Atomic-scale Ru anchored on chromium-shavings as a precursor for a pH-universal hydrogen evolution reaction electrocatalyst.

In the leather manufacturing industry, the management of substantial quantities of solid waste containing chrome shavings remains a formidable challenge. Concurrently, there is a pressing need for the development of pH-universal and economically viable electrocatalysts for the hydrogen evolution reaction (HER). In response to these intertwined challenges, this study proposes an innovative approach wherein the amino groups present on the surface of chrome shavings are utilized to immobilize single ruthenium atoms during pyrolysis, thereby facilitating the synthesis of hydrogen evolution electrocatalysts. The optimized sample, denoted as CN/Cr2O3/Ru-1, demonstrates exceptional electrocatalytic performance, exhibiting an ultra-low overpotential of -28 mV in 1.0 M KOH at a current density of 10 mA cm-2, and it also exhibits good performance in acidic and neutral electrolytes. Importantly, these overpotentials surpass those reported for many previous ruthenium-based catalysts. Density functional theory (DFT) calculations elucidate that both oxygen (O) and chromium (Cr) moieties within Cr2O3 can engage in favorable interactions with the coordination patterns of the ruthenium (Ru) atoms, thereby elucidating the synergistic enhancement conferred by the chromium element in CN/Cr2O3/Ru, which ultimately facilitates and promotes the catalytic activity of the ruthenium atoms serving as the catalytic center. This facile synthesis route not only presents a green solution for addressing waste chromium pollutants but also offers a promising avenue for the development of high-performance, cost-efficient electrocatalysts.

Fast Model Selection and Hyperparameter Tuning for Generative Models.

Generative models have gained significant attention in recent years. They are increasingly used to estimate the underlying structure of high-dimensional data and artificially generate various kinds of data similar to those from the real world. The performance of generative models depends critically on a good set of hyperparameters. Yet, finding the right hyperparameter configuration can be an extremely time-consuming task. In this paper, we focus on speeding up the hyperparameter search through adaptive resource allocation, early stopping underperforming candidates quickly and allocating more computational resources to promising ones by comparing their intermediate performance. The hyperparameter search is formulated as a non-stochastic best-arm identification problem where resources like iterations or training time constrained by some predetermined budget are allocated to different hyperparameter configurations. A procedure which uses hypothesis testing coupled with Successive Halving is proposed to make the resource allocation and early stopping decisions and compares the intermediate performance of generative models by their exponentially weighted Maximum Means Discrepancy (MMD). The experimental results show that the proposed method selects hyperparameter configurations that lead to a significant improvement in the model performance compared to Successive Halving for a wide range of budgets across several real-world applications.

Lrp10 suppresses IL7R limiting CD8 T cell homeostatic expansion and anti-tumor immunity.

Signals emanating from the T cell receptor (TCR), co-stimulatory receptors, and cytokine receptors each influence CD8 T cell fate. Understanding how these signals respond to homeostatic and microenvironmental cues can reveal new ways to therapeutically direct T cell function. Through forward genetic screening in mice, we discovered that loss-of-function mutations in LDL receptor related protein 10 ( Lrp10 ) caused naïve and central memory CD8 T cells to accumulate in peripheral lymphoid organs. Lrp10 encodes a conserved cell surface protein of unknown immunological function. Lrp10 was induced with T cell activation and its expression post-translationally suppressed IL7 receptor (IL7R) levels. Accordingly, Lrp10 deletion enhanced T cell homeostatic expansion through IL7R signaling. Lrp10 -deficient mice were also intrinsically resistant to syngeneic tumors. This phenotype depended on dense tumor infiltration of CD8 T cells that displayed increased memory cell characteristics, reduced terminal exhaustion, and augmented responses to immune checkpoint inhibition. Here, we present Lrp10 as a new negative regulator of CD8 T cell homeostasis and a host factor that controls tumor resistance with implications for immunotherapy.

TeaBERT: An Efficient Knowledge Infused Cross-Lingual Language Model for Mapping Chinese Medical Entities to the Unified Medical Language System.

