RESUMO
AIMS: To offer a holistic view of the personal, external, and psychological factors influencing adherence to nutrition and diet in patients undergoing metabolic/bariatric surgery. METHODS: This systematic synthesis of mixed methods research involved a comprehensive search for articles in English databases, including PubMed, Cochrane Library, Web of Science, EBSCO, Scopus, and Embase, as well as Chinese databases. The search encompassed articles published from the inception of the database up to June 2023. Following the evaluation of literature quality and extraction of relevant information from the selected studies, data from both quantitative and qualitative studies were integrated. The extracted data were analyzed separately, and themes were identified and summarized to elucidate the factors influencing adherence to nutritional and dietary guidelines. The methodology adhered to the guidelines recommended by the Joanna Briggs Institute (JBI) for mixed methods systematic evaluations. RESULTS: Three themes and their corresponding descriptive elements were identified, including: (1) Personal factors: subjective factors (attitude, capability, awareness, behaviors), objective factors (age, sex, work status, economic level, physical activity, dietary habits, weight change); (2) External factors: medication (quantity of pills, complexity of intake times, side effects, unpleasant smell or taste), surgery factor, social influences (family members, dietitians, and peers); (3) Psychological factors: self-efficacy, attachment anxiety, and mental health problems. CONCLUSIONS: The synthesis provided a comprehensive overview of the factors influencing postoperative compliance of nutrition and diet among patients undergoing metabolic and bariatric surgery. It emphasizes the necessity for clinical staff to tailor interventions based on these diverse factors, as well as to attach importance to patients' mental health, giving multidimensional dietary guidance and health care.
RESUMO
The detection of seismic activity precursors as part of an alarm system will provide opportunities for minimization of the social and economic impact caused by earthquakes. It has long been envisaged, and a growing body of empirical evidence suggests that the Earth's electromagnetic field could contain precursors to seismic events. The ability to capture and monitor electromagnetic field activity has increased in the past years as more sensors and methodologies emerge. Missions such as Swarm have enabled researchers to access near-continuous observations of electromagnetic activity at second intervals, allowing for more detailed studies on weather and earthquakes. In this paper, we present an approach designed to detect anomalies in electromagnetic field data from Swarm satellites. This works towards developing a continuous and effective monitoring system of seismic activities based on SWARM measurements. We develop an enhanced form of a probabilistic model based on the Martingale theories that allow for testing the null hypothesis to indicate abnormal changes in electromagnetic field activity. We evaluate this enhanced approach in two experiments. Firstly, we perform a quantitative comparison on well-understood and popular benchmark datasets alongside the conventional approach. We find that the enhanced version produces more accurate anomaly detection overall. Secondly, we use three case studies of seismic activity (namely, earthquakes in Mexico, Greece, and Croatia) to assess our approach and the results show that our method can detect anomalous phenomena in the electromagnetic data.
RESUMO
AIMS: To explore the inter-predictive role and causal relationship between family functioning, self-perceived burden and loneliness in people with type 2 diabetes. METHODS: In this study, patients with type 2 diabetes admitted to two tertiary care hospitals in China were selected for an 8-month follow-up, and the patients' scores on the Family Functioning, Self-perceived Burden, and Loneliness scales were measured repeatedly at three time periods: during hospitalisation (T1), 1 month after discharge (T2), and 3 months after discharge (T3). RESULTS: The results showed that family function at the T1 time point had a negative predictive effect on self-perceived burden at the T2 time point, ß = - 0.43, P = 0.005. Loneliness at the T1 time point had a positive predictive effect on self-perceived burden at the T2 time point, ß = 0.08, P = 0.021. Unlike the pathway at time point T1, family functioning at time point T2 negatively predicted loneliness at time point T3, ß = - 0.32, P = 0.013. Loneliness at time point T2 positively predicted family functioning at time point T3, ß = 0.025, P = 0.013. Loneliness at time point T2 negatively predicted self-perceived burden at time point T3 (P = 0.011). CONCLUSIONS: The results of the cross-lagged analysis show that there is a mutually predictive and moderating relationship between family functioning and loneliness in patients with type 2 diabetes. Loneliness can predict the level of self-perceived burden at the next time point.
