A Patient Similarity Network (CHDmap) to Predict Outcomes After Congenital Heart Surgery: Development and Validation Study.

Background: Although evidence-based medicine proposes personalized care that considers the best evidence, it still fails to address personal treatment in many real clinical scenarios where the complexity of the situation makes none of the available evidence applicable. "Medicine-based evidence" (MBE), in which big data and machine learning techniques are embraced to derive treatment responses from appropriately matched patients in real-world clinical practice, was proposed. However, many challenges remain in translating this conceptual framework into practice. Objective: This study aimed to technically translate the MBE conceptual framework into practice and evaluate its performance in providing general decision support services for outcomes after congenital heart disease (CHD) surgery. Methods: Data from 4774 CHD surgeries were collected. A total of 66 indicators and all diagnoses were extracted from each echocardiographic report using natural language processing technology. Combined with some basic clinical and surgical information, the distances between each patient were measured by a series of calculation formulas. Inspired by structure-mapping theory, the fusion of distances between different dimensions can be modulated by clinical experts. In addition to supporting direct analogical reasoning, a machine learning model can be constructed based on similar patients to provide personalized prediction. A user-operable patient similarity network (PSN) of CHD called CHDmap was proposed and developed to provide general decision support services based on the MBE approach. Results: Using 256 CHD cases, CHDmap was evaluated on 2 different types of postoperative prognostic prediction tasks: a binary classification task to predict postoperative complications and a multiple classification task to predict mechanical ventilation duration. A simple poll of the k-most similar patients provided by the PSN can achieve better prediction results than the average performance of 3 clinicians. Constructing logistic regression models for prediction using similar patients obtained from the PSN can further improve the performance of the 2 tasks (best area under the receiver operating characteristic curve=0.810 and 0.926, respectively). With the support of CHDmap, clinicians substantially improved their predictive capabilities. Conclusions: Without individual optimization, CHDmap demonstrates competitive performance compared to clinical experts. In addition, CHDmap has the advantage of enabling clinicians to use their superior cognitive abilities in conjunction with it to make decisions that are sometimes even superior to those made using artificial intelligence models. The MBE approach can be embraced in clinical practice, and its full potential can be realized.

Improved Transcranial Plane-Wave Imaging With Learned Speed-of-Sound Maps.

Although transcranial ultrasound plane-wave imaging (PWI) has promising clinical application prospects, studies have shown that variable speed-of-sound (SoS) would seriously damage the quality of ultrasound images. The mismatch between the conventional constant velocity assumption and the actual SoS distribution leads to the general blurring of ultrasound images. The optimization scheme for reconstructing transcranial ultrasound image is often solved using iterative methods like full-waveform inversion. These iterative methods are computationally expensive and based on prior magnetic resonance imaging (MRI) or computed tomography (CT) information. In contrast, the multi-stencils fast marching (MSFM) method can produce accurate time travel maps for the skull with heterogeneous acoustic speed. In this study, we first propose a convolutional neural network (CNN) to predict SoS maps of the skull from PWI channel data. Then, use these maps to correct the travel time to reduce transcranial aberration. To validate the performance of the proposed method, numerical, phantom and intact human skull studies were conducted using a linear array transducer (L11-5v, 128 elements, pitch = 0.3 mm). Numerical simulations demonstrate that for point targets, the lateral resolution of MSFM-restored images increased by 65%, and the center position shift decreased by 89%. For the cyst targets, the eccentricity of the fitting ellipse decreased by 75%, and the center position shift decreased by 58%. In the phantom study, the lateral resolution of MSFM-restored images was increased by 49%, and the position shift was reduced by 1.72 mm. This pipeline, termed AutoSoS, thus shows the potential to correct distortions in real-time transcranial ultrasound imaging, as demonstrated by experiments on the intact human skull.

RDmaster: A novel phenotype-oriented dialogue system supporting differential diagnosis of rare disease.

