Effects of computerized cognitive training on functional brain networks in patients with vascular cognitive impairment and no dementia.

AIMS: Previous neuroimaging studies of vascular cognitive impairment, no dementia (VCIND), have reported functional alterations, but far less is known about the effects of cognitive training on functional connectivity (FC) of intrinsic connectivity networks (ICNs) and how they relate to intervention-related cognitive improvement. This study provides comprehensive research on the changes in intra- and inter-brain functional networks in patients with VCIND who received computerized cognitive training, with a focus on the underlying mechanisms and potential therapeutic strategies. METHODS: We prospectively collected 60 patients with VCIND who were randomly divided into the training group (N = 30) receiving computerized cognitive training and the control group (N = 30) receiving fixed cognitive training. Functional MRI scans and cognitive assessments were performed at baseline, at the 7-week training, and at the 6-month follow-up. Utilizing templates for ICNs, the study employed a linear mixed model to compare intra- and inter-network FC changes between the two groups. Pearson correlation was applied to calculate the relationship between FC and cognitive function. RESULTS: We found significantly decreased intra-network FC within the default mode network (DMN) following computerized cognitive training at Month 6 (p = 0.034), suggesting a potential loss of functional specialization. Computerized training led to increased functional coupling between the DMN and sensorimotor network (SMN) (p = 0.01) and between the language network (LN) and executive control network (ECN) at Month 6 (p < 0.001), indicating compensatory network adaptations in patients with VCIND. Notably, the intra-LN exhibited enhanced functional specialization after computerized cognitive training (p = 0.049), with significant FC increases among LN regions, which correlated with improvements in neuropsychological measures (p < 0.05), emphasizing the targeted impact of computerized cognitive training on language abilities. CONCLUSIONS: This study provides insights into neuroplasticity and adaptive changes resulting from cognitive training in patients with VCIND, with implications for potential therapeutic strategies.

Representation of time-varying and time-invariant EMR data and its application in modeling outcome prediction for heart failure patients.

OBJECTIVE: To represent a patient record with both time-invariant and time-varying features as a single vector using an end-to-end deep learning model, and further to predict the kidney failure (KF) status and mortality of heart failure (HF) patients. MATERIALS AND METHODS: The time-invariant EMR data included demographic information and comorbidities, and the time-varying EMR data were lab tests. We used a Transformer encoder module to represent the time-invariant data, and refined a long short-term memory (LSTM) with a Transformer encoder attached to the top to represent the time-varying data, taking the original measured values and their corresponding embedding vectors, masking vectors, and two types of time intervals as inputs. The proposed representations of patients with time-invariant and time-varying data were used to predict KF status (949 out of 5268 HF patients diagnosed with KF) and mortality (463 in-hospital deaths) for HF patients. Comparative experiments were conducted between the proposed model and some representative machine learning models. Ablation experiments were also performed around the time-varying data representation, including replacing the refined LSTM with the standard LSTM, GRU-D and T-LSTM, respectively, and removing the Transformer encoder and the time-varying data representation module, respectively. The visualization of the attention weights of the time-invariant and time-varying features was used to clinically interpret the predictive performance. We used the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), and the F1-score to evaluate the predictive performance of the models. RESULTS: The proposed model achieved superior performance, with average AUROCs, AUPRCs and F1-scores of 0.960, 0.610 and 0.759 for KF prediction and 0.937, 0.353 and 0.537 for mortality prediction, respectively. Predictive performance improved with the addition of time-varying data from longer time periods. The proposed model outperformed the comparison and ablation references in both prediction tasks. CONCLUSIONS: Both time-invariant and time-varying EMR data of patients could be efficiently represented by the proposed unified deep learning model, which shows higher performance in clinical prediction tasks. The way to use time-varying data in the current study is hopeful to be used in other kinds of time-varying data and other clinical tasks.

Improving the Performance of Outcome Prediction for Inpatients With Acute Myocardial Infarction Based on Embedding Representation Learned From Electronic Medical Records: Development and Validation Study.

BACKGROUND: The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention. OBJECTIVE: We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI). METHODS: Medical concepts, including patients' age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score. RESULTS: Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice. CONCLUSIONS: The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

Quality Management of Pulmonary Nodule Radiology Reports Based on Natural Language Processing.