Assuntos
Diabetes Mellitus Tipo 2 , Humanos , Solidão , China/epidemiologiaRESUMO
BACKGROUND: Type 2 Diabetes mellitus (T2DM) has become a major lifestyle disease endangering human health worldwide. Patients with T2DM face varying degrees of loneliness, which adversely affects their family and the larger society. This study investigates the serial multiple mediating roles of depression and self-perceived burden between family function and loneliness in the T2DM population of China. METHODS: In total, 260 T2DM patients were included. They rated themselves based on UCLA Loneliness Scale, Self-Rating Depression Scale, Self-Rating Anxiety Scale, Family Care Index, and Self-Perceived Burden Scale. Pearson and Spearman correlation analyses were conducted to clarify the association among variables. The SPSS macro-PROCESS program was used for a series of multiple mediation analyses. RESULTS: Family function, depression, self-perceived burden, and loneliness were significantly correlated (P < 0.01). Family function not only has a direct negative impact (effect = -2.809; SE = 0.213; 95%CI: LL = -3.228, UL = -2.390) on loneliness, but also has an indirect impact on loneliness through the independent mediating role of depression (effect = -0.862; SE = 0.165; 95%CI: LL = -1.202, UL = -0.567) and self-perceived burden (effect = -0.288; SE = 0.107; 95%CI: LL = -0.525, UL = -0.114) and the chain mediating role of depression and self-perceived burden (effect = -0.202; SE = 0.066; 95%CI: LL = -0.342, UL = -0.088). CONCLUSIONS: Diversified interventions aimed at improving family function of T2DM patients would help in reducing the level of depression and self-perceived burden, and ultimately reducing loneliness.
Assuntos
Depressão , Diabetes Mellitus Tipo 2 , Humanos , Solidão , China , Estilo de VidaRESUMO
We aimed to determine the association between distinct body mass index (BMI) trajectories, using group-based trajectory modeling, and the subsequent risk of incident diabetes. Five databases were systematically searched. Fourteen population-based cohort studies that summarized the association between different BMI trajectories and subsequent diabetes, with the four most common BMI trajectories including the "stable," "increasing," "decreasing," and "turning" groups, were included. The rapid increase and stable high-level BMI groups showed the strongest association with the subsequent risk of diabetes compared with the stable normal BMI group. Increased baseline BMI levels resulted in a steeper slope and greater risk of subsequent diabetes. In the decreasing BMI group, one study reported that those aged >50 years showed the highest incidence of subsequent diabetes, whereas the other two studies reported no association between these two variables. In the turning group, an increase followed by a decrease in BMI levels from adolescence to late adulthood could reduce the risk of developing diabetes, although the residual risk remained. By contrast, the incidence of subsequent diabetes remained high in the middle-aged BMI-turning group. This study can provide further insights for identifying populations at high risk of diabetes and for developing targeted prevention strategies.
Assuntos
Diabetes Mellitus , Pessoa de Meia-Idade , Adolescente , Humanos , Adulto , Índice de Massa Corporal , Estudos Longitudinais , Diabetes Mellitus/epidemiologia , Estudos de Coortes , Incidência , Fatores de RiscoRESUMO
Background: The spatial and temporal variability inherent in malaria transmission within countries implies that targeted interventions for malaria control in high-burden settings and subnational elimination are a practical necessity. Identifying the spatio-temporal incidence, risk, and trends at different administrative geographies within malaria-endemic countries and monitoring them in near real-time as change occurs is crucial for developing and introducing cost-effective, subnational control and elimination intervention strategies. Methods: This study developed intelligent data analytics incorporating Bayesian trend and spatio-temporal Integrated Laplace Approximation models to analyse high-burden over 32 million reported malaria cases from 1743 health facilities in Zambia between 2009 and 2015. Results: The results show that at least 5.4 million people live in catchment areas with increasing trends of malaria, covering over 47% of all health facilities, while 5.7 million people live in areas with a declining trend (95% CI), covering 27% of health facilities. A two-scale spatio-temporal trend comparison identified significant differences between health facilities and higher-level districts, and the pattern observed in the southeastern region of Zambia provides the first evidence of the impact of recently implemented localised interventions. Conclusions: The results support our recommendation for an adaptive scaling approach when implementing national malaria monitoring, control and elimination strategies and a particular need for stratified subnational approaches targeting high-burden regions with increasing disease trends. Strong clusters along borders with highly endemic countries in the north and south of Zambia underscore the need for coordinated cross-border malaria initiatives and strategies.
