Critical Retrospection of Performance of Emerging Mobile Technologies in Health Data Management

The new normal of remote work: exploring individual and organizational factors affecting work-related outcomes and well-being in academia

Background

Flexible work arrangements have become increasingly popular, driven by the widespread adoption of digital technologies in the workplace because of the pandemic. However, there is a scarcity of studies concerning remote work, especially related to technical-administrative staff (TAS) in academia. Therefore, the current study, adopting the Job Demands-Resources model, aimed to investigate the relationships between remote working self-efficacy, organizational support, techno-complexity, mental well-being, and job performance among TAS during remote working.

Methods

A total of 373 individuals from TAS of a large Italian university participated in this study by completing a self-report questionnaire.

Results

The findings showed positive and significant relationships between remote self-efficacy and job satisfaction as well as between such a perceived efficacy and mental well-being. Perceived support from supervisors acted as a protective factor against techno-complexity. In contrast, perceived support from colleagues emerged as able to promote well-being and job satisfaction. In addition, the latter was positively associated with well-being. Finally, individual job performance was positively affected by job satisfaction and negatively by techno-complexity.

Conclusion

This study highlights the need for interventions to support TAS in remote working environments by leveraging employees' self-efficacy as a key factor in reducing stress related to new technologies as well as enhancing well-being, job satisfaction, and, in turn, their performance.

Machine learning based model for detecting depression during Covid-19 crisis

Covid-19 has impacted negatively on people all over the world. Some of the ways that it has affected people include such as Health, Employment, Mental Health, Education, Social isolation, Economic Inequality and Access to healthcare and essential services. Apart from physical symptoms, it has caused considerable damage to mental health of individuals. Among all, depression is identified as one of the common illnesses which leads to early death. People suffering from depression are at a higher risk of developing other health conditions, such as heart disease and stroke, and are also at a higher risk of suicide. The importance of early detection and intervention of depression cannot be overstated. Identifying and treating depression early can prevent the illness from becoming more severe and can also prevent the development of other health conditions. Early detection can also prevent suicide, which is a leading cause of death among people with depression. Millions of people have affected from this disease. To proceed with the study of depression detection among individuals we have conducted a survey with 21 questions based on Hamilton tool and advise of psychiatrist. With the use of Python's scientific programming principles and machine learning methods like Decision Tree, KNN, and Naive Bayes, survey results were analysed. Further a comparison of these techniques is done. Study concludes that KNN has given better results than other techniques based on the accuracy and decision tree has given better results in the terms of latency to detect the depression of a person. At the conclusion, a machine learning-based model is suggested to replace the conventional method of detecting sadness by asking people encouraging questions and getting regular feedback from them.

Retracted: Critical Retrospection of Performance of Emerging Mobile Technologies in Health Data Management

[This retracts the article DOI: 10.1155/2022/8903604.].

Monitoring Cardiovascular Problems in Heart Patients Using Machine Learning

The World Health Organization reports that heart disease is the most common cause of death globally, accounting for 17.9 million fatalities annually. The fundamentals of a cure, it is thought, are important symptoms and recognition of the illness. Traditional techniques are facing many challenges, ranging from delayed or unnecessary treatment to incorrect diagnoses, which can affect treatment progress, increase the bill, and give the disease more time to spread and harm the patient's body. Such errors could be avoided and minimized by employing ML and AI techniques. Many significant efforts have been made in recent years to increase computer-aided diagnosis and detection applications, which is a rapidly growing area of research. Machine learning algorithms are especially important in CAD, which is used to detect patterns in medical data sources and make nontrivial predictions to assist doctors and clinicians in making timely decisions. This study aims to develop multiple methods for machine learning using the UCI set of data based on individuals' medical attributes to aid in the early detection of cardiovascular disease. Various machine learning techniques are used to evaluate and review the results of the UCI machine learning heart disease dataset. The proposed algorithms had the highest accuracy, with the random forest classifier achieving 96.72% and the extreme gradient boost achieving 95.08%. This will assist the doctor in taking appropriate actions. The proposed technology will only be able to determine whether or not a person has a heart issue. The severity of heart disease cannot be determined using this method.

MaD GUI: An Open-Source Python Package for Annotation and Analysis of Time-Series Data

Developing machine learning algorithms for time-series data often requires manual annotation of the data. To do so, graphical user interfaces (GUIs) are an important component. Existing Python packages for annotation and analysis of time-series data have been developed without addressing adaptability, usability, and user experience. Therefore, we developed a generic open-source Python package focusing on adaptability, usability, and user experience. The developed package, Machine Learning and Data Analytics (MaD) GUI, enables developers to rapidly create a GUI for their specific use case. Furthermore, MaD GUI enables domain experts without programming knowledge to annotate time-series data and apply algorithms to it. We conducted a small-scale study with participants from three international universities to test the adaptability of MaD GUI by developers and to test the user interface by clinicians as representatives of domain experts. MaD GUI saves up to 75% of time in contrast to using a state-of-the-art package. In line with this, subjective ratings regarding usability and user experience show that MaD GUI is preferred over a state-of-the-art package by developers and clinicians. MaD GUI reduces the effort of developers in creating GUIs for time-series analysis and offers similar usability and user experience for clinicians as a state-of-the-art package.

A latent profile analysis of residents' knowledge, attitude, and practice toward common chronic diseases among ethnic minority area in China

Background

Health literacy plays an important role in preventing and managing chronic diseases, while low levels of health literacy among ethnic minorities are a major manifestation of health inequities. We believe that before effective health literacy intervention strategies, it is preferable to understand the features of health literacy among ethnic minorities. The present study firstly updated insights on health literacy among ethnic minorities by investigating the knowledge, attitude, and practice (KAP) profile of common chronic diseases in ethnic minority areas, and secondly discussed the KAP profiles in detail to inspire future health education interventions.

Methods

A cross-sectional, health-literacy-sensitive study was conducted in China's typical ethnic minority area. Participants included 801 adult residents who lived in the ethnic minority area. The primary outcome was participant scores on the KAP questionnaire of common chronic diseases, followed by latent profile analysis to identify participants with similar KAP score patterns and determine whether membership in specific groups was associated with demographic or clinical characteristics.

Results

The participants included 496 ethnic minorities (61.9%) and 305 Han Chinese (38.1%). Three-profile solution was determined after the latent profile analysis: incomplete transfer [I.T.] (n = 215), better practice [B.P.] (n = 301), and average [A.V.] (n = 285). IT group (26.84%) was characterized by the highest level of knowledge and attitude toward common chronic diseases and below average level for practice. Participants in B.P. group performed poorly in both knowledge and attitude toward common chronic diseases but had the highest level of practice. A.V. group reflected average knowledge, attitude, and practice toward common chronic diseases among three subgroups. Ethnic minorities were the dominant population in A.V. group (68.8%). Compared with other groups, the A.V. group contained the largest proportions of married participants (84.2%), participants with no formal education (46.7%), and high annual out-of-pocket medical expense (33.3%).

Conclusion

A more specific and nuanced understanding of minority health literacy can enable service providers to provide more effective health education to their recipients, thereby improving health inequities.