Medical entity normalization is an important task for medical information processing. The Unified Medical Language System (UMLS), a well-developed medical terminology system, is crucial for medical entity normalization. However, the UMLS primarily consists of English medical terms. For languages other than English, such as Chinese, a significant challenge for normalizing medical entities is the lack of robust terminology systems. To address this issue, we propose a translation-enhancing training strategy that incorporates the translation and synonym knowledge of the UMLS into a language model using the contrastive learning approach. In this work, we proposed a cross-lingual pre-trained language model called TeaBERT, which can align synonymous Chinese and English medical entities across languages at the concept level. As the evaluation results showed, the TeaBERT language model outperformed previous cross-lingual language models with Acc@5 values of 92.54%, 87.14% and 84.77% on the ICD10-CN, CHPO and RealWorld-v2 datasets, respectively. It also achieved a new state-of-the-art cross-lingual entity mapping performance without fine-tuning. The translation-enhancing strategy is applicable to other languages that face the similar challenge due to the absence of well-developed medical terminology systems.

Recent advance of small-molecule drugs for clinical treatment of osteoporosis: A review.

Osteoporosis is a metabolic bone disorder typified by a reduction in bone mass and structural degradation of bone tissue, leading to heightened fragility and vulnerability to fractures. The incidence of osteoporosis increases with age, making it a significant public health challenge. The pathogenesis of osteoporosis involves an imbalance between osteoblast-mediated bone formation and resorption. The current treatment options for osteoporosis include bisphosphonates, hormone replacement therapy (HRT), selective estrogen receptor modulators (SERMs), and denosumab. The recent advances in small-molecule drugs for the clinical treatment of osteoporosis offer promising options for improving bone health and reducing fracture risk. This review aims to provide an overview of the clinical applications and synthetic routes of representative small-molecule drugs for the treatment of osteoporosis. A comprehensive understanding of the synthetic methods of drug molecules for osteoporosis may inspire the development of new, more effective, and practical synthetic techniques for treating this condition.

Mapping Chinese Medical Entities to the Unified Medical Language System.

Background: Chinese medical entities have not been organized comprehensively due to the lack of well-developed terminology systems, which poses a challenge to processing Chinese medical texts for fine-grained medical knowledge representation. To unify Chinese medical terminologies, mapping Chinese medical entities to their English counterparts in the Unified Medical Language System (UMLS) is an efficient solution. However, their mappings have not been investigated sufficiently in former research. In this study, we explore strategies for mapping Chinese medical entities to the UMLS and systematically evaluate the mapping performance. Methods: First, Chinese medical entities are translated to English using multiple web-based translation engines. Then, 3 mapping strategies are investigated: (a) string-based, (b) semantic-based, and (c) string and semantic similarity combined. In addition, cross-lingual pretrained language models are applied to map Chinese medical entities to UMLS concepts without translation. All of these strategies are evaluated on the ICD10-CN, Chinese Human Phenotype Ontology (CHPO), and RealWorld datasets. Results: The linear combination method based on the SapBERT and term frequency-inverse document frequency bag-of-words models perform the best on all evaluation datasets, with 91.85%, 82.44%, and 78.43% of the top 5 accuracies on the ICD10-CN, CHPO, and RealWorld datasets, respectively. Conclusions: In our study, we explore strategies for mapping Chinese medical entities to the UMLS and identify a satisfactory linear combination method. Our investigation will facilitate Chinese medical entity normalization and inspire research that focuses on Chinese medical ontology development.

Expression profile analysis to identify potential gene changes induced by dexamethasone in the trabecular meshwork.

AIM: To investigate potential gene changes in trabecular meshwork (TM) induced by dexamethasone (DEX) in steroid-induced glaucoma (SIG). METHODS: The expression data of 24 cases from a public functional genomics data were sorted to identify the mechanisms of action of DEX on the TM. The relationships of the differentially expressed genes (DEGs) were enriched using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis. In addition, the hub genes were screened by the Search Tool for the Retrieval of Interacting Genes Database (STRING) and Cytoscape tools. Finally, human TM cells (HTMCs) were treated with DEX to preliminarily explore the function of hub genes. RESULTS: Totally 47 DEGs, including 21 downregulated and 26 upregulated genes were identified. The primary enriched results of the DEGs consisted of inflammatory response, extracellular matrix (ECM), negative regulation of cell proliferation, TNF signalling pathway and the regulation of tryptophan channels by inflammatory mediators. Subsequently, pro-melanin-enriched hormone (PMCH) and Bradykinin B1 receptor (BDKRB1) were screened as hub genes. It is verified in GSE37474 data set. Western blot and quantitative real-time polymerase chain reaction (qPCR) results showed that protein and RNA expression levels of BDKRB1 were significantly decreased after DEX treatment, while PMCH was not significantly changed. CONCLUSION: BDKRB1 may be a key gene involved in SIG onset, providing a suitable therapeutic target for improving the prognosis of SIG patients.

