Forecasting severe respiratory disease hospitalizations using machine learning algorithms.

Background: Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload.

Predicting the risk of diabetes complications using machine learning and social administrative data in a country with ethnic inequities in health: Aotearoa New Zealand.

Background: In the age of big data, linked social and administrative health data in combination with machine learning (ML) is being increasingly used to improve prediction in chronic disease, e.g., cardiovascular diseases (CVD).

Predicting high health-cost users among people with cardiovascular disease using machine learning and nationwide linked social administrative datasets.

Objectives: To optimise planning of public health services, the impact of high-cost users needs to be considered. However, most of the existing statistical models for costs do not include many clinical and social variables from administrative data that are associated with elevated health care resource use, and are increasingly available. This study aimed to use machine learning approaches and big data to predict high-cost users among people with cardiovascular disease (CVD).

Prioritization of intervention domains to prevent cardiovascular disease: a country-level case study using global burden of disease and local data.

Aim: We aimed to combine Global Burden of Disease (GBD) Study data and local data to identify the highest priority intervention domains for preventing cardiovascular disease (CVD) in the case study country of Aotearoa New Zealand (NZ).

Methods: Risk factor data for CVD in NZ were extracted from the GBD using the "GBD Results Tool." We prioritized risk factor domains based on consideration of the size of the health burden (disability-adjusted life years [DALYs]) and then by the domain-specific interventions that delivered the highest health gains and cost-savings.

Using household economic survey data to assess food expenditure patterns and trends in a high-income country with notable health inequities.

This study aimed to identify dietary trends in Aotearoa New Zealand (NZ) and whether inequities in dietary patterns are changing. We extracted data from the Household Economic Survey (HES), which was designed to provide information on impacts of policy-making in NZ, and performed descriptive analyses on food expenditures. Overall, total household food expenditure per capita increased by 0.

Health promoting and demoting consumption: What accounts for budget share differentials by ethnicity in New Zealand.

Background: Health demoting consumption of alcohol and tobacco are some of the most important risk factors for health loss worldwide, however there is limited information on these consumption risk factors in New Zealand (NZ) and whether inequities in the risk factors are ethnically patterned.

Methods: We used three nationally representative Household Economic Survey waves (2006/07, 2009/10, 2012/13) (n = 9030) in NZ to examine household expenditure for key health risk-related components of consumption by ethnicity, and its contributors to the differences using non-parametric, parametric and decomposition methods.

Results: Māori households (NZ indigenous population) were significantly poorer (25% less) than non-Māori households in terms of household per capita expenditure.

Modelling the impacts of tobacco denicotinisation on achieving the Smokefree 2025 goal in Aotearoa New Zealand.

Aim: To provide preliminary high-level modelling estimates of the impact of denicotinisation of tobacco on changes in smoking prevalence in Aotearoa New Zealand relative to the New Zealand Government's Smokefree 2025 goal.

Methods: An Excel spreadsheet was populated with smoking and vaping prevalence data from the New Zealand Health Survey and we projected business-as-usual trends. Using various parameters from the literature (New Zealand trial data, New Zealand EASE-ITC Study results), we modelled the potential impact of denicotinisation of tobacco (with no other tobacco permitted for sale) out to 2025.

Can a Greenhouse Gas Emissions Tax on Food also Be Healthy and Equitable? A Systemised Review and Modelling Study from Aotearoa New Zealand.

Policies to mitigate climate change are essential. The objective of this paper was to estimate the impact of greenhouse gas (GHG) food taxes and assess whether such a tax could also have health benefits in Aotearoa NZ. We undertook a systemised review on GHG food taxes to inform four tax scenarios, including one combined with a subsidy.

The Cost-effectiveness of a Mass Media Campaign to Promote Smartphone Apps for Weight Loss: Updated Modeling Study.

Background: Evidence suggests that smartphone apps can be effective in the self-management of weight. Given the low cost, broad reach, and apparent effectiveness of weight loss apps, governments may seek to encourage their uptake as a tool to reduce excess weight in the population. Mass media campaigns are 1 mechanism for promoting app use.

Relative contribution of trends in myocardial infarction event rates and case fatality to declines in mortality: an international comparative study of 1·95 million events in 80·4 million people in four countries.

Background: Myocardial infarction mortality has declined since the 1970s, but contemporary drivers of this trend remain unexplained. The aim of this study was to compare the contribution of trends in event rates and case fatality to declines in myocardial infarction mortality in four high-income jurisdictions from 2002-15.

Methods: Linked hospitalisation and mortality data were obtained from New South Wales (NSW), Australia; Ontario, Canada; New Zealand; and England, UK.

Impact of taxes on purchases of close substitute foods: analysis of cross-price elasticities using data from a randomized experiment.

Objective: To examine the effects of health-related food taxes on substitution and complementary purchases within food groups, including from unhealthier to healthier alternatives and between brands.

Methods: We used data from a virtual supermarket experiment with data from 4,259 shopping events linked to varying price sets. Substitution or complementary effects within six frequently purchased food categories were analyzed.

Potential impact of COVID-19 related unemployment on increased cardiovascular disease in a high-income country: Modeling health loss, cost and equity.

Background: Cardiovascular disease (CVD) is a leading cause of health loss and health sector economic burdens in high-income countries. Unemployment is associated with increased risk of CVD, and so there is concern that the economic downturn associated with the COVID-19 pandemic will increase the CVD burden.

