Nevin ManimalaStud Health Technol Inform. 2025 May 15;327:1447-1448. doi: 10.3233/SHTI250643.
ABSTRACT
This paper explores and analyzes a high-frequency vital sign- and event dataset from surgical ward patients to prepare for the training and application of predictive models.
PMID:40380746 | DOI:10.3233/SHTI250643
Stud Health Technol Inform. 2025 May 15;327:1413-1417. doi: 10.3233/SHTI250635.
ABSTRACT
Depression is one of the most prevalent mental health illnesses and a significant public health concern in Saudi Arabia. Due to misconceptions about mental health diseases, such as depression, in Saudi Arabia, there is widespread stigma. Many people with depression, therefore, seek health information via social media such as blogs, microblogs, and online communities. Online mental health communities (OMHCs) have been developed only recently in the country. This study explores the challenges people experience when engaging in OMHCs. A sample of 1,422 posts was generated from two OMHCs and analyzed using inductive thematic analysis. Three main themes were identified: misinformation, triggering vulnerability, and judgment. Findings from this study will be shared with the OMHCs and will help administrators to develop strategies and policies to enhance the experience of people with depression in using OMHCs.
PMID:40380738 | DOI:10.3233/SHTI250635
Stud Health Technol Inform. 2025 May 15;327:1403-1407. doi: 10.3233/SHTI250633.
ABSTRACT
In this study, we attempted to identify the subtypes of autism spectrum disorder (ASD) with the help of anatomical alterations found in structural magnetic resonance imaging (sMRI) data of the ASD brain and machine learning tools. Initially, the sMRI data was preprocessed using the FreeSurfer toolbox. Further, the brain regions were segmented into 148 regions of interest using the Destrieux atlas. Features such as volume, thickness, surface area, and mean curvature were extracted for each brain region. We performed principal component analysis independently on the volume, thickness, surface area, and mean curvature features and identified the top 10 features. Further, we applied k-means clustering on these top 10 features and validated the number of clusters using Elbow and Silhouette method. Our study identified two clusters in the dataset which significantly shows the existence of two subtypes in ASD. We identified the features such as volume of scaled lh_G_front middle, thickness of scaled rh_S_temporal transverse, area of scaled lh_S_temporal sup, and mean curvature of scaled lh_G_precentral as the significant features discriminating the two clusters with statistically significant p-value (p<0.05). Thus, our proposed method is effective for the identification of ASD subtypes and can also be useful for the screening of other similar neurological disorders.
PMID:40380736 | DOI:10.3233/SHTI250633
Stud Health Technol Inform. 2025 May 15;327:1353-1357. doi: 10.3233/SHTI250623.
ABSTRACT
As pressure to increase operational efficiency in clinical trials grows, organizations are looking to advances such as tools enabling extraction of Electronic Health Record (EHR) data and transmission to the study database or electronic Case Report Form (eCRF). As interest and adoption of these tools, often called EHR-to-eCRF software, grows in clinical research, consistent evaluative data on key outcomes, such as data accuracy, remains limited. This study compared the accuracy of data collected from EHRs using EHR-to-eCRF technology to traditional methods of clinical trial data collection. The accuracy of the EHR-extracted data was significantly higher than that of data collected through the traditional approach. These results suggest that EHR-based data collection could substantially enhance data quality in clinical trials.
PMID:40380726 | DOI:10.3233/SHTI250623
Stud Health Technol Inform. 2025 May 15;327:1338-1342. doi: 10.3233/SHTI250620.
ABSTRACT
Implementing Electronic Medical Records (EMRs) is a key advancement in modern healthcare. These systems aim to improve operational efficiency, patient care, and staff satisfaction. However, their implementation often faces challenges that affect workflows, especially in high-pressure environments like emergency rooms (ERs). This paper presents a comprehensive evaluation of an EMR system implemented at Niguarda Hospital’s ER, focusing on its impact on documentation efficiency, staff satisfaction, and overall operational performance. We employed a combination of time-based metrics and qualitative staff feedback to capture both the quantitative and human factors influencing the adoption of the system. Our findings indicate significant improvements in documentation times, patient flow, and staff workflow following the adoption of Dedalus’ EMR system. However, initial challenges, such as resistance to change and system integration issues, were also observed.
