Effect of a fall within three months of admission on delirium in critically Ill elderly patients: a population-based cohort study.

BACKGROUND: Delirium is common among elderly patients in the intensive care unit (ICU) and is associated with prolonged hospitalization, increased healthcare costs, and increased risk of death. Understanding the potential risk factors and early prevention of delirium is critical to facilitate timely intervention that may reverse or mitigate the harmful consequences of delirium. AIM: To clarify the effects of pre-admission falls on ICU outcomes, primarily delirium, and secondarily pressure injuries and urinary tract infections. METHODS: The study relied on data sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Statistical tests (Wilcoxon rank-sum or chi-squared) compared cohort characteristics. Logistic regression was employed to investigate the association between a history of falls and delirium, as well as secondary outcomes, while Kaplan-Meier survival curves were used to assess short-term survival in delirium and non-delirium patients. RESULTS: Study encompassed 22,547 participants. Delirium incidence was 40%, significantly higher in patients with a history of falls (54.4% vs. 34.5%, p < 0.001). Logistic regression, controlling for confounders, not only confirmed that a history of falls elevates the odds of delirium (OR: 2.11; 95% CI: 1.97-2.26; p < 0.001) but also showed it increases the incidence of urinary tract infections (OR:1.50; 95% CI:1.40-1.62; p < 0.001) and pressure injuries (OR:1.36; 95% CI:1.26-1.47; p < 0.001). Elderly delirium patients exhibited lower 30-, 180-, and 360-day survival rates than non-delirium counterparts (all p < 0.001). CONCLUSIONS: The study reveals that history of falls significantly heighten the risk of delirium and other adverse outcomes in elderly ICU patients, leading to decreased short-term survival rates. This emphasizes the critical need for early interventions and could inform future strategies to manage and prevent these conditions in ICU settings.

Development and validation of a risk prediction model for frailty in patients with diabetes.

BACKGROUND: Frailty is the third most common complication of diabetes after macrovascular and microvascular complications. The aim of this study was to develop a validated risk prediction model for frailty in patients with diabetes. METHODS: The research used data from the China Health and Retirement Longitudinal Study (CHARLS), a dataset representative of the Chinese population. Twenty-five indicators, including socio-demographic variables, behavioral factors, health status, and mental health parameters, were analyzed in this study. The study cohort was randomly divided into a training set and a validation set at a ratio of 70 to 30%. LASSO regression analysis was used to screen the variables for the best predictors of the model based on a 10-fold cross-validation. The logistic regression model was applied to explore the associated factors of frailty in patients with diabetes. A nomogram was constructed to develop the prediction model. Calibration curves were applied to evaluate the accuracy of the nomogram model. The area under the receiver operating characteristic curve and decision curve analysis were conducted to assess predictive performance. RESULTS: One thousand four hundred thirty-six patients with diabetes from the CHARLS database collected in 2013 (n = 793) and 2015 (n = 643) were included in the final analysis. A total of 145 (10.9%) had frailty symptoms. Multivariate logistic regression analysis showed that marital status, activities of daily living, waist circumference, cognitive function, grip strength, social activity, and depression as predictors of frailty in people with diabetes. These factors were used to construct the nomogram model, which showed good concordance and accuracy. The AUC values of the predictive model and the internal validation set were 0.912 (95%CI 0.887-0.937) and 0.881 (95% CI 0.829-0.934). Hosmer-Lemeshow test values were P = 0.824 and P = 0.608 (both > 0.05). Calibration curves showed significant agreement between the nomogram model and actual observations. ROC and DCA indicated that the nomogram had a good predictive performance. CONCLUSIONS: Comprehensive nomogram constructed in this study was a promising and convenient tool to evaluate the risk of frailty in patients with diabetes, and contributed clinicians to screening the high-risk population.

Interaction effect of midday napping duration and depressive symptoms on subjective memory impairment among older people in China: evidence from the China health and retirement longitudinal study database.

