scholarly journals Creating symptom-based criteria for diagnostic testing: a case study based on a multivariate analysis of data collected during the first wave of the COVID-19 pandemic in New Zealand

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Nigel French ◽  
Geoff Jones ◽  
Cord Heuer ◽  
Virginia Hope ◽  
Sarah Jefferies ◽  
...  
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Multivariate Analysis ◽  
New Zealand ◽  
Sensitivity And Specificity ◽  
Respiratory Symptoms ◽  
Diagnostic Testing ◽  
Search Algorithms ◽  
The Cost ◽  
Automated Search

Abstract Background Diagnostic testing using PCR is a fundamental component of COVID-19 pandemic control. Criteria for determining who should be tested by PCR vary between countries, and ultimately depend on resource constraints and public health objectives. Decisions are often based on sets of symptoms in individuals presenting to health services, as well as demographic variables, such as age, and travel history. The objective of this study was to determine the sensitivity and specificity of sets of symptoms used for triaging individuals for confirmatory testing, with the aim of optimising public health decision making under different scenarios. Methods Data from the first wave of COVID-19 in New Zealand were analysed; comprising 1153 PCR-confirmed and 4750 symptomatic PCR negative individuals. Data were analysed using Multiple Correspondence Analysis (MCA), automated search algorithms, Bayesian Latent Class Analysis, Decision Tree Analysis and Random Forest (RF) machine learning. Results Clinical criteria used to guide who should be tested by PCR were based on a set of mostly respiratory symptoms: a new or worsening cough, sore throat, shortness of breath, coryza, anosmia, with or without fever. This set has relatively high sensitivity (> 90%) but low specificity (< 10%), using PCR as a quasi-gold standard. In contrast, a group of mostly non-respiratory symptoms, including weakness, muscle pain, joint pain, headache, anosmia and ageusia, explained more variance in the MCA and were associated with higher specificity, at the cost of reduced sensitivity. Using RF models, the incorporation of 15 common symptoms, age, sex and prioritised ethnicity provided algorithms that were both sensitive and specific (> 85% for both) for predicting PCR outcomes. Conclusions  If predominantly respiratory symptoms are used for test-triaging,  a large proportion of the individuals being tested may not have COVID-19. This could overwhelm testing capacity and hinder attempts to trace and eliminate infection. Specificity can be increased using alternative rules based on sets of symptoms informed by multivariate analysis and automated search algorithms, albeit at the cost of sensitivity. Both sensitivity and specificity can be improved through machine learning algorithms, incorporating symptom and demographic data, and hence may provide an alternative approach to test-triaging that can be optimised according to prevailing conditions.

Locking down behavioural compliance: The role of emotion and emotion regulation in breaches of COVID-19 mitigation measures in Aotearoa New Zealand

2021 ◽  
pp. 135910532110299
Author(s):  
Terise Broodryk ◽  
Kealagh Robinson
Keyword(s):  
Public Health ◽  
Young Adults ◽  
New Zealand ◽  
Health Behaviours ◽  
Mitigation Measures ◽  
Aotearoa New Zealand ◽  
High Knowledge ◽  
The Cost ◽  
Insight Into

Although anxiety and worry can motivate engagement with COVID-19 preventative behaviours, people may cognitively reframe these unpleasant emotions, restoring wellbeing at the cost of public health behaviours. New Zealand young adults ( n = 278) experiencing nationwide COVID-19 lockdown reported their worry, anxiety, reappraisal and lockdown compliance. Despite high knowledge of lockdown policies, 92.5% of participants reported one or more policy breaches ( M  = 2.74, SD = 1.86). Counter to predictions, no relationships were found between anxiety or worry with reappraisal or lockdown breaches. Findings highlight the importance of targeting young adults in promoting lockdown compliance and offer further insight into the role of emotion during a pandemic.

scholarly journals The Result of Treatment of Deep Neck Infection in Patients Referred According to Public Health System