RESUMO
PROBLEM: Fear of hypoglycemia is a significant concern for parents of children/ adolescents with type 1 diabetes. Although some studies have explained the parental fear of hypoglycemia, the related factors were yet to be determined. This systematic review aims to identify the related factors of fear of hypoglycemia in the parents of children and adolescents with type 1 diabetes and provide a theoretical basis for further intervention. ELIGIBILITY CRITERIA: PubMed, MEDLINE, EMBASE, Scopus, CINAHL, EBSCO, Web of Science, and Cochrane Library were systematically searched from 2010 to 2021. Studies evaluating the fear of hypoglycemia of parents and its associated factors were included. SAMPLE: Twenty-three observational articles met the criteria. RESULTS: Significant associations were found between fear of hypoglycemia and specific factors, including motherhood, nocturnal hypoglycemia, and the number of blood glucose monitoring. Psychological factors, including anxiety, depression, pediatric parenting stress, mindfulness, self-efficacy, quality of life, and sleep disorders, were conclusive and associations with parental fear of hypoglycemia. CONCLUSIONS: Understanding parental fear of hypoglycemia can help parents prevent potential problems in diabetes management, thus promoting children's growth. According to current evidence, effective targeted interventions based on modifiable relevant factors can be developed to reduce the fear of hypoglycemia in parents while maintaining optimal blood glucose control in children/ adolescents. IMPLICATIONS: Health professionals should pay more attention to the mental health of parents, and parents should be involved in the care plan and have the opportunity to discuss their fear of hypoglycemia in the most appropriate way to manage type 1 diabetes.
Assuntos
Diabetes Mellitus Tipo 1 , Hipoglicemia , Adolescente , Glicemia , Automonitorização da Glicemia , Criança , Medo , Humanos , Pais , Qualidade de VidaRESUMO
AIMS: This study aimed to explore the effect of fear of hypoglycaemia (FOH) on self-management and its specific action path in patients with type 2 diabetes mellitus (T2DM) to provide a basis for developing targeted nursing interventions. DESIGN: A cross-sectional study. METHODS: From June to October 2019, we recruited 258 patients with T2DM from the endocrinology department of three hospitals to complete questionnaires, including the Hypoglycaemia Fear Survey-II, Diabetes Distress Scale, Self-Stigma Scale, Social Support Rating Scale and Summary of Diabetes Self-Care Activities, in Jiangsu Province, China. Pearson's correlation analyses and structural equation modelling were conducted to explore the relationship and influence path among the above variables. RESULTS: The correlation analysis of FOH, distress, self-stigma, social support and self-management showed that, except for social support not being correlated with FOH and distress (P > 0.05), all variables were correlated in pairs (r = - 0.19-0.77, P < 0.01). The final model fit well, and the fitting indexes of the model were as follows: χ2/df = 2.191, GFI = 0.934, CFI = 0.954, TLI = 0.934, RMSEA = 0.068, and SRMR = 0.0649. The effects of FOH on self-management in patients with T2DM included one direct path and two indirect paths: (a) FOH had a direct impact on self-management (P < 0.05); (b) FOH had an indirect impact on self-management through distress (P < 0.05); and (c) FOH had an indirect impact on self-management through self-stigma and social support (P < 0.05). CONCLUSIONS: FOH could directly influence self-management in patients with T2DM. Furthermore, distress, self-stigma and social support were important mediating variables of FOH influencing self-management. Researchers can develop personalized interventions to improve the self-management of patients with T2DM by regulating distress, self-stigma and social support levels.
Assuntos
Diabetes Mellitus Tipo 1 , Diabetes Mellitus Tipo 2 , Hipoglicemia , Autogestão , Estudos Transversais , Diabetes Mellitus Tipo 2/terapia , Medo , Humanos , Análise de Classes Latentes , Inquéritos e QuestionáriosRESUMO
Remarkable evidence supports the link between type 2 diabetes (T2DM) and fatigue. However, a unifying recommendation to identify and prevent fatigue or to prevent its clinical consequences in T2DM is not available at present. Therefore, this study aimed to conduct a systematic review to summarize the definition, measurement tools, and contributing factors of fatigue in T2DM. Nine articles were included for analysis, and results showed that T2DM fatigue was associated with five major factors, including sociodemographic factors, clinical disease factors, inflammatory factors, psychological factors, and behavior and lifestyle. The contributing factors of T2DM fatigue are reviewed, and clinical benefits provide a theoretical basis for further clinical intervention to prevent the occurrence of fatigue and improve the patient's treatment compliance and self-management ability and may be beneficial to their quality of life.
