Exploration of Digital Health Technologies

Special Issue Topic

Data-informed Decision Making in Healthcare

Submission Deadline: November 30, 2024

Guest Editor

Sil Aarts E-Mail

Assistant professor, Living Lab in Ageing and Long-term Care, Department of Health Services Research, Care and Public Health Research Institute (CAPHRI), Maastricht University, Maastricht, Netherlands.

Research Keywords: quality of care; nursing home science; technology in healthcare; data; statistics; R(stats); qualitative research

About the Special Issue

Data is invaluable to health care: the availability of increasing amounts of data offer new possibilities to support personalized health care. Healthcare organisation collect large amounts of data at client, employee and organizational level: data in electronic health records or data collected by digital techniques such as sensors or wearables, but also qualitative data in the form of texts collected in, for example, multidisciplinary consultations. Hence, care organisations collect a wealth of data, and thus information. This data can be used to support shared decision making, and thus in turn, improve quality of care for clients or patients or quality of work for employees. The present Special Issue responds to the remarkable change in the focus of the use of data in healthcare, where the use of data to make informed and shared decisions in care becomes vital. This Special Issue is focused on publishing highest quality papers in areas associated to data, data science and data-informed decision making in healthcare. Papers involving the use of data and/or data science methods with relevance to care, including care echelons such as long-term care or family medicine, will be considered for publication.

Keywords: data; data science; data-informed decision making; personalized health care

Call for Papers

Published Articles

Open Access

Original Article

Developing a multi-variate prediction model for COVID-19 from crowd-sourced respiratory voice data
Aim: COVID-19 has affected more than 223 countries worldwide and in the post-COVID era, there is a pressing need for non-invasive, low-cost, and highly scalable solutions to detect COVID-19. This [...] Read more.

Aim:

COVID-19 has affected more than 223 countries worldwide and in the post-COVID era, there is a pressing need for non-invasive, low-cost, and highly scalable solutions to detect COVID-19. This study focuses on the analysis of voice features and machine learning models in the automatic detection of COVID-19.

Methods:

We develop a deep learning model to identify COVID-19 from voice recording data. The novelty of this work is in the development of deep learning models for COVID-19 identification from only voice recordings. We use the Cambridge COVID-19 Sound database which contains 893 speech samples, crowd-sourced from 4,352 participants via a COVID-19 Sounds app. Voice features including Mel-spectrograms and Mel-frequency cepstral coefficients (MFCC) and convolutional neural network (CNN) Encoder features are extracted. Based on the voice data, we develop deep learning classification models to detect COVID-19 cases. These models include long short-term memory (LSTM), CNN and Hidden-Unit BERT (HuBERT).

Results:

We compare their predictive power to baseline machine learning models. HuBERT achieves the highest accuracy of 86% and the highest AUC of 0.93.

Conclusions:

The results achieved with the proposed models suggest promising results in COVID-19 diagnosis from voice recordings when compared to the results obtained from the state-of-the-art.

Yuyang Yan ... Visara Urovi

Published: August 11, 2024 Explor Digit Health Technol. 2024;2:202–217
DOI: https://doi.org/10.37349/edht.2024.00022

Full Text

PDF

View:1304

Download:106

Times Cited: 0

Aim:

COVID-19 has affected more than 223 countries worldwide and in the post-COVID era, there is a pressing need for non-invasive, low-cost, and highly scalable solutions to detect COVID-19. This study focuses on the analysis of voice features and machine learning models in the automatic detection of COVID-19.

Methods:

We develop a deep learning model to identify COVID-19 from voice recording data. The novelty of this work is in the development of deep learning models for COVID-19 identification from only voice recordings. We use the Cambridge COVID-19 Sound database which contains 893 speech samples, crowd-sourced from 4,352 participants via a COVID-19 Sounds app. Voice features including Mel-spectrograms and Mel-frequency cepstral coefficients (MFCC) and convolutional neural network (CNN) Encoder features are extracted. Based on the voice data, we develop deep learning classification models to detect COVID-19 cases. These models include long short-term memory (LSTM), CNN and Hidden-Unit BERT (HuBERT).

Results:

We compare their predictive power to baseline machine learning models. HuBERT achieves the highest accuracy of 86% and the highest AUC of 0.93.

Conclusions:

The results achieved with the proposed models suggest promising results in COVID-19 diagnosis from voice recordings when compared to the results obtained from the state-of-the-art.

Open Access

Review

Digital twin technology training and research in health higher education: a review
Healthcare strives to ensure overall physical, mental, and emotional well-being for individuals while managing limited resources efficiently. Digital technologies can offer cost reduction, improved [...] Read more.

