Explore the vast range of titles available.

Musculoskeletal disorders affect the locomotor system and are the leading contributor to disability worldwide. Patients suffer chronic pain and limitations in mobility, dexterity, and functional ability. Musculoskeletal (bone) X-ray is an essential tool in diagnosing the abnormalities. In recent years, deep learning algorithms have increasingly been applied in musculoskeletal radiology and have produced remarkable results. In our study, we introduce a new calibrated ensemble of deep learners for the task of identifying abnormal musculoskeletal radiographs. Our model leverages the strengths of three baseline deep neural networks (ConvNet, ResNet, and DenseNet), which are typically employed either directly or as the backbone architecture in the existing deep learning-based approaches in this domain. Experimental results based on the public MURA dataset demonstrate that our proposed model outperforms three individual models and a traditional ensemble learner, achieving an overall performance of (AUC: 0.93, Accuracy: 0.87, Precision: 0.93, Recall: 0.81, Cohen’s kappa: 0.74). The model also outperforms expert radiologists in three out of the seven upper extremity anatomical regions with a leading performance of (AUC: 0.97, Accuracy: 0.93, Precision: 0.90, Recall:0.97, Cohen’s kappa: 0.85) in the humerus region. We further apply the class activation map technique to highlight the areas essential to our model’s decision-making process. Given that the best radiologist performance is between 0.73 and 0.78 in Cohen’s kappa statistic, our study provides convincing results supporting the utility of a calibrated ensemble approach for assessing abnormalities in musculoskeletal X-rays.

The COVID-19 pandemic has presented unprecedented challenges for university students, creating uncertainties for their academic careers, social lives, and mental health. Our study utilized a machine learning approach to examine the degree to which students’ college adjustment and coping styles impacted their adjustment to COVID-19 disruptions. More specifically, we developed predictive models to distinguish between well-adjusted and not well-adjusted students in each of five psychological domains: academic adjustment, emotionality adjustment, social support adjustment, general COVID-19 regulations response, and discriminatory impact. The predictive features used for these models are students’ individual characteristics in three psychological domains, i.e., Ways of Coping (WAYS), Adaptation to College (SACQ), and Perceived Stress Scale (PSS), assessed using established commercial and open-access questionnaires. We based our study on a proprietary survey dataset collected from 517 U.S. students during the initial peak of the pandemic. Our models achieved an average of 0.91 AUC score over the five domains. Using the SHAP method, we further identified the most relevant risk factors associated with each classification task. The findings reveal the relationship of students’ general adaptation to college and coping in relation to their adjustment during COVID-19. Our results could help universities identify systemic and individualized strategies to support their students in coping with stress and to facilitate students’ college adjustment in this era of challenges and uncertainties.

Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease characterized by flares ranging from mild to life-threatening. Severe flares and complications can require hospitalizations, which account for most of the direct costs of SLE care. This study investigates two machine learning approaches in predicting SLE hospitalizations using longitudinal data from 925 patients enrolled in a multicenter electronic health record (EHR)-based lupus cohort. Our first Differential approach accounts for the time dependencies in sequential data by introducing additional lagged variables between consecutive time steps. We next evaluate the performance of LSTM, a state-of-the-art deep learning model designed for time series. Our experimental results demonstrate that both methods can effectively predict lupus hospitalizations, but each has its strengths and limitations. Specifically, the Differential approach can be integrated into any non-temporal machine learning algorithms and is preferred for tasks with short observation periods. On the contrary, the LSTM model is desirable for studies utilizing long observation intervals attributing to its capability in capturing long-term dependencies embedded in the longitudinal data. Furthermore, the Differential approach has more options in handling class imbalance in the underlying data and delivers stable performance across different prognostic horizons. LSTM, on the other hand, demands more class-balanced training data and outperforms the Differential approach when there are sufficient positive samples facilitating model training. Capitalizing on our experimental results, we further study the optimal length of patient monitoring periods for different prediction horizons.

Background The golden pompano ( Trachinotus ovatus ) is an economically significant warm-water aquaculture species in China. The time required for sexual maturity of T. ovatus is relatively long. Consequently, it has prompted researchers to investigate gonadal development process of this fish. To gain further insight into the function of competing endogenous RNA (ceRNA) in the gonads of T. ovatus and the regulatory mechanism of the ceRNA network, whole transcriptome libraries were constructed from the testes and ovaries. Results Overall, a total of 96 differentially expressed microRNAs (DE-miRNAs), 2,338 differentially expressed messenger RNAs (DE-mRNAs), 973 differentially expressed long non-coding RNAs (DE-lncRNAs), and 94 differentially expressed circular RNAs (DE-circRNAs) were identified. Additionally, a ceRNA network was constructed, and enrichment analysis confirmed the involvement of numerous pathways in reproduction and gonadal development, including the TGF-β signaling pathway and GnRH signaling pathway. The ceRNA network analysis revealed that the oni-let-7d-1-p3 and PC-3p-112794_13 may play significant roles in T. ovatus gonadal development. And we have observed a possible relationship related to gonadal development involving R-spondin-1 ( Rspo1 ), oni-let-7d-1-p3, and MSTRG.14909.1 (lnc- TGFβR ). Dual-luciferase gene reporter system and fluorescence in situ hybridization analyses preliminary verified the regulation relationship between Rspo1 and oni-let-7d-1-p3, as well as lnc- TGFβR and oni-let-7d-1-p3 in the cytoplasm of sertoli cells. Conclusion It is hypothesized that the lnc- TGFβR functions as a sponge for oni-let-7d-1-p3, participating in regulating the process of testis development. These findings could enhance our understanding of ncRNAs in gonadal development. It also provides new insight into the function of ncRNAs and the regulatory relationship of ceRNA between males and females. These results might contribute to discussions on the regulation of ncRNA during gametogenesis.