Deep Phenotyping of Chinese Electronic Health Records by Recognizing Linguistic Patterns of Phenotypic Narratives With a Sequence Motif Discovery Tool: Algorithm Development and Validation.

BACKGROUND: Phenotype information in electronic health records (EHRs) is mainly recorded in unstructured free text, which cannot be directly used for clinical research. EHR-based deep-phenotyping methods can structure phenotype information in EHRs with high fidelity, making it the focus of medical informatics. However, developing a deep-phenotyping method for non-English EHRs (ie, Chinese EHRs) is challenging. Although numerous EHR resources exist in China, fine-grained annotation data that are suitable for developing deep-phenotyping methods are limited. It is challenging to develop a deep-phenotyping method for Chinese EHRs in such a low-resource scenario. OBJECTIVE: In this study, we aimed to develop a deep-phenotyping method with good generalization ability for Chinese EHRs based on limited fine-grained annotation data. METHODS: The core of the methodology was to identify linguistic patterns of phenotype descriptions in Chinese EHRs with a sequence motif discovery tool and perform deep phenotyping of Chinese EHRs by recognizing linguistic patterns in free text. Specifically, 1000 Chinese EHRs were manually annotated based on a fine-grained information model, PhenoSSU (Semantic Structured Unit of Phenotypes). The annotation data set was randomly divided into a training set (n=700, 70%) and a testing set (n=300, 30%). The process for mining linguistic patterns was divided into three steps. First, free text in the training set was encoded as single-letter sequences (P: phenotype, A: attribute). Second, a biological sequence analysis tool-MEME (Multiple Expectation Maximums for Motif Elicitation)-was used to identify motifs in the single-letter sequences. Finally, the identified motifs were reduced to a series of regular expressions representing linguistic patterns of PhenoSSU instances in Chinese EHRs. Based on the discovered linguistic patterns, we developed a deep-phenotyping method for Chinese EHRs, including a deep learning-based method for named entity recognition and a pattern recognition-based method for attribute prediction. RESULTS: In total, 51 sequence motifs with statistical significance were mined from 700 Chinese EHRs in the training set and were combined into six regular expressions. It was found that these six regular expressions could be learned from a mean of 134 (SD 9.7) annotated EHRs in the training set. The deep-phenotyping algorithm for Chinese EHRs could recognize PhenoSSU instances with an overall accuracy of 0.844 on the test set. For the subtask of entity recognition, the algorithm achieved an F1 score of 0.898 with the Bidirectional Encoder Representations from Transformers-bidirectional long short-term memory and conditional random field model; for the subtask of attribute prediction, the algorithm achieved a weighted accuracy of 0.940 with the linguistic pattern-based method. CONCLUSIONS: We developed a simple but effective strategy to perform deep phenotyping of Chinese EHRs with limited fine-grained annotation data. Our work will promote the second use of Chinese EHRs and give inspiration to other non-English-speaking countries.

PIAT: An Evolutionarily Intelligent System for Deep Phenotyping of Chinese Electronic Health Records.

Electronic health record (EHR) resources are valuable but remain underexplored because most clinical information, especially phenotype information, is buried in the free text of EHRs. An intelligent annotation tool plays an important role in unlocking the full potential of EHRs by transforming free-text phenotype information into a computer-readable form. Deep phenotyping has shown its advantage in representing phenotype information in EHRs with high fidelity; however, most existing annotation tools are not suitable for the deep phenotyping task. Here, we developed an intelligent annotation tool named PIAT with a major focus on the deep phenotyping of Chinese EHRs. PIAT can improve the annotation efficiency for EHR-based deep phenotyping with a simple but effective interactive interface, automatic preannotation support, and a learning mechanism. Specifically, experts can proofread automatic annotation results from the annotation algorithm in the web-based interactive interface, and EHRs reviewed by experts can be used for evolving the underlying annotation algorithm. In this way, the annotation process of deep phenotyping EHRs will become easier. In conclusion, we create a powerful intelligent system for the deep phenotyping of Chinese EHRs. It is hoped that our work will inspire further studies in constructing intelligent systems for deep phenotyping English and non-English EHRs.

Predicting Elevated TSH Levels in the Physical Examination Population With a Machine Learning Model.

