Conectar
by Yang Guo, Shuai Jiang, Wei Zhu, Longwang Tan, Chuang Liu, Yongjun Jia, Chi Zhang, Kok-Yong Chin
BackgroundMachine learning (ML) shows promise in using clinical data to predict chronic diseases. However, its application in PMOP risk assessment using readily available clinical and biochemical parameters is underexplored.
ObjectiveThis study aimed to develop and validate an interpretable ML-based model for assessing PMOP using clinical features and laboratory biomarkers, and to identify factors associated with PMOP using SHapley Additive exPlanations (SHAP).
MethodsA retrospective cross-sectional study included 1,717 postmenopausal women from two hospitals in Northwest China. PMOP was diagnosed with dual-energy X-ray absorptiometry (DXA T-score ≤−2.5). Data collected included demographics, clinical details, and various laboratory parameters, such as bone metabolism markers, 25-hydroxyvitamin D [25-(OH)D], electrolytes, and routine blood counts. Ten ML algorithms were employed for feature selection and model construction on a dataset split into training (n = 1201) and testing (n = 516) sets. Performance was evaluated using the Area Under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and calibration.
ResultsThe Extra Trees (ET) model achieved the best test-set performance, with an AUC of 0.717 (95% CI: 0.682–0.752). SHAP analysis revealed that age was the most significant associated factor (SHAP value: 0.0648), followed by body mass index (BMI) (0.0243) and chloride ion levels (0.0209). Other top predictors included the use of antihypertensive drugs and years since menopause.
ConclusionThe ET ML algorithm showed the best performance in assessing PMOP, with age, BMI, and circulating chloride levels as significant associated factors.
Smart home technology, as an emerging innovation, holds significant potential to support proactive health by enabling accurate prediction and intelligent warning of health issues. This study aims to explore older adults' perceptions of adopting smart home technology to promote proactive health.
An exploratory qualitative study.
Focus groups and one-on-one interviews were held with 20 older adults recruited from a retirement activity center, a nursing home, and the geriatrics department of a tertiary hospital in China between June and October 2024. The interview transcripts were analysed using thematic analysis and further examined through the framework of the Technology Acceptance Model.
The analysis identified four themes: (1) The need for care is the primary determinant for older adults' consideration of adopting smart home technology. When care is needed, factors such as self-care ability, care from children and the caregiving capabilities of smart home technology play a crucial role in their decision-making process. (2) Older adults expect smart home technology to deliver essential healthcare services, including health monitoring and counselling, emergency assistance and emotional support. (3) Individual differences, interplay with life experiences, significantly influence older adults' willingness to adopt smart home technology. (4) The perceived effectiveness of technology, age-friendly design, potential technical malfunctions and privacy concerns are also critical factors affecting adoption decisions. All themes were also matched to perceived usefulness, perceived ease of use and attitude in the Technology Acceptance Model.
This study provides valuable insights into older adults' perspectives on adopting smart home technology and serves as a reference for its development in geriatric health management. To enhance the applicability of these technologies, nurses should collaborate with developers, integrating their expertise in elderly care and daily living needs.
The findings offer guidance for advancing smart home technology to better address the health needs of older adults. By integrating these technologies into practice, nurses can more effectively respond to the unique health conditions of older adults, optimise nursing workflows and enhance the overall quality of care. Ultimately, this ensures that older adults remain the primary beneficiaries of technological advancements in healthcare.
The study adhered to the Consolidated Criteria for Reporting Qualitative Research guidelines.
Limited patient and public involvement was incorporated, focusing on feedback on data analysis.
To identify the barriers and enablers in the implementation of evidence-based physical activity (PA) programmes for the improvement of health outcomes among pregnant women with gestational diabetes mellitus (GDM), and to develop strategies for implementing this evidence in clinical practice.
A convergent mixed-methods study was conducted, integrating a descriptive qualitative research design with a cross-sectional survey. In-depth interview was used to collect the views and cognitions about physical activity from medical staff, leaders and pregnant women. The qualitative data was analysed using directed content analysis, guided by the Ottaw Model of Research Use (OMRU). A self-designed questionnaire, which was based on the current best evidence for physical activity during pregnancy, was administered to gather data regarding nurse’ knowledge of physical activity (PA safety, managing blood glucose with PA, etc.), their management practice (timing of assessments, provision of information, etc.), as well as the knowledge levels of physical activity among pregnant women with GDM (principles of exercise, PA precautions, etc.).
A total of 12 medical staff members and 14 pregnant women were interviewed. Ten nurses and 102 pregnant women with GDM completed the questionnaire. We generated 12 subthemes organised within three themes of the OMRU from the data, including insufficient professional autonomy, positive attitudes towards evidence implementation, shortage of nursing staff, implementation climate, etc. The average knowledge score of physical activity among nurses and pregnant women was 5 (SD 2.36) points and 5.2 (SD 1.70) points, respectively. Ten strategies for overcoming barriers and amplifying enablers for the implementation of the physical activity improvement programme for pregnant women with GDM, under the guidance of the OMRU were constructed.
An accumulation of evidence, adopters and practice environment factors across the OMRU domains explains why physical activity improvement initiatives for pregnant women with GDM are hard to implement.
This study helps to recognise barriers and facilitators to physical activity improvement particularly at the evidence, potential adopter and practical environment level.
Healthcare workers (doctors, nurses, etc.) and pregnant women with GDM in a university hospital located in Sichuan Province.
FreshRSS 