Search

Chronic diseases are one of the most severe health issues in the world, due to their terrible clinical presentations such as long onset cycle, insidious symptoms, and various complications. Recently, machine learning has become a promising technique to assist the early diagnosis of chronic diseases. However, existing works ignore the problems of feature hiding and imbalanced class distribution in chronic disease datasets. In this paper, we present a universal and efficient diagnostic framework to alleviate the above two problems for diagnosing chronic diseases timely and accurately. Specifically, we first propose a network-limited polynomial neural network (NLPNN) algorithm to efficiently capture high-level features hidden in chronic disease datasets, which is data augmentation in terms of its feature space and can also avoid over-fitting. Then, to alleviate the class imbalance problem, we further propose an attention-empowered NLPNN algorithm to improve the diagnostic accuracy for sick cases, which is also data augmentation in terms of its sample space. We evaluate the proposed framework on nine public and two real chronic disease datasets (partly with class imbalance). Extensive experiment results demonstrate that the proposed diagnostic algorithms outperform state-of-the-art machine learning algorithms, and can achieve superior performances in terms of accuracy, recall, F1, and G_mean. The proposed framework can help to diagnose chronic diseases timely and accurately at an early stage. [ABSTRACT FROM AUTHOR]

At present, more patients suffer from multiple chronic diseases. However, the hospital's existing chronic disease management is carried out according to the department. This means that a patient needs to go to more than one department for a chronic disease treatment. Therefore, this study proposes 6 dimensions (organizational management, medical service support, medical service, community alliance, self-management support, management information system) and 36 questions, to help evaluate the current chronic disease management system in China's large third-class hospitals. In this study, 143 survey samples from doctors and nurses were collected. A principal component analysis was used to extract three key elements of chronic disease management service delivery system (service management organization, management information system, medical core service). Then, multiple regression was used to establish the relationship model between the overall performance of the system and the main elements. Three key service nodes of the system (medical specialist support, patient tracking management and personalized intervention) were determined according to the weight of the regression model. The regression coefficients of the above three main elements show a similar impact on the overall performance of the system, but the key service nodes under each major element have relative differences, including medical specialist support, patient tracking management and personalized intervention. Finally, to establish a chronic disease management system with multiple departmental continuous care for chronic diseases, it is necessary to improve the chronic disease management system from three aspects of medical specialty support, patient tracking management and personalized intervention. This paper proposes corresponding improvement strategies. [ABSTRACT FROM AUTHOR]

In a context where pandemic crises and chronic conditions are a constant and increasing threat, the success of public health projects is absolutely critical. However, little is known about the factors that influence the success of projects that aim to provide conditions for people to be healthy and prolong the life of the population as a whole. A mixed-method study was carried out to fill the literature gap, resulting in a new model of success factors for public health projects. The research work theorizes the success factors that impact public health project success, providing relevant knowledge for project managers and contributing to the successful management of public health projects. [ABSTRACT FROM AUTHOR]

The absence of a long COVID (LC) or post-acute sequelae of COVID-19 (PASC) diagnostic has profound implications for research and potential therapeutics given the lack of specificity with symptom-based identification of LC and the overlap of symptoms with other chronic inflammatory conditions. Here, we report a machine-learning approach to LC/PASC diagnosis on 347 individuals using cytokine hubs that are also capable of differentiating LC from chronic lyme disease (CLD). We derived decision tree, random forest, and gradient-boosting machine (GBM) classifiers and compared their diagnostic capabilities on a dataset partitioned into training (178 individuals) and evaluation (45 individuals) sets. The GBM model generated 89% sensitivity and 96% specificity for LC with no evidence of overfitting. We tested the GBM on an additional random dataset (106 LC/PASC and 18 Lyme), resulting in high sensitivity (97%) and specificity (90%) for LC. We constructed a Lyme Index confirmatory algorithm to discriminate LC and CLD. [ABSTRACT FROM AUTHOR]