BACKGROUND: Clinicians often lack the necessary expertise to differentially diagnose multiple underlying rare diseases (RDs) due to their complex and overlapping clinical features, leading to misdiagnoses and delayed treatments. The aim of this study is to develop a novel electronic differential diagnostic support system for RDs. METHOD: Through integrating two Bayesian diagnostic methods, a candidate list was generated with enhance clinical interpretability for the further Q&A based differential diagnosis (DDX). To achieve an efficient Q&A dialogue strategy, we introduce a novel metric named the adaptive information gain and Gini index (AIGGI) to evaluate the expected gain of interrogated phenotypes within real-time diagnostic states. RESULTS: This DDX tool called RDmaster has been implemented as a web-based platform (http://rdmaster.nbscn.org/). A diagnostic trial involving 238 published RD patients revealed that RDmaster outperformed existing RD diagnostic tools, as well as ChatGPT, and was shown to enhance the diagnostic accuracy through its Q&A system. CONCLUSIONS: The RDmaster offers an effective multi-omics differential diagnostic technique and outperforms existing tools and popular large language models, particularly enhancing differential diagnosis in collecting diagnostically beneficial phenotypes.

Re-ordered fuzzy conformance checking for uncertain clinical records.

Modern hospitals implement clinical pathways to standardize patients' treatments. Conformance checking techniques provide an automated tool to assess whether the actual executions of clinical processes comply with the corresponding clinical pathways. However, clinical processes are typically characterized by a high degree of uncertainty, both in their execution and recording. This paper focuses on uncertainty related to logging clinical processes. The logging of the activities executed during a clinical process in the hospital information system is often performed manually by the involved actors (e.g., the nurses). However, such logging can occur at a different time than the actual execution time, which hampers the reliability of the diagnostics provided by conformance checking techniques. To address this issue, we propose a novel conformance checking algorithm that leverages principles of fuzzy set theory to incorporate experts' knowledge when generating conformance diagnostics. We exploit this knowledge to define a fuzzy tolerance in a time window, which is then used to assess the magnitude of timestamp violations of the recorded activities when evaluating the overall process execution compliance. Experiments conducted on a real-life case study in a Dutch hospital show that the proposed method obtains more accurate diagnostics than the state-of-the-art approaches. We also consider how our diagnostics can be used to stimulate discussion with domain experts on possible strategies to mitigate logging uncertainty in the clinical practice.

Multi-Feature Map Integrated Attention Model for Early Prediction of Type 2 Diabetes Using Irregular Health Examination Records.

Type 2 diabetes (T2D) is a worldwide chronic disease that is difficult to cure and causes a heavy social burden. Early prediction of T2D can effectively identify high-risk populations and facilitate earlier implementation of appropriate preventive interventions. Various early prediction models for T2D have been proposed. However, these methods do not consider the following factors: 1) health examination records (HER) containing health information before diagnosis; 2) rating information containing clinical knowledge; and 3) local and global information of time-series features. These diagnostically relevant factors need to be considered. It is challenging due to irregular and multivariate time series. In this paper, we propose the multi-feature map integrated attention model (MFMAM) for early diabetes prediction using HER. Specifically, HER is converted into the multi-feature map to capture local and global volatility, as well as the sequence order of high-dimensional features. We concatenate rating indicators to introduce clinical knowledge. In addition, considering missing and temporal patterns, we utilize missing and time embedding to learn the complex transition of health status. We adopt attention mechanisms to capture essential features (channels) and time points (spatial). To evaluate the proposed model, we conducted experiments on real-world long-term HER. The results demonstrated that MFMAM outperformed baseline models on tasks of varying sequence lengths and prediction windows. Moreover, we applied our designs to baseline models, and their performance was considerably improved. The proposed model contributes to the short-term and long-term early prediction of T2D in individuals with varying information richness.

Transcranial Acoustic Metamaterial Parameters Inverse Designed by Neural Networks.