To investigate the feasibility of automated follow-up recommendations based on findings in radiology reports, this paper proposed a Natural Language Processing model specific for Pulmonary Nodule Radiology Reports. Unstructured findings used to describe pulmonary nodules in 48,091 radiology reports were processed in this study. We established an NLP model to extract information entities from findings of radiology reports, using deep learning and conditional random-field algorithms. Subsequently, we constructed a knowledge graph comprising 168 entities and four relationships, based on the export recommendations of the internationally renowned Fleischner Society for pulmonary nodules. These were employed in combination with rule templates to automatically generate follow-up recommendations. The automatically generated recommendations were then compared to the impression part of the reports to evaluate the matching rate of proper follow ups in the current situation. The NLP model identified eight types of entities with a recognition accuracy of up to 94.22%. A total of 43,898 out of 48,091 clinical reports were judged to contain appropriate follow-up recommendations, corresponding to the matching rate of 91.28%. The results show that NLP can be used on Chinese radiology reports to extract structured information at the content level, thereby realizing the prompt and intelligent follow-up suggestion generation or post-quality management of follow-up recommendations.

Sequential Data-Based Patient Similarity Framework for Patient Outcome Prediction: Algorithm Development.

BACKGROUND: Sequential information in electronic medical records is valuable and helpful for patient outcome prediction but is rarely used for patient similarity measurement because of its unevenness, irregularity, and heterogeneity. OBJECTIVE: We aimed to develop a patient similarity framework for patient outcome prediction that makes use of sequential and cross-sectional information in electronic medical record systems. METHODS: Sequence similarity was calculated from timestamped event sequences using edit distance, and trend similarity was calculated from time series using dynamic time warping and Haar decomposition. We also extracted cross-sectional information, namely, demographic, laboratory test, and radiological report data, for additional similarity calculations. We validated the effectiveness of the framework by constructing k-nearest neighbors classifiers to predict mortality and readmission for acute myocardial infarction patients, using data from (1) a public data set and (2) a private data set, at 3 time points-at admission, on Day 7, and at discharge-to provide early warning patient outcomes. We also constructed state-of-the-art Euclidean-distance k-nearest neighbor, logistic regression, random forest, long short-term memory network, and recurrent neural network models, which were used for comparison. RESULTS: With all available information during a hospitalization episode, predictive models using the similarity model outperformed baseline models based on both public and private data sets. For mortality predictions, all models except for the logistic regression model showed improved performances over time. There were no such increasing trends in predictive performances for readmission predictions. The random forest and logistic regression models performed best for mortality and readmission predictions, respectively, when using information from the first week after admission. CONCLUSIONS: For patient outcome predictions, the patient similarity framework facilitated sequential similarity calculations for uneven electronic medical record data and helped improve predictive performance.

Patient Representation From Structured Electronic Medical Records Based on Embedding Technique: Development and Validation Study.

BACKGROUND: The secondary use of structured electronic medical record (sEMR) data has become a challenge due to the diversity, sparsity, and high dimensionality of the data representation. Constructing an effective representation for sEMR data is becoming more and more crucial for subsequent data applications. OBJECTIVE: We aimed to apply the embedding technique used in the natural language processing domain for the sEMR data representation and to explore the feasibility and superiority of the embedding-based feature and patient representations in clinical application. METHODS: The entire training corpus consisted of records of 104,752 hospitalized patients with 13,757 medical concepts of disease diagnoses, physical examinations and procedures, laboratory tests, medications, etc. Each medical concept was embedded into a 200-dimensional real number vector using the Skip-gram algorithm with some adaptive changes from shuffling the medical concepts in a record 20 times. The average of vectors for all medical concepts in a patient record represented the patient. For embedding-based feature representation evaluation, we used the cosine similarities among the medical concept vectors to capture the latent clinical associations among the medical concepts. We further conducted a clustering analysis on stroke patients to evaluate and compare the embedding-based patient representations. The Hopkins statistic, Silhouette index (SI), and Davies-Bouldin index were used for the unsupervised evaluation, and the precision, recall, and F1 score were used for the supervised evaluation. RESULTS: The dimension of patient representation was reduced from 13,757 to 200 using the embedding-based representation. The average cosine similarity of the selected disease (subarachnoid hemorrhage) and its 15 clinically relevant medical concepts was 0.973. Stroke patients were clustered into two clusters with the highest SI (0.852). Clustering analyses conducted on patients with the embedding representations showed higher applicability (Hopkins statistic 0.931), higher aggregation (SI 0.862), and lower dispersion (Davies-Bouldin index 0.551) than those conducted on patients with reference representation methods. The clustering solutions for patients with the embedding-based representation achieved the highest F1 scores of 0.944 and 0.717 for two clusters. CONCLUSIONS: The feature-level embedding-based representations can reflect the potential clinical associations among medical concepts effectively. The patient-level embedding-based representation is easy to use as continuous input to standard machine learning algorithms and can bring performance improvements. It is expected that the embedding-based representation will be helpful in a wide range of secondary uses of sEMR data.

Study on the semi-supervised learning-based patient similarity from heterogeneous electronic medical records.

BACKGROUND: A new learning-based patient similarity measurement was proposed to measure patients' similarity for heterogeneous electronic medical records (EMRs) data. METHODS: We first calculated feature-level similarities according to the features' attributes. A domain expert provided patient similarity scores of 30 randomly selected patients. These similarity scores and feature-level similarities for 30 patients comprised the labeled sample set, which was used for the semi-supervised learning algorithm to learn the patient-level similarities for all patients. Then we used the k-nearest neighbor (kNN) classifier to predict four liver conditions. The predictive performances were compared in four different situations. We also compared the performances between personalized kNN models and other machine learning models. We assessed the predictive performances by the area under the receiver operating characteristic curve (AUC), F1-score, and cross-entropy (CE) loss. RESULTS: As the size of the random training samples increased, the kNN models using the learned patient similarity to select near neighbors consistently outperformed those using the Euclidean distance to select near neighbors (all P values < 0.001). The kNN models using the learned patient similarity to identify the top k nearest neighbors from the random training samples also had a higher best-performance (AUC: 0.95 vs. 0.89, F1-score: 0.84 vs. 0.67, and CE loss: 1.22 vs. 1.82) than those using the Euclidean distance. As the size of the similar training samples increased, which composed the most similar samples determined by the learned patient similarity, the performance of kNN models using the simple Euclidean distance to select the near neighbors degraded gradually. When exchanging the role of the Euclidean distance, and the learned patient similarity in selecting the near neighbors and similar training samples, the performance of the kNN models gradually increased. These two kinds of kNN models had the same best-performance of AUC 0.95, F1-score 0.84, and CE loss 1.22. Among the four reference models, the highest AUC and F1-score were 0.94 and 0.80, separately, which were both lower than those for the simple and similarity-based kNN models. CONCLUSIONS: This learning-based method opened an opportunity for similarity measurement based on heterogeneous EMR data and supported the secondary use of EMR data.

Measurement and application of patient similarity in personalized predictive modeling based on electronic medical records.

BACKGROUND: Conventional risk prediction techniques may not be the most suitable approach for personalized prediction for individual patients. Therefore, individualized predictive modeling based on similar patients has emerged. This study aimed to propose a comprehensive measurement of patient similarity using real-world electronic medical records data, and evaluate the effectiveness of the individualized prediction of a patient's diabetes status based on the patient similarity. RESULTS: When using no more than 30% of the whole training sample, the personalized predictive models outperformed corresponding traditional models built on randomly selected training samples of the same size as the personalized models (P < 0.001 for all). With only the top 1000 (10%), 700 (7%) and 1400 (14%) similar samples, personalized random forest, k-nearest neighbor and logistic regression models reached the globally optimal performance with the area under the receiver-operating characteristic (ROC) curve of 0.90, 0.82 and 0.89, respectively. CONCLUSIONS: The proposed patient similarity measurement was effective when developing personalized predictive models. The successful application of patient similarity in predicting a patient's diabetes status provided useful references for diagnostic decision-making support by investigating the evidence on similar patients.

Study on Patient Similarity Measurement Based on Electronic Medical Records.

A comprehensive scheme of patient similarity based on different types of patient features and the corresponding similarity measurements was proposed. Patient similarity was used in building a predictive model where training samples similar to the index patient were selected instead of randomly selected samples. The predictive models using the proposed patient similarity measurement outperformed those using Euclidean distance based similarity and those not using patient similarity.

Implementation of Enterprise Imaging Strategy at a Chinese Tertiary Hospital.

Medical images have become increasingly important in clinical practice and medical research, and the need to manage images at the hospital level has become urgent in China. To unify patient identification in examinations from different medical specialties, increase convenient access to medical images under authentication, and make medical images suitable for further artificial intelligence investigations, we implemented an enterprise imaging strategy by adopting an image integration platform as the main tool at Xuanwu Hospital. Workflow re-engineering and business system transformation was also performed to ensure the quality and content of the imaging data. More than 54 million medical images and approximately 1 million medical reports were integrated, and uniform patient identification, images, and report integration were made available to the medical staff and were accessible via a mobile application, which were achieved by implementing the enterprise imaging strategy. However, to integrate all medical images of different specialties at a hospital and ensure that the images and reports are qualified for data mining, some further policy and management measures are still needed.

Application safety evaluation of the radio frequency identification tag under magnetic resonance imaging.

BACKGROUND: Radio Frequency Identification(RFID) has been widely used in healthcare facilities, but it has been paid little attention whether RFID applications are safe enough under healthcare environment. The purpose of this study is to assess the effects of RFID tags on Magnetic Resonance (MR) imaging in a typical electromagnetic environment in hospitals, and to evaluate the safety of their applications. METHODS: A Magphan phantom was used to simulate the imaging objects, while active RFID tags were placed at different distances (0, 4, 8, 10 cm) from the phantom border. The phantom was scanned by using three typical sequences including spin-echo (SE) sequence, gradient-echo (GRE) sequence and inversion-recovery (IR) sequence. The quality of the image was quantitatively evaluated by using signal-to-noise ratio (SNR), uniformity, high-contrast resolution, and geometric distortion. RFID tags were read by an RFID reader to calculate their usable rate. RESULTS: RFID tags can be read properly after being placed in high magnetic field for up to 30 minutes. SNR: There were no differences between the group with RFID tags and the group without RFID tags using SE and IR sequence, but it was lower when using GRE sequence.Uniformity: There was a significant difference between the group with RFID tags and the group without RFID tags using SE and GRE sequence. Geometric distortion and high-contrast resolution: There were no obvious differences found. CONCLUSIONS: Active RFID tags can affect MR imaging quality, especially using the GRE sequence. Increasing the distance from the RFID tags to the imaging objects can reduce that influence. When the distance was longer than 8 cm, MR imaging quality were almost unaffected. However, the Gradient Echo related sequence is not recommended when patients wear a RFID wristband.

Design and application of an information system for the emergency observation room in a Chinese hospital.

The emergency observation room (EOR) in a Chinese hospital provides medium-term observation and treatment, as well holding patients who will be admitted to the wards. The operational pattern of the EOR lies between those of the outpatient and inpatient services. We developed a novel information system for the EOR to meet the specific requirements for issuing medication, which includes both order sheets and prescriptions, and tested it in a Grade 3 and Class A hospital. The system reduced the frequency of cashier interactions and the time taken for patients to access their medications, and also reduced the workloads of doctors and other staff members.

An objective evaluation method designed for pulsating cardiac phantom with 64-row MDCT.

In the research of non-invasive cardiac coronary imaging with multi-detector CT (MDCT), it is necessary to use a standard cardiac phantom to perform the mass repetitive experiments. The standard phantom can help to investigate the regularity of a technology, and hence provide the instructions to clinic. In this study, an objective evaluation method of coronary stenosis rate, which can process CT images automatically, is developed with a cardiac phantom, to enhance working efficiency and to reduce subjective error. Several experiments were designed to verify the accuracy, the sensitivity and the consistency of this method. Based on the results, we found the accuracy of this objective method is within the clinical acceptable range. This method is sensitive to image quality change, and the results of the method are consistent without being affected by the environment and the operators. This proposed method can help to improve the efficiency of processing mass experimental data based on the cardiac phantom and establish a good foundation for the research on the cardiac coronary imaging with MDCT. This method is also applied to clinical images for tests and acceptable results are achieved in stenosis of low density.

64-MDCT coronary angiography: phantom study of effects of vascular attenuation on detection of coronary stenosis.