Aims: This modeling study aimed to quantify potential health loss, health cost burden and health inequities among people with CVD due to additional unemployment caused by COVID-19 pandemic-related economic disruption in one high-income country: New Zealand (NZ).

Should prioritising health interventions be informed by modelling studies? The case of cancer control in Aotearoa New Zealand.

In this viewpoint, we suggest that policymakers should prioritise health interventions by using evidence around health gain, impact on equity, health-system costs and cost-effectiveness. We take the example of the new cancer control agency in New Zealand, Te Aho o Te Kahu, and argue that its decision-making can now be informed by many methodologically compatible epidemiological and health economic analyses. These analyses span primary prevention of cancer (eg, tobacco control, dietary and physical activity interventions and HPV vaccination), cancer screening, cancer treatment and palliative care.

Increased unemployment from the COVID-19 pandemic, what might be the adverse impacts on cardiovascular disease in Aotearoa/New Zealand and how might this be prevented?

Despite success with eliminating the COVID-19 pandemic in Aotearoa New Zealand (at least to early August 2020), the response to the pandemic threat has resulted in a range of negative social and economic impacts, including job losses. Understanding the health consequences of these impacts will be increasingly important in the 'recovery' phase. This article contributes to this understanding by exploring the relationship between unemployment and cardiovascular disease (CVD)-a major contributor to health loss in Aotearoa New Zealand.

The effect of food taxes and subsidies on population health and health costs: a modelling study.

Background: One possible policy response to the burden of diet-related disease is food taxes and subsidies, but the net health gains of these approaches are uncertain because of substitution effects between foods. We estimated the health and cost impacts of various food taxes and subsidies in one high-income country, New Zealand.

Methods: In this modelling study, we compared the effects in New Zealand of a 20% fruit and vegetable subsidy, of saturated fat, sugar and salt taxes (each set at a level that increased the total food price by the same magnitude of decrease from the fruit and vegetable subsidy), and of an 8% so-called junk food tax (on non-essential, energy-dense food).

Modelling the health impact of food taxes and subsidies with price elasticities: The case for additional scaling of food consumption using the total food expenditure elasticity.

Background: Food taxes and subsidies are one intervention to address poor diets. Price elasticity (PE) matrices are commonly used to model the change in food purchasing. Usually a PE matrix is generated in one setting then applied to another setting with differing starting consumptions and prices of foods.

Preventive Pharmacotherapy for Cardiovascular Disease: A Modelling Study Considering Health Gain, Costs, and Cost-Effectiveness when Stratifying by Absolute Risk.

Cardiovascular disease (CVD) is the leading cause of death internationally. We aimed to model the impact of CVD preventive double therapy (a statin and anti-hypertensive) by clinician-assessed absolute risk level. An established and validated multi-state life-table model for the national New Zealand (NZ) population was adapted.

Achieving Healthy and Sustainable Diets: A Review of the Results of Recent Mathematical Optimization Studies.

Climate protection and other environmental concerns render it critical that diets and agriculture systems become more sustainable. Mathematical optimization techniques can assist in identifying dietary patterns that both improve nutrition and reduce environmental impacts. Here we review 12 recent studies in which such optimization was used to achieve nutrition and environmental sustainability aims.

Health benefits and costs of weight-loss dietary counselling by nurses in primary care: a cost-effectiveness analysis.

Objective: We aimed to estimate the cost-effectiveness of brief weight-loss counselling by dietitian-trained practice nurses, in a high-income-country case study.

Design: A literature search of the impact of dietary counselling on BMI was performed to source the 'best' effect size for use in modelling. This was combined with multiple other input parameters (e.

Predicting the onset of type 2 diabetes using wide and deep learning with electronic health records.

Objective: Diabetes is responsible for considerable morbidity, healthcare utilisation and mortality in both developed and developing countries. Currently, methods of treating diabetes are inadequate and costly so prevention becomes an important step in reducing the burden of diabetes and its complications. Electronic health records (EHRs) for each individual or a population have become important tools in understanding developing trends of diseases.

Can cost-effectiveness results be combined into a coherent league table? Case study from one high-income country.

Background: Doubts exist around the value of compiling league tables for cost-effectiveness results for health interventions, primarily due to methods differences. We aimed to determine if a reasonably coherent league table could be compiled using published studies for one high-income country: New Zealand (NZ).

Methods: Literature searches were conducted to identify NZ-relevant studies published in the peer-reviewed journal literature between 1 January 2010 and 8 October 2017.

The effect of food price changes on consumer purchases: a randomised experiment.

Background: Most evidence on health-related food taxes and subsidies relies on observational data and effects on single nutrients or foods instead of total diet. The aim of this study was to measure the effect of randomly assigned food price variations on consumer purchasing, where sets of prices emulated commonly discussed food tax and subsidy policies, including a subsidy on fruit and vegetables, a sweetened beverage tax, and taxes on foods according to sugar, sodium, and saturated fat content.

Methods: In this study, adult participants (≥18 years) in New Zealand completed up to five weekly shops in a virtual supermarket.

Mass media promotion of a smartphone smoking cessation app: modelled health and cost-saving impacts.

Background: Smartphones are increasingly available and some high quality apps are available for smoking cessation. However, the cost-effectiveness of promoting such apps has never been studied. We therefore aimed to estimate the health gain, inequality impacts and cost-utility from a five-year promotion campaign of a smoking cessation smartphone app compared to business-as-usual (no app use for quitting).