Objective: The objective of this work is to investigate the mapping relationship between transcranial ultrasound image quality and transcranial acoustic metamaterial parameters using inverse design methods. Impact Statement: Our study provides insights into inverse design methods and opens the route to guide the preparation of transcranial acoustic metamaterials. Introduction: The development of acoustic metamaterials has enabled the exploration of cranial ultrasound, and it has been found that the influence of the skull distortion layer on acoustic waves can be effectively eliminated by adjusting the parameters of the acoustic metamaterial. However, the interaction mechanism between transcranial ultrasound images and transcranial acoustic metamaterial parameters is unknown. Methods: In this study, 1,456 transcranial ultrasound image datasets were used to explore the mapping relationship between the quality of transcranial ultrasound images and the parameters of transcranial acoustic metamaterials. Results: The multioutput parameter prediction model of transcranial metamaterials based on deep back-propagation neural network was built, and metamaterial parameters under transcranial image evaluation indices are predicted using the prediction model. Conclusion: This inverse big data design approach paves the way for guiding the preparation of transcranial metamaterials.

Automatic ICD-10 coding: Deep semantic matching based on analogical reasoning.

Background: ICD-10 has been widely used in statistical analysis of mortality rates and medical reimbursement. Automatic ICD-10 coding is desperately needed because manually assigning codes is expensive, time-consuming, and labor-intensive. Diagnoses described in medical records differ significantly from those used in ICD-10 classification, making it impossible for existing automatic coding techniques to perform well enough to support medical billing, resource allocation, and research requirements. Meanwhile, most of the current automatic coding approaches are oriented toward English ICD-10. This method for automatically assigning ICD-10 codes to diagnoses extracted from Chinese discharge records was provided in this paper. Method: First, BERT creates word representations of the two texts. Second, the context representation layer incorporates contextual information into the representation of each time step of the word representations using a bidirectional Long Short-Term Memory. Third, the matching layer compares each contextual embedding of the uncoded diagnosis record against a weighted version of all contextual character embeddings of the manually coded diagnosis record. The matching strategy is element-wise subtraction and element-wise multiplication and then through a neural network layer. Fourth, the matching vectors are combined using a one-layer convolutional neural network. A sigmoid is then used to output matching results. Results: To evaluate the proposed method, 1,003,558 manually coded primary diagnoses were gathered from the homepage of the discharge medical records. The experimental results showed that the proposed method outperformed popular deep semantic matching algorithms, such as DSSM, ConvNet, ESIM, and ABCNN, and demonstrated state-of-the-art results in a single text matching with an accuracy of 0.986, a precision of 0.979, a recall of 0.983, and an F1-score of 0.981. Conclusion: The automatic ICD-10 coding of Chinese diagnoses is successful when using the proposed deep semantic matching approach based on analogical reasoning.

Systematic exploration of eczema-associated paediatric diseases in a Chinese population of millions: A retrospective observation study.

BACKGROUND: Eczema is the most common form of dermatitis and also the starting point of atopic march. Although many eczema-associated allergic and immunologic disorders have been studied, there remains a gap in the systematic quantitative knowledge regarding the relationships between all childhood disorders and eczema. This study aimed to systematically explore eczema-associated childhood diseases using a real-world, long-term clinical dataset generated from millions of children in China. METHODS: Data were collected at 8,907,735 outpatient healthcare visits from 2,592,147 children between January 1, 2013, and August 15, 2019, at the largest comprehensive pediatric medical center in Zhejiang Province of China. The period prevalence differences in various pediatric diseases between children with and without eczema were used to test the independence of various pediatric disorders and eczema using Fisher's exact test. Bonferroni correction was used to adjust the p value in multiple testing. Odds ratio >2 with 95% confidence interval not including 1 and adjusted p < 0.05 was used to identify eczema-associated diseases. RESULTS: Overall, 234 pediatric disorders were identified from more than 6000 different pediatric disorders. An interactive eczema-associated disease map that has related quantitative epidemiological features called ADmap was published at http://pedmap.nbscn.org/admap. Thirty-six of these disease associations have not been reported in previous studies. CONCLUSION: This systematic exploratory study confirmed the associations of many well-known diseases with eczema in Chinese children and also identified some novel and interesting associations. These results are valuable for the development of a comprehensive approach to the management of eczema in childhood.

A robust phenotype-driven likelihood ratio analysis approach assisting interpretable clinical diagnosis of rare diseases.

