Ireneous Soyiri

Evolving forecasting classifications and applications in health forecasting

Health forecasting forewarns the health community about future health situations and disease episodes so that health systems can better allocate resources and manage demand. The tools used for developing and measuring the accuracy and validity of health forecasts commonly are not defined although they are usually adapted forms of statistical procedures. This review identifies previous typologies used in classifying the forecasting methods commonly used in forecasting health conditions or situations. It then discusses the strengths and weaknesses of these methods and presents the choices available for measuring the accuracy of health-forecasting models, including a note on the discrepancies in the modes of validation.

Land cover and air pollution are associated with asthma hospitalisations: A cross-sectional study

BACKGROUNDnThere is increasing policy interest in the potential for vegetation in urban areas to mitigate harmful effects of air pollution on respiratory health. We aimed to quantify relationships between tree and green space density and asthma-related hospitalisations, and explore how these varied with exposure to background air pollution concentrations.nnnMETHODSnPopulation standardised asthma hospitalisation rates (1997-2012) for 26,455 urban residential areas of England were merged with area-level data on vegetation and background air pollutant concentrations. We fitted negative binomial regression models using maximum likelihood estimation to obtain estimates of asthma-vegetation relationships at different levels of pollutant exposure.nnnRESULTSnGreen space and gardens were associated with reductions in asthma hospitalisation when pollutant exposures were lower but had no significant association when pollutant exposures were higher. In contrast, tree density was associated with reduced asthma hospitalisation when pollutant exposures were higher but had no significant association when pollutant exposures were lower.nnnCONCLUSIONSnWe found differential effects of natural environments at high and low background pollutant concentrations. These findings can provide evidence for urban planning decisions which aim to leverage health co-benefits from environmental improvements.

Patient reported outcome measures for allergy and asthma in children

There is increasing recognition of the importance of patients perceptions of disease and their assessments of heathcare processes. Patient‐reported outcome measures (PROMs) are therefore now regarded as at least as important as the traditional objective measures of disease. For minors, parental and, except in the very young and severally cognitively impaired, the childs perspectives are important because they provide unique and complementary information. In this review, we summarize the evidence on PROMs for allergy and asthma for use in children. Overall, there are fewer PROMs available for use in children than in adults. We were able to identify some validated pediatric PROMs that have been developed for use in atopic eczema/dermatitis, food allergy, allergic rhinitis/rhinoconjunctivitis, and asthma. There is very limited evidence on deploying these instruments out with research settings. There is therefore a pressing need to report on the experiences of using PROMs for allergy and asthma in routine clinical care. In particular, there is a need to understand how acceptable these are to children/carers, whether they can be incorporated into routine clinical assessments and if they are responsive to changes in treatment made in routine clinical practice.

Predicting probable Alzheimer’s disease using linguistic deficits and biomarkers

BackgroundThe manual diagnosis of neurodegenerative disorders such as Alzheimer’s disease (AD) and related Dementias has been a challenge. Currently, these disorders are diagnosed using specific clinical diagnostic criteria and neuropsychological examinations. The use of several Machine Learning algorithms to build automated diagnostic models using low-level linguistic features resulting from verbal utterances could aid diagnosis of patients with probable AD from a large population. For this purpose, we developed different Machine Learning models on the DementiaBank language transcript clinical dataset, consisting of 99 patients with probable AD and 99 healthy controls.ResultsOur models learned several syntactic, lexical, and n-gram linguistic biomarkers to distinguish the probable AD group from the healthy group. In contrast to the healthy group, we found that the probable AD patients had significantly less usage of syntactic components and significantly higher usage of lexical components in their language. Also, we observed a significant difference in the use of n-grams as the healthy group were able to identify and make sense of more objects in their n-grams than the probable AD group. As such, our best diagnostic model significantly distinguished the probable AD group from the healthy elderly group with a better Area Under the Receiving Operating Characteristics Curve (AUC) using the Support Vector Machines (SVM).ConclusionsExperimental and statistical evaluations suggest that using ML algorithms for learning linguistic biomarkers from the verbal utterances of elderly individuals could help the clinical diagnosis of probable AD. We emphasise that the best ML model for predicting the disease group combines significant syntactic, lexical and top n-gram features. However, there is a need to train the diagnostic models on larger datasets, which could lead to a better AUC and clinical diagnosis of probable AD.

