Meta-lasso: new insight on infection prediction after minimally invasive surgery.

Surgical site infection (SSI) after minimally invasive lung cancer surgery constitutes an important factor influencing the direct and indirect economic implications, patient prognosis, and the 5-year survival rate for early-stage lung cancer patients. In the realm of predictive healthcare, machine learning algorithms have been instrumental in anticipating various surgical outcomes, including SSI. However, accurately predicting infection after minimally invasive surgery remains a clinical challenge due to the multitude of physiological and surgical factors associated with it. Furthermore, clinical patient data, in addition to being high-dimensional, often exists the long-tail problem, posing difficulties for traditional machine learning algorithms in effectively processing such data. Based on this insight, we propose a novel approach called meta-lasso for infection prediction following minimally invasive surgery. Our approach leverages the sparse learning algorithm lasso regression to select informative features and introduces a meta-learning framework to mitigate bias towards the dominant class. We conducted a retrospective cohort study on patients who had undergone minimally invasive surgery for lung cancer at Shanghai Chest Hospital between 2018 and 2020. The evaluation encompassed key performance metrics, including sensitivity, specificity, precision (PPV), negative predictive value (NPV), and accuracy. Our approach has surpassed the performance of logistic regression, random forest, Naive Bayes classifier, gradient boosting decision tree, ANN, and lasso regression, with sensitivity at 0.798, specificity at 0.779, precision at 0.789, NPV at 0.798, and accuracy at 0.788 and has greatly improved the classification performance of the inferior class.

Comparing the influence of big data resources on medical knowledge recall for staff with and without medical collaboration platform.

BACKGROUND: This study aims to examine how big data resources affect the recall of prior medical knowledge by healthcare professionals, and how this differs in environments with and without remote consultation platforms. METHOD: This study investigated two distinct categories of medical institutions, namely 132 medical institutions with platforms, and 176 medical institutions without the platforms. Big data resources are categorized into two levels-medical institutional level and public level-and three types, namely data, technology, and services. The data are analyzed using SmartPLS2. RESULTS: (1) In both scenarios, shared big data resources at the public level have a significant direct impact on the recall of prior medical knowledge. However, there is a significant difference in the direct impact of big data resources at the institutional level in both scenarios. (2) In institutions with platforms, for the three big data resources (the medical big data assets and big data deployment technical capacity at the medical institutional level, and policies of medical big data at the public level) without direct impacts, there exist three indirect pathways. (3) In institutions without platforms, for the two big data resources (the service capability and big data technical capacity at the medical institutional level) without direct impacts, there exist three indirect pathways. CONCLUSIONS: The different interactions between big data, technology, and services, as well as between different levels of big data resources, affect the way clinical doctors recall relevant medical knowledge. These interaction patterns vary between institutions with and without platforms. This study provides a reference for governments and institutions to design big data environments for improving clinical capabilities.

Blockchain-based Electronic Medical Record Security Sharing Scheme.

To solve the difficulty of medical data sharing in traditional medical information systems, we proposed an electronic medical record secure-sharing scheme based on the Blockchain technique. The encrypted text of the patient's electronic medical record is stored in the cloud server while the metadata of the medical record and access strategy is stored in the blockchain system. We employed smart contracts in the blockchain system to achieve user rights management. We used the decentralized, tamper-proof, and traceable features of the blockchain to realize the safe sharing of electronic medical records. The experimental results of security analysis show that the method can defend against potential network attacks while satisfying patient privacy protection and confidentiality. This study verifies the feasibility and great operating efficiency of the blockchain-based electronic medical record security sharing scheme.Clinical relevance- Our proposed blockchain-based electronic medical record-sharing scheme has great potential for the safe access of third-party users to patient data.

Particle filter-based parameter estimation algorithm for prognostic risk assessment of progression in non-small cell lung cancer.

Non-small cell lung cancer (NSCLC) is a malignant tumor that threatens human life and health. The development of a new NSCLC risk assessment model based on electronic medical records has great potential for reducing the risk of cancer recurrence. In this process, machine learning is a powerful method for automatically extracting risk factors and indicating impact weights for NSCLC deaths. However, when the number of samples reaches a certain value, it is difficult for machine learning to improve the prediction accuracy, and it is also challenging to use the characteristic data of subsequent patients effectively. Therefore, this study aimed to build a postoperative survival risk assessment model for patients with NSCLC that updates the model parameters and improves model accuracy based on new patient data. The model perspective was a combination of particle filtering and parameter estimation. To demonstrate the feasibility and further evaluate the performance of our approach, we performed an empirical analysis experiment. The study showed that our method achieved an overall accuracy of 92% and a recall of 71% for deceased patients. Compared with traditional machine learning models, the accuracy of the model estimated by particle filter parameters has been improved by 2%, and the recall rate for dead patients has been improved by 11%. Additionally, this study outcome shows that this method can better utilize subsequent patients' characteristic data, be more relevant to different patients, and help achieve precision medicine.

Machine learning-based risk models for procedural complications of radiofrequency ablation for atrial fibrillation.

BACKGROUND: Radiofrequency ablation (RFA) for atrial fibrillation (AF) is associated with a risk of complications. This study aimed to develop and validate risk models for predicting complications after radiofrequency ablation of atrial fibrillation patients. METHODS: This retrospective cohort study included 3365 procedures on 3187 patients with atrial fibrillation at a single medical center from 2018 to 2021. The outcome was the occurrence of postoperative procedural complications during hospitalization. Logistic regression, decision tree, random forest, gradient boosting machine, and extreme gradient boosting were used to develop risk models for any postoperative complications, cardiac effusion/tamponade, and hemorrhage, respectively. Patients' demographic characteristics, medical history, signs, symptoms at presentation, electrocardiographic features, procedural characteristics, laboratory values, and postoperative complications were collected from the medical record. The prediction results were evaluated by performance metrics (i.e., the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F score, and Brier score) with repeated fivefold cross-validation. RESULTS: Of the 3365 RFA procedures, there were 62 procedural complications with a rate of 1.84% in the entire cohort. The most common complications were cardiac effusion/tamponade (28 cases, 0.83%), and hemorrhage (21 cases, 0.80%). There was no procedure-related mortality. The machine learning algorithms of random forest (RF) outperformed other models for any complication (AUC 0.721 vs 0.627 to 0.707), and hemorrhage (AUC 0.839 vs 0.649 to 0.794). The extreme gradient boosting (XGBoost) model outperformed other models for cardiac effusion/tamponade (AUC 0.696 vs 0.606 to 0.662). CONCLUSIONS: The developed risk models using machine learning algorithms showed good performance in predicting complications after RFA of AF patients. These models help identify patients at high risk of complications and guiding clinical decision-making.

China lung cancer screening (CLUS) version 2.0 with new techniques implemented: Artificial intelligence, circulating molecular biomarkers and autofluorescence bronchoscopy.

OBJECTIVE: The present study, CLUS version 2.0, was conducted to evaluate the performance of new techniques in improving the implementation of lung cancer screening and to validate the efficacy of LDCT in reducing lung cancer-specific mortality in a high-risk Chinese population. METHODS: From July 2018 to February 2019, high-risk participants from six screening centers in Shanghai were enrolled in our study. Artificial intelligence, circulating molecular biomarkers and autofluorescencebronchoscopy were applied during screening. RESULTS: A total of 5087 eligible high-risk participants were enrolled in the study; 4490 individuals were invited, and 4395 participants (97.9%) finally underwent LDCT detection. Positive screening results were observed in 857 (19.5%) participants. Solid nodules represented 53.6% of all positive results, while multiple nodules were the most common location type (26.8%). Up to December 2020, 77 participants received lung resection or biopsy, including 70 lung cancers, 2 mediastinal tumors, 1 tracheobronchial tumor, 1 malignant pleural mesothelioma and 3 benign nodules. Lung cancer patients accounted for 1.6% of all the screened participants, and 91.4% were in the early stage (stage 0-1). CONCLUSIONS: LDCT screening can detect a high proportion of early-stage lung cancer patients in a Chinese high-risk population. The utilization of new techniques would be conducive to improving the implementation of LDCT screening.

Use of machine learning models to predict in-hospital mortality in patients with acute coronary syndrome.

BACKGROUND: Cardiovascular diseases are a significant health burden with the prevalence increasing worldwide. Thus, a highly accurate assessment and prediction of death risk are crucial to meet the clinical demand. This study sought to develop and validate a model to predict in-hospital mortality among patients with the acute coronary syndrome (ACS) using nonlinear algorithms. METHODS: A total of 2414 ACS patients were enrolled in this study. All samples were divided into five groups for cross-validation. The logistic regression (LR) model and XGboost model were applied to predict in-hospital mortality. The results of two models were compared between the variable set by the global registry of acute coronary events (GRACE) score and the selected variable set. RESULTS: The in-hospital mortality rate was 3.5% in the dataset. Model performance on the selected variable set was better than that on GRACE variables: a 3% increase in area under the receiver operating characteristic (ROC) curve (AUC) for LR and 1.3% for XGBoost. The AUC of XGBoost is 0.913 (95% confidence interval [CI]: 0.910-0.916), demonstrating a better discrimination ability than LR (AUC = 0.904, 95% CI: 0.902-0.905) on the selected variable set. Almost perfect calibration was found in XGBoost (slope of predicted to observed events, 1.08; intercept, -0.103; p < .001). CONCLUSIONS: XGboost modeling, an advanced machine learning algorithm, identifies new variables and provides high accuracy for the prediction of in-hospital mortality in ACS patients.

Associations of family functioning with sleep disturbance and depressive symptoms among primary and secondary school students / 中国学校卫生

Objective@#The study aims to explore the associations of family functioning with sleep disturbance and depressive symptoms among primary and secondary school students, to provide scientific reference for preventing depression in primary and middle school students.@*Methods@#A convenience sampling method was used to recruit 124 357 primary and secondary school students in Baoan District, Shenzhen. A self administered general information questionnaire, the Youth Self Rating Insomnia Scale, and the Patient Heath Questionnaire-9 were used to assess the students demographic characteristics, family functioning, sleep disturbance, and depressive symptoms.@*Results@#About 34.6% of students reported moderate family dysfunction, and 8.7% reported severe family dysfunction. The prevalence rates of sleep disturbance and depressive symptoms were 13.0% and 13.1% in elementary and secondary school students, respectively. The prevalence rates of sleep disturbance and depressive symptoms were statistically significantly higher in girls(14.6%, 16.8%) than boys(11.6%, 9.9%) ( χ 2=255.25, 1 269.50, P <0.01). Depressive symptoms were positively correlated with sleep disturbance ( r =0.61) and negatively correlated with family functioning ( r =-0.31)( P <0.01). Family functioning moderated the relationship between sleep disturbance and depressive symptoms, and the positive predictive effect of sleep disturbance on depressive symptoms decreases as the level of family functioning increases.@*Conclusion@#Family functioning buffers the effects of sleep disturbance on depressive symptoms among primary and secondary school students. Attention should be paid to sleep quality among primary and secondary school students, to improve their family functioning, and thus decrease and prevent the occurrence of depression in adolescents.

Impact of big data resources on clinicians' activation of prior medical knowledge.

Background: Activating prior medical knowledge in diagnosis and treatment is an important basis for clinicians to improve their care ability. However, it has not been systematically explained whether and how various big data resources affect the activation of prior knowledge in the big data environment faced by clinicians. Objective: The aim of this study is to contribute to a better understanding on how the activation of prior knowledge of clinicians is affected by a wide range of shared and private big data resources, to reveal the impact of big data resources on clinical competence and professional development of clinicians. Method: Through the comprehensive analysis of extant research results, big data resources are classified as big data itself, big data technology and big data services at the public and institutional levels. A survey was conducted on clinicians and IT personnel in Chinese hospitals. A total of 616 surveys are completed, involving 308 medical institutions. Each medical institution includes a clinician and an IT personnel. SmartPLS version 2.0 software package was used to test the direct impact of big data resources on the activation of prior knowledge. We further analyze their indirect impact of those big data resources without direct impact. Results: (1) Big data quality environment at the institutional level and the big data sharing environment at the public level directly affect activation of prior medical knowledge; (2) Big data service environment at the institutional level directly affects activation of prior medical knowledge; (3) Big data deployment environment at the institutional level and big data service environment at the public level have no direct impact on activation of prior knowledge of clinicians, but they have an indirect impact through big data quality environment and service environment at the institutional level and the big data sharing environment at the public level. Conclusions: Big data technology, big data itself and big data service at the public level and institutional level interact and influence each other to activate prior medical knowledge. This study highlights the implications of big data resources on improvement of clinicians' diagnosis and treatment ability.

A predictive model based on ground glass nodule features via high-resolution CT for identifying invasiveness of lung adenocarcinoma.

Objective: The morphology of ground-glass nodule (GGN) under high-resolution computed tomography (HRCT) has been suggested to indicate different histological subtypes of lung adenocarcinoma (LUAD); however, existing studies only include the limited number of GGN characteristics, which lacks a systematic model for predicting invasive LUAD. This study aimed to construct a predictive model based on GGN features under HRCT for LUAD. Methods: A total of 301 surgical LUAD patients with HRCT-confirmed GGN were enrolled, and their GGN-related features were assessed by 2 individual radiologists. The pathological diagnosis of the invasive LUAD was established by pathologic examination following surgery (including 171 invasive and 130 non-invasive LUAD patients). Results: GGN features including shorter distance from pleura, larger diameter, area and mean CT attenuation, more heterogeneous uniformity of density, irregular shape, coarse margin, not defined nodule-lung interface, spiculation, pleural indentation, air bronchogram, vacuole sign, vessel changes, lobulation were observed in invasive LUAD patients compared with non-invasive LUAD patients. After adjustment by multivariate logistic regression model, GGN diameter (OR = 1.490, 95% CI, 1.326-1.674), mean CT attenuation (OR = 1.007, 95% CI, 1.004-1.011) and heterogeneous uniformity of density (OR = 3.009, 95% CI, 1.485-6.094) were independent risk factors for invasive LUAD. In addition, a predictive model integrating these three independent GGN features was established (named as invasion of lung adenocarcinoma by GGN features (ILAG)), and receiver-operating characteristic curve illustrated that the ILAG model presented good predictive value for invasive LUAD (AUC: 0.919, 95% CI, 0.889-0.949). Conclusions: ILAG predictive model integrating GGN diameter, mean CT attenuation and heterogeneous uniformity of density via HRCT shows great potential for early estimation of LUAD invasiveness.

Mechanism of Impact of Big Data Resources on Medical Collaborative Networks From the Perspective of Transaction Efficiency of Medical Services: Survey Study.

BACKGROUND: The application of big data resources and the development of medical collaborative networks (MCNs) boost each other. However, MCNs are often assumed to be exogenous. How big data resources affect the emergence, development, and evolution of endogenous MCNs has not been well explained. OBJECTIVE: This study aimed to explore and understand the influence of the mechanism of a wide range of shared and private big data resources on the transaction efficiency of medical services to reveal the impact of big data resources on the emergence and development of endogenous MCNs. METHODS: This study was conducted by administering a survey questionnaire to information technology staff and medical staff from 132 medical institutions in China. Data from information technology staff and medical staff were integrated. Structural equation modeling was used to test the direct impact of big data resources on transaction efficiency of medical services. For those big data resources that had no direct impact, we analyzed their indirect impact. RESULTS: Sharing of diagnosis and treatment data (ß=.222; P=.03) and sharing of medical research data (ß=.289; P=.04) at the network level (as big data itself) positively directly affected the transaction efficiency of medical services. Network protection of the external link systems (ß=.271; P=.008) at the level of medical institutions (as big data technology) positively directly affected the transaction efficiency of medical services. Encryption security of web-based data (as big data technology) at the level of medical institutions, medical service capacity available for external use, real-time data of diagnosis and treatment services (as big data itself) at the level of medical institutions, and policies and regulations at the network level indirectly affected the transaction efficiency through network protection of the external link systems at the level of medical institutions. CONCLUSIONS: This study found that big data technology, big data itself, and policy at the network and organizational levels interact with, and influence, each other to form the transaction efficiency of medical services. On the basis of the theory of neoclassical economics, the study highlighted the implications of big data resources for the emergence and development of endogenous MCNs.

Contextual embedding bootstrapped neural network for medical information extraction of coronary artery disease records.

Coronary artery disease (CAD) is the major cause of human death worldwide. The development of new CAD early diagnosis methods based on medical big data has a great potential to reduce the risk of CAD death. In this process, neural network (NN), as a powerful tool for electronic medical record (EMR) processing, enables extract structured data accurately to unlock medical information and to further improve CAD diagnosis. However, the excessive time and labor caused by dataset's annotation is the main limitation of its application, especially on the CAD records situation with large natural language text and biomedical professional content. In this study, we present an annotation cost saving NN approach for CAD records, which is bootstrapped by deep language model with contextual embedding pre-trained on large unannotated CAD corpus. To demonstrate the feasibility and to further evaluate the performance of our approach, we performed pre-training experiment and term classification experiment, by using the unannotated and annotated CAD records, respectively. The results showed that our contextual embedding bootstrapped NN for CAD records has better performance under the condition of annotations reduction.