Phenotype-based prioritization of candidate genes and diseases has become a well-established approach for multi-omics diagnostics of rare diseases. Most current algorithms exploit semantic analysis and probabilistic statistics based on Human Phenotype Ontology and are commonly superior to naive search methods. However, these algorithms are mostly less interpretable and do not perform well in real clinical scenarios due to noise and imprecision of query terms, and the fact that individuals may not display all phenotypes of the disease they belong to. We present a Phenotype-driven Likelihood Ratio analysis approach (PheLR) assisting interpretable clinical diagnosis of rare diseases. With a likelihood ratio paradigm, PheLR estimates the posterior probability of candidate diseases and how much a phenotypic feature contributes to the prioritization result. Benchmarked using simulated and realistic patients, PheLR shows significant advantages over current approaches and is robust to noise and inaccuracy. To facilitate clinical practice and visualized differential diagnosis, PheLR is implemented as an online web tool (https://phelr.nbscn.org).

Dealing With Missing, Imbalanced, and Sparse Features During the Development of a Prediction Model for Sudden Death Using Emergency Medicine Data: Machine Learning Approach.

BACKGROUND: In emergency departments (EDs), early diagnosis and timely rescue, which are supported by prediction modes using ED data, can increase patients' chances of survival. Unfortunately, ED data usually contain missing, imbalanced, and sparse features, which makes it challenging to build early identification models for diseases. OBJECTIVE: This study aims to propose a systematic approach to deal with the problems of missing, imbalanced, and sparse features for developing sudden-death prediction models using emergency medicine (or ED) data. METHODS: We proposed a 3-step approach to deal with data quality issues: a random forest (RF) for missing values, k-means for imbalanced data, and principal component analysis (PCA) for sparse features. For continuous and discrete variables, the decision coefficient R2 and the κ coefficient were used to evaluate performance, respectively. The area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) were used to estimate the model's performance. To further evaluate the proposed approach, we carried out a case study using an ED data set obtained from the Hainan Hospital of Chinese PLA General Hospital. A logistic regression (LR) prediction model for patient condition worsening was built. RESULTS: A total of 1085 patients with rescue records and 17,959 patients without rescue records were selected and significantly imbalanced. We extracted 275, 402, and 891 variables from laboratory tests, medications, and diagnosis, respectively. After data preprocessing, the median R2 of the RF continuous variable interpolation was 0.623 (IQR 0.647), and the median of the κ coefficient for discrete variable interpolation was 0.444 (IQR 0.285). The LR model constructed using the initial diagnostic data showed poor performance and variable separation, which was reflected in the abnormally high odds ratio (OR) values of the 2 variables of cardiac arrest and respiratory arrest (201568034532 and 1211118945, respectively) and an abnormal 95% CI. Using processed data, the recall of the model reached 0.746, the F1-score was 0.73, and the AUROC was 0.708. CONCLUSIONS: The proposed systematic approach is valid for building a prediction model for emergency patients.

A time-aware attention model for prediction of acute kidney injury after pediatric cardiac surgery.

OBJECTIVE: Acute kidney injury (AKI) is a common complication after pediatric cardiac surgery, and the early detection of AKI may allow for timely preventive or therapeutic measures. However, current AKI prediction researches pay less attention to time information among time-series clinical data and model building strategies that meet complex clinical application scenario. This study aims to develop and validate a model for predicting postoperative AKI that operates sequentially over individual time-series clinical data. MATERIALS AND METHODS: A retrospective cohort of 3386 pediatric patients extracted from PIC database was used for training, calibrating, and testing purposes. A time-aware deep learning model was developed and evaluated from 3 clinical perspectives that use different data collection windows and prediction windows to answer different AKI prediction questions encountered in clinical practice. We compared our model with existing state-of-the-art models from 3 clinical perspectives using the area under the receiver operating characteristic curve (ROC AUC) and the area under the precision-recall curve (PR AUC). RESULTS: Our proposed model significantly outperformed the existing state-of-the-art models with an improved average performance for any AKI prediction from the 3 evaluation perspectives. This model predicted 91% of all AKI episodes using data collected at 24 h after surgery, resulting in a ROC AUC of 0.908 and a PR AUC of 0.898. On average, our model predicted 83% of all AKI episodes that occurred within the different time windows in the 3 evaluation perspectives. The calibration performance of the proposed model was substantially higher than the existing state-of-the-art models. CONCLUSIONS: This study showed that a deep learning model can accurately predict postoperative AKI using perioperative time-series data. It has the potential to be integrated into real-time clinical decision support systems to support postoperative care planning.