Assuntos
Diabetes Mellitus Tipo 2 , Diabetes Mellitus Tipo 2/complicações , Fadiga/etiologia , Humanos , Estilo de Vida , Qualidade de Vida , Fatores SociodemográficosRESUMO
The van der Waals (vdW) integration enables to create heterostructures with intimate contact and bring new opportunities. However, it is not confined to layered materials but can also be generally extended to 3D materials. Multidimensional Bi2O3/BiVO4@graphene oxide (GO) van der Waals heterostructures are synthesized by one-pot wet chemistry method. Bi2O3/BiVO4 composite nanoparticles are self-assembled with GO framework by vdW interaction to form vdW heterostructures, in which GO framework allows short electron transport distance and rapid charge transfer and provides massive reactive sites. Such self-assembled heterostructures show a superior high photoactivity towards oxygen evolution with an enhanced oxygen generation rate of 1828 µmol h-1 g-1, nearly 3 times than that of pure BiVO4, attributed to the accelerated charge separation and transfer processes of Bi2O3/BiVO4@GO vdW heterostructures. This study indicates that our strategy provides a new avenue towards fabricating multi-dimensional vdW heterostructures and inspiring more innovative insights in oxygen evolution field.
RESUMO
In the last decade, many malaria-endemic countries, like Zambia, have achieved significant reductions in malaria incidence among children <5 years old but face ongoing challenges in achieving similar progress against malaria in older age groups. In parts of Zambia, changing climatic and environmental factors are among those suspectedly behind high malaria incidence. Changes and variations in these factors potentially interfere with intervention program effectiveness and alter the distribution and incidence patterns of malaria differentially between young children and the rest of the population. We used parametric and non-parametric statistics to model the effects of climatic and socio-demographic variables on age-specific malaria incidence vis-à-vis control interventions. Linear regressions, mixed models, and Mann-Kendall tests were implemented to explore trends, changes in trends, and regress malaria incidence against environmental and intervention variables. Our study shows that while climate parameters affect the whole population, their impacts are felt most by people aged ≥5 years. Climate variables influenced malaria substantially more than mosquito nets and indoor residual spraying interventions. We establish that climate parameters negatively impact malaria control efforts by exacerbating the transmission conditions via more conducive temperature and rainfall environments, which are augmented by cultural and socioeconomic exposure mechanisms. We argue that an intensified communications and education intervention strategy for behavioural change specifically targeted at ≥5 aged population where incidence rates are increasing, is urgently required and call for further malaria stratification among the ≥5 age groups in the routine collection, analysis and reporting of malaria mortality and incidence data.
Assuntos
Inseticidas , Malária , África Austral , Idoso , Criança , Pré-Escolar , Mudança Climática , Humanos , Incidência , Malária/epidemiologia , Controle de Mosquitos , ZâmbiaRESUMO
While mortality from malaria continues to decline globally, incidence rates in many countries are rising. Within countries, spatial and temporal patterns of malaria vary across communities due to many different physical and social environmental factors. To identify those areas most suitable for malaria elimination or targeted control interventions, we used Bayesian models to estimate the spatiotemporal variation of malaria risk, rates, and trends to determine areas of high or low malaria burden compared to their geographical neighbours. We present a methodology using Bayesian hierarchical models with a Markov Chain Monte Carlo (MCMC) based inference to fit a generalised linear mixed model with a conditional autoregressive structure. We modelled clusters of similar spatiotemporal trends in malaria risk, using trend functions with constrained shapes and visualised high and low burden districts using a multi-criterion index derived by combining spatiotemporal risk, rates and trends of districts in Zambia. Our results indicate that over 3 million people in Zambia live in high-burden districts with either high mortality burden or high incidence burden coupled with an increasing trend over 16 years (2000 to 2015) for all age, under-five and over-five cohorts. Approximately 1.6 million people live in high-incidence burden areas alone. Using our method, we have developed a platform that can enable malaria programs in countries like Zambia to target those high-burden areas with intensive control measures while at the same time pursue malaria elimination efforts in all other areas. Our method enhances conventional approaches and measures to identify those districts which had higher rates and increasing trends and risk. This study provides a method and a means that can help policy makers evaluate intervention impact over time and adopt appropriate geographically targeted strategies that address the issues of both high-burden areas, through intensive control approaches, and low-burden areas, via specific elimination programs.