Chronic liver diseases (CLD) affect 1.5 billion patients worldwide, with dramatically increasing incidence in recent decades. It has been hypothesized that the chronic hyperinflammation associated with CLD may increase the risk of a more severe course of acute pancreatitis (AP). This study aims to investigate the underlying impact of CLD on the outcomes of AP. A systematic search was conducted in Embase, Medline, and Central databases until October 2022. Studies investigating patients with acute pancreatitis and CLD, were included in the meta-analysis. A total of 14,963 articles were screened, of which 36 were eligible to be included. CLD was a risk factor for increased mortality with an odds ratio (OR) of 2.53 (CI 1.30 to 4.93, p = 0.01). Furthermore, renal, cardiac, and respiratory failures were more common in the CLD group, with ORs of 1.92 (CI 1.3 to 2.83, p = 0.01), 2.11 (CI 0.93 to 4.77, p = 0.062) and 1.99 (CI 1.08 to 3.65, p = 0.033), respectively. Moreover, the likelihood of developing Systemic Inflammatory Response Syndrome (SIRS) was significantly higher, with an OR of 1.95 (CI 1.03 to 3.68, p = 0.042). CLD is an important risk factor for worse outcomes in AP pancreatitis, leading to higher mortality and increased rates of local and systemic complications. [ABSTRACT FROM AUTHOR]

Rheumatoid Arthritis is a more serious threatening to people and suitable for QOL measurement. A few specific QOL instruments are available without considering Chinese culture. The present study was aimed to develop and validate the Rheumatoid Arthritis Scale among the System of Quality of Life Instruments for Chronic Diseases (QLICD-RA V2.0). The data collected from 379 patients with RA was used to evaluate the psychometric properties of the scale. The reliability was evaluated by the internal consistency Cronbach's α, test–retest reliability Pearson correlation r and intra-class correlation (ICC). We evaluated the construct validity and criteria-related validity by correlation analysis and structural equation modeling. We compared the differences in scores of QLICD-RA before and after treatment and used the Standard Response Mean (SRM) to assess the responsiveness. The results showed that the internal consistency coefficient Cronbach's α values were greater than 0.70. The correlations r and ICCs were greater than 0.80. The correlation analysis and structural equation modeling confirmed good construct validity and criterion-related validity. The SRM ranges from 0.07 to 0.27 for significant domains/facets. It concluded that QLICD-RA (2.0) is a reliable and valid instrument to measure QOL among patients with RA. [ABSTRACT FROM AUTHOR]

Chronic itching is a serious and uncomfortable condition. The scratch response might result in a vicious cycle of alternating itching and scratching. To develop psychological interventions for people suffering from chronic itching and to break the vicious itch-scratching-itch cycle, it is important to elucidate which environmental factors trigger itch sensations. Virtual reality (VR) techniques provide a useful tool to examine specific content characteristics in a three-dimensional (3D VR) environment and their influences on itch sensations and scratching behaviour. This article describes two experiments in which we focused on the effects of environmental information on itching and scratching behaviour. Additionally, in the second experiment, we examined the influence of having a chronic skin condition on sensitivity to itch induction. We found evidence for the importance of the content of audio–visual materials for the effectiveness in inducing feelings of itch in the observers. In both experiments, we observed significantly higher levels of perceived itch in the itch-inducing conditions than in the control condition. Moreover, the results showed that elevated levels of perceived itch were associated with an increase in scratching behaviours, which was especially salient in the contagious itch condition, in which perceived itch was accompanied by a significant increase in the number of scratches. Experiment 2 additionally showed increased perceived itch levels in participants who reported having a chronic skin condition, reflecting higher sensitivity to itch-inducing audio–visual stimuli in this group than in participants without a chronic skin condition. Based on the results we concluded that directing attention towards itch- or scratch aspects of related information in the environment and to the consequences for one's own skin are effective tools to induce itch sensations and scratching behaviour. This knowledge provides tools for developing novel strategies in advising and treating people suffering from chronic itching and breaking the vicious itch-scratching-itch cycle. [ABSTRACT FROM AUTHOR]