An end-to-end tracking method for polyp detectors in colonoscopy videos.

Deep learning based computer-aided diagnosis technology demonstrates an encouraging performance in aspect of polyp lesion detection on reducing the miss rate of polyps during colonoscopies. However, to date, few studies have been conducted for tracking polyps that have been detected in colonoscopy videos, which is an essential and intuitive issue in clinical intelligent video analysis task (e.g. lesion counting, lesion retrieval, report generation). In the paradigm of conventional tracking-by-detection system, detection task for lesion localization is separated from the tracking task for cropped lesions re-identification. In the multi object tracking problem, each target is supposed to be tracked by invoking a tracker after the detector, which introduces multiple inferences and leads to external resource and time consumption. To tackle these problems, we proposed a plug-in module named instance tracking head (ITH) for synchronous polyp detection and tracking, which can be simply inserted into object detection frameworks. It embeds a feature-based polyp tracking procedure into the detector frameworks to achieve multi-task model training. ITH and detection head share the model backbone for low level feature extraction, and then low level feature flows into the separate branches for task-driven model training. For feature maps from the same receptive field, the region of interest head assigns these features to the detection head and the ITH, respectively, and outputs the object category, bounding box coordinates, and instance feature embedding simultaneously for each specific polyp target. We also proposed a method based on similarity metric learning. The method makes full use of the prior boxes in the object detector to provide richer and denser instance training pairs, to improve the performance of the model evaluation on the tracking task. Compared with advanced tracking-by-detection paradigm methods, detectors with proposed ITH can obtain comparative tracking performance but approximate 30% faster speed. Optimized model based on Scaled-YOLOv4 detector with ITH illustrates good trade-off between detection (mAP 91.70%) and tracking (MOTA 92.50% and Rank-1 Acc 88.31%) task at the frame rate of 66 FPS. The proposed structure demonstrates the potential to aid clinicians in real-time detection with online tracking or offline retargeting of polyp instances during colonoscopies.

SNPMap-An integrated visual SNP interpretation tool.

New technologies, such as next-generation sequencing, have advanced the ability to diagnose diseases and improve prognosis but require the identification of thousands of variants in each report based on several databases scattered across places. Curating an integrated interpretation database is time-consuming, costly, and needs regular update. On the other hand, the automatic curation of knowledge sources always results in overloaded information. In this study, an automated pipeline was proposed to create an integrated visual single-nucleotide polymorphism (SNP) interpretation tool called SNPMap. SNPMap pipelines periodically obtained SNP-related information from LitVar, PubTator, and GWAS Catalog API tools and presented it to the user after extraction, integration, and visualization. Keywords and their semantic relations to each SNP are rendered into two graphs, with their significance represented by the size/width of circles/lines. Moreover, the most related SNPs for each keyword that appeared in SNPMap were calculated and sorted. SNPMap retains the advantage of an automatic process while assisting users in accessing more lucid and detailed information through visualization and integration with other materials.

An ensemble learning with active sampling to predict the prognosis of postoperative non-small cell lung cancer patients.

