International Journal of Environmental Research and Public Health

Research

11 pages, 1258 KiB

Open AccessArticle

Evaluation of a Medical Interview-Assistance System Using Artificial Intelligence for Resident Physicians Interviewing Simulated Patients: A Crossover, Randomized, Controlled Trial

by Akio Kanazawa, Kazutoshi Fujibayashi, Yu Watanabe, Seiko Kushiro, Naotake Yanagisawa, Yasuko Fukataki, Sakiko Kitamura, Wakako Hayashi, Masashi Nagao, Yuji Nishizaki, Takenori Inomata, Eri Arikawa-Hirasawa and Toshio Naito

Int. J. Environ. Res. Public Health 2023, 20(12), 6176; https://doi.org/10.3390/ijerph20126176 - 19 Jun 2023

Cited by 4 | Viewed by 2696

Abstract

Medical interviews are expected to undergo a major transformation through the use of artificial intelligence. However, artificial intelligence-based systems that support medical interviews are not yet widespread in Japan, and their usefulness is unclear. A randomized, controlled trial to determine the usefulness of [...] Read more.

Medical interviews are expected to undergo a major transformation through the use of artificial intelligence. However, artificial intelligence-based systems that support medical interviews are not yet widespread in Japan, and their usefulness is unclear. A randomized, controlled trial to determine the usefulness of a commercial medical interview support system using a question flow chart-type application based on a Bayesian model was conducted. Ten resident physicians were allocated to two groups with or without information from an artificial intelligence-based support system. The rate of correct diagnoses, amount of time to complete the interviews, and number of questions they asked were compared between the two groups. Two trials were conducted on different dates, with a total of 20 resident physicians participating. Data for 192 differential diagnoses were obtained. There was a significant difference in the rate of correct diagnosis between the two groups for two cases and for overall cases (0.561 vs. 0.393; p = 0.02). There was a significant difference in the time required between the two groups for overall cases (370 s (352–387) vs. 390 s (373–406), p = 0.04). Artificial intelligence-assisted medical interviews helped resident physicians make more accurate diagnoses and reduced consultation time. The widespread use of artificial intelligence systems in clinical settings could contribute to improving the quality of medical care. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

11 pages, 1160 KiB

Open AccessArticle

Advanced Sentiment Analysis for Managing and Improving Patient Experience: Application for General Practitioner (GP) Classification in Northamptonshire

by Aavash Raj Pandey, Mahdi Seify, Udoka Okonta and Amin Hosseinian-Far

Int. J. Environ. Res. Public Health 2023, 20(12), 6119; https://doi.org/10.3390/ijerph20126119 - 13 Jun 2023

Cited by 2 | Viewed by 2361

Abstract

This paper presents a novel analytical approach for improving patients’ experience in healthcare settings. The analytical tool uses a classifier and a recommend management approach to facilitate decision making in a timely manner. The designed methodology comprises of 4 key stages, which include [...] Read more.

This paper presents a novel analytical approach for improving patients’ experience in healthcare settings. The analytical tool uses a classifier and a recommend management approach to facilitate decision making in a timely manner. The designed methodology comprises of 4 key stages, which include developing a bot to scrap web data while performing sentiment analysis and extracting keywords from National Health Service (NHS) rate and review webpages, building a classifier with Waikato Environment for Knowledge Analysis (WEKA), analyzing speech with Python, and using Microsoft Excel for analysis. In the selected context, a total of 178 reviews were extracted from General Practitioners (GP) websites within Northamptonshire County, UK. Accordingly, 4764 keywords such as “kind”, “exactly”, “discharged”, “long waits”, “impolite staff”, “worse”, “problem”, “happy”, “late” and “excellent” were selected. In addition, 178 reviews were analyzed to highlight trends and patterns. The classifier model grouped GPs into gold, silver, and bronze categories. The outlined analytical approach complements the current patient feedback analysis approaches by GPs. This paper solely relied upon the feedback available on the NHS’ rate and review webpages. The contribution of the paper is to highlight the integration of easily available tools to perform higher level of analysis that provides understanding about patients’ experience. The context and tools used in this study for ranking services within the healthcare domain is novel in nature, since it involves extracting useful insights from the provided feedback. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

14 pages, 1135 KiB

Open AccessArticle

Predicting the Severity of Adverse Events on Osteoporosis Drugs Using Attribute Weighted Logistic Regression

by Neveen Ibrahim, Lee Kien Foo and Sook-Ling Chua

Int. J. Environ. Res. Public Health 2023, 20(4), 3289; https://doi.org/10.3390/ijerph20043289 - 13 Feb 2023

Cited by 1 | Viewed by 1460

Abstract

Osteoporosis is a serious bone disease that affects many people worldwide. Various drugs have been used to treat osteoporosis. However, these drugs may cause severe adverse events in patients. Adverse drug events are harmful reactions caused by drug usage and remain one of [...] Read more.

Osteoporosis is a serious bone disease that affects many people worldwide. Various drugs have been used to treat osteoporosis. However, these drugs may cause severe adverse events in patients. Adverse drug events are harmful reactions caused by drug usage and remain one of the leading causes of death in many countries. Predicting serious adverse drug reactions in the early stages can help save patients’ lives and reduce healthcare costs. Classification methods are commonly used to predict the severity of adverse events. These methods usually assume independence among attributes, which may not be practical in real-world applications. In this paper, a new attribute weighted logistic regression is proposed to predict the severity of adverse drug events. Our method relaxes the assumption of independence among the attributes. An evaluation was performed on osteoporosis data obtained from the United States Food and Drug Administration databases. The results showed that our method achieved a higher recognition performance and outperformed baseline methods in predicting the severity of adverse drug events. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

18 pages, 4759 KiB

Open AccessArticle

Trade Flow Optimization Model for Plastic Pollution Reduction

by Daming Li, Canyao Liu, Yu Shi, Jiaming Song and Yiliang Zhang

Int. J. Environ. Res. Public Health 2022, 19(23), 15963; https://doi.org/10.3390/ijerph192315963 - 30 Nov 2022

Viewed by 1967

Abstract

Managing plastic waste from an international perspective is complex, with many countries in the trade network playing distinct roles at different stages of the life-cycle of plastics. Trade flows are therefore the key to understanding global plastic market and its supply chains. In [...] Read more.