Assuntos
Malária , Modelos Biológicos , Modelos Estatísticos , Teorema de Bayes , Criança , Pré-Escolar , Biologia Computacional , Humanos , Incidência , Lactente , Recém-Nascido , Malária/epidemiologia , Malária/transmissão , Risco , Análise Espaço-Temporal , ZâmbiaRESUMO
AIM: The study aimed to explore the association between diabetes-related distress as a dependent variable and fear of hypoglycaemia as a independent variable in Chinese individuals with type 2 diabetes, which can provide a basis for the development of effective nursing interventions. DESIGN: A cross-sectional descriptive study. METHODS: Pre-piloted scales were used to determine whether they experienced fear of hypoglycaemia and whether this impacted upon their management of the disease. From June-October 2019, participants were asked to complete the "hypoglycaemia fear survey" and "diabetes distress scales" to assess levels of fear and distress. Stepwise multivariate regression analysis was applied to reveal relationship between distress as a dependent variable and fear as a independent variable. Covariates included demographic, clinical or lifestyle factors. RESULTS: A total of 258 participants were recruited for the survey, and they were characterized by little or no distress (39.53%), moderate distress (45.35%) and high distress (15.12%). The prevalence of moderate to severe distress in patients was 60.47%. Increased diabetes-related distress was strongly correlated with increased fear of hypoglycaemia and closely associated with the scores of the worry and behaviour subscales. These results indicated that 62.3% of diabetes-related distress may be explained by fear of hypoglycaemia. CONCLUSION: Increased diabetes-related distress is associated with increased fear of hypoglycaemia in individuals with type 2 diabetes.
Assuntos
Diabetes Mellitus Tipo 1 , Diabetes Mellitus Tipo 2 , Hipoglicemia , Estudos Transversais , Diabetes Mellitus Tipo 2/complicações , Medo , Humanos , Hipoglicemia/epidemiologia , HipoglicemiantesRESUMO
The role of climate change on global malaria is often highlighted in World Health Organisation reports. We modelled a Zambian socio-environmental dataset from 2000 to 2016, against malaria trends and investigated the relationship of near-term environmental change with malaria incidence using Bayesian spatio-temporal, and negative binomial mixed regression models. We introduced the diurnal temperature range (DTR) as an alternative environmental measure to the widely used mean temperature. We found substantial sub-national near-term variations and significant associations with malaria incidence-trends. Significant spatio-temporal shifts in DTR/environmental predictors influenced malaria incidence-rates, even in areas with declining trends. We highlight the impact of seasonally sensitive DTR, especially in the first two quarters of the year and demonstrate how substantial investment in intervention programmes is negatively impacted by near-term climate change, most notably since 2010. We argue for targeted seasonally-sensitive malaria chemoprevention programmes.
Assuntos
Teorema de Bayes , Mudança Climática , Malária/epidemiologia , Malária/transmissão , Plasmodium/isolamento & purificação , Análise Espaço-Temporal , Humanos , Incidência , Malária/parasitologia , Modelos Estatísticos , Zâmbia/epidemiologiaRESUMO
BACKGROUND: Oxidative stress is considered a possible mechanism of irritable bowel syndrome (IBS) and depression. This study determined the possible association of serum peroxiredoxin 1 (PRDX1; a key antioxidant enzyme) and brain-derived neurotrophic factor (BDNF) with anxiety and depression symptoms in IBS patients. METHODS: According to the Rome IV diagnostic criteria, 177 IBS patients from February 2019 to July 2019 were included. Serum levels of PRDX1, BDNF, and TNFα were detected by enzyme-linked immunosorbent assay. Levels of anxiety and depression were assessed with the Self-rating Anxiety Scale (SAS) and Self-rating Depression Scale (SDS). RESULTS: Compared with normal IBS patients, patients with anxiety and depression symptoms had significantly higher serum PRDX1 (p<0.001; p=0.002) and TNFα (p<0.001; p = 0.002) and significantly lower BDNF (p < 0.001; p = 0.002). Serum PRDX1 (r = 0.659, p < 0.001; r = 0.466, p < 0.001) and TNFα (r = 0.531, p < 0.001; r = 0.449, p < 0.001) were positively correlated with SAS and SDS, respectively, whereas BDNF was negatively correlated with SAS (r = 0.594, p < 0.001) and SDS (r = 0.534, p < 0.001). Multivariable regression analysis revealed that IBS severity, BDNF, and PRDX1 were significant predictors of anxiety. BDNF was also a significant predictor of depression. CONCLUSION: Elevated PRDX1 and decreased BDNF in serum may be closely related to psychological symptoms in IBS. Results of this study suggested that PRDX1 may be an important target for IBS treatment in fighting against intestinal and psychological symptoms.