Objective: The purpose of this study was to predict elevated TSH levels by developing an effective machine learning model based on large-scale physical examination results. Methods: Subjects who underwent general physical examinations from January 2015 to December 2019 were enrolled in this study. A total of 21 clinical parameters were analyzed, including six demographic parameters (sex, age, etc.) and 15 laboratory parameters (thyroid peroxidase antibody (TPO-Ab), thyroglobulin antibody (TG-Ab), etc.). The risk factors for elevated TSH levels in the univariate and multivariate Logistic analyses were used to construct machine learning models. Four machine learning models were trained to predict the outcome of elevated TSH levels one year/two years after patient enrollment, including decision tree (DT), linear regression (LR), eXtreme Gradient boosting (XGBoost), and support vector machine (SVM). Feature importance was calculated in the machine learning models to show which parameter plays a vital role in predicting elevated TSH levels. Results: A total of 12,735 individuals were enrolled in this study. Univariate and multivariate Logistic regression analyses showed that elevated TSH levels were significantly correlated with gender, FT3/FT4, total cholesterol (TC), TPO-Ab, Tg-Ab, creatinine (Cr), and triglycerides (TG). Among the four machine learning models, XGBoost performed best in the one-year task of predicting elevated TSH levels (AUC (0.87(+/- 0.03))). The most critical feature in this model was FT3/FT4, followed by TPO-Ab and other clinical parameters. In the two-year task of predicting TSH levels, none of the four models performed well. Conclusions: In this study, we trained an effective XGBoost model for predicting elevated TSH levels one year after patient enrollment. The measurement of FT3 and FT4 could provide an early warning of elevated TSH levels to prevent relative thyroid diseases.

Impact of anesthetic strategy on outcomes for patients with acute basilar artery occlusion undergoing mechanical thrombectomy.

BACKGROUND: The best anesthetic management strategy for patients with acute large vessel occlusion treated with mechanical thrombectomy (MT) remains uncertain. Most studies have focused on anterior-circulation stroke caused by large artery occlusion. Nevertheless, limited data are available on the appropriate choice of anesthetic for acute basilar artery occlusion (BAO). We aimed to investigate the effect of anesthetic method on clinical outcomes in patients with BAO undergoing MT. METHODS: Patients undergoing MT for acute BAO in the BASILAR registry (Acute Basilar Artery Occlusion Study) were included. We divided patients into three groups according to the anesthetic technique used during MT: general anesthesia (GA), local anesthesia (LA), and conscious sedation (CS). Propensity score matching was performed to achieve baseline balance. RESULTS: 639 patients were included. GA was used in 257 patients (40.2%), LA was used in 250 patients (39.1%), and CS was used in 132 patients (20.7%). After 1:1 matching, favorable outcome, mortality, and hemorrhagic transformation rates, as well as modified Rankin Scale (mRS) score at 90 days, did not differ between the GA, LA, and CS groups. CONCLUSIONS: The choice of anesthetic strategy, GA, LA, or CS, did not affect the clinical outcomes of patients with acute BAO treated with MT in the BASILAR registry.

Extended Thrombolysis In Cerebral Infarction (eTICI) grade 2c: a potential angiographic target for endovascular treatment in acute basilar artery occlusion?

BACKGROUND: Higher extended Thrombolysis In Cerebral Infarction (eTICI) grades are associated with better clinical outcomes after endovascular treatment (EVT) for proximal intracranial occlusion of the anterior circulation. However, the relationship between eTICI grade and outcomes after EVT in patients with acute basilar artery occlusion (BAO) remains unclear. We aimed to explore which eTICI category was the cut-off correlating with better clinical outcomes in patients with BAO undergoing EVT. METHODS: We included patients treated via EVT from the BASILAR study. Multivariable logistic regression analyses were performed to assess the impact of eTICI grades on 90-day favorable functional outcomes, defined as a modified Rankin Scale (mRS) score of 0-3. Other outcomes were functional independence (mRS 0-2), all-cause mortality, and symptomatic intracranial hemorrhage. RESULTS: Among 647 patients treated with EVT, 127 (19.6%), 128 (24.5%), 110 (21.1%), and 282 (54%) patients achieved eTICI grades of 0-2a, 2b, 2c, and 3, respectively. Compared with eTICI grades 0-2a, higher rates of favorable functional outcomes (adjusted OR (aOR) 2.96, 95% CI 1.33 to 6.57, and aOR 7.40, 95% CI 3.63 to 15.09, respectively) were observed for grades 2c and 3, not 2b (aOR 1.93, 95% CI 0.86 to 4.36). The risks of mortality and symptomatic intracranial hemorrhage were also lower for eTICI grades 2c and 3 than for grades 0-2a. CONCLUSIONS: An eTICI grade of 2c/3 may be a target for successful reperfusion after EVT in patients with acute BAO; however, further studies with larger sample sizes and clinical trials are needed.

