RESUMO
BACKGROUND: Predicting an individual's risk of death from COVID-19 is essential for planning and optimising resources. However, since the real-world mortality rate is relatively low, particularly in places like Hong Kong, this makes building an accurate prediction model difficult due to the imbalanced nature of the dataset. This study introduces an innovative application of graph convolutional networks (GCNs) to predict COVID-19 patient survival using a highly imbalanced dataset. Unlike traditional models, GCNs leverage structural relationships within the data, enhancing predictive accuracy and robustness. By integrating demographic and laboratory data into a GCN framework, our approach addresses class imbalance and demonstrates significant improvements in prediction accuracy. METHODS: The cohort included all consecutive positive COVID-19 patients fulfilling study criteria admitted to 42 public hospitals in Hong Kong between January 23 and December 31, 2020 (n = 7,606). We proposed the population-based graph convolutional neural network (GCN) model which took blood test results, age and sex as inputs to predict the survival outcomes. Furthermore, we compared our proposed model to the Cox Proportional Hazard (CPH) model, conventional machine learning models, and oversampling machine learning models. Additionally, a subgroup analysis was performed on the test set in order to acquire a deeper understanding of the relationship between each patient node and its neighbours, revealing possible underlying causes of the inaccurate predictions. RESULTS: The GCN model was the top-performing model, with an AUC of 0.944, considerably outperforming all other models (p < 0.05), including the oversampled CPH model (0.708), linear regression (0.877), Linear Discriminant Analysis (0.860), K-nearest neighbours (0.834), Gaussian predictor (0.745) and support vector machine (0.847). With Kaplan-Meier estimates, the GCN model demonstrated good discriminability between low- and high-risk individuals (p < 0.0001). Based on subanalysis using the weighted-in score, although the GCN model was able to discriminate well between different predicted groups, the separation was inadequate between false negative (FN) and true negative (TN) groups. CONCLUSION: The GCN model considerably outperformed all other machine learning methods and baseline CPH models. Thus, when applied to this imbalanced COVID survival dataset, adopting a population graph representation may be an approach to achieving good prediction.
Assuntos
COVID-19 , Redes Neurais de Computação , SARS-CoV-2 , Humanos , COVID-19/mortalidade , COVID-19/diagnóstico , Masculino , Feminino , Pessoa de Meia-Idade , Hong Kong/epidemiologia , Idoso , Adulto , Testes Hematológicos/métodos , Aprendizado de Máquina , Modelos de Riscos Proporcionais , Estudos de CoortesRESUMO
The study population contains 145 patients who were prospectively recruited for coronary CT angiography (CCTA) and fundoscopy. This study first examined the association between retinal vascular changes and the Coronary Artery Disease Reporting and Data System (CAD-RADS) as assessed on CCTA. Then, we developed a graph neural network (GNN) model for predicting the CAD-RADS as a proxy for coronary artery disease. The CCTA scans were stratified by CAD-RADS scores by expert readers, and the vascular biomarkers were extracted from their fundus images. Association analyses of CAD-RADS scores were performed with patient characteristics, retinal diseases, and quantitative vascular biomarkers. Finally, a GNN model was constructed for the task of predicting the CAD-RADS score compared to traditional machine learning (ML) models. The experimental results showed that a few retinal vascular biomarkers were significantly associated with adverse CAD-RADS scores, which were mainly pertaining to arterial width, arterial angle, venous angle, and fractal dimensions. Additionally, the GNN model achieved a sensitivity, specificity, accuracy and area under the curve of 0.711, 0.697, 0.704 and 0.739, respectively. This performance outperformed the same evaluation metrics obtained from the traditional ML models (p < 0.05). The data suggested that retinal vasculature could be a potential biomarker for atherosclerosis in the coronary artery and that the GNN model could be utilized for accurate prediction.
RESUMO
This study aims to propose a pooling approach to simulate the compulsory universal RT-PCR test in Hong Kong and explore the feasibility of implementing the pooling method on a household basis. The mathematical model is initially verified, and then the simulation is performed under different prevalence rates and pooled sizes. The simulated population is based in Hong Kong. The simulation included 10,000,000 swab samples, with a representative distribution of populations in Hong Kong. The samples were grouped into a batch size of 20. If the entire batch is positive, then the group is further divided into an identical group size of 10 for re-testing. Different combinations of mini-group sizes were also investigated. The proposed pooling method was extended to a household basis. A representative from each household is required to perform the RT-PCR test. Results of the simulation replications, indicate a significant reduction (p < 0.001) of 83.62, 64.18, and 48.46% in the testing volume for prevalence rate 1, 3, and 5%, respectively. Combined with the household-based pooling approach, the total number of RT-PCR is 437,304, 956,133, and 1,375,795 for prevalence rates 1, 3, and 5%, respectively. The household-based pooling strategy showed efficiency when the prevalence rates in the population were low. This pooling strategy can rapidly screen people in high-risk groups for COVID-19 infections and quarantine those who test positive, even when time and resources for testing are limited.