Assuntos
Ansiedade , Fator Neurotrófico Derivado do Encéfalo/sangue , Depressão , Síndrome do Intestino Irritável , Peroxirredoxinas/sangue , Ansiedade/epidemiologia , Depressão/epidemiologia , Humanos , Síndrome do Intestino Irritável/psicologiaRESUMO
AIMS AND OBJECTIVES: To summarize and thematize fear of hypoglycemia (FOH) in individuals with type 1 diabetes (T1D) and type 2 diabetes (T2D) to provide a theoretical basis for the development of effective interventions. BACKGROUND: FOH is common in this population and can reduce quality of life(QOL) and adversely impact upon diabetes self-care management. DESIGN: a systematic review METHODS: Articles published between 2000 and 2019 were searched in PubMed, MEDLINE, EMBASE, Web of Science and three Chinese databases (CNKI, Wan-fang data and VIP). Eligible articles were selected using the Preferred Reporting Item for Systematic Review and Meta-analysis (PRISMA) guidelines. The quality of all articles finally included was evaluated by the Joanna Briggs Institute (JBI) Critical Appraisal tools. RESULTS: Eighteen studies from 8654 papers were included. The sample size of each study ranged from 48 to 3812 subjects. FOH negatively impacted QOL, particularly psychosocial functioning, daily life and sleep quality. CONCLUSIONS: FOH is a common and serious problem for patients, leading to poor QOL. It has been suggested that psychological concerns, QOL and effective countermeasures in individuals with T1D and T2D should be taken seriously. Advanced technology should be evaluated for its benefits before being used by patients. RELEVANCE TO CLINICAL PRACTICE: The review highlights that FOH negatively impacts QOL, including psychosocial factors, daily life and sleep quality. Healthcare providers should develop targeted and professional assessment tools for FOH and QOL for patients with T2D, especially for patients who are about 60 years old. Advanced technology should be evaluated for its benefits before being used by patients.
RESUMO
AIM: To explore the relationship between spiritual climate and transformational leadership, and examine their impact on nurses perceived emotional exhaustion and intentions to quit. BACKGROUND: Transformational leadership is known to have a significant positive effect on work environment and job satisfaction. Additionally, promoting spiritual climate amongst staff can benefit workers by increasing self-worth. The relationship between the two is unknown. METHODS: Nurse clinicians from 2 sites in the Jiangsu Province of China completed self-report questionnaires based on spiritual climate, emotional exhaustion, clinical leadership and Turnover Intention Scales. Mediation analysis was applied to evaluate impact of spiritual climate. RESULTS: Perceived positive spirituality amongst nurse clinicians reinforces transformational leadership to reduce emotional exhaustion (indirect effect of -0.089, p < .01). Burnout and intention to leave showed significantly positive correlation with lower levels of perceived spirituality (r = .545, p < .01). CONCLUSION: Transformational leadership in the workplace can reduce nurses' burnout, and a positive spiritual climate increases meaningfulness in their work. This may help in nurse retention. IMPLICATIONS FOR NURSING MANAGEMENT: Health care leaders must look beyond transformational leadership to maintain a positive and supportive clinical climate, and this may involve acknowledgement of nurses' spiritual needs.
Assuntos
Liderança , Espiritualidade , Adulto , Esgotamento Profissional , China , Estudos Transversais , Feminino , Humanos , Intenção , Satisfação no Emprego , Masculino , Pessoa de Meia-Idade , Inquéritos e QuestionáriosRESUMO
This research presents viable solutions for prediction modelling of schistosomiasis disease based on vector density. Novel training models proposed in this work aim to address various aspects of interest in the artificial intelligence applications domain. Topics discussed include data imputation, semi-supervised labelling and synthetic instance simulation when using sparse training data. Innovative semi-supervised ensemble learning paradigms are proposed focusing on labelling threshold selection and stringency of classification confidence levels. A regression-correlation combination (RCC) data imputation method is also introduced for handling of partially complete training data. Results presented in this work show data imputation precision improvement over benchmark value replacement using proposed RCC on 70% of test cases. Proposed novel incremental transductive models such as ITSVM have provided interesting findings based on threshold constraints outperforming standard SVM application on 21% of test cases and can be applied with alternative environment-based epidemic disease domains. The proposed incremental transductive ensemble approach model enables the combination of complimentary algorithms to provide labelling for unlabelled vector density instances. Liberal (LTA) and strict training approaches provided varied results with LTA outperforming Stacking ensemble on 29.1% of test cases. Proposed novel synthetic minority over-sampling technique (SMOTE) equilibrium approach has yielded subtle classification performance increases which can be further interrogated to assess classification performance and efficiency relationships with synthetic instance generation.