Studies in health technology and informatics最新文献

This study presents a Decision Support System to predict epidemic trends in Greece using Open-Source software and machine learning algorithms. The system uses data from OurWorldData.org on COVID-19 from early 2020 to December 2022. We assess the accuracy of five forecasting algorithms: Linear Regression, Back Propagation (BP), Long Short-Term Memory (LSTM), ARIMA, and Prophet. By evaluating correlation, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), we identify the ARIMA model as the most effective for this context. Comparative analysis highlights the system's predictive reliability in Greek COVID-19 trends and suggests implications for broader epidemic forecasting applications.

Elderly people are suffering with aging-related health problems. This research aimed to study the factors affecting the quality of life (QoL) of dependent older adults. The study was applied to develop the long-term care model for dependent elderly 495 people in Sisongkhram District, Nakhon Phanom Province, Thailand during the COVID-19 Pandemic. As mixed methods research was selected participants of dependent elderly individuals from March 2020 to September 2022. Data were collected through a self-administered questionnaire. The stepwise multiple linear regression analyses and an independent sample t-test were used for the data analyses. The results showed variables that could predict factors affecting the QoL of their group. These factors were positively correlated, with a statistical significance at p-value < 0.05. The predictive coefficient was 64.9% such as the long-term care model for dependent elderly people self-care model was found to be an effective intervention for the QoL of elderly people. This model enhanced the QoL of elderly people by and drive activities by the primary health care process according to the UCCARE principles to enable all sectors to participate in helping and caring for the elderly who are dependent, resulting in a better quality of life.

Testicular cancer (TC) is a relatively rare but highly treatable malignancy that originates in the germ cells of the testicles. It primarily affects young men, particularly those between the ages of 15 and 35, though it can occur at any age. The most common histological subtypes are seminoma and non-seminomatous germ cell tumors (NSGCTs), the latter including embryonal carcinoma, yolk sac tumor, choriocarcinoma, and teratoma. The length of hospital stay (LOS) following surgery is a crucial indicator of clinical outcomes and resource utilization. This study examines the length of stay (LOS) after testicles cancer surgery at the Antonio Cardarelli Hospital in Naples, Italy, using a statistical learning technique. It builds on previous studies on the causes of extended hospital stays in surgical oncology. The main findings provide a chance to enhance patient care and quality by illustrating how the clinical and organizational aspects of the surgical technique impact hospital stays.

Neurovascular networks ensure the care of stroke patients in rural areas and guarantee medical care. Nursing staff and therapists working in the networks require appropriate knowledge of stroke care. Qualitative expert interviews and a quantitative survey using an online questionnaire were carried out to ascertain the requirements of nursing and therapy. The results of the five expert surveys and the perspective of the 72 respondents from the therapy field revealed a need for learning and openness towards interactive digital training in both groups.

This study looks at the available measurement tools of the quality impact of electronic systems and new technologies of e-government to the public health sector. The procedure for gathering data for this study includes the collection of existing information, theories, and best practices linked to electronic systems and innovative technologies in e-government. The results highlight that we have several approaches of measurement of attributes and quality of provided e-services with various indicators, tools for public trust and satisfaction but we don't have real estimation of the total quality impact for the users and also there is lack of the cost benefit analysis of e-government services.

Lung cancer remains a leading cause of cancer-related deaths globally, with non-small cell lung cancer (NSCLC) accounting for 85% of cases. Traditional methods for assessing the clinical status of cancer patients, such as Performance Status (PS), are subjective and may lack consistency across clinicians. Lung cancer remains a leading cause of cancer-related mortality worldwide. Monitoring the physical activity and PS of patients undergoing treatment is crucial for tailored therapeutic interventions. The LUPA study is a non-interventional, two-phase observational study aimed at assessing the usability of wearable devices and a mobile application for monitoring activity, sleep quality, and symptoms in lung cancer patients. A mixed-methods approach was used in Phase I to assess usability and data utility, while Phase II involved a one-group observational clinical study with 61 patients to explore correlations between clinician-reported PS and data collected through wearables. The results suggest moderate correlations between wearable data and ECOG-PS scores, but challenges remain in applying machine learning (ML) models to predict changes in patient condition. Future work should address model refinement, increased sample size, and the incorporation of additional features from wearable devices to enhance predictive accuracy.

This study examines dialysis nurses' perspectives on the use of continuous glucose monitoring (CGM) in hemodialysis (HD) patients with insulin-treated diabetes. Through eight semi-structured interviews, nurses highlighted how CGM improved the patients' and nurses' ability to monitor patients' glucose levels, enhancing patient engagement and nursing practices. The nurses emphasized the value of real-time glucose data during dialysis sessions, allowing for timely adjustments and better glycemic control. Despite these advantages, they also noted challenges, including a lack of knowledge regarding CGM technology. Overall, the nurses viewed CGM as a beneficial tool, providing a clearer understanding of patients' glucose patterns. Furthermore, the findings reveal that CGM fosters better communication and awareness among healthcare professionals and patients, ultimately improving the care provided to insulin-treated HD patients.

This short communication presents preliminary findings on the integration of Large Language Models (LLMs) and wearable technology to generate personalized recommendations aimed at enhancing student well-being and academic performance. By analyzing diverse student data profiles, including metrics from wearable devices and qualitative feedback from academic reports, we conducted sentiment analysis to assess students' emotional states. The results indicate that LLMs can effectively process and analyze textual data, providing actionable insights into student engagement and areas needing improvement. This approach demonstrates the potential of LLMs in educational settings, offering a more nuanced understanding of student needs compared to traditional methods.

The increasing integration of digital tools in healthcare has the potential to improve patient outcomes, yet often leads to frustration among users. This study explores the root causes of healthcare professionals' frustrations with technologies in hospitals. Secondary analysis of qualitative interviews with 52 clinicians in Switzerland revealed recurring challenges with digital tools, particularly clinical information systems, that are related to performance, usability, and data accessibility. These issues disrupt clinical workflows, compromise patient care, and can affect the well-being of clinicians. Addressing these issues through collaborative efforts could improve system design, reduce frustration, and enhance healthcare delivery.

Enhancing the secondary use of data from routine care through external data enrichment methods can significantly boost its quality. This paper demonstrates a process-driven prototyping approach that separates sensitive and non-sensitive data, empowering medical experts to map medical concepts in free text to standardized terminology codes, all while granting data protection and information security. This approach is based on a prototype-oriented framework developed through discussions in a focus group. It consists of four integral components: (A) Clinical Data Repository, (B) Transition Database, (C) Mapping Tools and (D) Validation Tools. Data flows between the components contain medical concepts in free text and structured lists of suggested or validated standard codes. They are operated with the help of extract, transform and load processes as well as workflow management tools. By utilizing the components along the process, quality-assured medical concepts and their mapping can be provided for the secondary use of routine patient data for research.