Patients with chronic liver disease progressed to compensated advanced chronic liver disease (cACLD), the risk of liver-related decompensation increased significantly. This study aimed to develop prediction model based on individual bile acid (BA) profiles to identify cACLD. This study prospectively recruited 159 patients with hepatitis B virus (HBV) infection and 60 healthy volunteers undergoing liver stiffness measurement (LSM). With the value of LSM, patients were categorized as three groups: F1 [LSM ≤ 7.0 kilopascals (kPa)], F2 (7.1 < LSM ≤ 8.0 kPa), and cACLD group (LSM ≥ 8.1 kPa). Random forest (RF) and support vector machine (SVM) were applied to develop two classification models to distinguish patients with different degrees of fibrosis. The content of individual BA in the serum increased significantly with the degree of fibrosis, especially glycine-conjugated BA and taurine-conjugated BA. The Marco-Precise, Marco-Recall, and Marco-F1 score of the optimized RF model were all 0.82. For the optimized SVM model, corresponding score were 0.86, 0.84, and 0.85, respectively. RF and SVM models were applied to identify individual BA features that successfully distinguish patients with cACLD caused by HBV. This study provides a new tool for identifying cACLD that can enable clinicians to better manage patients with chronic liver disease. [ABSTRACT FROM AUTHOR]

Fatigue is barrier of physical activity participation in adults with chronic conditions. However, physical activity alleviates fatigue symptoms. This systematic review and meta-analysis aimed to (1) synthesise evidence from randomised controlled trials (RCTs) exploring the effects of physical activity interventions on fatigue reduction and (2) evaluate their effectiveness. Medline/CINAHL/EMBASE/Web of Science and Scopus were searched up to June 24th, 2023. Two reviewers independently conducted study screening and selection (RCTs), extracted data and assessed risk of bias (RoB2). Outcome was the standardised mean difference (SMD) with 95% confidence intervals in fatigue between experimental and control groups. 38 articles met the inclusion criteria. Overall, physical activity interventions moderately reduced fatigue (SMD = 0.54, p < 0.0001). Interventions lasting 2–6 weeks demonstrated a larger effect on fatigue reduction (SMD = 0.86, p < 0.00001). Interventions with 18–24 sessions showed a large effect on fatigue reduction (SMD = 0.97, p < 0.00001). Aerobic cycling and combination training interventions had a large to moderate effect (SMD = 0.66, p = 0.0005; SMD = 0.60, p = 0.0010, respectively). No long-term effects were found during follow-up. Physical activity interventions moderately reduced fatigue among adults with chronic conditions. Duration, total sessions, and mode of physical activity were identified as key factors in intervention effectiveness. Further research is needed to explore the impact of physical activity interventions on fatigue. [ABSTRACT FROM AUTHOR]

The contribution of caregivers to self-care for chronically ill patients is important for improving patient outcomes. The Caregiver Contribution to Self-Care Chronic Illness Inventory (CC-SC-CII) has been used to assess caregivers' contributions to three distinct aspects of self-care (maintenance, monitoring, and management) globally. This study aimed to examine the psychometrics of the Korean version of the CC-SC-CII with 230 family caregivers (mean age = 49.8 years, 70% women) of patients with chronic illness. We demonstrated that the CC-SC-CII-Korean has good reliability with acceptable internal consistency and construct validity for all three factors using confirmatory factor analysis. The CC-SC-CII-Korean is a reliable and valid instrument to measure the contributions of Korean caregivers to the self-care of patients with chronic illnesses. [ABSTRACT FROM AUTHOR]

Few risk prediction scores are available to identify people at increased risk of work disability, particularly for those with an existing morbidity. We examined the predictive performance of disability risk scores for employees with chronic disease. We used prospective data from 88,521 employed participants (mean age 43.1) in the Finnish Public Sector Study including people with chronic disorders: musculoskeletal disorder, depression, migraine, respiratory disease, hypertension, cancer, coronary heart disease, diabetes, comorbid depression and cardiometabolic disease. A total of 105 predictors were assessed at baseline. During a mean follow-up of 8.6 years, 6836 (7.7%) participants were granted a disability pension. C-statistics for the 8-item Finnish Institute of Occupational Health (FIOH) risk score, comprising age, self-rated health, number of sickness absences, socioeconomic position, number of chronic illnesses, sleep problems, BMI, and smoking at baseline, exceeded 0.72 for all disease groups and was 0.80 (95% CI 0.80–0.81) for participants with musculoskeletal disorders, 0.83 (0.82–0.84) for those with migraine, and 0.82 (0.81–0.83) for individuals with respiratory disease. Predictive performance was not significantly improved in models with re-estimated coefficients or a new set of predictors. These findings suggest that the 8-item FIOH work disability risk score may serve as a scalable screening tool in identifying individuals with increased risk for work disability. [ABSTRACT FROM AUTHOR]

