RESUMEN
BACKGROUND AND OBJECTIVES: Implantable telemetric intracranial pressure (ICP) sensors (telesensors) enable routine, noninvasive ICP feedback, aiding clinical decision-making and attribution of pressure-related symptoms in patients with cerebrospinal fluid shunt systems. Here, we aim to explore the impact of these devices on service demand and costs in patients with adult hydrocephalus. METHODS: We performed an observational propensity-matched control study, comparing patients who had an MScio/Sensor Reservoir (Christoph Miethke, GmbH & Co) against those with a nontelemetric reservoir inserted between March 2016 and March 2018. Patients were matched on demographics, diagnosis, shunt-type, and revision status. Service usage was recorded with frequencies of neurosurgical admissions, outpatient clinics, scans, and further surgical procedures in the 2 years before and after shunt insertion. RESULTS: In total, 136 patients, 73 telesensors, and 63 controls were included in this study (48 matched pairs). Telesensor use led to a significant decrease in neurosurgical inpatient admissions, radiographic encounters, and procedures including ICP monitoring. After multivariate adjustment, the mean cumulative saving after 2 years was £5236 ($6338) in telesensor patients (£5498 on matched pair analysis). On break-even analysis, cost-savings were likely to be achieved within 8 months of clinical use, postimplantation. Telesensor patients also experienced a significant reduction in imaging-associated radiation (4 mSv) over 2 years. CONCLUSION: The findings of this exploratory study reveal that telesensor implantation is associated with reduced service demand and provides net financial savings from an institutional perspective. Moreover, telesensor patients required fewer appointments, invasive procedures, and had less radiation exposure, indicating an improvement in both their experience and safety.
RESUMEN
Background: Lung cancer is the leading cause of cancer-related mortality, and accurate prediction of patient survival can aid treatment planning and potentially improve outcomes. In this study, we proposed an automated system capable of lung segmentation and survival prediction using graph convolution neural network (GCN) with CT data in non-small cell lung cancer (NSCLC) patients. Methods: In this retrospective study, we segmented 10 parts of the lung CT images and built individual lung graphs as inputs to train a GCN model to predict 5-year overall survival. A Cox proportional-hazard model, a set of machine learning (ML) models, a convolutional neural network based on tumor (Tumor-CNN), and the current TNM staging system were used as comparison. Findings: A total of 1,705 patients (main cohort) and 125 patients (external validation cohort) with lung cancer (stages I and II) were included. The GCN model was significantly predictive of 5-year overall survival with an AUC of 0.732 (p < 0.0001). The model stratified patients into low- and high-risk groups, which were associated with overall survival (HR = 5.41; 95% CI:, 2.32-10.14; p < 0.0001). On external validation dataset, our GCN model achieved the AUC score of 0.678 (95% CI: 0.564-0.792; p < 0.0001). Interpretation: The proposed GCN model outperformed all ML, Tumor-CNN, and TNM staging models. This study demonstrated the value of utilizing medical imaging graph structure data, resulting in a robust and effective model for the prediction of survival in early-stage lung cancer.
