A study on the impact of icon structural features in human-computer interface on visual search efficiency.

This article, from the perspective of structural features, focuses on in-car user interface icons and explores the impact of different icon structural features on visual search efficiency. Initially, we categorised the icons into four groups based on structural features: individual structure icons (ISI), enclosed structure icons (ESI), horizontal structure icons (HSI) and vertical structure icons (VSI). Subsequently, we conducted a visual search experiment with structure as the sole variable, recording participants' behaviours and eye-tracking data. Finally, data analysis was conducted using methods including analysis of variance and logistic regression. The results indicate that differences in icon structural features significantly affect visual search efficiency, showcasing significant intergroup differences. HSI exhibit the highest visual search efficiency, while ESI show the lowest efficiency. ISI have shorter response times but the lowest matching accuracy. VSI only perform better than ESI. These findings hold significant implications for optimising icon design and enhancing visual search efficiency.

Visual search efficiency of icons is crucial for human-computer interaction. We investigated how the structural features of icons influence visual search efficiency. Horizontal icons are most effective, enclosed icons the least. Individual icons are quick but less accurate. Vertical icons outperform enclosed ones. Structural features should be considered in design.

SB-Net: Synergizing CNN and LSTM networks for uncovering retrosynthetic pathways in organic synthesis.

Retrosynthesis is vital in synthesizing target products, guiding reaction pathway design crucial for drug and material discovery. Current models often neglect multi-scale feature extraction, limiting efficacy in leveraging molecular descriptors. Our proposed SB-Net model, a deep-learning architecture tailored for retrosynthesis prediction, addresses this gap. SB-Net combines CNN and Bi-LSTM architectures, excelling in capturing multi-scale molecular features. It integrates parallel branches for processing one-hot encoded descriptors and ECFP, merging through dense layers. Experimental results demonstrate SB-Net's superiority, achieving 73.6 % top-1 and 94.6 % top-10 accuracy on USPTO-50k data. Versatility is validated on MetaNetX, with rates of 52.8 % top-1, 74.3 % top-3, 79.8 % top-5, and 83.5 % top-10. SB-Net's success in bioretrosynthesis prediction tasks indicates its efficacy. This research advances computational chemistry, offering a robust deep-learning model for retrosynthesis prediction. With implications for drug discovery and synthesis planning, SB-Net promises innovative and efficient pathways.

A closer look at the link between cycle threshold, clinical features and biomarkers: An observational study in COVID-19 patients.

Background: Symptoms for severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2) appear 2-3 days after exposure to the virus. Being a virus, detection is primarily by polymerase chain reaction as this offers superior sensitivity and specificity. There was a misconception that patients with low cycle threshold (Ct) have severe coronavirus disease (COVID), and for individuals with higher Ct, it is the other way around. The prognosis for COVID was derived from various biomarkers and physicians heavily relied on them. Materials and Methods: A cross-sectional study spanning a duration of 2 years was conducted at a tertiary care centre in western India. A total of 201 individuals were included and the correlation between Ct, clinical features and biomarkers was studied. Results: In the E-gene, 43.28% had lower Ct values and 40.79% had low Ct values in the RdRp gene. 50% of all patients had diabetes, with 60% being between the ages of 61 and 80. 54.1% of hypertension patients belonged to ages between 61 and 80. 90.54% of COVID-positive individuals had lactose dehydrogenase levels ranging from 440 to 760. 79% of patients had a procalcitonin value of more than one but less than six. 79.1% of patients had an erythrocyte sedimentation rate between 36 and 90. Conclusion: Ct value though has a research value; it is a poor prognostic marker when compared to the various biomarkers that have been studied earlier. We cannot conclusively state that all our findings are accurate due to a lack of data but further research into the prognostic value of Ct should be conducted which will help in the ongoing scenario.

Late Recurrence of Completely Resected Stage I-IIIA Lung Adenocarcinoma.

OBJECTIVE: Research into the risk factors associated with late recurrence (>2 years after surgery) of lung adenocarcinoma (LUAD) is limited. We investigated the incidence of and clinicopathologic and genomic features associated with late recurrence of resected stage I-IIIA LUAD. METHODS: We performed a retrospective analysis of patients with completely resected pathologic stage I-IIIA LUAD (2010-2019). Patients with a history of lung cancer, neoadjuvant therapy, or mucinous or noninvasive LUAD, or with follow-up of <2 years were excluded. Cox and logistic regression modeling were used to compare clinicopathologic variables among patients with no, early (≤2 years), and late recurrence. Comparisons of genomic mutations were corrected for multiple testing. RESULTS: Of the 2349 patients included, 537 developed a recurrence during follow-up. Most recurrences (55% [297/537]) occurred early; 45% (240/537) occurred late. A larger proportion of late recurrences than early recurrences were locoregional (37% vs. 29%; p=0.047). Patients with late recurrence had more aggressive pathologic features (IASLC grade 2 and 3, lymphovascular invasion, visceral pleural invasion) and higher stage than patients without recurrence. Pathologic features were similar between patients with early and late recurrence, except stage IIIA disease was more common in the early cohort. No genomic mutations were associated with late recurrence. CONCLUSIONS: Late recurrence of LUAD following resection is more common than previously reported. Patients without disease >2 years after surgery who had aggressive pathologic features at the time of resection have an elevated risk of recurrence and may benefit from more-aggressive follow-up.

Established the prediction model of early-stage non-small cell lung cancer spread through air spaces (STAS) by radiomics and genomics features.

BACKGROUND: This study was aimed to establish a prediction model for spread through air spaces (STAS) in early-stage non-small cell lung cancer based on imaging and genomic features. METHODS: We retrospectively collected 204 patients (47 STAS+ and 157 STAS-) with non-small cell lung cancer who underwent surgical treatment in the Jinling Hospital from January 2021 to December 2021. Their preoperative CT images, genetic testing data (including next-generation sequencing data from other hospitals), and clinical data were collected. Patients were randomly divided into training and testing cohorts (7:3). RESULTS: The study included a total of 204 eligible patients. STAS were found in 47 (23.0%) patients, and no STAS were found in 157 (77.0%) patients. The receiver operating characteristic curve showed that radiomics model, clinical genomics model, and mixed model had good predictive performance (area under the curve [AUC] = 0.85; AUC = 0.70; AUC = 0.85). CONCLUSIONS: The prediction model based on radiomics and genomics features has a good prediction performance for STAS.

A machine learning model based on clinical features and ultrasound radiomics features for pancreatic tumor classification.

Objective: This study aimed to construct a machine learning model using clinical variables and ultrasound radiomics features for the prediction of the benign or malignant nature of pancreatic tumors. Methods: 242 pancreatic tumor patients who were hospitalized at the First Affiliated Hospital of Guangxi Medical University between January 2020 and June 2023 were included in this retrospective study. The patients were randomly divided into a training cohort (n=169) and a test cohort (n=73). We collected 28 clinical features from the patients. Concurrently, 306 radiomics features were extracted from the ultrasound images of the patients' tumors. Initially, a clinical model was constructed using the logistic regression algorithm. Subsequently, radiomics models were built using SVM, random forest, XGBoost, and KNN algorithms. Finally, we combined clinical features with a new feature RAD prob calculated by applying radiomics model to construct a fusion model, and developed a nomogram based on the fusion model. Results: The performance of the fusion model surpassed that of both the clinical and radiomics models. In the training cohort, the fusion model achieved an AUC of 0.978 (95% CI: 0.96-0.99) during 5-fold cross-validation and an AUC of 0.925 (95% CI: 0.86-0.98) in the test cohort. Calibration curve and decision curve analyses demonstrated that the nomogram constructed from the fusion model has high accuracy and clinical utility. Conclusion: The fusion model containing clinical and ultrasound radiomics features showed excellent performance in predicting the benign or malignant nature of pancreatic tumors.

Morphological and Chemical Diversity within Japanese Laurencia Complex (Rhodomelaceae, Ceramiales, Rhodophyta).

Seaweeds of the red algal genus Laurencia are widely distributed worldwide in tropical, subtropical to temperate zones, and grow in Japan from Hokkaido to Okinawa. Laurencia is one of the most studied seaweeds by organic chemists because it produces a variety of compounds with unique structures. In Japan, various halogenated compounds have been found in Laurencia, while some species do not produce any halogenated compounds. Laurencia is one of the most difficult seaweeds to classify morphologically; however, the major halogenated secondary metabolites produced tend to be species-specific, and these compounds can be used as chemical markers for chemical systematics (chemotaxonomy). Similarly, it has been confirmed that domestic Laurencia species produce species-specific halogenated compounds of certain types. Laurencia is one of the "weedy seaweeds" that have not been effectively utilized at present, but it produces a wide variety of metabolites, so there is a good possibility that compounds with specific activity may be found. Thus, it can be seen that the secondary metabolites in Laurencia have many interesting aspects. In this review, we reported significant morphological features to distinguish species in this genus, and the morphological features, habitat, distribution, and chemical composition that help discriminate Japanese Laurencia species.

Comparison of clinicopathological features between cerebral cystic and alveolar echinococcosis: analysis of 27 cerebral echinococcosis cases in Xinjiang, China.

BACKGROUND: Cerebral echinococcosis is relatively rare, and it is important to distinguish cerebral cystic echinococcosis (CCE) from cerebral alveolar echinococcosis (CAE) in terms of pathological diagnosis. We aim to describe the different clinicopathological features among patients with CCE and CAE. METHODS: We collected 27 cases of cerebral echinococcosis which were diagnosed in the Department of Pathology of the First Affiliated Hospital of Xinjiang Medical University from January 1, 2012, to June 30, 2023. We compared the patients' clinical characteristics, MRI features, and pathologic manifestations of CCE and CAE. RESULTS: Among 27 cases of cerebral echinococcosis, 23 cases were CAE and 4 cases were CCE. The clinical manifestations of both CCE and CAE patients mainly included headache (21 patients, 77.78%), limb movement disorders (6 patients, 22.22%), epileptic seizures (4 patients, 14.81%) and visual disturbances (2 patients, 7.41%). The average onset age of CAE cases was 34.96 ± 11.11 years, which was 9.00 ± 7.26 years in CCE cases. All CAE patients presented with multiple involvements in the brain and extracranial organs while all CCE patients observed a solitary lesion in the brain and 3 CCE cases had no extracranial involvement. Lesions of CCE in MRI showed a single isolated circular, which was well demarcated from the surrounding tissues and with no obvious edema around the lesions, whereas CAE lesions presented as multiple intracranial lesions, with blurred edges and edema around the lesions, and multiple small vesicles could be observed in the lesions. The edge of CAE lesions could be enhanced, while CCE lesions have no obvious enhancement. CCE foci were clear cysts with a wall of about 0.1 cm. Microscopically, the walls of the cysts were characterized by an eosinophilic keratin layer, which was flanked on one side by basophilic germinal lamina cells, which were sometimes visible as protocephalic nodes. While the CAE lesion was a nodular structure with a rough and uneven nodule surface, and the cut section was cystic and solid; microscopically, the CAE lesion had areas of coagulative necrosis, and the proto-cephalic nodes were barely visible. Inflammatory cell areas consisting of macrophages, lymphocytes, epithelioid cells, plasma cells, eosinophils, and fibroblasts can be seen around the lesion. Brain tissues in the vicinity of the inflammatory cell areas may show apoptosis, degeneration, necrosis, and cellular edema, while brain tissues a little farther away from the lesion show a normal morphology. CONCLUSIONS: With the low incidence of brain echinococcosis, the diagnosis of echinococcosis and the differential diagnosis of CAE and CCE are challenging for pathologists. Grasping the different clinical pathology characteristics of CAE and CCE is helpful for pathologists to make accurate diagnoses.

Genomic characteristics and evolution of Multicentric Esophageal and gastric Cardiac Cancer.

BACKGROUND: Esophageal carcinoma (EC) and gastric cardiac adenocarcinoma (GCA) have high incidence rates in the Chaoshan region of South China. Multifocal esophageal and cardiac cancer (MECC) is commonly observed in this region in clinical practice. However, the genomic characteristics of MECC remains unclear. MATERIALS AND METHODS: In this study, a total of 2123 clinical samples of EC and GCA were analyzed to determine the frequency of multifocal tumors, as well as their occurrence sites and pathological types. Cox proportional hazards regression was used to model the relationship between age, sex, and tumor state concerning survival in our analysis of the cohort of 541 patients with available follow-up data. We performed whole-genome sequencing on 20 tumor foci and 10 normal samples from 10 MECC patients to infer clonal structure on 6 MECC patients to explore genome characteristics. RESULT: The MECC rate of EC and GCA was 5.65% (121 of 2123). Age and sex were potential factors that may influence the risk of MECC (p < 0.001). Furthermore, MECC patients showed worse survival compared with single tumor patients. We found that 12 foci from 6 patients were multicentric origin model (MC), which exhibited significant heterogeneity of variations in paired foci and had an increased number of germline mutations in immune genes compared to metastatic model. In MC cases, different lesions in the same patient were driven by distinct mutation and copy number variation (CNV) events. Although TP53 and other driver mutation genes have a high frequency in the samples, their mutation sites show significant heterogeneity in paired tumor specimens. On the other hand, CNV genes exhibited higher concordance in paired samples, especially in the amplification of oncogenes and the deletion of tumor suppressor genes. CONCLUSIONS: The extent of inter-tumor heterogeneity suggests both monoclonal and polyclonal origins of MECC, which could provide insight into the genome diversity of MECC and guide clinical implementation.

Cervical HPV infection and related diseases among 149,559 women in Fujian: an epidemiological study from 2018 to 2023.

Objectives: To comprehensively analyze the epidemiological features of human papillomavirus (HPV) and HPV-related cervical diseases in females aged 35-64 years. Methods: A total of 149,559 samples of exfoliated cervical cells screened for HPV and related cervical lesions from January 2018 to December 2023 were enrolled. The prevalence of 15 high-risk and 6 low-risk HPV genotypes were detected, and the cervical cytology were analyzed. The impact of single and multiple HPV infections was characterized, and the effect of age was studied. Results: The cervix cytology was normal in 86.60% of the females, while 7.13% of the females were diagnosed with cervix inflammation, 0.60% with ASC-US, 0.22% with ASC-H, 0.72% with LSIL, 0.49% with HSIL, 0.03% with ICC. The highest median age was observed in ASC-H group with 54 years old. Females with primary school education or lower have the highest positive rates. The overall HPV prevalence was 8.60%. The relatively prevalent HPV types were HPV52, 58, 16, 39, 51. HPV16, HPV18, HPV58, HPV33 and HPV52 were the top5 predominant types in ICC patients. 17.41% females suffered from multiple HPV infection with the most frequently co-infection subtypes being HPV52, HPV58 and HPV16. The prevalence of all HPV subtypes increased with age. Multiple HPV infections accounted for a larger proportion in those aged above 55 years. The peak HPV16 prevalence was observed in ICC group in cases aged 45-49 and 55-59. The peak HPV33 prevalence was observed in younger individuals aged 40-44 who developed ICC. Conclusion: More action should be taken against HPV33 infection.

Evaluation of demographic/clinical features and hemorrhagic complications in patients with ischemic stroke who underwent reperfusion therapy.

The relationship between demographic/clinical characteristics, clinical outcomes and the development of hemorrhagic complications in patients with ischemic stroke who underwent reperfusion therapy has not been studied sufficiently. We have aimed to compare genders and age groups in terms of clinical features and outcome; and types of reperfusion treatments and clinical features regarding the development of hemorrhagic complications in patients with ischemic stroke who underwent recombinant tissue plasminogen activator (rtPA) and/or thrombectomy. Patients with acute ischemic stroke undergoing rtPA and/or thrombectomy were divided into six age groups. Parameters including hemorrhagic complications, anticoagulant and antiaggregant use, hyperlipidemia, smoking status, biochemical parameters, and comorbidities were documented. National Institutes of Health Stroke Scale (NIHSS) scores, modified Rankin Score (mRS) and Glasgow Coma Scale scores were recorded. Etiological classification of stroke was done. These parameters were compared in terms of age groups, genders, and hemorrhagic complications. Significant differences were found between age groups concerning hypertension, coronary artery disease, smoking status, and antiaggregant use. Rate of hemorrhagic complications in rtPA group was significantly lower when compared with other treatment groups. Hemorrhagic complications developed mostly in the rtPA+thrombectomy group. Among the patients who developed hemorrhagic complications, NIHSS scores on admission were found to be significantly lower in men than women. Admission, discharge, and 3rd month mRS values in men were significantly lower than those of women. Knowing demographic and clinical features of patients that may have an impact on the clinical course of ischemic stroke managed with reperfusion therapy will be useful in predicting the hemorrhagic complications and clinical outcomes.

The Incidence and Presentation Features of Glaucoma in Vogt-Koyanagi-Harada Syndrome: A Systematic Review and Meta-Analysis.

TOPIC: To determine the cumulative incidence and features of glaucoma in Vogt-Koyanagi-Harada (VKH) syndrome patients compared to non-glaucoma patients. CLINICAL RELEVANCE: Knowing the exact burden of secondary glaucoma in VKH could guide its screening and management in clinical practice as a part of the regular follow-up for VKH patients. METHODS: The review protocol was pre-registered on PROSPERO [CRD42023462794]. PubMed, Scopus, Web of Science, EBSCOhost, and Google Scholar were searched for studies reporting the cumulative incidence and features of glaucoma presentation in VKH. A manual search was also conducted to supplement the primary search. Subgroup analyses based on glaucoma type, VKH stage, and patients' age were conducted. All analyses were conducted using STATA. Fixed- and random-effects models were selected according to the observed heterogeneity. Studies' methodological quality was determined using the NIH tool. RESULTS: The analysis of 7084 eyes revealed a progressive increase in the cumulative incidence of secondary glaucoma over time. The cumulative incidence was lowest at VKH onset (7%) and highest at 15 years (26%). Open-angle (12%; 95%CI: 9-14%) is more common than angle-closure glaucoma (7%; 95%CI: 3-13%). Glaucoma cumulative incidence is highest in the chronic recurrent stage of VKH (33%; 95%CI: 12-59%) and among children <18 years of age (26%; 95%CI: 16-37%). Features associated with glaucoma occurrence in VKH showed comparable rates to non-glaucoma cases. However, a meta-analysis to determine risk factors of glaucoma development in VKH was not feasible secondary to the lack of adjusted risk measures in included studies. Studies' quality was questionable in 5 studies. The certainty of evidence was moderate-to-high. CONCLUSION: The cumulative incidence of glaucoma increases throughout VKH's course, with a higher tendency in children, chronic recurrent stages, and long-term follow-up. Future research should focus on examining risk factors of glaucoma development in VKH through adjusted multivariable regression models.

Gastric Cancer: Clinical Features, Screening, Diagnosis, Treatment, and Prevention.

The objective of this article is to highlight the clinical features, screening, diagnosis, treatment, and prevention of gastric cancer (GC). Early GC is often asymptomatic leading to frequent delays in diagnosis. Weight loss and persistent abdominal pain are the most common symptoms at initial diagnosis. The diagnosis of GC typically involves a combination of endoscopy, biopsy, and imaging studies. Endoscopic resection techniques are emerging as successful treatment options for early GC. Treatment options for advanced GC include surgery and chemotherapy. The first line chemotherapy for advanced GC consists of doublet therapy with a combination of platinum and fluoropyrimidines. Trastuzumab, a monoclonal antibody, is used in the treatment of human epidermal growth factor 2 positive GCs. Antiangiogenic agents and immunotherapy are also useful in the treatment of GC. Currently there are no GC screening guidelines in the United States, but they exist in other regions where there is increased prevalence of GC. Prevention strategies for GC include Helicobacter pylori eradication and adoption of a healthy diet consisting of fruits and vegetables.

Going beyond still images to improve input variance resilience in multi-stream vision understanding models.

Traditionally, vision models have predominantly relied on spatial features extracted from static images, deviating from the continuous stream of spatiotemporal features processed by the brain in natural vision. While numerous video-understanding models have emerged, incorporating videos into image-understanding models with spatiotemporal features has been limited. Drawing inspiration from natural vision, which exhibits remarkable resilience to input changes, our research focuses on the development of a brain-inspired model for vision understanding trained with videos. Our findings demonstrate that models that train on videos instead of still images and include temporal features become more resilient to various alternations on input media.

Clinical and serological characteristics of patients allergic to LTP.

BACKGROUND: Allergy to lipid transfer proteins (LPT) is common in Mediterranean Europe, and it causes severe reactions in patients and affects multiple foods, impairing the quality of life. OBJECTIVE: This study aimed to describe the clinical and sensitization profile of patients with LTP syndrome and to determine a clinical pattern of severity. Molecular diagnosis is shown in a broad population through microarrays. MATERIAL AND METHODS: This study was performed at the LTP Allergy Consultation of the Reina Sofia Hospital in Murcia, Spain. We analyzed the patients' characteristics, reactions, cofactors, food implicated, quality of life, skin prick test to food and aeroallergens, and serologic parameters, such as total immunoglobulin E, peach LTP (Pru p 3 IgE) and immunoglobulin G4, and microarray Immuno Solid-phase Allergen Chip (ISAC). We related the severity of the reactions with other variables. RESULTS: We presented a series of 236 patients diagnosed with LTP allergy, 54.66% suffering from anaphylaxis, 36.02% from urticaria angioedema, and 9.32% from oral allergy syndrome. The most frequently implicated food was peach, producing symptoms in 70% of patients, followed by walnut in 55%, peanut in 45%, hazelnut in 44%, and apple in 38% patients. Regarding the food that provoked anaphylaxis, walnut was the most frequent instigator, along with peach, peanut, hazelnut, almond, sunflower seed, and apple. According to the severity of LPT reaction, we did not discover significant differences in gender, age, food group involved, and serologic parameters. We found differences in the presence of cofactors, with 48.84% of cofactors in patients with anaphylaxis, compared to 27.1% in patients without anaphylaxis and in family allergy background (P < 0.0001). CONCLUSION: In our series of patients, 54% presented anaphylaxis, and the foods that most frequently produced symptoms were peaches, apples, and nuts. Cofactors and family allergy backgrounds were associated with the severity of LPT reaction.

Analyzing the correlation between low proportion of hobnail features in papillary thyroid carcinoma and clinical aggressiveness risk.

PURPOSE: Hobnail features may enhance the clinical aggressiveness of papillary thyroid carcinoma (PTC). However, whether a low proportion (<30%) of these features contributes to increased PTC aggressiveness remains unclear. This study investigated whether PTC cases with a low proportion hobnail features (<30%) exhibit clinical invasiveness and pathological features of aggressiveness. METHODS: Pathological specimens from patients with postoperatively diagnosed PTC were retrospectively analyzed. Among them, 29 PTC cases with a low proportion of hobnail features (<30%) were compared with 173 consecutive classical PTC (cPTC) cases. Data regarding age at presentation, sex, tumor size, number of tumors, and histological characteristics were obtained by reviewing electronic medical records. Postoperative information was obtained during follow-up visits and telephone interviews. RESULTS: Twenty-nine patients with PTC with a low proportion of hobnail features (<30%) were identified, exhibiting a median age of 34 years. At a median follow-up of 31 (IQR, 23-37) months, two patients had recurrent disease in the PTC with a low proportion of hobnail features (<30%) group, whereas there was no recurrence in the cPTC group. No distant metastasis and postoperative mortality were observed in either group. Compared with the cPTC group, patients with PTC and a low proportion of hobnail features exhibited larger tumor volumes and higher susceptibility to capsular invasion and lymph node metastasis. Tumor size and hobnail features emerged as independent risk factors for lymph node metastasis. CONCLUSION: PTC with a low proportion hobnail features (<30%) and larger tumor volumes are associated with the occurrence of lymph node metastasis. A low proportion of hobnail features (<30%) in PTC may heighten invasiveness, elevating the risk of recurrence.

Global incidence and characteristics of spinal cord injury since 2000-2021: a systematic review and meta-analysis.

