Enhancing hospice care with psychological support and a nomogram to predict delirium in patients with advanced solid tumors.

To assesses the impact of integrating hospice care with psychological interventions on patient well-being and to introduce a predictive nomogram model for delirium that incorporates clinical and psychosocial variables, thereby improving the accuracy in hospice care environments. Data from 381 patients treated from September 2018 to February 2023 were analyzed. The patients were divided into a control group (n=177, receiving standard care) and an experimental group (n=204, receiving combined hospice care and psychological interventions) according to the treatment modality. The duration of care extended until the patient's discharge from the hospital or death. The experimental group demonstrated significant improvements in emotional well-being and a lower incidence of delirium compared to the control group. Specifically, emotional well-being assessments revealed marked improvements in the experimental group, as evidenced by lower scores on the Self-Rating Anxiety Scale (SAS) and Self-Rating Depression Scale (SDS) post-intervention. The nomogram model, developed using logistic regression based on clinical characteristics, effectively predicted the risk of delirium in patients with advanced cancer. Significant predictors in the model included ECOG score ≥3, Palliative Prognostic Index score ≥6, opioid usage, polypharmacy, infections, sleep disorders, organ failure, brain metastases, electrolyte imbalances, activity limitations, pre-care SAS score ≥60, pre-care SDS score ≥63, and pre-care KPS score ≥60. The model's predictive accuracy was validated, showing AUC values of 0.839 for the training cohort and 0.864 for the validation cohort, with calibration and Decision Curve Analysis (DCA) confirming its clinical utility. Integrating hospice care with psychological interventions not only significantly enhanced the emotional well-being of advanced cancer patients but also reduced the actual incidence of delirium. This approach, offering a valuable Nomogram model for precise care planning and risk management, underscores the importance of integrated, personalized care strategies in advanced cancer management.

Use of artificial intelligence to recover mandibular morphology after disease.

Mandibular tumors and radical oral cancer surgery often cause bone dysmorphia and defects. Most patients present with noticeable mandibular deformations, and doctors often have difficulty determining their exact mandibular morphology. In this study, a deep convolutional generative adversarial network (DCGAN) called CTGAN is proposed to complete 3D mandibular cone beam computed tomography data from CT data. After extensive training, CTGAN was tested on 6 mandibular tumor cases, resulting in 3D virtual mandibular completion. We found that CTGAN can generate mandibles with different levels and rich morphology, including positional and angular changes and local patterns. The completion results are shown as tomographic images combining generated and natural areas. The 3D generated mandibles have the anatomical morphology of the real mandibles and transition smoothly to the portions without disease, showing that CTGAN constructs mandibles with the expected patient characteristics and is suitable for mandibular morphological completion. The presented modeling principles can be applied to other areas for 3D morphological completion from medical images.Clinical trial registration: This study is not a clinical trial. Patient data were only used for testing in a virtual environment. The use of the digital data used in this study was ethically approved.

In Vitro Experimental Study of the Effect of Adjusting the Guide Sleeve Height and Using a Visual Direction-Indicating Guide on Implantation Accuracy.

PURPOSE: We used a single-variable method to analyze the influence of the guide sleeve height of a conventional template on implantation accuracy in vitro and improve the function of short-sleeve templates by adding a visual direction-indicating guide (VDING). MATERIALS AND METHODS: We created 100 copies of a volunteer's dentition plaster model. The normal template (NT) and the VDING template (VT) were made with guide sleeves 2, 5, 8, and 10 mm in height. Additionally, a freehand (FH) group and a group with an FH-based visual guide were used. Simulated implantation in an emulated head model was performed in each group. After surgery, cone-beam computed tomography images of the plaster were used for registration, and the accuracy was compared among the groups. RESULTS: When the NT sleeve height was 5 mm or less, increased deviation was found, and the results for some of the accuracy indicators were not different from those in the FH group. The accuracy of sleeves 5 mm or less in height was better in the VT group than in the NT or FH group. CONCLUSIONS: Use of the NT with a guide sleeve height of 5 mm or less can introduce large deviations in implantation, which can be prevented by the VT. However, the use of the VDING alone was not sufficient.