With the emergence of 3D bioprinting, tissue repair strategies have become more sophisticated and multifunctional. Natural biomaterials like alginate and gelatin have been widely studied to formulate bioinks due to their excellent biocompatibility and biodegradable characteristics. However, the requirement for balanced features combining adjustable degradation rate, printability, and biological functionality is still hard to achieve. In this study, alginate dialdehyde (ADA) – gelatin (GEL) based hydrogels have been supplemented with mesoporous bioactive glass nanoparticles (MBGNs) and human platelet lysate (HPL) to enhance the biological performance. MBGNs can reduce the degradation of ADA‐GEL 3D printed scaffolds and induce a mineralization effect while HPL is added as a source of growth factors. Improved printability and higher shape fidelity are observed by incorporating 0.1% (w/v) MBGNs, however, the addition of HPL led to a slight decrease in 3D printed shape fidelity. On the other hand, MBGNs and HPL both presented positive effects to improve cell activity and viability, which is characterized by using MC3T3‐E1 pre‐osteoblast cells. The ADA‐GEL‐based hydrogel with the incorporation of 0.1% (w/v) MBGNs and 5% (v/v) HPL shows the most balanced features, making it a promising biomaterial for 3D bioprinting of bone tissue scaffolds. Alginate dialdehyde (ADA)‐gelatin (GEL) hydrogels are supplemented with mesoporous bioactive glass nanoparticles (MBGNs) and human platelet lysate (HPL) to enhance the biological performance of 3D printed scaffolds. Improved printability and higher shape fidelity are observed by incorporating 0.1% (w/v) MBGNs. MBGNs and HPL enhance MC3T3‐E1 pre‐osteoblast cell viability. ADA‐GEL‐0.1% (w/v) MBGNs‐5% (v/v) HPL is promising for 3D bioprinting bone tissue scaffolds.

Gas therapy has received widespread attention from the medical community as an emerging and promising therapeutic approach to cancer treatment. Among all gas molecules, nitric oxide (NO) was the first one to be applied in the biomedical field for its intriguing properties and unique anti-tumor mechanisms which have become a research hotspot in recent years. Despite the great progress of NO in cancer therapy, the non-specific distribution of NO in vivo and its side effects on normal tissue at high concentrations have impaired its clinical application. Therefore, it is important to develop facile NO-based nanomedicines to achieve the on-demand release of NO in tumor tissue while avoiding the leakage of NO in normal tissue, which could enhance therapeutic efficacy and reduce side effects at the same time. In recent years, numerous studies have reported the design and development of NO-based nanomedicines which were triggered by exogenous stimulus (light, ultrasound, X-ray) or tumor endogenous signals (glutathione, weak acid, glucose). In this review, we summarized the design principles and release behaviors of NO-based nanomedicines upon various stimuli and their applications in synergistic cancer therapy. We also discuss the anti-tumor mechanisms of NO-based nanomedicines in vivo for enhanced cancer therapy. Moreover, we discuss the existing challenges and further perspectives in this field in the aim of furthering its development.

The graduate admissions process is time-consuming, subjective, and complicated by the need to combine information from diverse data sources. Letters of recommendation (LORs) are particularly difficult to evaluate and it is unclear how much impact they have on admissions decisions. This study addresses these concerns by building machine learning models to predict admissions decisions for two STEM graduate programs, with a focus on examining the contribution of LORs in the decision-making process. We train our predictive models leveraging information extracted from structured application forms (e.g., undergraduate GPA, standardized test scores, etc.), applicants’ resumes, and LORs. A particular challenge in our study is the different modalities of application data (i.e., text vs. structured forms). To address this issue, we converted the textual LORs into features using a commercial natural language processing product and a manual rating process that we developed. By analyzing the predictive performance of the models using different subsets of features, we show that LORs alone provide only modest, but useful, predictive signals to admission decisions; the best model for predicting admissions decisions utilized both LOR and non-LOR data and achieved 89% accuracy. Our experiments demonstrate promising results in the utility of automated systems for assisting with graduate admission decisions. The findings confirm the value of LORs and the effectiveness of our feature engineering methods from LOR text. This study also assesses the significance of individual features using the SHAP method, thereby providing insight into key factors affecting graduate admission decisions.