Coming of age, becoming obese: a cross-sectional analysis of obesity among adolescents and young adults in Malaysia

BackgroundMalaysians have become increasingly obese over recent years. The transition from adolescence to early adulthood is recognized as critical for the development of eating and activity habits. However, little obesity-related research focuses on this life stage. Drawing on data from a health and demographic surveillance site in Malaysia, this article describes obesity and overweight amongst adolescents and young adults in a multi-ethnic population.MethodsData were collected at the South East Asia Community Observatory (SEACO) in Segamat District, Johor. In this dynamic cohort of approximately 40,000 people, 5,475 were aged 16–35 in 2013–2014. The population consists of Malay, Chinese, Indian and Indigenous (Orang Asli) families in proportions that reflect the national ethnic diversity. Data were collected through health profiles (Body Mass Index [BMI] measurements in homes) and self-report questionnaires.ResultsAge and ethnicity were associated with overweight (BMI 25.0–29.9Kg/m2) and obesity (BMIu2009≥u200930Kg/m2). The prevalence of overweight was 12.8xa0% at ages 16–20 and 28.4xa0% at ages 31–35; obesity was 7.9xa0% and 20.9xa0% at the same age groups. The main ethnic groups also showed varied patterns of obesity and overweight at the different age groups with Chinese at lowest and Orang Asli at highest risk. Level of education, employment status, physical activity and frequency of eating out were poorly predictive of overweight and obesity.ConclusionThe pattern of overweight and obesity in the 16–35 age group further highlights this as a significant period for changes in health-related behaviours. Further longitudinal research is however needed to confirm the observed pattern and investigate causal factors.

Semistructured black-box prediction: proposed approach for asthma admissions in London

Asthma is a global public health problem and the most common chronic disease among children. The factors associated with the condition are diverse, and environmental factors appear to be the leading cause of asthma exacerbation and its worsening disease burden. However, it remains unknown how changes in the environment affect asthma over time, and how temporal or environmental factors predict asthma events. The methodologies for forecasting asthma and other similar chronic conditions are not comprehensively documented anywhere to account for semistructured noncausal forecasting approaches. This paper highlights and discusses practical issues associated with asthma and the environment, and suggests possible approaches for developing decision-making tools in the form of semistructured black-box models, which is relatively new for asthma. Two statistical methods which can potentially be used in predictive modeling and health forecasting for both anticipated and peak events are suggested. Importantly, this paper attempts to bridge the areas of epidemiology, environmental medicine and exposure risks, and health services provision. The ideas discussed herein will support the development and implementation of early warning systems for chronic respiratory conditions in large populations, and ultimately lead to better decision-making tools for improving health service delivery.

HDSS Profile: The South East Asia Community Observatory Health and Demographic Surveillance System (SEACO HDSS)

HDSS Profile: The South East Asia Community Observatory Health and Demographic Surveillance System (SEACO HDSS) Uttara Partap, Elizabeth H Young, Pascale Allotey, Ireneous N Soyiri, Nowrozy Jahan, Kridaraan Komahan, Nirmala Devarajan, Manjinder S Sandhu and Daniel D Reidpath* Department of Medicine, University of Cambridge, Cambridge, UK, Wellcome Trust Sanger Institute, Hinxton, UK, Jeffrey Cheah School of Medicine and Health Sciences, Monash University Malaysia, Selangor, Malaysia, South East Asia Community Observatory, Segamat, Malaysia and Centre of Medical Informatics, Usher Institute of Population Health Sciences and Informatics, University of Edinburgh, UK

Building a recruitment database for asthma trials: a conceptual framework for the creation of the UK Database of Asthma Research Volunteers