Managing plastic waste from an international perspective is complex, with many countries in the trade network playing distinct roles at different stages of the life-cycle of plastics. Trade flows are therefore the key to understanding global plastic market and its supply chains. In this paper, we formulate an optimization problem from the perspective of reducing global ocean plastic pollution, and create a novel framework based on a network flow model to identify the optimal international trade flows over the life-cycle of plastics. Our model quantifies global flows of production, consumption, and trade across the life-cycle of plastics from raw inputs and subsequent plastic products to its final stage as waste. Using panel data on plastic consumption, waste, and production, we compare the trade flows in reality and the optimal trade flows determined by our model and find that the two are highly correlated. We highlight the policy implications based on our model: increasing trade capacity and improving recycle rates in developing countries. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

16 pages, 559 KiB

Open AccessArticle

Risk Association of Liver Cancer and Hepatitis B with Tree Ensemble and Lifestyle Features

by Eunji Koh and Younghoon Kim

Int. J. Environ. Res. Public Health 2022, 19(22), 15171; https://doi.org/10.3390/ijerph192215171 - 17 Nov 2022

Viewed by 1965

Abstract

The second-largest cause of death by cancer in Korea is liver cancer, which leads to acute morbidity and mortality. Hepatitis B is the most common cause of liver cancer. About 70% of liver cancer patients suffer from hepatitis B. Early risk association of [...] Read more.

The second-largest cause of death by cancer in Korea is liver cancer, which leads to acute morbidity and mortality. Hepatitis B is the most common cause of liver cancer. About 70% of liver cancer patients suffer from hepatitis B. Early risk association of liver cancer and hepatitis B can help prevent fatal conditions. We propose a risk association method for liver cancer and hepatitis B with only lifestyle features. The diagnostic features were excluded to reduce the cost of gathering medical data. The data source is the Korea National Health and Nutrition Examination Survey (KNHANES) from 2007 to 2019. We use 3872 and 4640 subjects for liver cancer and hepatitis B model, respectively. Random forest is employed to determine functional relationships between liver diseases and lifestyle features. The performance of our proposed method was compared with six machine learning methods. The results showed the proposed method outperformed the other methods in the area under the receiver operator characteristic curve of 0.8367. The promising results confirm the superior performance of the proposed method and show that the proposed method with only lifestyle features provides significant advantages, potentially reducing the cost of detecting patients who require liver health care in advance. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

23 pages, 7293 KiB

Open AccessArticle

Improving Water Quality Index Prediction Using Regression Learning Models

by Jesmeen Mohd Zebaral Hoque, Nor Azlina Ab. Aziz, Salem Alelyani, Mohamed Mohana and Maruf Hosain

Int. J. Environ. Res. Public Health 2022, 19(20), 13702; https://doi.org/10.3390/ijerph192013702 - 21 Oct 2022

Cited by 19 | Viewed by 6666

Abstract

Rivers are the main sources of freshwater supply for the world population. However, many economic activities contribute to river water pollution. River water quality can be monitored using various parameters, such as the pH level, dissolved oxygen, total suspended solids, and the chemical [...] Read more.

Rivers are the main sources of freshwater supply for the world population. However, many economic activities contribute to river water pollution. River water quality can be monitored using various parameters, such as the pH level, dissolved oxygen, total suspended solids, and the chemical properties. Analyzing the trend and pattern of these parameters enables the prediction of the water quality so that proactive measures can be made by relevant authorities to prevent water pollution and predict the effectiveness of water restoration measures. Machine learning regression algorithms can be applied for this purpose. Here, eight machine learning regression techniques, including decision tree regression, linear regression, ridge, Lasso, support vector regression, random forest regression, extra tree regression, and the artificial neural network, are applied for the purpose of water quality index prediction. Historical data from Indian rivers are adopted for this study. The data refer to six water parameters. Twelve other features are then derived from the original six parameters. The performances of the models using different algorithms and sets of features are compared. The derived water quality rating scale features are identified to contribute toward the development of better regression models, while the linear regression and ridge offer the best performance. The best mean square error achieved is 0 and the correlation coefficient is 1. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

17 pages, 3383 KiB

Open AccessArticle

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

by Bahare Andayeshgar, Fardin Abdali-Mohammadi, Majid Sepahvand, Alireza Daneshkhah, Afshin Almasi and Nader Salari

Int. J. Environ. Res. Public Health 2022, 19(17), 10707; https://doi.org/10.3390/ijerph191710707 - 28 Aug 2022

Cited by 8 | Viewed by 2880

Abstract

Cardiovascular diseases, like arrhythmia, as the leading causes of death in the world, can be automatically diagnosed using an electrocardiogram (ECG). The ECG-based diagnostic has notably resulted in reducing human errors. The main aim of this study is to increase the accuracy of [...] Read more.