BACKGROUND: Subjective memory impairment (SMI) is common in older people. The aim of this study was to investigate the factors influencing SMI among older people in China, with specific focus on the interaction effect of midday napping duration and depressive symptoms on the risk of SMI. METHODS: Using a dataset representative of the Chinese population from a longitudinal study of health and retirement in China, subjects with SMI were screened using the question "how do you feel about your memory now?" and the Mini-Mental State Examination. A logistic regression model was applied to explore the factors affecting SMI. Additive and multiplicative models were used to analyze the interaction effect of midday napping duration and depressive symptoms on the risk of SMI. RESULTS: We enrolled 8,254 subjects included and the incidence of SMI was 63.9%. Depressive symptoms, nap time, and physical activity were influencing factors of SMI. Midday napping duration and depressive symptoms had positive additive interaction effects on the risk of SMI. When extended-length naps and depressive symptoms coexisted, the risk of SMI was 1.06 times greater than that for either alone (RERI, relative excess risk due to interaction = 0.27, 95% CI = 0.07-0.43; AP, attributable proportion = 0.14, 95% CI = 0.01-0.23; S, synergy index = 1.06, 95% CI = 0.57-1.62). When short naps and depressive symptoms coexisted, the risk of SMI was 1.2 times higher than that for either alone (RERI = 0.12, 95% CI=-0.14-0.39; AP = 0.13, 95% CI=-0.07-0.22; S = 1.20, 95% CI = 0.79-1.82). LIMITATIONS: Since this was a cross-sectional study, the cause-and-effect relationships between the associated variables cannot be inferred. CONCLUSIONS: The interaction effect that exists between nap time and depressive symptoms in older people is important for the identification and early intervention of people at risk for SMI.

Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models.

The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.

Association between bidirectional intergenerational support and successful aging in China: Evidence from CHARLS 2018.

Aging has gradually accelerated in China, and achieving successful aging of older adults has become a public health concern. Intergenerational support is crucial for Chinese older adults in later life due to the culture of filial piety. However, the association between successful aging and intergenerational support remains poorly understood in China. This study aimed to examine the association between patterns of intergenerational support and successful aging of older adults in China. The present study is a secondary analysis of data obtained from the follow-up survey of the China Health and Retirement Longitudinal Study 2018. Data were analyzed using descriptive statistics and logistic regressions. Bidirectional intergenerational support was associated with successful aging in the participants. In addition, there was an association between different intergenerational financial, caring, and emotional support patterns and elements of successful aging.

Imaging diagnosis and research progress of carotid plaque vulnerability.

Ischemic stroke (IS) exhibits a high disability rate, mortality, and recurrence rate, imposing a serious threat to human survival and health. Its occurrence is affected by various factors. Although the previous research has demonstrated that the occurrence of IS is mainly associated with lumen stenosis caused by carotid atherosclerotic plaque (AP), recent studies have revealed that many patients will still suffer from IS even with mild carotid artery lumen stenosis. Blood supply disturbance causes 10% of IS to the corresponding cerebral blood supply area caused by carotid vulnerable plaque. Thrombus blockage of distal branch vessels caused by rupture of vulnerable carotid plaque is the main cause of ischemic stroke. Therefore, how to accurately evaluate vulnerable plaque and intervene as soon as possible is a problem that needs to be solved in clinic. The vulnerability of plaque is determined by its internal components, including thin and incomplete fibrous cap, necrotic lipid core, intra-plaque hemorrhage, intra-plaque neovascularization, and ulcerative plaque formation. The development of imaging technology enables the routine detection of AP vulnerability. By analyzing the pathological changes, characteristics, and formation mechanism of carotid plaque vulnerability, this article aims to explore the modern imaging methods which can be used to identify plaque composition and plaque vulnerability to provide a reference basis for disease diagnosis and differential diagnosis.

Neutrophil-to-lymphocyte ratio is associated with carotid intraplaque neovascularization in asymptomatic carotid stenosis patients.

BACKGROUND AND PURPOSE: Neutrophil-to-lymphocyte ratio (NLR) has been suggested as an available systemic inflammatory biomarker. This study aims to evaluate whether intraplaque neovascularization assessed by contrast-enhanced ultrasound (CEUS) is associated with NLR in asymptomatic carotid stenosis patients. MATERIALS AND METHODS: One hundred and forty-four asymptomatic patients with carotid luminal stenosis >30% were assessed using contrast-enhanced ultrasound imaging. The contrast enhancement within the plaque was classified on a visual semiquantitative grading scale. The data collected included the patient's risk factors, laboratory results, cardiovascular disease history, and drug use history. Univariate and multivariate analyses were assessed to identify independent factors related to intraplaque neovascularization with adjustment for potential confounders. RESULTS: Patients with CEUS grade 2 plaques had a higher level of LDL-C (p < .001), neutrophil count (p < .001), and blood glucose (p = .005), but lower level of lymphocyte count (p = .021). The presence of grade 2 plaques was significantly associated with high NLR values (OR 1.21, 95% CI 1.03-1.43, p = .017). Patients were divided into four groups according to the quartile of NLR values. Compared to the patients in the first quartile of NLR (<1.73), the patients in the fourth NLR quartile (≥3.38) were characterized by the most prevalence of CEUS grade 2 plaques (OR 4.55, 95% CI 1.69-12.25, p = .003). Multivariate logistic regression analysis after adjusting various variables demonstrated NLR remained an independent risk factor for the presence of CEUS grade 2 plaques. CONCLUSION: Intraplaque neovascularization is significantly associated with NLR in asymptomatic carotid stenosis patients.

Self-esteem and family functioning mediates the association of symptom severity and parental affiliate stigma among families with children with ASD.

PURPOSE: To investigate the level of affiliate stigma among parents of children with autism spectrum disorder and to explore the mediating role of self-esteem and family functioning. DESIGN AND METHODS: A cross-sectional study was conducted in a large regional hospital and two childhood rehabilitation centers in Guangdong, China. Data related to demographics, parental self-esteem, family functioning, and affiliate stigma were collected from 180 parents of children diagnosed with ASD. We used t-tests, analysis of variance, and correlation analysis to explore the related factors of parental affiliate stigma. Path analysis was used to determine the mediating roles of self-esteem and family functioning in the relationship between symptom severity and affiliate stigma. RESULTS: Parents of children with autism spectrum disorder in China experienced low self-esteem, family functioning, and high affiliate stigma. Symptom severity was negatively correlated with self-esteem and family functioning. Self-esteem and family functioning were significantly negatively correlated with affiliate stigma. Symptom severity was positively correlated with affiliate stigma. Self-esteem and family functioning mediated the relationship between symptom severity and affiliate stigma. CONCLUSIONS: Symptom severity affects parental affiliate stigma among families with children with ASD. Self-esteem and family functioning are the two mediators in the relationship. We should take steps to improve self-esteem and family functioning in order to alleviate parental affiliate stigma. PRACTICE IMPLICATIONS: This study emphasizes the importance of the influence of ASD severity and family functioning on affiliate stigma. In clinical practice, psychological support should be provided for parents of children with ASD to improve their mental health.

[Bioinformatics analysis and function prediction of ginseng TCP transcription factor family].

The longevity mechanism of ginseng(Panax ginseng) is related to its strong meristematic ability. In this paper, this study used bioinformatic methods to identify the members of the ginseng TCP gene family in the whole genome and analyzed their sequence characteristics. Then, quantitative real-time fluorescent PCR was performed to analyze the TCP genes containing elements rela-ted to meristem expression in the taproots, fibrous roots, stems, and leaves. According to the data, this study further explored the expression specificity of TCP genes in ginseng tissues, which facilitated the dissection of the longevity mechanism of ginseng. The ginseng TCP members were identified and analyzed using PlantTFDB, ExPASy, MEME, PLANTCARE, TBtools, MEGA and DNAMAN. The results demonstrated that there were 60 TCP gene family members in ginseng, and they could be divided into two classes: Class Ⅰ and Class Ⅱ, in which the Class Ⅱ possessed two subclasses: CYC-TCP and CIN-TCP. The deduced TCP proteins in ginseng had the length of 128-793 aa, the isoelectric point of 4.49-9.84 and the relative molecular mass of 14.2-89.3 kDa. They all contained the basic helix-loop-helix(bHLH) domain. There are a variety of stress response-related cis-acting elements in the promoter regions of ginseng TCP genes, and PgTCP20-PgTCP24 contained the elements associated with meristematic expression. The transcription levels of PgTCP20-PgTCP24 were high in fibrous roots and leaves, but low in stems, indicating the tissue-specific expression of ginseng TCP genes. The Class Ⅰ TCP members which contained PgTCP20-PgTCP23, may be important regulators for the growth and development of ginseng roots.

Unmet Family Needs Concerning Healthcare Services in the Setting of Childhood Hospitalization for Cancer Treatment in Mainland China: A Qualitative Study.

PURPOSE: The focus of this paper is to identify the unmet family needs during children's hospitalization for cancer treatment. DESIGN AND METHODS: Qualitative interviews were carried out with five fathers and fourteen mothers purposively sampled from four pediatric oncology departments in Mainland China from September 2013 to March 2014. Audiotaped interviews were transcribed verbatim, and data in transcripts were coded and analyzed by qualitative content analysis. RESULTS: The identified unmet family needs pertaining to healthcare service during a child's hospitalization for cancer treatment were unmet need for warm and supportive attitudes; competent care; adequate information; a comfortable environment; and catering support. CONCLUSIONS: The results showed that families with children hospitalized for cancer treatment have a variety of unmet needs related to healthcare service. These identified unmet family needs have already shed light on areas for healthcare service improvement. PRACTICE IMPLICATIONS: This study have reminded nurses' to become more concerned about unmet family needs instead of only focusing on the hospitalized child in clinical settings. Healthcare professionals can assist in promoting family adaptation to children's hospitalization by satisfying their unmet family needs.

A Qualitative Study Exploring Coping Strategies in Chinese Families During Children's Hospitalization for Cancer Treatment.

PURPOSE: To explore how Chinese families cope with children's hospitalization for cancer treatment. DESIGN AND METHODS: A descriptive qualitative inquiry was employed. Semi-structured interview was conducted in four pediatric oncology departments in four hospitals from November 2017 to June 2018. The interviews focused on how families cope with the challenges resulting from their children's hospitalization for cancer treatment. Twenty one parents participated into the study. RESULTS: Four categories related to family coping strategies emerged from the data, including increasing family strength, maintaining optimistic thoughts, seeking external support, and not disclosing the unfavorable information. CONCLUSIONS: Families had adopted multiple coping strategies to handle the challenges caused by children's hospitalization for cancer treatment. The influences of Chinese culture on family coping should be taken into consideration during family-centered interventions development. Further studies could analyze whether the spouse perspectives are independent from one another and whether the coping strategies change as the time of hospitalization. PRACTICE IMPLICATIONS: This study has reminded nurses' to become more concerned about the influences of culture on families' coping strategies during this challenging period. Other nurses in the world could understand how to enhance family coping strategies of Chinese clients.

Andrographolide disrupts meiotic maturation by blocking cytoskeletal reorganisation and decreases the fertilisation potential of mouse oocytes.

Andrographolide (AG) is a diterpenoid lactone isolated from the stem and leaves of Andrographis paniculata Nees that is used for the effective treatment of infectious diseases in Asian countries. Previous studies have reported adverse effects of AG on female fertility in rodents; however, the underlying mechanisms are unknown. The aim of the present study was to investigate the effects of AG on the IVM of mouse oocytes and their fertilisation potential. Immature oocytes incubated for 6, 14 or 24h in medium containing 5, 10 or 20µM AG showed time- and dose-dependent decreases in maturation rates compared with the control group. Immunostaining revealed that AG exposure disrupted spindle organisation and migration, as well as actin cap formation and cytokinesis. Furthermore, most oocytes exposed to 20µM AG underwent apoptosis, and the few oocytes exposed to 5 or 10µM AG that reached MII exhibited lower fertilisation rates after intracytoplasmic sperm injection. The findings of the present study suggest that AG may disrupt mouse oocyte meiotic maturation by blocking cytoskeletal reorganisation, and may thus have an adverse effect on female fertility.

Validation of Hospitalization Impact Scale among families with children hospitalized for cancer treatment.

AIM: To make further modifications to and validate the psychometric properties of the Hospitalization Impact Scale. BACKGROUND: A child's repeated and prolonged hospitalization for cancer treatment can result in great changes for the entire family. A hospitalization-specific screening tool is needed to help clinical nurses identify families who are experiencing major impacts during their child's hospitalization. DESIGN: A cross-sectional study was employed to examine the psychometric properties of the Hospitalization Impact Scale. METHOD: The sample consisted of 253 families with children hospitalized for cancer treatment in four paediatric oncology departments in four hospitals in mainland China from September 2013 - March 2014. Parents completed the 36-item Hospitalization Impact Scale, demographic measures and the Family Impact Module of the Pediatric Quality of Life Inventory. Reliability, construct validity, known-group validity and concurrent validity were examined. RESULT: The revised Hospitalization Impact Scale included six factors containing 34 items. It demonstrated sound concurrent validity with the Family Impact Module of the Pediatric Quality of Life Inventory and excellent internal consistency. CONCLUSION: The revised Hospitalization Impact Scale met the standard psychometric criteria for reliability and validity. Thus, it could be applied in paediatric oncology departments to help nurses assess and identify families experiencing major impacts during a child's hospitalization for cancer treatment.

[Histopathological changes in EV71-infected mouse model:a transmission electron microscopic study].