PMID:40380723 | DOI:10.3233/SHTI250620
Stud Health Technol Inform. 2025 May 15;327:1318-1322. doi: 10.3233/SHTI250616.
ABSTRACT
In implementing the new Electronic Health Record (EHR) Epic working practices change for clinicians in mental health care and their use of an Electronic Medication Management System (EMMS). In this case study two main aspects affecting their work practices were found. The new EMMS led to the work being more time-consuming, but it was also experienced as safer.
PMID:40380719 | DOI:10.3233/SHTI250616
Stud Health Technol Inform. 2025 May 15;327:1313-1317. doi: 10.3233/SHTI250615.
ABSTRACT
Monitoring the end-user experiences of electronic health records (EHR) and client information systems (CIS) in Finland enables data driven decision-making. This study focuses on a single individual-level indicator and identifies a predictive model that can help apply these modeling results in practice. The findings suggest that themes related to this indicator – specifically, the good grade given to the primary system’s (EHR/CIS) – are related to the functionality, usability, and support for nursing documentation within the primary system. Moreover, the information systems (IS) landscape, it’s potential to support carrying out duties and exchanging information, and benefits of IS, were crucial. IS benefits are usually linked to factors such as continuity of care, avoid duplicate tests, and medication safety. Improving all these themes could improve circumstances where end-users could achieve better performance in the care of the patients.
PMID:40380718 | DOI:10.3233/SHTI250615
Stud Health Technol Inform. 2025 May 15;327:1308-1312. doi: 10.3233/SHTI250614.
ABSTRACT
The mapping from the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) to the 11th Revision (ICD-11), initiated by the World Health Organization (WHO), presents a challenge for healthcare systems, most of which currently rely on extensive ICD-10 coded data for billing purposes. This paper introduces a methodology to generate a FHIR (Fast Healthcare Interoperability Resources) ConceptMap from the WHO-provided ICD-10 to ICD-11 mapping tables. The resulting ConceptMap allows healthcare organizations to automate the mapping process, facilitating the integration of ICD-11. The final ConceptMap includes ICD-11 mappings for 12,952 ICD-10 codes. This approach prepares healthcare systems for the transition to ICD-11.
PMID:40380717 | DOI:10.3233/SHTI250614
Stud Health Technol Inform. 2025 May 15;327:1305-1306. doi: 10.3233/SHTI250612.
ABSTRACT
This study explores how well large language models (like the kind that powers ChatGPT) can analyze online conversations about disability rights. We specifically looked at whether these models could: 1) identify if tweets about people with disabilities were positive or negative, and 2) tell if the tweets viewed disability as a problem with society (social model) or a problem with the individual (medical model). We collected 5,000 tweets and trained a language model to analyze them. The results demonstrated promising accuracy levels for sentiment analysis and social vs. medical model classification.
PMID:40380716 | DOI:10.3233/SHTI250612
Stud Health Technol Inform. 2025 May 15;327:1301-1302. doi: 10.3233/SHTI250610.
ABSTRACT
Assessing healthcare professionals’ (HCPs’) perceptions on the appropriateness, ease of use and reliability of connected digital health technologies can help to understand acceptance and their recommendations to patients/caregivers for personalization of growth hormone (GH) therapy. Two study cases representing different versions of a digital device were used to facilitate expert panel discussions in the UK and France involving 19 paediatric HCPs. Panel members commented that the new functionalities embodied user-friendly technological progression. The evolution of the easypod device should sustain clinical decision support and enhance personalized approaches to care and management of patients receiving GH therapy.
PMID:40380714 | DOI:10.3233/SHTI250610