BACKGROUND: Lung cancer is the leading cause of cancer death worldwide. Prognostic prediction plays a vital role in the decision-making process for postoperative non-small cell lung cancer (NSCLC) patients. However, the high imbalance ratio of prognostic data limits the development of effective prognostic prediction models. METHODS: In this study, we present a novel approach, namely ensemble learning with active sampling (ELAS), to tackle the imbalanced data problem in NSCLC prognostic prediction. ELAS first applies an active sampling mechanism to query the most informative samples to update the base classifier to give it a new perspective. This training process is repeated until no enough samples are queried. Next, an internal validation set is employed to evaluate the base classifiers, and the ones with the best performances are integrated as the ensemble model. Besides, we set up multiple initial training data seeds and internal validation sets to ensure the stability and generalization of the model. RESULTS: We verified the effectiveness of the ELAS on a real clinical dataset containing 1848 postoperative NSCLC patients. Experimental results showed that the ELAS achieved the best averaged 0.736 AUROC value and 0.453 AUPRC value for 6 prognostic tasks and obtained significant improvements in comparison with the SVM, AdaBoost, Bagging, SMOTE and TomekLinks. CONCLUSIONS: We conclude that the ELAS can effectively alleviate the imbalanced data problem in NSCLC prognostic prediction and demonstrates good potential for future postoperative NSCLC prognostic prediction.

Deep Dynamic Patient Similarity Analysis: Model Development and Validation in ICU.

BACKGROUND: Personalized medicine requires the patient similarity analysis for providing specific treatments tailed for each patient. However, the patient similarity analysis in personalized clinical scenarios encounters challenges, which are twofold. First, heterogeneous and multi-type data are usually recorded to Electronic Health Records (EHRs) during the course of admissions, which makes it difficult to measure the patient similarity. Second, disease progression manifests diverse disease states at different times, which brings sequential complexity to dynamically retrieve similar patients' sequences. MATERIALS AND METHODS: To overcome the above-mentioned challenges, we propose a novel dynamic patient similarity analysis model based on deep learning. Specifically, the proposed model embeds the multi-type and heterogeneous data into hidden representations with a specially designed embedding and attention module. Thereafter, the proposed model retrieves similar patients' sequences based on these hidden representations in a dynamic manner. More importantly, we adopt two clinical tasks, i.e., diagnosis prediction and medication recommendation, to validate the effectiveness of the proposed model. It is worth noticing that the proposed model integrates a drug-drug interaction (DDI) knowledge graph in the medication recommendation task to reduce adverse reactions caused by combinational treatments, such that a more rational strategy can be realized. We evaluate our proposed model using the critical care database MIMIC-III, which includes 5,430 patients covering 14,096 clinical visits. RESULTS: The proposed model outperforms several state-of-the-art methods. For diagnosis prediction, the average PR-AUC score of the proposed model reaches 0.6200, which is significantly higher than that of the baseline models (0.2497∼0.5407). Meanwhile, for medication recommendation, the average PR-AUC of the proposed model is 0.6682 (Jaccard: 0.4070; F1: 0.5672; Recall: 0.7832) whereas the K-nearest model can only reach 0.3805 (Jaccard: 0.3911; F1: 0.5465; Recall: 0.5705). In addition, our proposed model achieves a lower DDI rate. CONCLUSION: We propose a novel dynamic patient similarity analysis model, which can be implemented into a decision support system for clinical tasks including diagnosis prediction, surgical procedure selection, medication recommendation, etc. Also, the proposed model serves as an explainable protocol in clinical practice thanks to its analogy to real clinical reasoning where a doctor diagnoses diseases and prescribes medications according to the previous cured patients empirically.

Making Specific Plan Improves Physical Activity and Healthy Eating for Community-Dwelling Patients With Chronic Conditions: A Systematic Review and Meta-Analysis.