OBJECTIVE: The purpose of this study was to investigate the effects of vascular attenuation on the accuracy of stenosis evaluation with 64-MDCT coronary angiography. MATERIALS AND METHODS: A pulsating cardiac phantom was used to simulate the beating heart and coronary arteries of 5 and 3 mm in diameter with three degrees of stenosis (25%, 50%, and 75%) at a heart rate of 55 beats per minute. Coronary vascular enhancement had four attenuation levels: low, 200 H; moderately low, 300 H; moderately high, 350 H; and high, 500 H. Cardiac scans were obtained with 64-MDCT. Percentage stenosis, plaque area, and plaque density were measured on axial images. RESULTS: For 50% and 75% stenosis in 5-mm vessels, there were no significant differences among the four attenuation groups. For 50% and 75% stenosis in 3-mm vessels, significant underestimation of percentage stenosis occurred in the high-attenuation group compared with the moderate- and low-attenuation groups (p < 0.05). For 25% stenosis in 5-mm vessels, low attenuation led to significant overestimation of degree of stenosis compared with the moderate and high attenuation levels (p < 0.05). None of the instances of 25% stenosis in 3-mm vessels were detected in the high-attenuation group. Underestimation was found only for 3-mm vessels. For 75% stenosis, all plaques were detected irrespective of contrast attenuation and vessel size. CONCLUSION: Use of higher attenuation leads to a significant underestimation of stenosis in smaller vessels. Lower attenuation leads to slight and clinically acceptable overestimation of stenosis. The optimal vascular attenuation for stenosis detection in coronary 64-MDCT angiography is approximately 350 H.

Effect of dose-reduced scan protocols on cardiac coronary image quality with 64-row MDCT: a cardiac phantom study.

OBJECTIVE: To evaluate the feasibility of using relative low-dose scan protocols in coronary imaging with 64-row MDCT. MATERIALS AND METHODS: A pulsating cardiac phantom was used to simulate coronary arteries of two sizes (3 and 5mm in diameter) with three stenosis degrees (25, 50 and 75%) at 55bpm heart rate. Cardiac scans were performed on a 64-row MDCT scanner (GE LightSpeed VCT) with rotation time of 350ms and pitch of 0.2 under six different scan protocols: 120kV/650mA, 1137.5mAs (effective) (CTDI(vol) 121.69mGy), 120kV/550mA, 962.5mAs (CTDI(vol) 102.96mGy), 120kV/450mA, 787.5mAs (CTDI(vol) 84.24mGy), 120kV/350mA, 612.5mAs (CTDI(vol) 65.52mGy), 100kV/590mA, 1032.5mAs (CTDI(vol) 65.17mGy) and 140kV/390mA, 682.5mAs (CTDI(vol) 102.22mGy). The simulative coronary arteries were filled with contrast media to reach 300HU in the lumen. Background noise was measured to describe the basic image quality accordingly. CNR, SNR and contour sharpness represented in slope of CT density curve was calculated as well. Measured stenosis area and rates, described by the percentage area of stenosis on the cross-section images were also calculated. RESULTS: The corresponding image noise levels described in standard deviation of background signals varied with radiation dose, CNR and SNR mainly varied with tube current. The contour sharpness, which can reflect actual spatial resolution, is affected mainly by tube voltage. The first five protocols depicted obviously steeper curves than the sixth one (P<0.05). As for 25% stenosis, there was no significant difference among the stenosis rates of the six protocols (P>0.05). As for evaluation on 50 and 75% stenosis, there was no significant difference between the first two protocols, and between the second two protocols as well. However, significant difference presented between these two groups (P>0.05). When comparing the groups with similar radiation dose, protocols with lower tube voltage gain more accuracy in representing stenosis area and rate. CONCLUSION: Dose level and corresponding image quality is relevant to the accuracy of stenosis evaluation on simulated coronary arteries with 64-row MDCT. In this study, we find relative low-dose protocols with acceptable image quality showed a tendency of overestimating stenosis. Furthermore, using a lower tube voltage and higher tube current to gain accurate imaging result is more applicable than other protocols with the same radiation dose level.

[Effect of fibrinogen on the adherence of Porphyromonas gingivalis to human oral epithelial cells].

OBJECTIVE: To study the role of fibrinogen molecule in the pathogenesis of periodontal diseases. METHODS: An in vitro cell culture model was used. Methyl-(3)H Thymidine radiolabeled Porphyromonas gingivalis (Pg) ATCC 33277 were examined for their ability to adhere to and invade the confluent monolayers of human oral epithelial KB cells with or without exogenous human fibrinogens by scintillation spectrometry. RESULTS: The addition of exogenous fibrinogens made more amount of and higher ratios of adhesive and invasive Pg, in contrast to the group without exogenous fibrinogen (P < 0.001). At different concentrations of exogenous fibrinogen, the amount and ratios of adhesive and invasive Pg varied significantly (P < or = 0.007). The higher concentrations of exogenous fibrinogen was added, the greater amount and ratios of adhesive and invasive Pg were found. CONCLUSIONS: Fibrinogen promotes the adherence of Pg to human oral epithelial cells and may play an important role in the pathogenesis of periodontal diseases.