In low-and-middle-income countries, people develop chronic diseases at a younger age, leading to health-and-economic loss. Estimates of the age of onset of chronic disease provide evidence for policy intervention, but in the Indian context, evidence is limited. The present study aims to explore the onset of seven chronic diseases across adults and the elderly, along with the prognostic factors of chronic disease onset. Using Wave 1 data of the Longitudinal Ageing Study in India (LASI), we estimated the statistical distributions, the median age at onset, and Loglogistic and Weibull accelerated failure time model to understand the onset of seven medically diagnosed self-reported chronic diseases across age groups. We also obtained the sub-distribution hazard ratio (SHR) from the Fine-Gray model to determine the risk of contracting selected chronic diseases in a competing risk setup. The seven chronic diseases– hypertension, diabetes, lung disease, heart disease/stroke, arthritis, neurological disease, and cancer– were developing early, especially in individuals aged 45–54 and 55–64. Arthritis risk was higher in rural areas, and physically active adults and elderly were 1.32 times (95% CI 1.12–1.56) more likely to develop heart disease/stroke. The emerging evidence of the early onset of neurological diseases in middle-aged adults (i.e., among the 45–54 age group) reminds us of the need to reinforce a balance between the physical and mental life of individuals. The early onset of chronic diseases in the independent and working-age category (45–54 years) can have many social and economic implications. For instance, it can create a greater healthcare burden when these individuals grow older with these diseases. Further, disease-specific interventions would be helpful in reducing future chronic disease burden. [ABSTRACT FROM AUTHOR]

We analyze the effect of obesity on the incidence of hypertension, hyperlipidemia and diabetes in USA using a health production theoretical framework along with a bivariate flexible semi-parametric recursive copula model that account for endogeneity. In this approach, the effects of control variables are flexibly determined using additive predictors that allow for a variety of effects. Our findings suggest that there exist a positive and significant effect of obesity on the prevalence of all chronic diseases examined. In particular, after endogeneity is accounted for, the probability of having hypertension, hyperlipidemia and diabetes for obese individuals are, respectively, 35%, 28% and 11% higher than those under the obesity threshold. These findings suggest that lowering obesity rates could lead to significant reductions in the morbidity and mortality associated with these diseases. [ABSTRACT FROM AUTHOR]

In the medical field, various clinical information has been accumulated to help clinicians provide personalized medicine and make better diagnoses. As chronic diseases share similar characteristics, it is possible to predict multiple chronic diseases using the accumulated data of each patient. Thus, we propose an intra-person multi-task learning framework that jointly predicts the status of correlated chronic diseases and improves the model performance. Because chronic diseases occur over a long period and are affected by various factors, we considered features related to each chronic disease and the temporal relationship of the time-series data for accurate prediction. The study was carried out in three stages: (1) data preprocessing and feature selection using bidirectional recurrent imputation for time series (BRITS) and the least absolute shrinkage and selection operator (LASSO); (2) a convolutional neural network and long short-term memory (CNN-LSTM) for single-task models; and (3) a novel intra-person multi-task learning CNN-LSTM framework developed to predict multiple chronic diseases simultaneously. Our multi-task learning method between correlated chronic diseases produced a more stable and accurate system than single-task models and other baseline recurrent networks. Furthermore, the proposed model was tested using different time steps to illustrate its flexibility and generalization across multiple time steps. [ABSTRACT FROM AUTHOR]

