Conectar
by Xie Qiu, Shuo Hu, Shumin Dong, Haijun Sun
ObjectiveTo develop a predictive framework integrating machine learning and clinical parameters for postoperative pulmonary complications (PPCs) in non-small cell lung cancer (NSCLC) patients undergoing video-assisted thoracic surgery (VATS).
MethodsThis retrospective study analyzed 286 NSCLC patients (2022–2024), incorporating 13 demographic, metabolic-inflammatory, and surgical variables. An Improved Blood-Sucking Leech Optimizer (IBSLO) enhanced via Cubic mapping and opposition-based learning was developed. Model performance was evaluated using AUC-ROC, F1-score, and decision curve analysis (DCA). SHAP interpretation identified key predictors.
ResultsThe IBSLO demonstrated significantly superior convergence performance versus original BSLO, ant lion optimizer (ALO), Harris hawks optimization (HHO), and whale optimization algorithm (WOA) across all 12 CEC2022 test functions. Subsequently, the IBSLO-optimized automated machine learning (AutoML) model achieved ROC-AUC/PR-AUC values of 0.9038/0.8091 (training set) and 0.8775/0.8175 (testing set), significantly outperforming four baseline models: logistic regression (LR), support vector machine (SVM), XGBoost, and LightGBM. SHAP interpretability identified six key predictors: preoperative leukocyte count, body mass index (BMI), surgical approach, age, intraoperative blood loss, and C-reactive protein (CRP). Decision curve analysis demonstrated significantly higher net clinical benefit of the AutoML model compared to conventional methods across expanded threshold probability ranges (training set: 8–99%; testing set: 3–80%).
ConclusionThis study establishes an interpretable machine learning framework that improves preoperative risk stratification for NSCLC patients, offering actionable guidance for thoracic oncology practice.
Identifying the core information needs of breast cancer radiotherapy patients serves as the foundation for delivering targeted information services. The Kano model, a qualitative tool for classifying service needs, is increasingly being employed to prioritise patient needs and enhance healthcare quality.
This study aims to examine the informational needs of breast cancer patients undergoing radiotherapy using the Kano model as the analytical framework.
Between October 2024 and February 2025, 260 patients with breast cancer undergoing radiotherapy were recruited as study participants. A cross-sectional survey was conducted using the Information Needs Questionnaire. Kano analysis was applied to identify and assess the information needs of these patients. This study adhered to the STROBE guidelines.
Among the 36 items analysed, 15 items (41.7%) were classified as one-dimensional attributes, primarily related to adverse reaction identification and self-management information. 11 items (30.5%) were identified as attractive attributes, mainly concerning the impact of radiation therapy and social–emotional needs five items (13.9%) were must-be attributes, focusing on basic radiotherapy information. Five items (13.9%) were indifference attributes, including the impact of radiotherapy on breast reconstruction, and guidance on image-related concerns during radiotherapy. The quadrant chart findings revealed that 15 needs were predominant in Area I, five in Improving Area II, five in Secondary Improving Area III and 11 in Reserving Area IV.
The information needs of breast cancer radiotherapy patients are diverse. Kano model analysis aids medical staff in developing health guidance and meeting patients' informational needs.
Understanding the differentiated informational needs of patients with breast cancer undergoing radiotherapy provides valuable insights for developing targeted educational interventions, ultimately improving patient engagement and outcomes.
The contributions of patients/members of the public were limited solely to data collection.
The efficacy of radiotherapy and the satisfaction of patients can be significantly improved by adequately addressing their information needs. This process is impeded by the current lack of a comprehensive tool for assessing these needs.
To develop an Information Needs Questionnaire for patients with breast cancer undergoing radiotherapy and to assess its reliability and validity.
The initial item pool for the questionnaire was developed through a literature analysis and semi-structured interviews with 12 patients with breast cancer receiving radiotherapy. The Delphi method was employed to consult 16 experts and the questionnaire content was refined based on expert feedback and item ratings to form the first draft. A pre-investigation was conducted on 30 patients with breast cancer treated with radiotherapy to refine the item expression. From March–October 2024, item analysis, factor analyses, and reliability tests were conducted on 220 patients. This study adhered to STROBE guidelines.
The final questionnaire comprised 36 items. Exploratory factor analysis revealed 5 dimensions, with all item factor loading within their respective dimensions being ≥ 0.4 and no items exhibiting multiple loadings. These five factors accounted for 72.805% of the total variance. The overall content validity index was 0.980, with item-level content validity index ranging from 0.900 to 1.000. The Cronbach's α coefficient for the entire questionnaire was 0.959, and the coefficients for each dimension ranged from 0.786 to 0.958.
The Information Needs Questionnaire demonstrated excellent reliability and validity in patients with breast cancer undergoing radiotherapy. It can effectively guide medical staff to accurately assess the information needs of patients with breast cancer who are undergoing radiotherapy.
Identifying the authentic informational needs of breast cancer patients throughout the entire radiotherapy process is instrumental in enabling medical staff to devise personalised and targeted information support interventions.
A total of 220 participants provided perspectives on their information needs.
A meta-analysis was conducted to evaluate the impact of transconjunctival sutureless vitrectomy (TSV) over 20 G vitrectomy on wound healing, as well as the requirements for closing the wound in order to treat vitreoretinal diseases. Among the 500 cases who had been treated with vitrectomy to September 2023, 250 were treated by transconjunctiva without vitrectomy and 250 were treated with 20 G vitrectomy. The odds ratio (OR) and mean difference (MD) of 95% confidence interval (CI) were computed to evaluate the influence of wound opening and closing on vitrectomy diseases. The evaluation of vitreoretinal diseases was performed with either a random-or fixed-effect model, which involved TSV compared to 20 G vitrectomy. Compared to 20 G vitrectomy, the opening time of the wound in TSV was less (MD, −2.03; 95% CI, −2.87, −1.19; p < 0.0001); Compared to 20 G vitrectomy, the closing time of the wound was less (MD, −4.84; 95% CI, −6.38, −3.03; p < 0.0001); Nevertheless, there were no statistically significant differences in the incidence of vitreous haemorrhage after TSV surgery compared with 20 G vitrectomy (OR, 0.74; 95% CI, 0.25, 2.18; p = 0.59). TSV vitrectomy can shorten the duration of the operation and speed up the healing of the wound. It is suggested that additional studies be carried out with a larger sample size in order to verify this conclusion.
FreshRSS 