2019 ◽  
Vol 99 (10) ◽  
pp. 627-632
Author(s):  
Chuan Cheepcharoenrat
Keyword(s):  
Public Health ◽  
Multivariate Analysis ◽  
Univariate Analysis ◽  
Deep Neck Infection ◽  
Neck Infection ◽  
Public Health Systems ◽  
Results Of Treatment ◽  
Appropriate Treatment ◽  
Treatment Morbidity ◽  
The Cost

There are many factors that result in the treatment of deep neck infection (DNI). This study aims to compare the results of DNI treatment between referred and walk-in patients. This retrospective cohort study reviewed the data of 282 DNI patients. The peritonsillar abscesses and limited intraoral abscesses were excluded. The outcome of treatment such as duration of hospital stay, the expense of treatment, morbidity, and mortality were reviewed during staying in the hospital. A total of 282 patients were included in this study, there were 152 referred patients and 130 walk-in patients. Patients who were sent to have treatment results were not significantly different from those who had come directly to the hospital regardless of the length of stay, the cost of medical treatment, complications, and death due to complications with sepsis ( P = .013). However, the referred patients exhibited a risk to have sepsis 1.1 times more than the patients who went straight to the medical specialists (univariate analysis risk ratio [RR]: 1.1, 95% confidence interval [CI]: 0.8-1.3; P = .620). The results were confirmed in the multivariate analysis after adjusting for age, gender, diabetes, chronic renal failure, cirrhosis, and dental care. It was found that the risk to have sepsis in the “refer in” group was 1.1 times more than the other group (multivariate analysis RR: 1.1, 95% CI: 0.8-1.3; P = .658). In conclusion, the results of treatment in referred patients were not different from walk-in patients. Deep neck infection patients at hospitals that do not have a specialized doctor will receive appropriate treatment because of the effective DNI referral system according to public health systems. However, in referred patients, sepsis should be maintained prior to delivery.

scholarly journals Retrospective Derivation and Validation of a Search Algorithm to Identify Emergent Endotracheal Intubations in the Intensive Care Unit

2013 ◽  
Vol 04 (03) ◽  
pp. 419-427 ◽  
Author(s):  
V.M. Velagapudi ◽  
J.A. Onigkeit ◽  
B.W. Pickering ◽  
V. Herasevich ◽  
R. Kashyap ◽  
...  
Keyword(s):  
Intensive Care Unit ◽  
Intensive Care ◽  
Medical Record ◽  
Sensitivity And Specificity ◽  
Search Strategy ◽  
Search Algorithm ◽  
Search Algorithms ◽  
Critically Ill Patient ◽  
Predictive Values ◽  
Automated Search

Summary Background: The development and validation of automated electronic medical record (EMR) search strategies are important in identifying emergent endotracheal intubations in the intensive care unit (ICU). Objective: To develop and validate an automated search algorithm (strategy) for emergent endotracheal intubation in the critically ill patient. Methods: The EMR search algorithm was created through sequential steps with keywords applied to an institutional EMR database. The search strategy was derived retrospectively through a secondary analysis of a 450-patient subset from the 2,684 patients admitted to either a medical or surgical ICU from January 1, 2010, through December 31, 2011. This search algorithm was validated against an additional 450 randomly selected patients. Sensitivity, specificity, and negative and positive predictive values of the automated search algorithm were compared with a manual medical record review (the reference standard) for data extraction of emergent endotracheal intubations. Results: In the derivation subset, the automated electronic note search strategy achieved a sensitivity of 74% (95% CI, 69%-79%) and a specificity of 98% (95% CI, 92%-100%). With refinements in the search algorithm, sensitivity increased to 95% (95% CI, 91%-97%) and specificity decreased to 96% (95% CI, 92%-98%) in this subset. After validation of the algorithm through a separate patient subset, the final reported sensitivity and specificity were 95% (95% CI, 86%-99%) and 100% (95% CI, 98%-100%). Conclusions: Use of electronic search algorithms allows for correct extraction of emergent endotracheal intubations in the ICU, with high degrees of sensitivity and specificity. Such search algorithms are a reliable alternative to manual chart review for identification of emergent endotracheal intubations.

Feature extraction and prediction of Dengue Outbreaks

2020 ◽  
pp. 216-222
Author(s):  
Kunal Parikh ◽  
Tanvi Makadia ◽  
Harshil Patel
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Developing Countries ◽  
Feature Extraction ◽  
Predictive Analytics ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Health Concerns ◽  
The World ◽  
Dengue Outbreaks

Dengue is unquestionably one of the biggest health concerns in India and for many other developing countries. Unfortunately, many people have lost their lives because of it. Every year, approximately 390 million dengue infections occur around the world among which 500,000 people are seriously infected and 25,000 people have died annually. Many factors could cause dengue such as temperature, humidity, precipitation, inadequate public health, and many others. In this paper, we are proposing a method to perform predictive analytics on dengue’s dataset using KNN: a machine-learning algorithm. This analysis would help in the prediction of future cases and we could save the lives of many.

Clostridium difficileinfection: epidemiology, disease burden and therapy

2013 ◽  
Vol 154 (30) ◽  
pp. 1188-1193 ◽  
Author(s):  
László Gulácsi ◽  
Adrienne Kertész ◽  
Irén Kopcsóné Németh ◽  
János Banai ◽  
Endre Ludwig ◽  
...  
Keyword(s):  
Public Health ◽  
Health Economics ◽  
Disease Burden ◽  
Hungarian Literature ◽  
Medline Database ◽  
The Cost ◽  
Vancomycin Treatment

Introduction:C. difficile causes 25 percent of the antibiotic associated infectious nosocomial diarrhoeas. C. difficile infection is a high-priority problem of public health in each country. The available literature of C. difficile infection’s epidemiology and disease burden is limited. Aim: Review of the epidemiology, including seasonality and the risk of recurrences, of the disease burden and of the therapy of C. difficile infection. Method: Review of the international and Hungarian literature in MEDLINE database using PubMed up to and including 20th of March, 2012. Results: The incidence of nosocomial C. difficile associated diarrhoea is 4.1/10 000 patient day. The seasonality of C. difficile infection is unproved. 20 percent of the patients have recurrence after metronidazole or vancomycin treatment, and each recurrence increases the chance of a further one. The cost of C. difficile infection is between 130 and 500 thousand HUF (430 € and 1665 €) in Hungary. Conclusions: The importance of C. difficile infection in public health and the associated disease burden are significant. The available data in Hungary are limited, further studies in epidemiology and health economics are required. Orv. Hetil., 2013, 154, 1188–1193.

The Experience in Organizing and Conducting the Analysis of Data on Nutrition of School-Aged Children in the Sverdlovsk Region within the Federal Public Health Promotion Project

2020 ◽  
pp. 10-17
Author(s):  
NA Moiseeva ◽  
IL Kholstinina ◽  
MF Knyazeva ◽  
TV Mazhaeva ◽  
OL Malykh ◽  
...  
Keyword(s):  
Public Health ◽  
Health Promotion ◽  
Rural Areas ◽  
Nutritional Value ◽  
School Meals ◽  
School Aged Children ◽  
Healthy Nutrition ◽  
Urban And Rural Areas ◽  
The Cost ◽  
Public Health Promotion

