, social support, and participation in social activities were found to have protective effects. The findings indicate the need for community-based interventions, including appropriate diagnosis and treatment of mental health conditions, and mental health promotion programs targeting the risk and protective factors.

Assessment of the iodine nutritional status among Chinese school-aged children

OBJECTIVE

The remarkable success of iodine deficiency disorders (IDD) elimination in China has been achieved through a mandatory universal salt iodization (USI) program. The study aims to estimate the relationship between urinary iodine concentration (UIC) and iodine content in edible salt to assess the current iodine nutritional status of school aged children.

METHODS

A total of 5565 students from 26 of 39 districts/counties in Chongqing participated in the study, UIC and iodine content in table salt were measured. Thyroid volumes of 3311 students were examined by ultrasound and goiter prevalence was calculated.

RESULTS

The overall median UIC of students was 222 μg/L (IQR: 150-313 μg/L). Median UIC was significantly different among groups with non-iodized salt (iodine content <5 mg/kg), inadequately iodized salt (between 5 and 21 mg/kg), adequately iodized (between 21 and 39 mg/kg) and excessively iodized (>39 mg/kg) salt (P < 0.01). The total goiter rate was 1.9% (60/3111) and 6.0% (186/3111) according to Chinese national and WHO reference values, respectively. Thyroid volume and goiter prevalence were not different within the three iodine nutritional status groups (insufficient, adequate and excessive, P > 0.05).

CONCLUSIONS

The efficient implementation of current USI program is able to reduce the goiter prevalence in Chongqing as a low incidence of goiter in school aged children is observed in this study. The widened UIC range of 100-299 μg/L indicating sufficient iodine intake is considered safe with a slim chance of causing goiter or thyroid dysfunction. Further researches were needed to evaluate the applicability of WHO reference in goiter diagnose in Chongqing or identifying more accurate criteria of normal thyroid volume of local students in the future.

Delivery of cardio-metabolic preventive services to Hungarian Roma of different socio-economic strata

BACKGROUND

Because the cardiovascular mortality in Hungary is high, particularly among the socio-economically deprived and the Roma, it is implied that primary health care (PHC) has a limited ability to exploit the opportunities of evidence-based preventions, and it may contribute to social health inequalities.

OBJECTIVES

Our study investigated the underuse of PHC preventive services.

METHODS

Random samples of adults aged 21-64 years free of hypertension and diabetes mellitus were surveyed with participation rate of 97.7% in a cross-sectional study. Data from 2199 adults were collected on socio-demographic status, ethnicity, lifestyle and history of cardio-metabolic preventive service use. Delivery rates were calculated for those aged 21-44 years and those aged 45-64 years, and the influence of socio-demographic variables was determined using multivariate logistic regression.

RESULTS

Delivery rates varied between 12.79% and 99.06%, and the majority was far from 100%. Although most preventive service use was independent of education, younger participants with vocational educations underutilized problematic drinking (P = 0.011) and smoking (P = 0.027) assessments, and primary or less educated underutilized blood glucose (P = 0.001) and serum cholesterol (P = 0.005) checks. Health care measures of each lifestyle assessment (P _nutrition = 0.032; P _smoking = 0.021; P _alcohol = 0.029) and waist circumference measurement (P = 0.047) were much less frequently used among older Roma. The blood glucose check (P = 0.001) and family history assessment (P = 0.043) were less utilized among Roma.

CONCLUSIONS

The Hungarian PHC underutilizes the cardio-metabolic prevention contributing to the avoidable mortality, not generating considerably health inequalities by level of education, but contributing to the bad health status among the Roma.