One-Year Outcome After Endovascular Treatment for Acute Basilar Artery Occlusion.

BACKGROUND AND PURPOSE: The BASILAR registry, a nationwide prospective nonrandomized study conducted in China, enrolled consecutive patients with acute basilar artery occlusion receiving endovascular treatment or conventional-treatment from January 2014 to May 2019. This article aimed to report the results of clinical follow-up at one year among these patients. METHODS: The primary outcome was the modified Rankin Scale at one year, assessed as a common odds ratio using ordinal logistic regression analysis adjusted for prespecified prognostic factors. Secondary outcomes included the modified Rankin Scale-based outcome group at one year (0-1, 0-2, or 0-3) and all-cause death. RESULTS: Of the 829 patients enrolled in the original BASILAR registry, one-year data were available for 785 patients (94.7%). The distribution of outcomes on the modified Rankin Scale favored endovascular treatment over conventional-treatment (adjusted common odds ratio, 4.50 [95% CI, 2.81-7.29]; P<0.001). The cumulative one-year mortality rate was 54.6% in the endovascular treatment group versus 83.5% in the conventional-treatment group (adjusted odds ratio, 4.36 [95% CI, 2.69-7.29]; P<0.001). CONCLUSIONS: The beneficial effect of endovascular treatment on functional outcome at one year in patients with acute basilar artery occlusion is similar to that reported at 90 days in the original study. REGISTRATION: URL: http://www.chictr.org.cn; Unique identifier: ChiCTR1800014759.

Thermal face recognition under different conditions.

BACKGROUND: A thermal face recognition under different conditions is proposed in this article. The novelty of the proposed method is applying temperature information in the recognition of thermal face. The physiological information is obtained from the face using a thermal camera, and a machine learning classifier is utilized for thermal face recognition. The steps of preprocessing, feature extraction and classification are incorporated in training phase. First of all, by using Bayesian framework, the human face can be extracted from thermal face image. Several thermal points are selected as a feature vector. These points are utilized to train Random Forest (RF). Random Forest is a supervised learning algorithm. It is an ensemble of decision trees. Namely, RF merges multiple decision trees together to obtain a more accurate classification. Feature vectors from the testing image are fed into the classifier for face recognition. RESULTS: Experiments were conducted under different conditions, including normal, adding noise, wearing glasses, face mask, and glasses with mask. To compare the performance with the convolutional neural network-based technique, experimental results of the proposed method demonstrate its robustness against different challenges. CONCLUSIONS: Comparisons with other techniques demonstrate that the proposed method is robust under less feature points, which is around one twenty-eighth to one sixtieth of those by other classic methods.

Distribution of Pathogens in Elderly Chinese Patients With Pneumonia: A Systematic Review and Meta-Analysis.

Background: To summarize the distribution of pathogenic bacteria in elderly Chinese patients with pneumonia and provide guidance for the clinical application of antibiotics. Methods: The electronic databases of PubMed, Embase, Cochrane library, and China National Knowledge Infrastructure were searched. The primary outcomes included the prevalence of gram-positive cocci, gram-negative bacilli, and fungus. The summary prevalence and 95% confidence interval (CI) were calculated using the random-effects model. Results: A total of 17 retrospective studies reporting a total of 5,729 elderly patients with pneumonia were selected for final analysis. The summary prevalence of gram-positive cocci was 25% (95% CI: 20-30%; p < 0.001), whereas the prevalence of gram-negative bacilli was 56% (95% CI: 46-67%; p < 0.001). Moreover, the pooled prevalence of fungus in elderly patients with pneumonia was 11% (95% CI: 8-14%; p < 0.001). The most common gram-positive cocci were Staphylococcus aureus (ES: 8%; 95% CI: 6-11%; p <0.001), Streptococcus hemolyticus (ES: 7%; 95% CI: 6-8%; p < 0.001), and Streptococcus pneumoniae (ES: 5%; 95% CI: 3-7%; p < 0.001). Pseudomonas aeruginosa (ES: 18%; 95% CI: 14-22%; p <0.001) and Klebsiella pneumoniae (ES: 14%; 95% CI: 11-18%; p <0.001) were most common gram-negative bacilli. Furthermore, the pooled prevalence of Candida albicans in elderly patients with pneumonia was 6% (95% CI: 5-8%; p < 0.001). Conclusions: The findings demonstrated the comprehensive distribution of pathogenic bacteria in elderly Chinese patients with pneumonia, which could guide further antibiotic therapies.