Chronic cheilitis (CC) is a spectrum of inflammatory changes of unknown etiology that affect the vermilion of the lips. This study aimed to describe the epidemiology, clinical presentations and risk factors of CC. Patients with CC were recruited from the National Clinical Research Center for Oral Disease of China. A convenience sample of inhabitants who live in the same geographical region were recruited as the control group. The lip skin transepidermal water loss (TEWL) and capacitance of CC patients were compared with that of age- and gender-matched controls. Our results demonstrated that of the 109 patients with CC, 72 (66.1%; 95% CI: 57.0–75.1%) were female. The common clinical presentations of CC consisted of desquamation (n = 99; 90.8%), and/or chapping (n = 81; 74.3%), and/or pruritus (n = 64; 58.7%). Multivariable analysis showed that allergic dermatologic diseases (P < 0.001; OR: 4.5; 95% CI: 2.4–8.4), anemia (P = 0.001; OR: 3.3; 95% CI: 1.5–7.5), and indoor/outdoor alternate working environment (P < 0.001; OR: 2.1; 95% CI: 1.5–2.8) were the significant risk factors for CC. The mean lip skin TEWL was found to be significantly higher, while the capacitance was lower in CC patients compared to that of control individuals. This study provides insights into the etiopathogenesis of CC and may help clinicians to identify the most effective management strategies. [ABSTRACT FROM AUTHOR]

The co-occurrence of mental and physical chronic conditions is a growing concern and a largely unaddressed challenge in low-and-middle-income countries. This study aimed to investigate the independent and multiplicative effects of depression and physical chronic conditions on health-related quality of life (HRQoL) in China, and how it varies by age and gender. We used two waves of the China Health and Retirement Longitudinal Study (2011, 2015), including 9227 participants aged ≥ 45 years, 12 physical chronic conditions and depressive symptoms. We used mixed-effects linear regression to assess the effects of depression and physical multimorbidity on HRQoL, which was measured using a proxy measure of Physical Component Scores (PCS) and Mental Component Scores (MCS) of the matched SF-36 measure. We found that each increased number of physical chronic conditions, and the presence of depression were independently associated with lower proxy PCS and MCS scores. There were multiplicative effects of depression and physical chronic conditions on PCS (− 0.83 points, 95% CI − 1.06, − 0.60) and MCS scores (− 0.50 points, 95% CI − 0.73, − 0.27). The results showed that HRQoL decreased markedly with multimorbidity and was exacerbated by the presence of co-existing physical and mental chronic conditions. [ABSTRACT FROM AUTHOR]

Patients with primary hyperoxaluria type I (PH I) are prone to develop early kidney failure. Systemic deposition of calcium-oxalate (CaOx) crystals starts, when renal function declines and plasma oxalate increases. All tissue, but especially bone, heart and eyes are affected. However, liver involvement, as CaOx deposition or chronic hepatitis/fibrosis has never been reported. We examined liver specimen from 19 PH I patients (aged 1.5 to 52 years at sample collection), obtained by diagnostic biopsy (1), at autopsy (1), or transplantation (17). With polarization microscopy, birefringent CaOx crystals located in small arteries, but not within hepatocytes were found in 3/19 patients. Cirrhosis was seen in one, fibrosis in 10/19 patients, with porto-portal and nodular fibrosis (n = 1), with limitation to the portal field in 8 and/or to central areas in 5 patients. Unspecific hepatitis features were observed in 7 patients. Fiber proliferations were detectable in 10 cases and in one sample transformed Ito-cells (myofibroblasts) were found. Iron deposition, but also megakaryocytes as sign of extramedullary erythropoiesis were found in 9, or 3 patients, respectively. Overall, liver involvement in patients with PH I was more pronounced, as previously described. However, CaOx deposition was negligible in liver, although the oxalate concentration there must be highest. [ABSTRACT FROM AUTHOR]

We analyzed the associations of screen-based behaviors with obesity, hypertension, and diabetes, and the moderation of different physical activity (PA) domains in these associations. We used data from the 2019 Brazilian National Health Survey, including data from 80,940 adults (mean age of 32.6 years). TV viewing, other screens (PC, tablet, and cell phone), PA domains (leisure-time, occupational, and transport) were collected via interview. Logistic regression models were used. There was a dose–response association of higher TV viewing with diabetes. Within the groups with medium and higher time spent on other screens, those with < 150 min/week in leisure-time PA increased the odds for obesity [1–2.9 h/day: OR = 1.18 (1.01, 1.39)] and hypertension [1–2.9 h/day: OR = 1.29 (1.08, 1.53); ≥ 6 h/day: OR = 1.47 (1.03, 2.09)]. Likewise, among the participants who spent ≥ 6 h/day of TV viewing, those with < 150 min/week of occupational PA presented higher odds for hypertension [OR = 1.61 (1.03, 2.53)]. In the group with higher use of other screens, < 150 min per week of occupational PA was associated with lower odds for obesity [1–2.9 h/day: OR = 0.81 (0.68, 0.97)] and hypertension [≥ 6 h/day: OR = 0.65 (0.44, 0.98)]. In conclusion, the associations of other screens with obesity and hypertension were strongest among those without leisure-time PA, while the moderator role of occupational PA was not clear. [ABSTRACT FROM AUTHOR]