Cardiovascular diseases, like arrhythmia, as the leading causes of death in the world, can be automatically diagnosed using an electrocardiogram (ECG). The ECG-based diagnostic has notably resulted in reducing human errors. The main aim of this study is to increase the accuracy of arrhythmia diagnosis and classify various types of arrhythmias in individuals (suffering from cardiovascular diseases) using a novel graph convolutional network (GCN) benefitting from mutual information (MI) indices extracted from the ECG leads. In this research, for the first time, the relationships of 12 ECG leads measured using MI as an adjacency matrix were illustrated by the developed GCN and included in the ECG-based diagnostic method. Cross-validation methods were applied to select both training and testing groups. The proposed methodology was validated in practice by applying it to the large ECG database, recently published by Chapman University. The GCN-MI structure with 15 layers was selected as the best model for the selected database, which illustrates a very high accuracy in classifying different types of rhythms. The classification indicators of sensitivity, precision, specificity, and accuracy for classifying heart rhythm type, using GCN-MI, were computed as 98.45%, 97.89%, 99.85%, and 99.71%, respectively. The results of the present study and its comparison with other studies showed that considering the MI index to measure the relationship between cardiac leads has led to the improvement of GCN performance for detecting and classifying the type of arrhythmias, in comparison to the existing methods. For example, the above classification indicators for the GCN with the identity adjacency matrix (or GCN-Id) were reported to be 68.24%, 72.83%, 95.24%, and 92.68%, respectively. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

17 pages, 4655 KiB

Open AccessArticle

Strategies for Imputation of High-Resolution Environmental Data in Clinical Randomized Controlled Trials

by Yohan Kim, Scott Kelly, Deepu Krishnan, Jay Falletta and Kerryn Wilmot

Int. J. Environ. Res. Public Health 2022, 19(3), 1307; https://doi.org/10.3390/ijerph19031307 - 24 Jan 2022

Cited by 2 | Viewed by 2526

Abstract

Time series data collected in clinical trials can have varying degrees of missingness, adding challenges during statistical analyses. An additional layer of complexity is introduced for missing data in randomized controlled trials (RCT), where researchers must remain blinded between intervention and control groups. [...] Read more.

Time series data collected in clinical trials can have varying degrees of missingness, adding challenges during statistical analyses. An additional layer of complexity is introduced for missing data in randomized controlled trials (RCT), where researchers must remain blinded between intervention and control groups. Such restriction severely limits the applicability of conventional imputation methods that would utilize other participants’ data for improved performance. This paper explores and compares various methods to impute high-resolution temperature logger data in RCT settings. In addition to the conventional non-parametric approaches, we propose a spline regression (SR) approach that captures the dynamics of indoor temperature by time of day that is unique to each participant. We investigate how the inclusion of external temperature and energy use can improve the model performance. Results show that SR imputation results in 16% smaller root mean squared error (RMSE) compared to conventional imputation methods, with the gap widening to 22% when more than half of data is missing. The SR method is particularly useful in cases where missingness occurs simultaneously for multiple participants, such as concurrent battery failures. We demonstrate how proper modelling of periodic dynamics can lead to significantly improved imputation performance, even with limited data. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

14 pages, 1305 KiB

Open AccessArticle

Chemical-Mediated Microbial Interactions Can Reduce the Effectiveness of Time-Series-Based Inference of Ecological Interaction Networks

by Kenta Suzuki, Masato S. Abe, Daiki Kumakura, Shinji Nakaoka, Fuki Fujiwara, Hirokuni Miyamoto, Teruno Nakaguma, Mashiro Okada, Kengo Sakurai, Shohei Shimizu, Hiroyoshi Iwata, Hiroshi Masuya, Naoto Nihei and Yasunori Ichihashi

Int. J. Environ. Res. Public Health 2022, 19(3), 1228; https://doi.org/10.3390/ijerph19031228 - 22 Jan 2022

Cited by 5 | Viewed by 3254

Abstract

Network-based assessments are important for disentangling complex microbial and microbial–host interactions and can provide the basis for microbial engineering. There is a growing recognition that chemical-mediated interactions are important for the coexistence of microbial species. However, so far, the methods used to infer [...] Read more.

Network-based assessments are important for disentangling complex microbial and microbial–host interactions and can provide the basis for microbial engineering. There is a growing recognition that chemical-mediated interactions are important for the coexistence of microbial species. However, so far, the methods used to infer microbial interactions have been validated with models assuming direct species-species interactions, such as generalized Lotka–Volterra models. Therefore, it is unclear how effective existing approaches are in detecting chemical-mediated interactions. In this paper, we used time series of simulated microbial dynamics to benchmark five major/state-of-the-art methods. We found that only two methods (CCM and LIMITS) were capable of detecting interactions. While LIMITS performed better than CCM, it was less robust to the presence of chemical-mediated interactions, and the presence of trophic competition was essential for the interactions to be detectable. We show that the existence of chemical-mediated interactions among microbial species poses a new challenge to overcome for the development of a network-based understanding of microbiomes and their interactions with hosts and the environment. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

20 pages, 1838 KiB

Open AccessArticle

Examining Type 1 Diabetes Mathematical Models Using Experimental Data

by Hannah Al Ali, Alireza Daneshkhah, Abdesslam Boutayeb and Zindoga Mukandavire

Int. J. Environ. Res. Public Health 2022, 19(2), 737; https://doi.org/10.3390/ijerph19020737 - 10 Jan 2022

Cited by 11 | Viewed by 3945

Abstract

Type 1 diabetes requires treatment with insulin injections and monitoring glucose levels in affected individuals. We explored the utility of two mathematical models in predicting glucose concentration levels in type 1 diabetic mice and determined disease pathways. We adapted two mathematical models, one [...] Read more.