Healthcare strives to ensure overall physical, mental, and emotional well-being for individuals while managing limited resources efficiently. Digital technologies can offer cost reduction, improved user experience, and expanded capacity. In addition, modern automation technologies, which were implemented in industrial control systems or industrial automation control systems, are essential for ensuring the availability of societies’ critical cyber-physical systems (CPSs) and the services they provide, such as healthcare. This narrative literature review produces information that can be applied when planning and implementing an interdisciplinary biomedical and health informatics (BMHI) master’s education focused on the challenges of digitalization in the health sector. The review results that virtual human twins (VHTs) are revolutionizing healthcare by addressing people’s complex medical problems with real-time monitoring and precision care while digital twin (DT) technology can make the hospital’s operational processes resilient and efficient. Thus, future BMHI education must address these technologies with a multidisciplinary approach, including computer science, information science, engineering, basic sciences, health sciences, socio-behavioral sciences, and ethical, legal, and policy aspects. Collected and cumulative data is essential for cognitive DTs. A prerequisite for this data is information sharing between different CPSs. Better information sharing and the development of scalable cognitive DTs and VHTs, the provision of critical services, quality, and cost-effectiveness, as well as health, safety, and resilience, will improve. Similarities between peoples’ health information exchange and information needed for ensuring the resilience of CPSs exist. Since humans are in many ways more complex than CPSs, security engineers have a lot to learn from VHTs in maintaining the resilience of CPSs. Cross-sectoral research and cooperation with different disciplines are essential for the progress of both human health and the resilience of CPSs. Along with interdisciplinary research cooperation, educational cooperation should also be intensified.

Jyri Rajamäki

Published: August 05, 2024 Explor Digit Health Technol. 2024;2:188–201
DOI: https://doi.org/10.37349/edht.2024.00021

Full Text

PDF

View:1530

Download:127

Times Cited: 0

Healthcare strives to ensure overall physical, mental, and emotional well-being for individuals while managing limited resources efficiently. Digital technologies can offer cost reduction, improved user experience, and expanded capacity. In addition, modern automation technologies, which were implemented in industrial control systems or industrial automation control systems, are essential for ensuring the availability of societies’ critical cyber-physical systems (CPSs) and the services they provide, such as healthcare. This narrative literature review produces information that can be applied when planning and implementing an interdisciplinary biomedical and health informatics (BMHI) master’s education focused on the challenges of digitalization in the health sector. The review results that virtual human twins (VHTs) are revolutionizing healthcare by addressing people’s complex medical problems with real-time monitoring and precision care while digital twin (DT) technology can make the hospital’s operational processes resilient and efficient. Thus, future BMHI education must address these technologies with a multidisciplinary approach, including computer science, information science, engineering, basic sciences, health sciences, socio-behavioral sciences, and ethical, legal, and policy aspects. Collected and cumulative data is essential for cognitive DTs. A prerequisite for this data is information sharing between different CPSs. Better information sharing and the development of scalable cognitive DTs and VHTs, the provision of critical services, quality, and cost-effectiveness, as well as health, safety, and resilience, will improve. Similarities between peoples’ health information exchange and information needed for ensuring the resilience of CPSs exist. Since humans are in many ways more complex than CPSs, security engineers have a lot to learn from VHTs in maintaining the resilience of CPSs. Cross-sectoral research and cooperation with different disciplines are essential for the progress of both human health and the resilience of CPSs. Along with interdisciplinary research cooperation, educational cooperation should also be intensified.

Open Access

Systematic Review

Do you need a blockchain in healthcare data sharing? A tertiary review
Background: This study addresses the complexities of utilizing blockchain technology in healthcare, aiming to provide a decision-making tool for healthcare professionals and policymakers evaluati [...] Read more.

Background:

This study addresses the complexities of utilizing blockchain technology in healthcare, aiming to provide a decision-making tool for healthcare professionals and policymakers evaluating blockchain’s suitability for healthcare data sharing applications.

Methods:

A tertiary review was conducted on existing systematic literature reviews concerning blockchain in the healthcare domain. Reviews that focused on data sharing were selected, and common key factors assessing blockchain’s suitability in healthcare were extracted.

Results:

Our review synthesized findings from 27 systematic literature reviews, which led to the development of a refined decision-making flowchart. This tool outlines criteria such as scalability, integrity/immutability, interoperability, transparency, patient involvement, cost, and public verifiability, essential for assessing the suitability of blockchain in healthcare data sharing. This flowchart was validated through multiple case studies from various healthcare domains, testing its utility in real-world scenarios.