Correction: Constructing High-Fidelity Phenotype Knowledge Graphs for Infectious Diseases With a Fine-Grained Semantic Information Model: Development and Usability Study.

[This corrects the article DOI: 10.2196/26892.].

Recovery of a patient with severe COVID-19 by acupuncture and Chinese herbal medicine adjuvant to standard care.

There is currently no drug or therapy that can cure the coronavirus disease 2019 (COVID-19), which is highly contagious and can be life-threatening in severe cases. Therefore, seeking potential effective therapies is an urgent task. An older female at the Leishenshan Hospital in Wuhan, China, with a severe case of COVID-19 with significant shortness of breath and decrease in peripheral oxygen saturation (SpO2), was treated using manual acupuncture and Chinese herbal medicine granule formula Fuzheng Rescue Lung with Xuebijing Injection in addition to standard care. The patient's breath rate, SpO2, heart rate, ratio of neutrophil/lymphocyte (NLR), ratio of monocyte/lymphocyte (MLR), C-reactive protein (CRP), and chest computed tomography were monitored. Acupuncture significantly improved the patient's breathing function, increased SpO2, and decreased her heart rate. Chinese herbal medicine might make the effect of acupuncture more stable; the use of herbal medicine also seemed to accelerate the absorption of lung infection lesions when its dosage was increased. The combination of acupuncture and herbs decreased NLR from 14.14 to 5.83, MLR from 1.15 to 0.33 and CRP from 15.25 to 6.01 mg/L. These results indicate that acupuncture and Chinese herbal medicine, as adjuvants to standard care, might achieve better results in treating severe cases of COVID-19.

Constructing High-Fidelity Phenotype Knowledge Graphs for Infectious Diseases With a Fine-Grained Semantic Information Model: Development and Usability Study.

BACKGROUND: Phenotypes characterize the clinical manifestations of diseases and provide important information for diagnosis. Therefore, the construction of phenotype knowledge graphs for diseases is valuable to the development of artificial intelligence in medicine. However, phenotype knowledge graphs in current knowledge bases such as WikiData and DBpedia are coarse-grained knowledge graphs because they only consider the core concepts of phenotypes while neglecting the details (attributes) associated with these phenotypes. OBJECTIVE: To characterize the details of disease phenotypes for clinical guidelines, we proposed a fine-grained semantic information model named PhenoSSU (semantic structured unit of phenotypes). METHODS: PhenoSSU is an "entity-attribute-value" model by its very nature, and it aims to capture the full semantic information underlying phenotype descriptions with a series of attributes and values. A total of 193 clinical guidelines for infectious diseases from Wikipedia were selected as the study corpus, and 12 attributes from SNOMED-CT were introduced into the PhenoSSU model based on the co-occurrences of phenotype concepts and attribute values. The expressive power of the PhenoSSU model was evaluated by analyzing whether PhenoSSU instances could capture the full semantics underlying the descriptions of the corresponding phenotypes. To automatically construct fine-grained phenotype knowledge graphs, a hybrid strategy that first recognized phenotype concepts with the MetaMap tool and then predicted the attribute values of phenotypes with machine learning classifiers was developed. RESULTS: Fine-grained phenotype knowledge graphs of 193 infectious diseases were manually constructed with the BRAT annotation tool. A total of 4020 PhenoSSU instances were annotated in these knowledge graphs, and 3757 of them (89.5%) were found to be able to capture the full semantics underlying the descriptions of the corresponding phenotypes listed in clinical guidelines. By comparison, other information models, such as the clinical element model and the HL7 fast health care interoperability resource model, could only capture the full semantics underlying 48.4% (2034/4020) and 21.8% (914/4020) of the descriptions of phenotypes listed in clinical guidelines, respectively. The hybrid strategy achieved an F1-score of 0.732 for the subtask of phenotype concept recognition and an average weighted accuracy of 0.776 for the subtask of attribute value prediction. CONCLUSIONS: PhenoSSU is an effective information model for the precise representation of phenotype knowledge for clinical guidelines, and machine learning can be used to improve the efficiency of constructing PhenoSSU-based knowledge graphs. Our work will potentially shift the focus of medical knowledge engineering from a coarse-grained level to a more fine-grained level.

Prognostic Structural Neural Markers of MRI in Response to Mechanical Thrombectomy for Basilar Artery Occlusion.

Objective: Mechanical thrombectomy (MT) has been an effective first-line therapeutic strategy for ischemic stroke. With impairment characteristics separating it from anterior circulation stroke, we aimed to explore prognostic structural neural markers for basilar artery occlusion (BAO) after MT. Methods: Fifty-four BAO patients with multi-modal magnetic resonance imaging at admission from the multicenter real-world designed BASILAR research were enrolled in this study. Features including volumes for cortical structures and subcortical regions, locations and volumes of infarctions, and white matter hyperintensity (WMH) volumes were recorded from all individuals. The impact features were identified using ANCOVA and logistic analysis. Another cohort (n = 21) was further recruited to verify the prognostic roles of screened prognostic structures. Results: For the primary clinical outcome, decreased brainstem volume and total infarction volumes from mesencephalon and midbrain were significantly related to reduced 90-day modified Rankin score (mRS) after MT treatment. WMH volume, WMH grade, average cortex thickness, white matter volume, and gray matter volume did not exhibit a remarkable relationship with the prognosis of BAO. The increased left caudate volume was obviously associated with early symptomatic recovery after MT. The prognostic role of the ratio of pons and midbrain infarct volume in brainstem was further confirmed in another cohort with area under the curve (AUC) = 0.77. Conclusions: This study was the first to provide comprehensive structural markers for the prognostic evaluation of BAO. The fully automatic and semiautomatic segmentation approaches in our study supported that the proportion of mesencephalon and midbrain infarct volume in brainstem was a crucial prognostic structural neural marker for BAO.

Values of Baseline Posterior Circulation Acute Stroke Prognosis Early Computed Tomography Score for Treatment Decision of Acute Basilar Artery Occlusion.

BACKGROUND AND PURPOSE: This study aimed to analyze the impact of baseline posterior circulation Acute Stroke Prognosis Early Computed Tomography Score (pc-ASPECTS) on the efficacy and safety of endovascular therapy (EVT) for patients with acute basilar artery occlusion. METHODS: The BASILAR was a nationwide prospective registry of consecutive patients with a symptomatic and radiologically confirmed acute basilar artery occlusion within 24 hours of symptom onset. We estimated the effect of standard medical therapy alone (SMT group) versus SMT plus EVT (EVT group) for patients with documented pc-ASPECTS on noncontrast CT, both as a categorical (0-4 versus 5-7 versus 8-10) and as a continuous variable. The primary outcomes included favorable functional outcomes (modified Rankin Scale ≤3) at 90 days and mortality within 90 days. RESULTS: In total, 823 cases were included: 468 with pc-ASPECTS 8 to 10 (SMT: 71; EVT: 397), 317 with pc-ASPECTS 5 to 7 (SMT: 85; EVT: 232), and 38 with pc-ASPECTS 0 to 4 (SMT: 13; EVT: 25). EVT was associated with higher rate of favorable outcomes (adjusted relative risk with 95% CI, 4.35 [1.30-14.48] and 3.20 [1.68-6.09]; respectively) and lower mortality (60.8% versus 77.6%, P=0.005 and 35.0% versus 66.2%, P<0.001; respectively) than SMT in the pc-ASPECTS 5 to 7 and 8 to 10 subgroups. Continuous benefit curves also showed the superior efficacy and safety of EVT over SMT in patients with pc-ASPECTS ≥5. Furthermore, the prognostic effect of onset to puncture time on favorable outcome with EVT was not significant after adjustment for pc-ASPECTS (adjusted odds ratio, 0.98 [95% CI, 0.94-1.02]). CONCLUSIONS: Patients of basilar artery occlusion with pc-ASPECTS ≥5 could benefit from EVT. The baseline pc-ASPECTS appears more important for decision making and predicting prognosis than time to EVT. Registration: URL: http://www.chictr.org.cn. Unique identifier: ChiCTR1800014759.