Background: Implementation intention formed by making a specific action plan has been proved effective in improving physical activity (PA) and dietary behavior (DB) for the general, healthy population, but there has been no meta-analysis of their effectiveness for patients with chronic conditions. This research aims to analyze several explanatory factors and overall effect of implementation intention on behavioral and health-related outcomes among community-dwelling patients. Methods: We searched CIHNAL (EBSCO), PUBMED, Web of Science, Science Direct, SAGE Online, Springer Link, Taylor & Francis, Scopus, Wiley Online Library, CNKI, and five other databases for eligible studies. Random-effects meta-analysis was conducted to estimate effect sizes of implementation intention on outcomes, including PA, DB, weight, and body mass index. And the eligible studies were assessed by the Cochrane Collaboration's tool for risk of bias assessment. Sensitivity analysis adopted sequential algorithm and the p-curve analysis method. Results: A total of 54 studies were identified. Significant small effect sizes of the intervention were found for PA [standard mean difference (SMD) 0.24, 95% confidence interval (CI) (0.10, 0.39)] and for the DB outcome [SMD -0.25, 95% CI (-0.34, -0.15)]. In moderation analysis, the intervention was more effective in improving PA for men (p < 0.001), older adults (p = 0.006), and obese/overweight patients with complications (p = 0.048) and when the intervention was delivered by a healthcare provider (p = 0.01). Conclusion: Implementation intentions are effective in improving PA and DB for community dwelling patients with chronic conditions. The review provides evidence to support the future application of implementation intention intervention. Besides, the findings from this review offer different directions to enhance the effectiveness of this brief and potential intervention in improving patients' PA and DB. Systematic Review Registration: https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=160491.

Ultrasonic Methods for Brain Imaging: Techniques and Implications.

Brain imaging technology is widely used in the diagnosis of brain diseases. Computed tomography and magnetic resonance imaging are the most common imaging modalities used for clinical brain imaging, whereas ultrasound is rarely used because the skull substantially reduces the incident energy of ultrasonic waves to levels too low for imaging. However, remarkable developments of novel technologies in ultrasound brain imaging have been achieved recently, including Doppler-based imaging, contrast agent imaging, ultrasound elastography, and phase compensation imaging. Doppler-based imaging, including ultrafast Doppler imaging and functional ultrasound, is able to obtain reliable cerebral blood volume changes and has the best penetration depth and a better spatiotemporal resolution. Contrast agent brain imaging, including ultrasound localization microscopy, can obtain super spatial resolution vasculature maps over a large region within a few minutes of acquisition and reconstruction time. Ultrasound elastography reflects the stiffness of brain tissues. Phase correction imaging, such as time reversal mirror and spatiotemporal inverse filter, aims at focusing smoothly in the skull. These methods have been widely performed on animal models, newborn children, and adults in preclinical studies, with results demonstrating great potential in the diagnosis and treatment of brain diseases. This review discusses the ultrasound methods developed in recent years for brain imaging and highlights the promising future they hold.

Risk factors for central venous catheter-associated deep venous thrombosis in pediatric critical care settings identified by fusion model.

BACKGROUND: An increase in the incidence of central venous catheter (CVC)-related thrombosis (CRT) has been reported in pediatric intensive care patients over the past decade. Risk factors for the development of CRT are not well understood, especially in children. The study objective was to identify potential clinical risk factors associated with CRT with novel fusion machine learning models. METHODS: Patients aged 0-18 who were admitted to intensive care units from December 2015 to December 2018 and underwent at least one CVC placement were included. Two fusion model approaches (stacking and blending) were used to build a better performance model based on three widely used machine learning models (logistic regression, random forest and gradient boosting decision tree). High-impact risk factors were identified based on their contribution in both fusion artificial intelligence models. RESULTS: A total of 478 factors of 3871 patients and 3927 lines were used to build fusion models, one of which achieved quite satisfactory performance (AUC = 0.82, recall = 0.85, accuracy = 0.65) in 5-fold cross validation. A total of 11 risk factors were identified based on their independent contributions to the two fusion models. Some risk factors, such as D-dimer, thrombin time, blood acid-base balance-related factors, dehydrating agents, lymphocytes and basophils were identified or confirmed to play an important role in CRT in children. CONCLUSIONS: The fusion model, which achieves better performance in CRT prediction, can better understand the risk factors for CRT and provide potential biomarkers and measures for thromboprophylaxis in pediatric intensive care settings.

Multi-label recognition of cancer-related lesions with clinical priors on white-light endoscopy.