Type 1 diabetes requires treatment with insulin injections and monitoring glucose levels in affected individuals. We explored the utility of two mathematical models in predicting glucose concentration levels in type 1 diabetic mice and determined disease pathways. We adapted two mathematical models, one with

β

-cells and the other with no

β

-cell component to determine their capability in predicting glucose concentration and determine type 1 diabetes pathways using published glucose concentration data for four groups of experimental mice. The groups of mice were numbered Mice Group 1–4, depending on the diabetes severity of each group, with severity increasing from group 1–4. A Markov Chain Monte Carlo method based on a Bayesian framework was used to fit the model to determine the best model structure. Akaike information criteria (AIC) and Bayesian information criteria (BIC) approaches were used to assess the best model structure for type 1 diabetes. In fitting the model with no

β

-cells to glucose level data, we varied insulin absorption rate and insulin clearance rate. However, the model with

β

-cells required more parameters to match the data and we fitted the

β

-cell glucose tolerance factor, whole body insulin clearance rate, glucose production rate, and glucose clearance rate. Fitting the models to the blood glucose concentration level gave the least difference in AIC of

1.2

, and a difference in BIC of

0.12

for Mice Group 4. The estimated AIC and BIC values were highest for Mice Group 1 than all other mice groups. The models gave substantial differences in AIC and BIC values for Mice Groups 1–3 ranging from

2.10

to

4.05

. Our results suggest that the model without

β

-cells provides a more suitable structure for modelling type 1 diabetes and predicting blood glucose concentration for hypoglycaemic episodes. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Graphical abstract

16 pages, 4563 KiB

Open AccessArticle

Disease Progression Detection via Deep Sequence Learning of Successive Radiographic Scans

by Jamil Ahmad, Abdul Khader Jilani Saudagar, Khalid Mahmood Malik, Waseem Ahmad, Muhammad Badruddin Khan, Mozaherul Hoque Abul Hasanat, Abdullah AlTameem, Mohammed AlKhathami and Muhammad Sajjad

Int. J. Environ. Res. Public Health 2022, 19(1), 480; https://doi.org/10.3390/ijerph19010480 - 2 Jan 2022

Cited by 8 | Viewed by 2327

Abstract

The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a [...] Read more.

The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a rapid and accurate triage system, monitor progression, and predict patients at higher risk of deterioration in order to make informed decisions regarding hospital resource management. Disease detection in radiographic scans, severity estimation, and progression and prognosis prediction have been extensively studied with the help of end-to-end methods based on deep learning. The majority of recent works have utilized a single scan to determine severity or predict progression of the disease. In this paper, we present a method based on deep sequence learning to predict improvement or deterioration in successive chest X-ray scans and build a mathematical model to determine individual patient disease progression profile using successive scans. A deep convolutional neural network pretrained on a diverse lung disease dataset was used as a feature extractor to generate the sequences. We devised three strategies for sequence modeling in order to obtain both fine-grained and coarse-grained features and construct sequences of different lengths. We also devised a strategy to quantify positive or negative change in successive scans, which was then combined with age-related risk factors to construct disease progression profile for COVID-19 patients. The age-related risk factors allowed us to model rapid deterioration and slower recovery in older patients. Experiments conducted on two large datasets showed that the proposed method could accurately predict disease progression. With the best feature extractor, the proposed method was able to achieve AUC of 0.98 with the features obtained from radiographs. Furthermore, the proposed patient profiling method accurately estimated the health profile of patients. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

19 pages, 41417 KiB

Open AccessArticle

Scientometric Analysis of Disaster Risk Perception: 2000–2020

by Tianlong Yu, Hao Yang, Xiaowei Luo, Yifeng Jiang, Xiang Wu and Jingqi Gao

Int. J. Environ. Res. Public Health 2021, 18(24), 13003; https://doi.org/10.3390/ijerph182413003 - 9 Dec 2021

Cited by 8 | Viewed by 4140

Abstract

This paper used 1526 works from the literature on disaster risk perception from 2000 to 2020 in the Web of Science core collection database as the research subject. The CiteSpace knowledge graph analysis tool was used to visual analyze the country, author, institution, [...] Read more.

This paper used 1526 works from the literature on disaster risk perception from 2000 to 2020 in the Web of Science core collection database as the research subject. The CiteSpace knowledge graph analysis tool was used to visual analyze the country, author, institution, discipline distribution, keywords, and keyword clustering mapping. The paper drew the following conclusions. Firstly, disaster risk perception research has experienced three stages of steady development, undulating growth, and rapid growth. Secondly, the field of disaster risk perception was mainly concentrated in the disciplines of engineering, natural science, and management science. Thirdly, meteorological disasters, earthquakes, nuclear radiation, and epidemics were the main disasters in the field of disaster risk perception. Residents and adolescents were the main subjects of research in the field of disaster risk perception. Fourthly, research on human risk behavior and risk psychology and research on disaster risk control and emergency management were two major research hotspots in the field of disaster risk perception. Finally, the research field of disaster risk perception is constantly expanding. There is a trend from theory to application and multi-perspective combination, and future research on disaster risk perception will be presented more systematically. The conclusion can provide a reference for disaster risk perception research, as well as directions for future research. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

9 pages, 329 KiB

Open AccessArticle

Validation of an Arabic Version of the Self-Efficacy for Appropriate Medication Use Scale

by Hawazin Alhazzani, Ghaida AlAmmari, Nouf AlRajhi, Ibrahim Sales, Amr Jamal, Turky H. Almigbal, Mohammed A. Batais, Yousif A. Asiri and Yazed AlRuthia

Int. J. Environ. Res. Public Health 2021, 18(22), 11983; https://doi.org/10.3390/ijerph182211983 - 15 Nov 2021

Cited by 7 | Viewed by 2804

Abstract

Background: Medication adherence is essential for optimal treatment outcomes in patients with chronic diseases. Medication nonadherence compromises patient clinical outcomes and patient safety as well as leading to an increase in unnecessary direct and indirect medical costs. Therefore, early identification of non-adherence by [...] Read more.