Healthcare delivery reorganization during the COVID-19 emergency may have had a significant impact on access to care for older adults with chronic conditions. We investigated such impact among all adults with chronic conditions aged ≥ 65 years, identified through the electronic health databases of two local health agencies—ATS Brianza and ATS Bergamo—from the Lombardy region, Italy. We considered hospitalizations for 2020 compared to the average 2017–2019 and quantified differences using rate ratios (RRs). Overall, in 2017–2019 there were a mean of 374,855 older adults with ≥ 1 chronic condition per year in the two ATS and 405,371 in 2020. Hospitalizations significantly decreased from 84,624 (225.8/1000) in 2017–2019 to 78,345 (193.3/1000) in 2020 (RR 0.86). Declines were reported in individuals with many chronic conditions and for most Major Diagnostic Categories, except for diseases of the respiratory system. The strongest reductions were observed in hospitalizations for individuals with active tumours, particularly for surgical ones. Hospitalization rates increased in individuals with diabetes, likely due to COVID-19-related diseases. Although determinants of the decrease in demand and supply for care among chronic older adults are to be further explored, this raises awareness on their impacts on chronic patients' health in the medium and long run. [ABSTRACT FROM AUTHOR]

Several studies highlighted a correlation between exhaled air volatile organic compounds (VOCs) and some pathological conditions, such as chronic kidney disease (CKD), chronic liver disease, etc. In fact, in literature has been reported that CKD is characterized by an increased concentration of ammonia, trimethylamine (TMA) and isoprene compared to healthy subjects. Currently, there is not a validate and standardized method to detect VOCs. For this purpose, we examined the utility of selected ion flow tube-mass spectrometry (SIFT-MS) to measure VOCs in CKD patients and we evaluated the possible correlation between VOCs and the presence of CKD and its stage. We enrolled 68 CKD patients under conservative therapy and 54 healthy subjects. The analysis of the VOCs of the exhaled air of the enrolled subjects was performed by SIFT-MS. Among all the VOCs analyzed, the most relevant results by ROC curves were observed for TMA, acetone, ammonia and dimethyl sulfide. We found that a breath TMA concentration superior to 26 ppbv characterizes a 6.11 times greater risk of CKD, compared to subjects with lower levels. Moreover, we detected an increased concentration of acetone and ammonia in CKD patients compared to healthy subjects. We highlight the potential utility of SIFT-MS in CKD clinical management. Clinical trial registry: R.S. 15.19 of 6 February 2019. [ABSTRACT FROM AUTHOR]

Chronic disease prediction is a critical task in healthcare. Existing studies fulfil this requirement by employing machine learning techniques based on patient features, but they suffer from high dimensional data problems and a high level of bias. We propose a framework for predicting chronic disease based on Graph Neural Networks (GNNs) to address these issues. We begin by projecting a patient-disease bipartite graph to create a weighted patient network (WPN) that extracts the latent relationship among patients. We then use GNN-based techniques to build prediction models. These models use features extracted from WPN to create robust patient representations for chronic disease prediction. We compare the output of GNN-based models to machine learning methods by using cardiovascular disease and chronic pulmonary disease. The results show that our framework enhances the accuracy of chronic disease prediction. The model with attention mechanisms achieves an accuracy of 93.49% for cardiovascular disease prediction and 89.15% for chronic pulmonary disease prediction. Furthermore, the visualisation of the last hidden layers of GNN-based models shows the pattern for the two cohorts, demonstrating the discriminative strength of the framework. The proposed framework can help stakeholders improve health management systems for patients at risk of developing chronic diseases and conditions. [ABSTRACT FROM AUTHOR]