Deep learning-based computer-aided diagnosis techniques have demonstrated encouraging performance in endoscopic lesion identification and detection, and have reduced the rate of missed and false detections of disease during endoscopy. However, the interpretability of the model-based results has not been adequately addressed by existing methods. This phenomenon is directly manifested by a significant bias in the representation of feature localization. Good recognition models experience severe feature localization errors, particularly for lesions with subtle morphological features, and such unsatisfactory performance hinders the clinical deployment of models. To effectively alleviate this problem, we proposed a solution to optimize the localization bias in feature representations of cancer-related recognition models that is difficult to accurately label and identify in clinical practice. Optimization was performed in the training phase of the model through the proposed data augmentation method and auxiliary loss function based on clinical priors. The data augmentation method, called partial jigsaw, can "break" the spatial structure of lesion-independent image blocks and enrich the data feature space to decouple the interference of background features on the space and focus on fine-grained lesion features. The annotation-based auxiliary loss function used class activation maps for sample distribution correction and led the model to present localization representation converging on the gold standard annotation of visualization maps. The results show that with the improvement of our method, the precision of model recognition reached an average of 92.79%, an F1-score of 92.61%, and accuracy of 95.56% based on a dataset constructed from 23 hospitals. In addition, we quantified the evaluation representation of visualization feature maps. The improved model yielded significant offset correction results for visualized feature maps compared with the baseline model. The average visualization-weighted positive coverage improved from 51.85% to 83.76%. The proposed approach did not change the deployment capability and inference speed of the original model and can be incorporated into any state-of-the-art neural network. It also shows the potential to provide more accurate localization inference results and assist in clinical examinations during endoscopies.

Exploring and Characterizing Patient Multibehavior Engagement Trails and Patient Behavior Preference Patterns in Pathway-Based mHealth Hypertension Self-Management: Analysis of Use Data.

BACKGROUND: Hypertension is a long-term medical condition. Mobile health (mHealth) services can help out-of-hospital patients to self-manage. However, not all management is effective, possibly because the behavior mechanism and behavior preferences of patients with various characteristics in hypertension management were unclear. OBJECTIVE: The purpose of this study was to (1) explore patient multibehavior engagement trails in the pathway-based hypertension self-management, (2) discover patient behavior preference patterns, and (3) identify the characteristics of patients with different behavior preferences. METHODS: This study included 863 hypertensive patients who generated 295,855 use records in the mHealth app from December 28, 2016, to July 2, 2020. Markov chain was used to infer the patient multibehavior engagement trails, which contained the type, quantity, time spent, sequence, and transition probability value (TP value) of patient behavior. K-means algorithm was used to group patients by the normalized behavior preference features: the number of behavioral states that a patient performed in each trail. The pages in the app represented the behavior states. Chi-square tests, Z-test, analyses of variance, and Bonferroni multiple comparisons were conducted to characterize the patient behavior preference patterns. RESULTS: Markov chain analysis revealed 3 types of behavior transition (1-way transition, cycle transition, and self-transition) and 4 trails of patient multibehavior engagement. In perform task trail (PT-T), patients preferred to start self-management from the states of task blood pressure (BP), task drug, and task weight (TP value 0.29, 0.18, and 0.20, respectively), and spent more time on the task food state (35.87 s). Some patients entered the states of task BP and task drug (TP value 0.20, 0.25) from the reminder item state. In the result-oriented trail (RO-T), patients spent more energy on the ranking state (19.66 s) compared to the health report state (13.25 s). In the knowledge learning trail (KL-T), there was a high probability of cycle transition (TP value 0.47, 0.31) between the states of knowledge list and knowledge content. In the support acquisition trail (SA-T), there was a high probability of self-transition in the questionnaire (TP value 0.29) state. Cluster analysis discovered 3 patient behavior preference patterns: PT-T cluster, PT-T and KL-T cluster, and PT-T and SA-T cluster. There were statistically significant associations between the behavior preference pattern and gender, education level, and BP. CONCLUSIONS: This study identified the dynamic, longitudinal, and multidimensional characteristics of patient behavior. Patients preferred to focus on BP, medications, and weight conditions and paid attention to BP and medications using reminders. The diet management and questionnaires were complicated and difficult to implement and record. Competitive methods such as ranking were more likely to attract patients to pay attention to their own self-management states. Female patients with lower education level and poorly controlled BP were more likely to be highly involved in hypertension health education.