Background: Medication adherence is essential for optimal treatment outcomes in patients with chronic diseases. Medication nonadherence compromises patient clinical outcomes and patient safety as well as leading to an increase in unnecessary direct and indirect medical costs. Therefore, early identification of non-adherence by healthcare professionals using medication adherence scales should help in preventing poor clinical outcomes among patients with chronic health conditions, such as diabetes and hypertension. Unfortunately, there are very few validated medication adherence assessment scales in Arabic. Thus, the aim of this study was to validate a newly translated Arabic version of the Self-Efficacy for Appropriate Medication Use Scale (SEAMS) among patients with chronic diseases. Methods: In this single-center cross-sectional study that was conducted between March 2019 and March 2021 at the primary care clinics of King Saud University Medical City (KSUMC) in Riyadh, Saudi Arabia, the English version of SEAMS was translated to Arabic using the forward–backward method and piloted among 22 adults (≥18 yrs.) with chronic diseases. The reliability of the newly translated scale was examined using the test–retest and Cronbach’s alpha methods. Exploratory and confirmatory factor analyses were conducted to examine the construct validity of the Arabic version of SEAMS. Results: The number of patients who consented to participate and filled out the questionnaire was 202. Most of the participants were males (69.9%), aged ≥50 years (65.2%), and had diabetes (96.53%). The 13-item Arabic-translated SEAMS mean score was 32.37 ± 5.31, and the scale showed acceptable internal consistency (Cronbach’s alpha = 0.886) and reliability (Intraclass correlation coefficient = 0.98). Total variance of the 13-item Arabic-SEAMS could be explained by two factors as confirmed by the factor analysis. Conclusion: The Arabic version of SEAMS should help in detecting poor self-efficacy for medication adherence among Arabic-speaking patient populations with chronic diseases, such as diabetes and hypertension. Future studies should examine its validity among more diverse patient populations in different Arabic-speaking countries. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

16 pages, 1277 KiB

Open AccessArticle

Driver, Collision and Meteorological Characteristics of Motor Vehicle Collisions among Road Trauma Survivors

by Melita J. Giummarra, Rongbin Xu, Yuming Guo, Joanna F. Dipnall, Jennie Ponsford, Peter A. Cameron, Shanthi Ameratunga and Belinda J. Gabbe

Int. J. Environ. Res. Public Health 2021, 18(21), 11380; https://doi.org/10.3390/ijerph182111380 - 29 Oct 2021

Cited by 2 | Viewed by 2422

Abstract

Road trauma remains a significant public health problem. We aimed to identify sub-groups of motor vehicle collisions in Victoria, Australia, and the association between collision characteristics and outcomes up to 24 months post-injury. Data were extracted from the Victorian State Trauma Registry for [...] Read more.

Road trauma remains a significant public health problem. We aimed to identify sub-groups of motor vehicle collisions in Victoria, Australia, and the association between collision characteristics and outcomes up to 24 months post-injury. Data were extracted from the Victorian State Trauma Registry for injured drivers aged ≥16 years, from 2010 to 2016, with a compensation claim who survived ≥12 months post-injury. People with intentional or severe head injury were excluded, resulting in 2735 cases. Latent class analysis was used to identify collision classes for driver fault and blood alcohol concentration (BAC), day and time of collision, weather conditions, single vs. multi-vehicle and regional vs. metropolitan injury location. Five classes were identified: (1) daytime multi-vehicle collisions, no other at fault; (2) daytime single-vehicle predominantly weekday collisions; (3) evening single-vehicle collisions, no other at fault, 36% with BAC ≥ 0.05; (4) sunrise or sunset weekday collisions; and (5) dusk and evening multi-vehicle in metropolitan areas with BAC < 0.05. Mixed linear and logistic regression analyses examined associations between collision class and return to work, health (EQ-5D-3L summary score) and independent function Glasgow Outcome Scale - Extended at 6, 12 and 24 months. After adjusting for demographic, health and injury characteristics, collision class was not associated with outcomes. Rather, risk of poor outcomes was associated with age, sex and socioeconomic disadvantage, education, pre-injury health and injury severity. People at risk of poor recovery may be identified from factors available during the hospital admission and may benefit from clinical assessment and targeted referrals and treatments. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

14 pages, 1698 KiB

Open AccessArticle

COVID-Transformer: Interpretable COVID-19 Detection Using Vision Transformer for Healthcare

by Debaditya Shome, T. Kar, Sachi Nandan Mohanty, Prayag Tiwari, Khan Muhammad, Abdullah AlTameem, Yazhou Zhang and Abdul Khader Jilani Saudagar

Int. J. Environ. Res. Public Health 2021, 18(21), 11086; https://doi.org/10.3390/ijerph182111086 - 21 Oct 2021

Cited by 89 | Viewed by 6200

Abstract

In the recent pandemic, accurate and rapid testing of patients remained a critical task in the diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of the sudden increase in cases, most countries have faced scarcity and a low rate [...] Read more.