Discussion:

Blockchain technology could significantly benefit healthcare data sharing, provided its application is carefully evaluated against tailored criteria for healthcare needs. The decision-making flowchart developed from this review offers a systematic approach to assist stakeholders in navigating the complexities of implementing blockchain technology in healthcare settings.

Kun Li ... Visara Urovi

Published: June 14, 2024 Explor Digit Health Technol. 2024;2:101–123
DOI: https://doi.org/10.37349/edht.2024.00014

Full Text

PDF

View:3404

Download:205

Times Cited: 0

Background:

This study addresses the complexities of utilizing blockchain technology in healthcare, aiming to provide a decision-making tool for healthcare professionals and policymakers evaluating blockchain’s suitability for healthcare data sharing applications.

Methods:

A tertiary review was conducted on existing systematic literature reviews concerning blockchain in the healthcare domain. Reviews that focused on data sharing were selected, and common key factors assessing blockchain’s suitability in healthcare were extracted.

Results:

Our review synthesized findings from 27 systematic literature reviews, which led to the development of a refined decision-making flowchart. This tool outlines criteria such as scalability, integrity/immutability, interoperability, transparency, patient involvement, cost, and public verifiability, essential for assessing the suitability of blockchain in healthcare data sharing. This flowchart was validated through multiple case studies from various healthcare domains, testing its utility in real-world scenarios.

Discussion:

Blockchain technology could significantly benefit healthcare data sharing, provided its application is carefully evaluated against tailored criteria for healthcare needs. The decision-making flowchart developed from this review offers a systematic approach to assist stakeholders in navigating the complexities of implementing blockchain technology in healthcare settings.

Open Access

Systematic Review

Data science techniques to gain novel insights into quality of care: a scoping review of long-term care for older adults
Background: The increase in powerful computers and technological devices as well as new forms of data analysis such as machine learning have resulted in the widespread availability of data scienc [...] Read more.

Background:

The increase in powerful computers and technological devices as well as new forms of data analysis such as machine learning have resulted in the widespread availability of data science in healthcare. However, its role in organizations providing long-term care (LTC) for older people LTC for older adults has yet to be systematically synthesized. This analysis provides a state-of-the-art overview of 1) data science techniques that are used with data accumulated in LTC and for what specific purposes and, 2) the results of these techniques in researching the study objectives at hand.

Methods:

A scoping review based on guidelines of the Joanna Briggs Institute. PubMed and Cumulative Index to Nursing and Allied Health Literature (CINAHL) were searched using keywords related to data science techniques and LTC. The screening and selection process was carried out by two authors and was not limited by any research design or publication date. A narrative synthesis was conducted based on the two aims.

Results:

The search strategy yielded 1,488 studies: 27 studies were included of which the majority were conducted in the US and in a nursing home setting. Text-mining/natural language processing (NLP) and support vector machines (SVMs) were the most deployed methods; accuracy was the most used metric. These techniques were primarily utilized for researching specific adverse outcomes including the identification of risk factors for falls and the prediction of frailty. All studies concluded that these techniques are valuable for their specific purposes.

Discussion:

This review reveals the limited use of data science techniques on data accumulated in or by LTC facilities. The low number of included articles in this review indicate the need for strategies aimed at the effective utilization of data with data science techniques and evidence of their practical benefits. There is a need for a wider adoption of these techniques in order to exploit data to their full potential and, consequently, improve the quality of care in LTC by making data-informed decisions.

Ard Hendriks ... Sil Aarts

Published: April 12, 2024 Explor Digit Health Technol. 2024;2:67–85
DOI: https://doi.org/10.37349/edht.2024.00012

Full Text

PDF

View:4419

Download:249

Times Cited: 0

Background:

The increase in powerful computers and technological devices as well as new forms of data analysis such as machine learning have resulted in the widespread availability of data science in healthcare. However, its role in organizations providing long-term care (LTC) for older people LTC for older adults has yet to be systematically synthesized. This analysis provides a state-of-the-art overview of 1) data science techniques that are used with data accumulated in LTC and for what specific purposes and, 2) the results of these techniques in researching the study objectives at hand.

Methods:

A scoping review based on guidelines of the Joanna Briggs Institute. PubMed and Cumulative Index to Nursing and Allied Health Literature (CINAHL) were searched using keywords related to data science techniques and LTC. The screening and selection process was carried out by two authors and was not limited by any research design or publication date. A narrative synthesis was conducted based on the two aims.