OBJECTIVE: To document ultrastructural changes of brain, spinal cord, skeletal muscle, jejunum and lung of EV71 infection mouse model, and to explore the myotropism and pathogenesis of EV71 in nervous system. METHODS: Ten-day-old suckling mice were infected with EV71 strain via the intraperitoneal route. Mice with paralysis were scarified on day 4 post infection and the brain, spinal cord, skeletal muscle, jejunum and lung were sampled for transmission electron microscopy and light microscopy. RESULTS: Lesions in brain were generally mild with inner chamber swelling in some of mitochondria. Myelin sheaths of medullated fibers were split with vacuolated changes. The Nissl bodies in anterior motor neurons disappeared along with mitochondria swelling, rough endoplasmic reticulum swelling and degranulation. Cytoplasm of anterior motor neurons showed cribriform appearance accompanied by neuronophagia. The bands of skeletal muscle in the infected group disappeared with degeneration and karyopyknosis in myocytes, in addition to mitochondrial swelling. Microvilli of epithelium in jejunum became loosely arranged along with formation of spiral medullary sheath structure and mitochondria swelling. Interstitial pneumonia was observed in lungs with type II pneumocyte proliferation and evacuation of the multilamellar bodies. CONCLUSIONS: EV71 infection causes severe myositis in the mouse model suggesting a strong myotropism of EV71 virus. The presence of lesions of various degrees in central nervous system and changes in anterior motor neurons may be associated with limb paralysis.

Genetically Designed Living Bacteria with Melanogenesis for Tumor-Specific Pigmentation and Therapeutic Intervention.

Visual observation and therapeutic intervention against tumors hold significant appeal for tumor treatment, particularly in meeting the demands of intraoperative navigation. From a clinical perspective, the naked-eye visualization of tumors provides a direct and convenient approach to identifying tumors and navigating during surgery. Nevertheless, there is an ongoing need to develop effective solutions in this frontier. Genetically engineered microorganisms are promising as living therapeutics for combatting malignant tumors, leveraging precise tumor targeting and versatile programmed functionalities. Here, genetically modified Escherichia coli (E. coli) MG1655 bacterial cells are introduced, called MelaBac cells, designed to express tyrosinase continuously. This bioengineered melanogenesis produces melanin capable of pigmenting both subcutaneous CT26 xenografts and chemically induced colorectal cancer (CRC). Additionally, MelaBac cells demonstrate the initiation of photonic hyperthermia therapy and immunotherapy against tumors, offering promising selective therapeutic interventions with high biocompatibility.

Incubation of sperm heads impairs fertilization and early embryo development following intracytoplasmic sperm injection (ICSI) by decreasing oocyte activation in mice.

When intracytoplasmic sperm injection (ICSI) is performed in mice, isolation of sperm heads is usually performed prior to injections in order to increase the efficiency of the procedure. Consequently, the isolated sperm heads undergo an inevitable incubation in vitro. However, little is known about the effects of this incubation step on fertilization and embryo development following ICSI. When we incubated sperm heads at 37 °C, there was a significant time-dependent decrease in fertilization and blastocyst formation. Moreover, the DNA integrity of the sperm heads was maintained over 12 h incubation. Using assisted oocyte activation, these defects in fertilization and embryo development were rescued. Taken together, incubation of sperm heads following isolation can affect the oocyte-activating capacity of sperm thereby compromising fertilization and embryo development associated with ICSI.

Phylogenetic implications based on an ultrastructural study with emphasis on the tracheal system of the compound eyes of three species of nymphalid butterflies.

Compound eyes are the prominent visual organs of insects and can provide valuable information for the reconstruction of insect phylogeny. Although the largest butterfly family (Nymphalidae) has been well defined, the infrafamilial phylogenetic relationships remain controversial hitherto. In the present study the ultrastructure of the compound eyes of three nymphalids Neptis beroe, Childrena zenobia, and Palaeonympha opalina was investigated using light and transmission electron microscopy in an attempt to seek potentially important phylogenetic characters. The compound eyes of the nymphalids share a tracheal system in a "1-4-8" branching pattern. The eight tracheal subbranches exhibit distinct distribution patterns along the basal retinula cell as follows: the tracheal subbranches of Palaeonympha opaline are close to the rhabdom in the distance from the distalmost part of the basal retinula cell to the rhabdom end, while those of N. beroe and C. zenobia are on the periphery of the retinula along almost the whole basal retinula cell and become close to the rhabdom just at the proximal end of the basal retinula cell. The tracheal structure of the three nymphalids is discussed for their potential phylogenetic implications.

Health literacy and quality of life of patients with coronary heart disease in Tibet, China: The mediating role of self-efficacy and self-management.