Recent advances in Artificial Intelligence (AI), such as the development of large language models like ChatGPT, have blurred the boundaries between human and AI-generated text. This has led to a pressing need for tools that can determine whether text has been created or revised using AI. A general and universally effective detection model would be extremely useful, but appears to be beyond the reach of current technology and detection methods. The research described in this study adopts a domain and task specific approach and shows that specialized detection models can attain high accuracy. The study focuses on the higher education graduate admissions process, with the specific goal of identifying AI-generated and AI-revised Letters of Recommendation (LORs) and Statements of Intent (SOIs). Detecting such application materials is essential to ensure that applicants are evaluated on their true merits and abilities, and to foster an equitable and trustworthy admissions process. Our research is based on 3755 LORs and 1973 SOIs extracted from the application records of Fordham University’s Master’s programs in Computer Science and Data Science. To facilitate the construction and evaluation of detection models, we generated AI counterparts for each LOR and SOI using the GPT-3.5 Turbo API. The prompts for AI-generation text were derived from the admission data of the respective applicants, and the AI-revised LORs and SOIs were generated directly from the human-authored versions. We also utilize an open-access GPT-wiki-intro dataset to further validate our hypothesis regarding the feasibility of constructing domain-specific AI content detectors. Our experiments yield promising results in developing classifiers tailored to a specific domain when provided with sufficient training samples. Additionally, we present a comparative analysis of the word frequency and statistical characteristics of the text, which provides convincing evidence that ChatGPT employs distinctive vocabulary and paragraph structure compared to human-authored text. The code for this study is available on GitHub, and the models can be executed on user-provided data via an interactive web interface.

Background Retroiliac ureter is an extremely rare congenital anomaly, even more rarely accompanied by persisting mesonephric duct and vesicoureteral reflux(VUR). We report such a unique case involving a left inguinal mass that appeared during defecation. Case presentation A two-year-old boy presented with a tubular structure resembling a dilated ureter discovered incidentally during open left inguinal hernia repair. Contrast radiography and voiding cystourethrogram(VCUG) revealed a tubular structure in the left groin mimicking a ureter, with grade IV reflux into a branch-shaped left renal pelvis. Three-dimensional CT reconstruction demonstrated a dilated left ureter and a tubular structure distortion, angulation, and depression at the L5–S1 level. Cystoscopy showed the left ureteral orifice near the midline of bladder trigone. Laparoscopic exploration revealed an abnormally deep aortic bifurcation in the left iliac fossa, superior to the left ureter and the tubular structure. The left vas deferens was absent, while the tubular structure traversed the internal ring with the left spermatic vessels and inserted into the distal ipsilateral ureter. Four years later, the patient was readmitted due to decreased left renal function. VCUG persistent left-sided grade IV VUR. Robot-assisted laparoscopic left ureter reimplantation via the Lich-Gregoir technique was conducted, along with resection of the abdominal and inguinal segment of the dilated tubular structure and closure of the ipsilateral internal ring. The tubular structure was ultimately confirmed as an abnormally dilated left vas deferens, and the diagnosis of retroiliac ureter accompanied by persisting mesonephric duct and VUR was made. At the 3-month follow-up, ultrasonography revealed mild hydronephrosis and ureteral dilation of left kidney. Conclusion Diagnosing retroiliac ureter with persisting mesonephric duct and VUR is challenging. Although imaging provide critical information, surgical exploration is often required for definitive diagnosis. Treatment involves vas deferens excision and ureteral reimplantation to preserve renal function.

To explore the value of machine learning methods for predicting multiple sclerosis disease course. 1693 CLIMB study patients were classified as increased EDSS≥1.5 (worsening) or not (non-worsening) at up to five years after baseline visit. Support vector machines (SVM) were used to build the classifier, and compared to logistic regression (LR) using demographic, clinical and MRI data obtained at years one and two to predict EDSS at five years follow-up. Baseline data alone provided little predictive value. Clinical observation for one year improved overall SVM sensitivity to 62% and specificity to 65% in predicting worsening cases. The addition of one year MRI data improved sensitivity to 71% and specificity to 68%. Use of non-uniform misclassification costs in the SVM model, weighting towards increased sensitivity, improved predictions (up to 86%). Sensitivity, specificity, and overall accuracy improved minimally with additional follow-up data. Predictions improved within specific groups defined by baseline EDSS. LR performed more poorly than SVM in most cases. Race, family history of MS, and brain parenchymal fraction, ranked highly as predictors of the non-worsening group. Brain T2 lesion volume ranked highly as predictive of the worsening group. SVM incorporating short-term clinical and brain MRI data, class imbalance corrective measures, and classification costs may be a promising means to predict MS disease course, and for selection of patients suitable for more aggressive treatment regimens.