Results:

The search strategy yielded 1,488 studies: 27 studies were included of which the majority were conducted in the US and in a nursing home setting. Text-mining/natural language processing (NLP) and support vector machines (SVMs) were the most deployed methods; accuracy was the most used metric. These techniques were primarily utilized for researching specific adverse outcomes including the identification of risk factors for falls and the prediction of frailty. All studies concluded that these techniques are valuable for their specific purposes.

Discussion:

This review reveals the limited use of data science techniques on data accumulated in or by LTC facilities. The low number of included articles in this review indicate the need for strategies aimed at the effective utilization of data with data science techniques and evidence of their practical benefits. There is a need for a wider adoption of these techniques in order to exploit data to their full potential and, consequently, improve the quality of care in LTC by making data-informed decisions.

Open Access

Original Article

Use of responsible artificial intelligence to predict health insurance claims in the USA using machine learning algorithms
Aim: This study investigates the potential of artificial intelligence (AI) in revolutionizing healthcare insurance claim processing in the USA. It aims to determine the most effective machine lea [...] Read more.

Aim:

This study investigates the potential of artificial intelligence (AI) in revolutionizing healthcare insurance claim processing in the USA. It aims to determine the most effective machine learning (ML) model for predicting health insurance claims, leading to cost savings for insurance companies.

Methods:

Six ML algorithms were used to predict health insurance claims, and their performance was evaluated using various metrics. The algorithms examined include support vector machine (SVM), decision tree (DT), random forest (RF), linear regression (LR), extreme gradient boosting (XGBoost), and k-nearest neighbors (KNN). The research involves a performance assessment that encompasses key metrics. Additionally, a feature importance analysis is conducted to illuminate the critical variables that exert influence on the prediction of insurance claims.

Results:

The findings demonstrate that the XGBoost and RF models outperformed the other algorithms, displaying the highest R-squared values of 79% and 77% and the lowest prediction errors. The feature importance analysis underscores the pivotal role of variables such as smoking habits, body mass index (BMI), and blood pressure levels in the domain of insurance claim prediction. These results emphasize the degree to which these variables should be included in the formulation of insurance policies and pricing strategies.

Conclusions:

This study supports the transformative potential of AI, with specific emphasis on the XGBoost model, in extending the precision and efficiency of healthcare insurance claim processing. The identification of key variables and the mitigation of prediction errors not only signal the potential for substantial cost savings but also affirm the potential to integrate AI into healthcare insurance processes. This research supports the value of the utilization of AI as an emerging tool for process optimization and data-informed decision-making within the healthcare insurance domain.

Ashrafe Alam, Victor R. Prybutok

Published: February 28, 2024 Explor Digit Health Technol. 2024;2:30–45
DOI: https://doi.org/10.37349/edht.2024.00009

Full Text

PDF

View:6058

Download:343

Times Cited: 1

Aim:

This study investigates the potential of artificial intelligence (AI) in revolutionizing healthcare insurance claim processing in the USA. It aims to determine the most effective machine learning (ML) model for predicting health insurance claims, leading to cost savings for insurance companies.

Methods:

Six ML algorithms were used to predict health insurance claims, and their performance was evaluated using various metrics. The algorithms examined include support vector machine (SVM), decision tree (DT), random forest (RF), linear regression (LR), extreme gradient boosting (XGBoost), and k-nearest neighbors (KNN). The research involves a performance assessment that encompasses key metrics. Additionally, a feature importance analysis is conducted to illuminate the critical variables that exert influence on the prediction of insurance claims.

Results:

The findings demonstrate that the XGBoost and RF models outperformed the other algorithms, displaying the highest R-squared values of 79% and 77% and the lowest prediction errors. The feature importance analysis underscores the pivotal role of variables such as smoking habits, body mass index (BMI), and blood pressure levels in the domain of insurance claim prediction. These results emphasize the degree to which these variables should be included in the formulation of insurance policies and pricing strategies.

Conclusions:

This study supports the transformative potential of AI, with specific emphasis on the XGBoost model, in extending the precision and efficiency of healthcare insurance claim processing. The identification of key variables and the mitigation of prediction errors not only signal the potential for substantial cost savings but also affirm the potential to integrate AI into healthcare insurance processes. This research supports the value of the utilization of AI as an emerging tool for process optimization and data-informed decision-making within the healthcare insurance domain.

Guest Editor

About the Special Issue

Call for Papers

Published Articles

Aim:

Methods:

Results:

Conclusions:

Aim:

Methods:

Results:

Conclusions:

Background:

Methods:

Results:

Discussion:

Background:

Methods:

Results:

Discussion:

Background:

Methods:

Results:

Discussion:

Background:

Methods:

Results:

Discussion:

Aim:

Methods:

Results:

Conclusions:

Aim:

Methods:

Results:

Conclusions: