RESUMEN
OBJECTIVE: Developing a severity assessment scale for critically ill patients' thirst and conducting reliability and validity tests, aiming to provide healthcare professionals with a scientific and objective tool for assessing the level of thirst. METHODS: Based on literature review and qualitative interviews, a pool of items was generated, and a preliminary scale was formed through two rounds of Delphi expert consultation. Convenience sampling was employed to select 178 ICU patients in a top-three hospital from May 2023 to October 2023 as the study subjects to examine the reliability and validity of the severity assessment scale for critically ill patients' thirst. RESULTS: The developed severity assessment scale for critically ill patients' thirst consists of 8 evaluation items and 26 evaluation indicators. The agreement coefficients for two rounds of expert consultation were 100% and 92.6% for the positive coefficient, and the authority coefficients were .900 and .906. Kendall's concordance coefficients were .101 and .120 (all p < .001). The overall Cronbach's α coefficient for the scale was .827. The inter-rater reliability coefficient was .910. The Item-Content Validity Index (I-CVI) ranged from .800 to 1.000, and the Scale-Content Validity Index/Average (S-CVI/Ave) was .950. CONCLUSION: The critically ill patients' thirst assessment scale is reliable and valid and can be widely used in clinical practice. PATIENT OR PUBLIC CONTRIBUTION: The AiMi Academic Services (www.aimieditor.com) for English language editing and review services. IMPLICATIONS FOR CLINICAL PRACTICE: The scale developed in this study is a simple and ICU-specific scale that can be used to assess the severity of thirst in critically ill patients. As such, the severity of thirst in critically ill patients can be evaluated quickly so that targeted interventions can be implemented according to the patient's specific disease and treatment conditions. Therefore, patient comfort can be improved, and thirst-related health problems can be prevented.
RESUMEN
Objective: This study was aimed at exploring the feasibility and validity of a self-administered immersive virtual reality (VR) tool designed to assess cognitive impairment in patients with cancer. Methods: In a cross-sectional survey study, an immersive tool was used to rate the previously recommended core assessment domains of cancer-related cognitive impairment-comprising attention, verbal learning memory, processing speed, executive function and verbal fluency-via an interactive VR scenario. Results: A total of 165 patients with cancer participated in this study. The participants' mean age was 47.74 years (SD â= â10.59). Common cancer types included lung, liver, breast and colorectal cancer, and most patients were in early disease stages (n â= â146, 88.5%). Participants' performance in the VR cognition assessment showed a moderate to strong positive correlation with their paper-and-pencil neurocognitive test results (r â= â0.34-0.76, P â< â0.001), thus indicating high concurrent validity of the immersive VR cognition assessment tool. For all participants, the mean score for the VR-based cognition assessment was 5.41 (SD â= â0.70) out of a potential maximum of 7.0. The mean simulation sickness score for the VR-based tool, as rated by the patients, was 0.35 (SD â= â0.19), thereby indicating that minimal simulation sickness occurred during the VR-assisted cognition assessment. Conclusions: Given its demonstrated validity, and the patients' high presence scores and minimal sickness scores, this VR-based cognition assessment tool is a feasible and acceptable instrument for measuring cognitive impairment in patients with cancer. However, further psychometric assessments should be implemented in clinical settings.
RESUMEN
Objective: Predictive models for the occurrence of cancer symptoms by using machine learning (ML) algorithms could be used to aid clinical decision-making in order to enhance the quality of cancer care. This study aimed to develop and validate a selection of classification models that used ML algorithms to predict the occurrence of breast cancer-related lymphedema (BCRL) among Chinese women. Methods: This was a retrospective cohort study of consecutive cases that had been diagnosed with breast cancer, stages I-IV. Forty-eight variables were grouped into five feature sets. Five classification models with ML algorithms were developed, and the models' performance and the variables' relative importance were assessed accordingly. Results: Of 370 eligible female participants, 91 had BCRL (24.6%). The mean age of this study sample was 49.89 (SD â= â7.45). All participants had had breast cancer surgery, and more than half of them had had a modified radical mastectomy (n â= â206, 55.5%). The mean follow-up time after breast cancer surgery was 28.73 months (SD â= â11.71). Most of the tumors were either stage I (n â= â49, 31.2%) or stage II (n â= â252, 68.1%). More than half of the sample had had postoperative chemotherapy (n â= â227, 61.4%). Overall, the logistic regression model achieved the best performance in terms of accuracy (91.6%), precision (82.1%), and recall (91.4%) for BCRL. Although this study included 48 predicting variables, we found that the five models required only 22 variables to achieve predictive performance. The most important variable was the number of positive lymph nodes, followed in descending order by the BCRL occurring on the same side as the surgery, a history of sentinel lymph node biopsy, a dietary preference for meat and fried food, and an exercise frequency of less than three times per week. These factors were the most influential predictors for enhancing the ML models' performance. Conclusions: This study found that in the ML training dataset, the multilayer perceptron model and the logistic regression model were the best discrimination models for predicting the outcome of BCRL, and the k-nearest neighbors and support vector machine models demonstrated good calibration performance in the ML validation dataset. Future research will need to use large-sample datasets to establish a more robust ML model for predicting BCRL deeply and reliably.
RESUMEN
This brief report aimed to describe a narrative review about the application of machine learning (ML) methods and Blockchain technology (BCT) in the healthcare field, and to illustrate the integration of these two technologies in cancer survivorship care. A total of six eligible papers were included in the narrative review. ML and BCT are two data-driven technologies, and there is rapidly growing interest in integrating them for clinical data management and analysis in healthcare. The findings of this report indicate that both technologies can integrate feasibly and effectively. In conclusion, this brief report provided the state-of-art evidence about the integration of the most promising technologies of ML and BCT in health field, and gave an example of how to apply these two most disruptive technologies in cancer survivorship care.