BACKGROUND: The disease burden of coronary heart disease patients in Tibet, China, ranks high in the country. Due to the local culture and environment, patients with coronary heart disease have increased risk factors for the disease, and their survival is worrisome. OBJECTIVES: The purpose of this study was to determine the relationship between health literacy and quality of life for patients with coronary heart disease in Tibet, China, and to explore the mediating roles of self-efficacy and self-management. METHODS: A cross-sectional study was conducted from August 2020 to July 2021 in Tibet. A total of 258 patients with coronary heart disease in Tibet participated. Self-reported questionnaires were used to assess health literacy, self-efficacy, self-management, and quality of life. Pearson correlation analysis and the SPSS PROCESS macro were used to analyze the data. RESULTS: The mean total score for the health literacy of patients with coronary heart disease in Tibet was 3.59 ± 0.80 points, showing the existence of a limited level of literacy. The quality of life was of an average level, with scores of 57.20 ± 21.70 points and 63.63 ± 20.66 points for physical and mental status, respectively. Self-efficacy and self-management mediated the relationship between health literacy and quality of life. CONCLUSIONS: Self-efficacy and self-management mediate the relationship between health literacy and quality of life. Targeted interventions for health literacy, self-efficacy, and self-management skills are important to improve the quality of life of Tibetan patients with coronary heart disease.

Finite-Sample Analysis of Deep CCA-Based Unsupervised Post-Nonlinear Multimodal Learning.

Canonical correlation analysis (CCA) has been essential in unsupervised multimodal/multiview latent representation learning and data fusion. Classic CCA extracts shared information from multiple modalities of data using linear transformations. In recent years, deep neural networks-based nonlinear feature extractors were combined with CCA to come up with new variants, namely the ``DeepCCA'' line of work. These approaches were shown to have enhanced performance in many applications. However, theoretical supports of DeepCCA are often lacking. To address this challenge, the recent work of Lyu and Fu (2020) showed that, under a reasonable postnonlinear generative model, a carefully designed DeepCCA criterion provably removes unknown distortions in data generation and identifies the shared information across modalities. Nonetheless, a critical assumption used by Lyu and Fu (2020) for identifiability analysis was that unlimited data is available, which is unrealistic. This brief paper puts forth a finite-sample analysis of the DeepCCA method by Lyu and Fu (2020). The main result is that the finite-sample version of the method can still estimate the shared information with a guaranteed accuracy when the number of samples is sufficiently large. Our analytical approach is a nontrivial integration of statistical learning, numerical differentiation, and robust system identification, which may be of interest beyond the scope of DeepCCA and benefit other unsupervised learning paradigms.

Texture Analysis Based on Vascular Ultrasound to Identify the Vulnerable Carotid Plaques.

Vulnerable carotid plaques are closely related to the occurrence of ischemic stroke. Therefore, accurate and rapid identification of the nature of carotid plaques is essential. This study aimed to determine whether texture analysis based on a vascular ultrasound can be applied to identify vulnerable plaques. Data from a total of 150 patients diagnosed with atherosclerotic plaque (AP) by carotid ultrasound (CDU) and high-resolution magnetic resonance imaging (HRMRI) were collected. HRMRI is the in vivo reference to assess the nature of AP. MaZda software was used to delineate the region of interest and extract 303 texture features from ultrasonic images of plaques. Following regression analysis using the least absolute shrinkage and selection operator (LASSO) algorithm, the overall cohort was randomized 7:3 into the training (n = 105) and testing (n = 45) sets. In the training set, the conventional ultrasound model, the texture feature model, and the conventional ultrasound-texture feature combined model were constructed. The testing set was used to validate the model's effectiveness by calculating the area under the curve (AUC), accuracy, sensitivity, and specificity. Based on the combined model, a nomogram risk prediction model was established, and the consistency index (C-index) and the calibration curve were obtained. In the training and testing sets, the AUC of the prediction performance of the conventional ultrasonic-texture feature combined model was higher than that of the conventional ultrasonic model and the texture feature model. In the training set, the AUC of the combined model was 0.88, while in the testing set, AUC was 0.87. In addition, the C-index results were also favorable (0.89 in the training set and 0.84 in the testing set). Furthermore, the calibration curve was close to the ideal curve, indicating the accuracy of the nomogram. This study proves the performance of vascular ultrasound-based texture analysis in identifying the vulnerable carotid plaques. Texture feature extraction combined with CDU sonogram features can accurately predict the vulnerability of AP.