BACKGROUND: This study employs systematic review and meta-analysis to explore the incidence and characteristics of spinal cord injury (SCI) between 2000 and 2021, aiming to provide the most recent and comprehensive data support for the prevention, diagnosis, treatment, and care of SCI. METHODS: Systematic searches were conducted on epidemiological studies of SCI published between January 1, 2000, and March 29, 2024. Meta-analysis, subgroup analysis, meta-regression, publication bias detection, and literature quality assessment were extensively utilized. RESULTS: The pooled results from 229 studies indicated that the overall incidence rate of SCI was 23.77 (95% CI, 21.50-26.15) per million people, with traumatic spinal cord injuries (TSCI) at a rate of 26.48 (95% CI, 24.15-28.93) per million people, and non-traumatic spinal cord injuries (NTSCI) at a rate of 17.93 (95% CI, 13.30-23.26) per million people. The incidence of TSCI exhibited a marked age-related increase and was significantly higher in community settings compared to hospital and database sources. Males experienced TSCI at a rate 3.2 times higher than females. Between 2000 and 2021, the incidence of TSCI remained consistently high, between 20 and 45 per million people, whereas NTSCI incidence has seen a steady rise since 2007, stabilizing at a high rate of 25-35 per million people. Additionally, the incidence of TSCI in developing countries was notably higher than that in developed countries. There were significant differences in the causes of injury, severity, injury segments, gender, and age distribution among the TSCI and NTSCI populations, but the proportion of male patients was much higher than that of female patients. Moreover, study quality, country type, and SCI type contributed to the heterogeneity in the meta-analysis. CONCLUSIONS: The incidence rates of different types of SCI remain high, and the demographic distribution of SCI patients is changing, indicating a serious disease burden on healthcare systems and affected populations. These findings underscore the necessity of adopting targeted preventive, therapeutic, and rehabilitative measures based on the incidence and characteristics of SCI.

Machine learning-based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series.

AIMS: To assess the predictive value of early-stage physiological time-series (PTS) data and non-interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes. METHODS: Using data from TBI patients in the multi-center eICU database, we focused on in-hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm. RESULTS: The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in-hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use. CONCLUSION: Our study highlights the importance of early-stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision-making, contributing to the development of accurate prediction models and timely clinical intervention.

Group-informed attentive framework for enhanced diabetes mellitus progression prediction.

The increasing prevalence of Diabetes Mellitus (DM) as a global health concern highlights the paramount importance of accurately predicting its progression. This necessity has propelled the use of deep learning's advanced analytical and predictive capabilities to the forefront of current research. However, this approach is confronted with significant challenges, notably the prevalence of incomplete data and the need for more robust predictive models. Our research aims to address these critical issues, leveraging deep learning to enhance the precision and reliability of diabetes progression predictions. We address the issue of missing data by first locating individuals with data gaps within specific patient clusters, and then applying targeted imputation strategies for effective data imputation. To enhance the robustness of our model, we implement strategies such as data augmentation and the development of advanced group-level feature analysis. A cornerstone of our approach is the implementation of a deep attentive transformer that is sensitive to group characteristics. This framework excels in processing a wide array of data, including clinical and physical examination information, to accurately predict the progression of DM. Beyond its predictive capabilities, our model is engineered to perform advanced feature selection and reasoning. This is crucial for understanding the impact of both individual and group-level factors on deep models' predictions, providing invaluable insights into the dynamics of DM progression. Our approach not only marks a significant advancement in the prediction of diabetes progression but also contributes to a deeper understanding of the multifaceted factors influencing this chronic disease, thereby aiding in more effective diabetes management and research.

Youth attention, perceptions, and appeal in response to e-cigarette advertising features: A focus group study.

Background: E-cigarette marketing exposure may influence vaping-related outcomes among youth, but less is known on which specific advertising features impact youth attention, perceptions, and appeal. This study qualitatively examines responses to different e-cigarette advertising features among e-cigarette-naïve youth. Methods: We conducted four online focus groups in 2021 with a national U.S. sample of 13-17 year olds (n = 25) who had never used e-cigarettes. Participants viewed and discussed their reactions to different e-cigarette advertisements varying in the inclusion of ad features, including color, models in imagery, text claims targeting smokers, and the nicotine warning label. Results: Participants were attracted to ads with bright colors, particularly when contrasted against a dark background. Ads featuring models attracted attention and reduced perceptions that the product is harmful. Comments indicated mixed reactions to smoker-targeted text claims. On one hand, participants perceived ads with text that specified "for smokers" as targeting older adults. On the other hand, text referring to "switching" from cigarettes to e-cigarettes led to some perceptions that the product is healthy, and certain text that implicitly referred to smoking (e.g., "no odor") had the potential to appeal to youth who wanted to use e-cigarettes discreetly. The level of attention paid to warnings depended on warning size and the color contrast between the warning and the rest of the ad. Conclusions: Findings suggest specific e-cigarette ad features play an important role in attracting youth attention and influencing perceptions. More research is needed on the potential public health benefits versus unintended consequences of smoker-targeted text claims.