In the recent pandemic, accurate and rapid testing of patients remained a critical task in the diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of the sudden increase in cases, most countries have faced scarcity and a low rate of testing. Chest X-rays have been shown in the literature to be a potential source of testing for COVID-19 patients, but manually checking X-ray reports is time-consuming and error-prone. Considering these limitations and the advancements in data science, we proposed a Vision Transformer-based deep learning pipeline for COVID-19 detection from chest X-ray-based imaging. Due to the lack of large data sets, we collected data from three open-source data sets of chest X-ray images and aggregated them to form a 30 K image data set, which is the largest publicly available collection of chest X-ray images in this domain to our knowledge. Our proposed transformer model effectively differentiates COVID-19 from normal chest X-rays with an accuracy of 98% along with an AUC score of 99% in the binary classification task. It distinguishes COVID-19, normal, and pneumonia patient’s X-rays with an accuracy of 92% and AUC score of 98% in the Multi-class classification task. For evaluation on our data set, we fine-tuned some of the widely used models in literature, namely, EfficientNetB0, InceptionV3, Resnet50, MobileNetV3, Xception, and DenseNet-121, as baselines. Our proposed transformer model outperformed them in terms of all metrics. In addition, a Grad-CAM based visualization is created which makes our approach interpretable by radiologists and can be used to monitor the progression of the disease in the affected lungs, assisting healthcare. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

9 pages, 337 KiB

Open AccessArticle

Item Analysis of the Czech Version of the WJ IV COG Battery from a Group of Romani Children

by Alena Kajanová, Tomáš Urbánek, Tomáš Mrhálek, Stanislav Ondrášek, Olga Shivairová and Jan Hynek

Int. J. Environ. Res. Public Health 2021, 18(19), 10518; https://doi.org/10.3390/ijerph181910518 - 7 Oct 2021

Viewed by 1817

Abstract

The objective of the article is to present an item analysis of selected subtests of the Czech version of the WJ IV COG battery from a group of Romani children, ages 7–11. The research sample consisted of 400 school-aged Romani children from the [...] Read more.

The objective of the article is to present an item analysis of selected subtests of the Czech version of the WJ IV COG battery from a group of Romani children, ages 7–11. The research sample consisted of 400 school-aged Romani children from the Czech Republic who were selected by quota sampling. A partial comparative sample for the analysis was the Czech population collected as norms of the Czech edition of © Propsyco (n = 936). The Woodcock–Johnson IV COG was used as a research tool. Statistical analysis was performed in Winstep software using Differential Item Functioning; differences between groups were expressed in logits and tested via the Rasch–Welch T-test. It was discovered that higher item difficulty was noted in the verbal subtests, although variability in item difficulty was found across all subtests. The analysis of individual items makes it possible to discover which tasks are most culturally influenced. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

14 pages, 926 KiB

Open AccessArticle

Modeling SF-6D Health Utilities: Is Bayesian Approach Appropriate?

by Samer A. Kharroubi

Int. J. Environ. Res. Public Health 2021, 18(16), 8409; https://doi.org/10.3390/ijerph18168409 - 9 Aug 2021

Cited by 4 | Viewed by 2125

Abstract

Background: Valuation studies of preference-based health measures like SF6D have been conducted in many countries. However, the cost of conducting such studies in countries with small populations or low- and middle-income countries (LMICs) can be prohibitive. There is potential to use results from [...] Read more.

Background: Valuation studies of preference-based health measures like SF6D have been conducted in many countries. However, the cost of conducting such studies in countries with small populations or low- and middle-income countries (LMICs) can be prohibitive. There is potential to use results from readily available countries’ valuations to produce better valuation estimates. Methods: Data from Lebanon and UK SF-6D value sets were analyzed, where values for 49 and 249 health states were extracted from samples of Lebanon and UK populations, respectively, using standard gamble techniques. A nonparametric Bayesian model was used to estimate a Lebanon value set using the UK data as informative priors. The resulting estimates were then compared to a Lebanon value set obtained using Lebanon data by itself via various prediction criterions. Results: The findings permit the UK evidence to contribute potential prior information to the Lebanon analysis by producing more precise valuation estimates than analyzing Lebanon data only under all criterions used. Conclusions: The positive findings suggest that existing valuation studies can be merged with a small valuation set in another country to produce value sets, thereby making own country value sets more attainable for LMICs. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

16 pages, 491 KiB

Open AccessFeature PaperArticle

Economic Evaluation of Mental Health Effects of Flooding Using Bayesian Networks

by Tabassom Sedighi, Liz Varga, Amin Hosseinian-Far and Alireza Daneshkhah

Int. J. Environ. Res. Public Health 2021, 18(14), 7467; https://doi.org/10.3390/ijerph18147467 - 13 Jul 2021

Cited by 4 | Viewed by 3501

Abstract

The appraisal of appropriate levels of investment for devising flooding mitigation and to support recovery interventions is a complex and challenging task. Evaluation must account for social, political, environmental and other conditions, such as flood state expectations and local priorities. The evaluation method [...] Read more.

The appraisal of appropriate levels of investment for devising flooding mitigation and to support recovery interventions is a complex and challenging task. Evaluation must account for social, political, environmental and other conditions, such as flood state expectations and local priorities. The evaluation method should be able to quickly identify evolving investment needs as the incidence and magnitude of flood events continue to grow. Quantification is essential and must consider multiple direct and indirect effects on flood related outcomes. The method proposed is this study is a Bayesian network, which may be used ex-post for evaluation, but also ex-ante for future assessment, and near real-time for the reallocation of investment into interventions. The particular case we study is the effect of flood interventions upon mental health, which is a gap in current investment analyses. Natural events such as floods expose people to negative mental health disorders including anxiety, distress and post-traumatic stress disorder. Such outcomes can be mitigated or exacerbated not only by state funded interventions, but by individual and community skills and experience. Success is also dampened when vulnerable and previously exposed victims are affected. Current measures evaluate solely the effectiveness of interventions to reduce physical damage to people and assets. This paper contributes a design for a Bayesian network that exposes causal pathways and conditional probabilities between interventions and mental health outcomes as well as providing a tool that can readily indicate the level of investment needed in alternative interventions based on desired mental health outcomes. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

14 pages, 3465 KiB

Open AccessArticle

Systemic Lupus Erythematosus Research: A Bibliometric Analysis over a 50-Year Period

by Malcolm Koo

Int. J. Environ. Res. Public Health 2021, 18(13), 7095; https://doi.org/10.3390/ijerph18137095 - 2 Jul 2021

Cited by 54 | Viewed by 5174

Abstract

Bibliometric analysis is a well-established approach to quantitatively assess scholarly productivity. However, there have been few assessments of research productivity on systemic lupus erythematosus (SLE) to date. The aim of this study was to analyze global research productivity through original articles published in [...] Read more.

Bibliometric analysis is a well-established approach to quantitatively assess scholarly productivity. However, there have been few assessments of research productivity on systemic lupus erythematosus (SLE) to date. The aim of this study was to analyze global research productivity through original articles published in journals indexed by the Web of Science from 1971 to 2020. Bibliometric data was obtained from the Science Citation Index Expanded in the Web of Science Core Collection database. Only original articles published between 1971 and 2020 on SLE were included in the analysis. Over the 50-year period, publication production in SLE research has steadily increased with a mean annual growth rate of 8.0%. A total of 44,967 articles published in 3435 different journals were identified. The journal Lupus published the largest number of articles (n = 3371; 8.0%). A total of 148 countries and regions contributed to the articles. The global productivity ranking was led by the United States (n = 11,244, 25.0%), followed by China (n = 4893, 10.9%). A three-field plot showed that the Oklahoma Medical Research Foundation and the Johns Hopkins University together contributed 18.5% of all articles from the United States. A co-occurrence network analysis revealed five highly connected clusters of SLE research. In conclusion, this bibliometric analysis provided a comprehensive overview of the status of SLE research, which could enable a better understanding of the development in this field in the past 50 years. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

22 pages, 2629 KiB

Open AccessArticle

Using Machine Learning Algorithms to Develop a Clinical Decision-Making Tool for COVID-19 Inpatients

by Abhinav Vepa, Amer Saleem, Kambiz Rakhshan, Alireza Daneshkhah, Tabassom Sedighi, Shamarina Shohaimi, Amr Omar, Nader Salari, Omid Chatrabgoun, Diana Dharmaraj, Junaid Sami, Shital Parekh, Mohamed Ibrahim, Mohammed Raza, Poonam Kapila and Prithwiraj Chakrabarti

Int. J. Environ. Res. Public Health 2021, 18(12), 6228; https://doi.org/10.3390/ijerph18126228 - 9 Jun 2021

Cited by 18 | Viewed by 5974

Abstract

Background: Within the UK, COVID-19 has contributed towards over 103,000 deaths. Although multiple risk factors for COVID-19 have been identified, using this data to improve clinical care has proven challenging. The main aim of this study is to develop a reliable, multivariable predictive [...] Read more.

Background: Within the UK, COVID-19 has contributed towards over 103,000 deaths. Although multiple risk factors for COVID-19 have been identified, using this data to improve clinical care has proven challenging. The main aim of this study is to develop a reliable, multivariable predictive model for COVID-19 in-patient outcomes, thus enabling risk-stratification and earlier clinical decision-making. Methods: Anonymised data consisting of 44 independent predictor variables from 355 adults diagnosed with COVID-19, at a UK hospital, was manually extracted from electronic patient records for retrospective, case–control analysis. Primary outcomes included inpatient mortality, required ventilatory support, and duration of inpatient treatment. Pulmonary embolism sequala was the only secondary outcome. After balancing data, key variables were feature selected for each outcome using random forests. Predictive models were then learned and constructed using Bayesian networks. Results: The proposed probabilistic models were able to predict, using feature selected risk factors, the probability of the mentioned outcomes. Overall, our findings demonstrate reliable, multivariable, quantitative predictive models for four outcomes, which utilise readily available clinical information for COVID-19 adult inpatients. Further research is required to externally validate our models and demonstrate their utility as risk stratification and clinical decision-making tools. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

19 pages, 4028 KiB

Open AccessArticle

Bibliometric Evaluation of Global Tai Chi Research from 1980–2020

by Yanwei You, Leizi Min, Meihua Tang, Yuquan Chen and Xindong Ma

Int. J. Environ. Res. Public Health 2021, 18(11), 6150; https://doi.org/10.3390/ijerph18116150 - 7 Jun 2021

Cited by 29 | Viewed by 6717

Abstract

While studies on the health benefits of Tai Chi have sprung up over the past four decades, few have engaged in collecting global data, estimating the developing trends, and conducting reviews from the perspective of visualization and bibliometric analysis. This study aimed to [...] Read more.

While studies on the health benefits of Tai Chi have sprung up over the past four decades, few have engaged in collecting global data, estimating the developing trends, and conducting reviews from the perspective of visualization and bibliometric analysis. This study aimed to provide a summary of the global scientific outputs on Tai Chi research from 1980 to 2020, explore the frontiers, identify cooperation networks, track research trends and highlight emerging hotspots. Relevant publications were downloaded from the Web of Science Core Collection (WoSCC) database between 1980 and 2020. Bibliometric visualization and comparative analysis of authors, cited authors, journals, co-cited journals, institutions, countries, references, and keywords were systematically conducted using CiteSpace software. A total of 1078 publications satisfied the search criteria, and the trend of annual related publications was generally in an upward trend, although with some fluctuations. China (503) and Harvard University (74) were the most prolific country and institution, respectively. Most of the related researches were published in the journals with a focus on sport sciences, alternative medicine, geriatrics gerontology, and rehabilitation. Our results indicated that the current concerns and difficulties of Tai Chi research are “Intervention method”, “Targeted therapy”, “Applicable population”, “Risk factors”, and “Research quality”. The frontiers and promising domains of Tai Chi exercise in the health science field are preventions and rehabilitations of “Fall risk”, “Cardiorespiratory related disease”, “Stroke”, “Parkinson’s disease”, and “Depression”, which should receive more attention in the future. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Graphical abstract

24 pages, 1538 KiB

Open AccessArticle

Evaluating the Bovine Tuberculosis Eradication Mechanism and Its Risk Factors in England’s Cattle Farms

by Tabassom Sedighi and Liz Varga

Int. J. Environ. Res. Public Health 2021, 18(7), 3451; https://doi.org/10.3390/ijerph18073451 - 26 Mar 2021

Cited by 6 | Viewed by 3102

Abstract

Controlling bovine tuberculosis (bTB) disease in cattle farms in England is seen as a challenge for farmers, animal health, environment and policy-makers. The difficulty in diagnosis and controlling bTB comes from a variety of factors: the lack of an accurate diagnostic test which [...] Read more.

Controlling bovine tuberculosis (bTB) disease in cattle farms in England is seen as a challenge for farmers, animal health, environment and policy-makers. The difficulty in diagnosis and controlling bTB comes from a variety of factors: the lack of an accurate diagnostic test which is higher in specificity than the currently available skin test; isolation periods for purchased cattle; and the density of active badgers, especially in high-risk areas. In this paper, to enable the complex evaluation of bTB disease, a dynamic Bayesian network (DBN) is designed with the help of domain experts and available historical data. A significant advantage of this approach is that it represents bTB as a dynamic process that evolves periodically, capturing the actual experience of testing and infection over time. Moreover, the model demonstrates the influence of particular risk factors upon the risk of bTB breakdown in cattle farms. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Graphical abstract

Review

Jump to: Research, Other

20 pages, 2950 KiB

Open AccessReview

Methodological Issues in Analyzing Real-World Longitudinal Occupational Health Data: A Useful Guide to Approaching the Topic

by Rémi Colin-Chevalier, Frédéric Dutheil, Sébastien Cambier, Samuel Dewavrin, Thomas Cornet, Julien Steven Baker and Bruno Pereira

Int. J. Environ. Res. Public Health 2022, 19(12), 7023; https://doi.org/10.3390/ijerph19127023 - 8 Jun 2022

Cited by 4 | Viewed by 2864

Abstract

Ever greater technological advances and democratization of digital tools such as computers and smartphones offer researchers new possibilities to collect large amounts of health data in order to conduct clinical research. Such data, called real-world data, appears to be a perfect complement to [...] Read more.

Ever greater technological advances and democratization of digital tools such as computers and smartphones offer researchers new possibilities to collect large amounts of health data in order to conduct clinical research. Such data, called real-world data, appears to be a perfect complement to traditional randomized clinical trials and has become more important in health decisions. Due to its longitudinal nature, real-world data is subject to specific and well-known methodological issues, namely issues with the analysis of cluster-correlated data, missing data and longitudinal data itself. These concepts have been widely discussed in the literature and many methods and solutions have been proposed to cope with these issues. As examples, mixed and trajectory models have been developed to explore longitudinal data sets, imputation methods can resolve missing data issues, and multilevel models facilitate the treatment of cluster-correlated data. Nevertheless, the analysis of real-world longitudinal occupational health data remains difficult, especially when the methodological challenges overlap. The purpose of this article is to present various solutions developed in the literature to deal with cluster-correlated data, missing data and longitudinal data, sometimes overlapped, in an occupational health context. The novelty and usefulness of our approach is supported by a step-by-step search strategy and an example from the Wittyfit database, which is an epidemiological database of occupational health data. Therefore, we hope that this article will facilitate the work of researchers in the field and improve the accuracy of future studies. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

Other

Jump to: Research, Review

16 pages, 2487 KiB

Open AccessCommentary

Catalyzing Knowledge-Driven Discovery in Environmental Health Sciences through a Community-Driven Harmonized Language

by Stephanie D. Holmgren, Rebecca R. Boyles, Ryan D. Cronk, Christopher G. Duncan, Richard K. Kwok, Ruth M. Lunn, Kimberly C. Osborn, Anne E. Thessen and Charles P. Schmitt

Int. J. Environ. Res. Public Health 2021, 18(17), 8985; https://doi.org/10.3390/ijerph18178985 - 26 Aug 2021

Cited by 9 | Viewed by 2757

Abstract

Harmonized language is critical for helping researchers to find data, collecting scientific data to facilitate comparison, and performing pooled and meta-analyses. Using standard terms to link data to knowledge systems facilitates knowledge-driven analysis, allows for the use of biomedical knowledge bases for scientific [...] Read more.

Harmonized language is critical for helping researchers to find data, collecting scientific data to facilitate comparison, and performing pooled and meta-analyses. Using standard terms to link data to knowledge systems facilitates knowledge-driven analysis, allows for the use of biomedical knowledge bases for scientific interpretation and hypothesis generation, and increasingly supports artificial intelligence (AI) and machine learning. Due to the breadth of environmental health sciences (EHS) research and the continuous evolution in scientific methods, the gaps in standard terminologies, vocabularies, ontologies, and related tools hamper the capabilities to address large-scale, complex EHS research questions that require the integration of disparate data and knowledge sources. The results of prior workshops to advance a harmonized environmental health language demonstrate that future efforts should be sustained and grounded in scientific need. We describe a community initiative whose mission was to advance integrative environmental health sciences research via the development and adoption of a harmonized language. The products, outcomes, and recommendations developed and endorsed by this community are expected to enhance data collection and management efforts for NIEHS and the EHS community, making data more findable and interoperable. This initiative will provide a community of practice space to exchange information and expertise, be a coordination hub for identifying and prioritizing activities, and a collaboration platform for the development and adoption of semantic solutions. We encourage anyone interested in advancing this mission to engage in this community. Full article

(This article belongs to the Special Issue Data Science for Environment and Health Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Data Science for Environment and Health Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (24 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI