Detecting mental and physical disorders using multi-task learning equipped with knowledge graph attention network

Mental and physical disorders (MPD) are inextricably linked in many medical cases; psychosomatic diseases can be induced by mental concerns and psychological discomfort can ensue from physiological diseases. However, existing medical informatics studies focus on identifying mental or physical disorders from a unilateral perspective. Consequently, no existing domain knowledge base, corpus, or detection modeling approach considers mental as well as physical aspects concurrently. This paper proposes a joint modeling approach to detect MPD. First, we crawl through online medical consultation records of patients from websites and build an MPD knowledge ontology by extracting the core conceptual features of the text. Based on the ontology, an MPD knowledge graph containing 12,673 nodes and 82,195 relations is obtained using term matching with a domain thesaurus of each concept. Subsequently, an MPD corpus with fine-grained severities (None, Mild, Moderate, Severe, Dangerous) and 8909 records is constructed by formulating MPD classification criteria and a data annotation process under the guidance of domain experts. Taking the knowledge graph and corpus as the dataset, we design a multi-task learning model to detect the MPD severity, in which a knowledge graph attention network (KGAT) is embedded to better extract knowledge features. Experiments are performed to demonstrate the effectiveness of our model. Furthermore, we employ ontology-based and centrality-based methods to discover additional potential inferred knowledge, which can be captured by KGAT so as to improve the prediction performance and interpretability of our model. Our dataset has been made publicly available, so it can be further used as a medical informatics reference in the fields of psychosomatic medicine, psychiatrics, physical co-morbidity, and so on.

Perceived neighbourhood environment and falls among community-dwelling adults: cross-sectional and prospective findings from the Survey of Health, Ageing and Retirement in Europe (SHARE)

We investigated the association between perceived neighbourhood characteristics and falls in community-dwelling adults, using data from Wave 5 and 6 of the Survey of Health, Ageing and Retirement in Europe (SHARE). We included 25,467 participants aged 50 to 103 years (mean age 66.2 ± 9.6, 58.5% women), from fourteen European countries (Austria, Belgium, Czech Republic, Denmark, Estonia, France, Germany, Israel, Italy, Luxembourg, Slovenia, Spain, Sweden, Switzerland). At baseline, we recorded individual-level factors (socio-demographic, socio-economic and clinical factors), contextual-level factors (country, urban versus rural area, European region) and perceived neighbourhood characteristics (vandalism or crime, cleanliness, feeling part of neighbourhood, helpful neighbours, accessibility to services) for each participant. We recorded falls in the six months prior to the baseline and 2-year follow-up interviews. The associations between neighbourhood characteristics and falls were analysed by binary logistic regression models; odds ratios (95% confidence intervals) were calculated. Participants reporting-versus not reporting-vandalism or crime had an increased falls risk of 1.16 (1.02-1.31) at follow-up, after full adjustment; lack of cleanliness, feeling part of the neighbourhood, perceiving neighbours as helpful and difficult accessibility to services were not associated with falls. Vandalism or crime was consistently associated with increased falls risks in women, adults without functional impairment and urban areas residents. In conclusion, adverse neighbourhood environments may account for inequality in falls risk among middle-aged and older adults and could be added to fall risk stratification tools.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10433-022-00685-3.

An exploratory survey study of disorder and its association with safety culture in four hospitals

Background

Signs of disorder in neighbourhoods (e.g., litter, graffiti) are thought to influence the behaviour of residents, potentially leading to violations of rules and petty criminal behaviour. Recently, these premises have been applied to the hospital context, with physical and social disorder found to have a negative association with patient safety. Building on these results, the present study investigates whether physical and social disorder differ between hospitals, and their relationship to safety culture.

Methods

We conducted a cross sectional survey with Likert-style and open response questions administered in four Australian hospitals. All staff were invited to participate in the pilot study from May to September 2018. An analysis of variance (ANOVA) was used to examine differences in disorder by hospital, and hierarchical linear regression assessed the relationship of physical and social disorder to key aspects of safety culture (safety climate, teamwork climate). Open responses were analysed using thematic analysis to elaborate on manifestations of hospital disorder.

Results

There were 415 survey respondents. Significant differences were found in perceptions of physical disorder across the four hospitals. There were no significant differences between hospitals in levels of social disorder. Social disorder had a significant negative relationship with safety and teamwork climate, and physical disorder significantly predicted a poorer teamwork climate. We identified five themes relevant to physical disorder and four for social disorder from participants’ open responses; the preponderance of these themes across hospitals supported quantitative results.

Conclusions

Findings indicate that physical and social disorder are important to consider in attempting to holistically understand a hospital’s safety culture. Interventions that target aspects of physical and social disorder in a hospital may hold value in improving safety culture and patient safety.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-07930-6.

Physical disorder and crime revisited: New evidence from intensive longitudinal data

OBJECTIVES

The purpose of this study is to investigate whether the often-debated association between physical disorder and crime exists longitudinally and operates through a specific spatial process.

METHODS

We combine four administrative and official databases to analyze patterns of crime occurring each month in New Orleans, LA, between 2012 and 2018 at the block group level. We adopt a generalized additive model (GAM) framework to efficiently account for potential spatial, temporal, and spatiotemporal autocorrelation to investigate this association.

RESULTS

The resident-driven self-report measure of physical disorder (i.e., 311 calls) consistently predicts neighborhood criminal activities in New Orleans. The spatial effects of 311 calls in adjacent areas on drug violations, property crime, and violence in a focal neighborhood are also observed. In contrast, official reports of physical disorder, captured with code violation, is either weakly related to crime or lacking an empirical relationship.

CONCLUSION

Overall, our findings suggest that the association between physical disorder and neighborhood crimes is robust over time. In addition, this association is conditioned by how physical disorder is operationalized, with dimensions such as residential report and official report of physical disorder playing a unique, and occasionally important role in understanding overall patterns of neighborhood criminal activity.

What predicts how safe people feel in their neighborhoods and does it depend on functional status?

Feeling unsafe in one's neighborhood is related to poor health. Features of the neighborhood environment have been suggested to inform perceptions of neighborhood safety. Yet, the relative contribution of these features (e.g., uneven sidewalks, crime, perceived neighborhood physical disorder) on perceived neighborhood safety, particularly among people with disabilities who may view themselves as more vulnerable, is not well understood. We examined whether sidewalk quality assessed by third party raters, county-level crime rates, and perceived neighborhood disorder would relate to neighborhood safety concerns, and whether functional limitations would exacerbate these links. Using data from the 2012/2014 waves of the Health and Retirement Study (n = 10,653, mean age = 66 years), a national sample of older US adults, we demonstrate that those with and without functional limitations felt less safe in areas with more crime and perceived as more disordered. When considered simultaneously, however, only perceived disorder statistically significantly predicted safety concerns. Living in neighborhoods with better sidewalk quality was statistically significantly related to feeling less safe, but only among those with functional limitations. Sidewalk quality was not statistically significantly related to safety reports among those without functional limitations. To our knowledge, this study is among the first to examine multiple features of the neighborhood environment simultaneously in relation to perceived neighborhood safety. Our findings highlight the relative importance of perceived physical disorder, and that these perceptions relate to safety concerns. Replication of this research is needed to determine the robustness of these patterns, including rich data on pedestrian use and sidewalk proximity to roadways. Community-level interventions that simultaneously target the multifaceted features of the neighborhood environment that shape people's safety reports may be needed to reduce burden of health.

Association Between Physical Status and the Effects of Combination Therapy With Renin-Angiotensin System Inhibitors and β-Blockers in Patients With Acute Heart Failure

Background: This study investigated whether combination therapy (CT) with renin-angiotensin system inhibitors and β-blockers improved endpoints in acute heart failure (AHF).

Methods and Results: AHF patients were recruited to this prospective multicenter cohort study between April 2015 and August 2017. Patients were divided into 3 categories based on ejection fraction (EF), namely heart failure (HF) with reduced EF (HFrEF), HF with midrange EF (HFmrEF), and HF with preserved EF (HFpEF), and a further into 2 groups according to physical status (those who could walk independently outdoors and those who could not). The composite endpoint included all-cause mortality and hospitalization for HF. Data at the 1-year follow-up were available for 1,018 patients. The incidence of the composite endpoint was significantly lower in the CT than non-CT group for HFrEF patients, but not among HFmrEF and HFpEF patients. For patients who could walk independently outdoors, a significantly lower rate of the composite endpoint was recorded only in the HFrEF group. The differences were maintained even after adjustment for comorbidities and prescriptions, with hazard ratios (95% confidence intervals) of 0.39 (0.20–0.76) and 0.48 (0.22–0.99), respectively.

Conclusions: In this study, CT was associated with the prevention of adverse outcomes in patients with HFrEF. Moreover, CT prevented adverse events only among patients without a physical disorder, not among those with a physical disorder.

Disablement in Context: Neighborhood Characteristics and Their Association With Frailty Onset Among Older Adults

OBJECTIVES

Frailty, an aggregate expression of risk resulting from age- or disease-associated physiologic accumulation, is responsible for large economic and societal costs. Little is known about how the context in which older adult's live may contribute to differences in frailty. This study clarifies the role of neighborhood structural characteristics and social processes for understanding declines in health status.

METHOD

Data from two waves of the National Social Life, Health and Aging Project were linked to tract-level information from the 2000 Census (n = 1,925). Frailty was measured with in-home assessments and self-report. Ordered logistic regressions were employed to estimate the role of tract-level structural and social process indicators at baseline on frailty at follow-up.

RESULTS

Living in a neighborhood characterized with a higher density of African Americans and with more residential instability was associated with higher odds of frailty. Adults in neighborhoods with increasing levels of physical disorder had higher odds of frailty (adjusted odds ratio [AOR]: 1.20, 95% confidence interval [CI]: 1.03, 1.39), while those exposed to more social cohesion had lower odds (AOR: 0.87, CI: 0.78, 0.97).

DISCUSSION

For older adults, both neighborhood structural and social process characteristics appear to be independently associated with frailty.

Epidemiology of physical and mental comorbidity in Canada and implications for health-related quality of life, suicidal ideation, and healthcare utilization: A nationwide cross-sectional study

BACKGROUND

The substantial burden of physical and mental comorbidity is increasingly gaining attention, but a comprehensive evaluation of this is limited in Canada. This study aimed to investigate the prevalence of physical and mental comorbidity and its implications in Canada.

METHODS

We used nationally representative data from Canadian Community Health Survey, 2014. We included individuals who were aged ≥18 years and excluded those who had missing information on physical or mental disorders. Chronic diseases referred to both physical and mental disorders.

RESULTS

Respondents included in our analysis represented 27,221,856 Canadians aged ≥18 years. Of these, 53.9% (95% CI 53.1-54.6) had one or more chronic diseases, 11.5% (95% CI 11.0-12.0) had mental disorder, and 8.4% (95% CI 8.0-8.8) had physical and mental comorbidity. Compared with those without chronic diseases, people with one or more chronic diseases had higher sex- and age-adjusted prevalence of severe impairment of health-related quality of life (HRQoL), suicidal ideation, and healthcare utilization; and the risks increased consistently with the number of chronic diseases. However, among those with the same number of chronic diseases, people with mental disorder or physical and mental comorbidity were more likely to have these adverse consequences than people with only physical disorders.

LIMITATIONS

Our study was based on self-reported data, and included only major chronic diseases rather than all probable chronic diseases.

CONCLUSIONS

Physical and mental comorbidity is prevalent in Canada and should be addressed with appropriate interventions considering its excessive adverse impact on HRQoL, suicidal ideation and healthcare utilization.

The comorbidity of mental and physical disorders with self-reported chronic back or neck pain: Results from the China Mental Health Survey

BACKGROUND

To investigate mental and physical health comorbidity with chronic back or neck pain in the Chinese population, and assess the level of disability associated with chronic back or neck pain.

METHODS

Data were derived from a large-scale and nationally representative community survey of adult respondents on mental health disorders in China (n = 28,140). Chronic back or neck pain, other chronic pain conditions and chronic physical conditions were assessed by self-report. Mental disorders were assessed by the Composite International Diagnostic Interview (CIDI). Role disability during the past 30 days was assessed with the World Health Organization Disability Assessment Schedule (WHO-DAS-II).

RESULTS

The 12-month prevalence of chronic back or neck pain was 10.8%. Most of respondents with chronic back or neck pain (71.2%) reported at least one other comorbid condition, including other chronic pain conditions (53.4%), chronic physical conditions (37.9%), and mental disorders (23.9%). It was found by logistic regression that mood disorders (OR = 3.7, 95%CI:2.8-4.8) showed stronger association with chronic back or neck pain than anxiety disorders and substance disorders. Most common chronic pains and physical conditions were significantly associated with chronic back or neck pain. Chronic back or neck pain was associated with role disability after controlling for demographics and for comorbidities. Physical and mental comorbidities explained 0.7% of the association between chronic back or neck pain and role disability.

CONCLUSIONS

Chronic back or neck pain and physical-mental comorbidity is very common in China and chronic back or neck pain may increase the likelihood of other physical and mental diseases. This presents a great challenge for both clinical treatment and public health education. We believe that further study needs to be conducted to improve the diagnostic and management skills for comorbidity conditions.

Measuring Neighborhood Order and Disorder: a Rapid Literature Review

PURPOSE OF REVIEW

Neighborhood disorder has received attention as a determinant of health in urban contexts, through pathways that include psychosocial stress, perceived safety, and physical activity. This review provides a summary of data collection methods, descriptive terms, and specific items employed to assess neighborhood disorder/order.

RECENT FINDINGS

The proliferation of methods and terminology employed in measuring neighborhood disorder (or neighborhood order) noted over the past two decades has made related studies increasingly difficult to compare. Following a search of peer-reviewed articles published from January 1998 to May 2018, this rapid literature review identified 18 studies that described neighborhood environments, yielding 23 broad terms related to neighborhood disorder/order, and a total of 74 distinct measurable items. A majority of neighborhood disorder/order measurements were assessed using primary data collection, often relying on resident self-report or investigatory observations conducted in person or using stored images for virtual audits. Items were balanced across signs of order or disorder, and further classification was proposed based on whether items were physically observable and relatively stable over time.

A Local View of Informal Urban Environments: a Mobile Phone-Based Neighborhood Audit of Street-Level Factors in a Brazilian Informal Community

Street-level environment characteristics influence the health behaviors and safety of urban residents, and may particularly threaten health within informal communities. However, available data on how such characteristics vary within and among informal communities is limited. We sought to adapt street audit strategies designed to characterize the physical environment for use in a large informal community, Rio das Pedras (RdP) located in Rio de Janeiro, Brazil. A smartphone-based systematic observation protocol was used to gather street-level information for a high-density convenience sample of street segments (N = 630, estimated as 86% of all street segments in the community). We adapted items related to physical disorder and physical deterioration. Measures selected to illustrate the approach include the presence of the following: (1) low-hanging or tangled wires, (2) litter, (3) structural evidence of sinking, and (4) an unpleasant odor. Intercept-only spatial generalized additive models (GAM) were used to evaluate and visualize spatial variation within the RdP community. We also examined how our estimates and conclusions about spatial variation might have been affected by lower-density sampling from random subsets street observations. Random subsets were selected to determine the robustness of study results in scenarios with sparser street sampling. Selected characteristics were estimated to be present for between 18% (unpleasant odor) to 59% (low-hanging or tangled wires) of the street segments in RdP; estimates remain similar (± 6%) when relying on a random subset created to simulate lower-density spatial sampling. Spatial patterns of variation based on predicted probabilities across RdP differed by indicator. Structural sinking and low-hanging or tangled wires demonstrated relatively consistent spatial distribution patterns across full and random subset sample sizes. Smartphone-based systematic observations represent an efficient and potentially feasible approach to systematically studying neighborhood environments within informal communities. Future deployment of such tools will benefit from incorporating data collection across multiple time points to explore reliability and quantify neighborhood change. These tools can prove useful means to assess street-level exposures that can be modifiable health determinants across a wide range of informal urban settings. Findings can contribute to improved urban planning and provide useful information for identifying potential locations for neighborhood-scaled interventions that can improve living conditions for residents in Rio das Pedras.

The role of neighborhoods in household food insufficiency: Considering interactions between physical disorder, low social capital, violence, and perceptions of danger

RATIONALE

Food insecurity is a significant public health concern, with implications for community and individual health and well-being. Although a growing body of literature points to the role of neighborhoods in household food insecurity, studies using nationally representative samples to explore interactions between neighborhood risks - including violence and danger - are lacking.

OBJECTIVE

The present study examines whether interactions between physical disorder, low social capital, and violence/danger in the neighborhood have significant implications for the risk of household food insufficiency using a large, nationally representative sample of U.S. children and their families.

METHOD

Data are from the 2016 National Survey of Children's Health, a survey of a cross-sectional weighted probability sample of U.S. children from 0 to 17 years of age. Multinomial logistic regression techniques were used to analyze the data.

RESULTS

Neighborhood risk factors interacted to predict household food insufficiency, with the confluence of low social capital and violence/danger yielding the strongest effects.

CONCLUSIONS

Our findings suggest that food hardship should be addressed within the context of neighborhood revitalization. The risk of food insufficiency among children and families in especially high-risk ecological contexts might be ameliorated with the provision of informal and formal sources of nutrition assistance and support.

[The efficacy of cognitive behavioral therapy in insomnic patients with or without comorbidities: a pilot study]

Objectives: To evaluate the effectiveness of cognitive behavior therapy for insomnia (CBT-i) in chronic insomnia patients in terms of the improvements of psychological and sleep diary parameters. Methods: Patients who met the diagnostic criteria of chronic insomnia, were divided into primary group or comorbid group. Both groups received standard CBT-i interventions. Psychological scales and sleep diaries were used to evaluate participants' severity of insomnia and psychological conditions related to insomnia at four time points: before intervention (baseline), immediate after intervention, 4 weeks and 16 weeks after intervention. Results: Both groups achieved significant improvements after intervention on psychological measurements and sleep diary parameters. Such improvements were maintained at 4-week and 16-week follow-ups. The sleep diary data indicated that by the end of the intervention, there were significant differences on sleep onset latency (51.72 min to 10.53 min in primary group, P<0.01; 59.26 min to 15.67min in comorbid group, P<0.01) and sleep efficiency (71% to 95% in primary group, P<0.01; 68% to 90% in comorbid group, P<0.01). There were differences on sleep onset latency (10.00 min vs. 13.93 min, P<0.05), total sleep time (355.71 min vs. 327.85 min, P<0.05) and sleep efficiency (95% vs. 91%, P<0.01) in primary group and comorbid group respectively. No differences were found on wake after sleep onset in the two groups. Conclusions: Chronic insomnia patients with or without comorbidities both have improvements after CBT-i. Sleep diary parameters rather than psychological measurements are different in two groups. Thus, CBT-i is an effective non-pharmaceutical therapy inpatients with chronic insomnia.

Prevalence and characteristics of self-reported physical and mental disorders among adults with hearing loss in Denmark: a national survey

PURPOSE

Existing research shows that people with hearing loss have a high risk of additional physical and mental disorders. However, only a few population-based studies have been conducted. This study assesses the prevalence and characteristics of additional disorders among adults with hearing loss in Denmark and thereby contributes a population-based study to this area of research.

METHOD

Data on self-reported physical and mental disorders from a national survey of 772 adults with hearing loss were compared to corresponding data from a national survey of 18,017 adults from the general population.

RESULTS

People with hearing loss reported more physical and mental disorders than the general population. Specifically, they reported higher incidences of visual impairment, cerebral palsy, intellectual impairment, and "other mental disorders".

CONCLUSION

Adults with hearing loss have a greater risk of additional physical and mental disorders. It is important for clinicians to have some understanding of the communication needs and characteristics of deaf and hard-of-hearing patients, so that they can recognize and treat symptoms and provide appropriate support.

Validation of a Google Street View-Based Neighborhood Disorder Observational Scale

Recently, there has been a growing interest in developing new tools to measure neighborhood features using the benefits of emerging technologies. This study aimed to assess the psychometric properties of a neighborhood disorder observational scale using Google Street View (GSV). Two groups of raters conducted virtual audits of neighborhood disorder on all census block groups (N = 92) in a district of the city of Valencia (Spain). Four different analyses were conducted to validate the instrument. First, inter-rater reliability was assessed through intraclass correlation coefficients, indicating moderated levels of agreement among raters. Second, confirmatory factor analyses were performed to test the latent structure of the scale. A bifactor solution was proposed, comprising a general factor (general neighborhood disorder) and two specific factors (physical disorder and physical decay). Third, the virtual audit scores were assessed with the physical audit scores, showing a positive relationship between both audit methods. In addition, correlations between the factor scores and socioeconomic and criminality indicators were assessed. Finally, we analyzed the spatial autocorrelation of the scale factors, and two fully Bayesian spatial regression models were run to study the influence of these factors on drug-related police interventions and interventions with young offenders. All these indicators showed an association with the general neighborhood disorder. Taking together, results suggest that the GSV-based neighborhood disorder scale is a reliable, concise, and valid instrument to assess neighborhood disorder using new technologies.