Introduction: Implementation of the Federal Public Health Promotion Project should raise awareness and develop skills of healthy nutrition in children, thus contributing to disease prevention. Our objective was to evaluate the results of pilot nutrition monitoring in school-aged children of the Sverdlovsk Region as part of the Federal Public Health Promotion Project and the National Demography Project. Results: We established that school meals were generally satisfactory: the rations complied with physiological needs of children in terms of their nutritional value, basic nutrients, energy, and distribution of calories by main meals. We noted differences in the cost and nutritional value of meals and the variety of dishes and foodstuffs used between urban and rural areas. As a rule, pupils have one or two school meals a day. Outside of school, their consumption of dairy products and fruit is limited. Conclusions: Our findings may promote the elaboration of municipal programs aimed, inter alia, at changing the amount of sugar and salt used in the manufacture of public catering products, the cost of dishes with a high content of sugar, saturated fats, and salt, and subsidies on healthy nutrition.

scholarly journals Social determinants of dietary patterns, food basket costs and expenditure on alcohol and tobacco amongst Greenland Inuit

2021 ◽  
pp. 1-10
Author(s):  
Peter Bjerregaard ◽  
Christina Viskum Lytken Larsen
Keyword(s):  
Public Health ◽  
Dietary Patterns ◽  
Social Position ◽  
Alcoholic Beverages ◽  
Targeted Interventions ◽  
Balanced Diet ◽  
Nutritious Food ◽  
Food Basket ◽  
Purchase Patterns ◽  
The Cost

Abstract Objective: Dietary transition, obesity and risky use of alcohol and tobacco are challenges to public health among indigenous peoples. The aim of the article was to explore the role of social position in dietary patterns and expenditures on food and other commodities. Design: Countrywide population health survey. Setting: Greenland. Participants: 2436 Inuit aged 15+ years. Results: Less than half of the expenditures on commodities (43 %) were used to buy nutritious food, and the remaining to buy non-nutritious food (21 %), alcoholic beverages (18 %) and tobacco (18 %). Participants were classified according to five dietary patterns. The cost of a balanced diet and an unhealthy diet was similar, but the cost per 1000 kJ was higher and the energy consumption was lower for the balanced diet. Participants with low social position chose the unhealthy pattern more often than those with high social position (40 % v. 24 %; P < 0·0001), whereas those with high social position more often chose the balanced alternative. Participants with low social position spent less money on the total food basket than those with high social position but more on non-nutritious food, alcohol and tobacco. Conclusions: Cost seems to be less important than other mechanisms in the shaping of social dietary patterns and the use of alcohol and tobacco among the Inuit in Greenland. Rather than increasing the price of non-nutritious food or subsidising nutritious food, socially targeted interventions and public health promotion regarding food choice and prevention of excessive alcohol use and smoking are needed to change the purchase patterns.

scholarly journals Quality Classification of Injection-Molded Components by Using Quality Indices, Grading, and Machine Learning

Polymers ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 353
Author(s):  
Kun-Cheng Ke ◽  
Ming-Shyan Huang
Keyword(s):  
Machine Learning ◽  
Integrated Circuit ◽  
Quality Indices ◽  
Statistical Process ◽  
Suitable Alternative ◽  
Quality Grading ◽  
Quality Of Products ◽  
The Cost ◽  
Mlp Model

Conventional methods for assessing the quality of components mass produced using injection molding are expensive and time-consuming or involve imprecise statistical process control parameters. A suitable alternative would be to employ machine learning to classify the quality of parts by using quality indices and quality grading. In this study, we used a multilayer perceptron (MLP) neural network along with a few quality indices to accurately predict the quality of “qualified” and “unqualified” geometric shapes of a finished product. These quality indices, which exhibited a strong correlation with part quality, were extracted from pressure curves and input into the MLP model for learning and prediction. By filtering outliers from the input data and converting the measured quality into quality grades used as output data, we increased the prediction accuracy of the MLP model and classified the quality of finished parts into various quality levels. The MLP model may misjudge datapoints in the “to-be-confirmed” area, which is located between the “qualified” and “unqualified” areas. We classified the “to-be-confirmed” area, and only the quality of products in this area were evaluated further, which reduced the cost of quality control considerably. An integrated circuit tray was manufactured to experimentally demonstrate the feasibility of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document