Assuntos
COVID-19 , Humanos , COVID-19/diagnóstico , COVID-19/epidemiologia , Hong Kong/epidemiologia , Teste para COVID-19 , Manejo de Espécimes , PrevalênciaRESUMO
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.
RESUMO
PURPOSE: A reduction in cancer services during the coronavirus disease of 2019 pandemic has affected cancer diagnoses. The purpose of this study is to quantitatively determine the impact on cancer diagnostic service in public facilities across Hong Kong. Quantifying the temporal changes in the number of cancer diagnoses before, during, and after the outbreak is useful to establish the scale of the problem and assess if there has been an adequate level of response. METHODS AND MATERIALS: This is a retrospective cohort study using a territory-wide database in Hong Kong from 2017 to 2020, and consecutive specimens received for pathologic diagnosis in public laboratories in 41 hospitals were retrieved. RESULTS: In 2020, a total of 455,453 pathologic specimens were received, which amounted to a 15.5% reduction compared with the prior 3-year average (P < .001). An analysis of confirmed malignant pathologic diagnoses revealed a statistically significant reduction in colorectal (-10.0%; P < .001) and prostate (-19.7%; P < .001), nonsignificant reduction in lung (-3.0%; P = .0526), and a marginal but nonsignificant increase for breast (0.7%; P = .7592) regions. Based on time series projection data, the estimated missed cancers for the 3 regions with reduced investigations were colorectal (10.0%), lung (3.0%), and prostate (19.7%). CONCLUSIONS: Variable impact on actual malignant pathologic diagnoses based on 4 body regions was observed, with a statistically significant reduction in colorectal, lung, and prostate regions, and marginal but insignificant increase in breast regions. The findings could help public health policy with future planning and intervention.
Assuntos
COVID-19/epidemiologia , Neoplasias/diagnóstico , Logradouros Públicos/estatística & dados numéricos , Feminino , Hong Kong/epidemiologia , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Estudos RetrospectivosRESUMO
Background: The COVID-19 pandemic has caused significant disruption to healthcare worldwide. In this study, we aim to quantify its impact of chest related radiological procedures over the different waves of local infection in Hong Kong across the territory's public hospitals. Methods: This was an observational study enrolling patients between January 2017 and December 2020. Consecutive population-based chest radiographs, CT, US, and interventional radiology (IR) procedures were obtained public hospitals across Hong Kong. Results: A significant reduction of 10.0% (p < 0.001) in the total number of chest radiographs was observed. Non-significant reduction of 2.5% (p = 0.0989), 39.1% (p = 0.2135), and 1.9% (p = 0.8446) was observed for Chest CT, Chest US, and Chest IR procedures, respectively, in 2020 compared to the projected values. Conclusion: Although, it was anticipated that there would be a significant impact to health services caused by the pandemic, for chest-related investigations in Hong Kong, the impact was not as severe. Quantitative analysis could help with future planning and public health decision making.
RESUMO
Background: To better understand the different clinical phenotypes across the disease spectrum in patients with COVID-19 using an unsupervised machine learning clustering approach. Materials and Methods: A population-based retrospective study was conducted utilizing demographics, clinical characteristics, comorbidities, and clinical outcomes of 7,606 COVID-19-positive patients on admission to public hospitals in Hong Kong in the year 2020. An unsupervised machine learning clustering was used to explore this large cohort. Results: Four clusters of differing clinical phenotypes based on data at initial admission was derived in which 86.6% of the deceased cases were aggregated in one of the clusters without prior knowledge of their clinical outcomes. Other distinctive clinical characteristics of this cluster were old age and high concurrent comorbidities as well as laboratory characteristics of lower hemoglobin/hematocrit levels, higher neutrophil, C-reactive protein, lactate dehydrogenase, and creatinine levels. The clinical patterns captured by the cluster analysis was validated on other temporally distinct cohorts in 2021. The phenotypes aligned with existing literature. Conclusion: The study demonstrated the usefulness of unsupervised machine learning techniques with the potential to uncover latent clinical phenotypes. It could serve as a more robust classification for patient triaging and patient-tailored treatment strategies.