BackgroundRandomised clinical trials are the ‘gold standard’ for evaluating the effectiveness of healthcare interventions. However, successful recruitment of participants remains a key challenge for many trialists. In this paper, we present a conceptual framework for creating a digital, population-based database for the recruitment of asthma patients into future asthma trials in the UK. Having set up the database, the goal is to then make it available to support investigators planning asthma clinical trials.MethodsThe UK Database of Asthma Research Volunteers will comprise a web-based front-end that interactively allows participant registration, and a back-end that houses the database containing participants’ key relevant data. The database will be hosted and maintained at a secure server at the Asthma UK Centre for Applied Research based at The University of Edinburgh. Using a range of invitation strategies, key demographic and clinical data will be collected from those pre-consenting to consider participation in clinical trials. These data will, with consent, in due course, be linkable to other healthcare, social, economic, and genetic datasets. To use the database, asthma investigators will send their eligibility criteria for participant recruitment; eligible participants will then be informed about the new trial and asked if they wish to participate. A steering committee will oversee the running of the database, including approval of usage access. Novel communication strategies will be utilised to engage participants who are recruited into the database in order to avoid attrition as a result of waiting time to participation in a suitable trial, and to minimise the risk of their being approached when already enrolled in a trial.ResultsThe value of this database will be whether it proves useful and usable to researchers in facilitating recruitment into clinical trials on asthma and whether patient privacy and data security are protected in meeting this aim.ConclusionsSuccessful recruitment is fundamental to the success of a clinical trial. The UK Database of Asthma Research Volunteers, the first of its kind in the context of asthma, presents a novel approach to overcoming recruitment barriers and will facilitate the catalysing of important clinical trials on asthma in the UK.

Searching for Health Information Online for My Child: A Perspective from South East Asia

Research studies investigating online health information searching behavior are abundant. While there is research pertaining to the online health information seeking behavior of parents in developed countries, similar information for countries with developing economies in the South East Asia region is not available. In this research study, we focus on information searching behavior of parents with children under the age of eighteen. This study describes the information searching behavior of 50 parents. Results indicate participants are motivated to search for information online for doctor visit and non-doctor visit purposes. Google is the most popular search engine used. Results provide insights on the information searching behavior of parents in South East Asia.

Smoke-free legislation and paediatric hospitalisations for acute respiratory tract infections: national quasi-experimental study with unexpected findings and important methodological implications

Objectives We investigated whether Scottish implementation of smoke-free legislation was associated with a reduction in unplanned hospitalisations or deaths (‘events’) due to respiratory tract infections (RTIs) among children. Design Interrupted time series (ITS). Setting/participants Children aged 0–12 years living in Scotland during 1996–2012. Intervention National comprehensive smoke-free legislation (March 2006). Main outcome measure Acute RTI events in the Scottish Morbidity Record-01 and/or National Records of Scotland Death Records. Results 135 134 RTI events were observed over 155u2009million patient-months. In our prespecified negative binomial regression model accounting for underlying temporal trends, seasonality, sex, age group, region, urbanisation level, socioeconomic status and seven-valent pneumococcal vaccination status, smoke-free legislation was associated with an immediate rise in RTI events (incidence rate ratio (IRR)=1.24, 95%u2009CI 1.20 to 1.28) and an additional gradual increase (IRR=1.05/year, 95%u2009CI 1.05 to 1.06). Given this unanticipated finding, we conducted a number of post hoc exploratory analyses. Among these, automatic break point detection indicated that the rise in RTI events actually preceded the smoke-free law by 16 months. When accounting for this break point, smoke-free legislation was associated with a gradual decrease in acute RTI events: IRR=0.91/year, 95%u2009CI 0.87 to 0.96. Conclusions Our prespecified ITS approach suggested that implementation of smoke-free legislation in Scotland was associated with an increase in paediatric RTI events. We were concerned that this result, which contradicted published evidence, was spurious. The association was indeed reversed when accounting for an unanticipated antecedent break point in the temporal trend, suggesting that the legislation may in fact be protective. ITS analyses should be subjected to comprehensive robustness checks to assess consistency.