Development and validation of machine learning models to predict perioperative transfusion risk for hip fractures in the elderly.

BACKGROUND: Patients with hip fractures frequently need to receive perioperative transfusions of concentrated red blood cells due to preoperative anemia or surgical blood loss. However, the use of perioperative blood products increases the risk of adverse events, and the shortage of blood products is prompting us to minimize blood transfusion. Our study aimed to construct a machine learning algorithm predictive model to identify patients at high risk for perioperative transfusion early in hospital admission and to manage their patient blood to reduce transfusion requirements. METHODS: This study collected patients hospitalized for hip fractures at a university hospital from May 2016 to November 2022. All patients included in the analysis were randomly divided into a training set and validation set according to 70:30. Eight machine learning algorithms, CART, GBM, KNN, LR, NNet, RF, SVM, and XGBoost, were used to construct the prediction models. The models were evaluated for discrimination, calibration, and clinical utility, and the best prediction model was selected. RESULTS: A total of 805 patients were included in the study, of whom 306 received transfusions during the perioperative period. We screened eight features used to construct the prediction model: age, fracture time, fracture type, hemoglobin, albumin, creatinine, calcium ion, and activated partial thromboplastin time. After evaluating and comparing the performance of each of the eight models, the model constructed by the XGBoost algorithm had the best performance, with MCC values of 0.828 and 0.939 in the training and validation sets, respectively. In addition, it had good calibration and clinical utility in both the training and validation sets. CONCLUSION: The model constructed by the XGBoost algorithm has the best performance, using this model to identify patients at high risk for transfusion early in their admission and promptly incorporating them into a patient blood management plan can help reduce the risk of transfusion.

Machine learning-based prediction of vitamin D deficiency: NHANES 2001-2018.

Background: Vitamin D deficiency is strongly associated with the development of several diseases. In the current context of a global pandemic of vitamin D deficiency, it is critical to identify people at high risk of vitamin D deficiency. There are no prediction tools for predicting the risk of vitamin D deficiency in the general community population, and this study aims to use machine learning to predict the risk of vitamin D deficiency using data that can be obtained through simple interviews in the community. Methods: The National Health and Nutrition Examination Survey 2001-2018 dataset is used for the analysis which is randomly divided into training and validation sets in the ratio of 70:30. GBM, LR, NNet, RF, SVM, XGBoost methods are used to construct the models and their performance is evaluated. The best performed model was interpreted using the SHAP value and further development of the online web calculator. Results: There were 62,919 participants enrolled in the study, and all participants included in the study were 2 years old and above, of which 20,204 (32.1%) participants had vitamin D deficiency. The models constructed by each method were evaluated using AUC as the primary evaluation statistic and ACC, PPV, NPV, SEN, SPE, F1 score, MCC, Kappa, and Brier score as secondary evaluation statistics. Finally, the XGBoost-based model has the best and near-perfect performance. The summary plot of SHAP values shows that the top three important features for this model are race, age, and BMI. An online web calculator based on this model can easily and quickly predict the risk of vitamin D deficiency. Conclusion: In this study, the XGBoost-based prediction tool performs flawlessly and is highly accurate in predicting the risk of vitamin D deficiency in community populations.

Machine learning algorithms to predict risk of postoperative pneumonia in elderly with hip fracture.

BACKGROUND: Hip fracture (HF) is one of the most common fractures in the elderly and is significantly associated with high mortality and unfavorable prognosis. Postoperative pneumonia (POP), the most common postoperative complication of HF, can seriously affect patient prognosis and increase the burden on the healthcare system. The aim of this study was to develop machine learning models for identifying elderly patients at high risk of pneumonia after hip fracture surgery. METHODS: From May 2016 to November 2022, patients admitted to a single central hospital for HF served as the study population. We extracted data that could be collected within 24 h of patient admission. The dataset was divided into training and validation sets according to 70:30. Based on the screened risk factors, prediction models were developed using seven machine learning algorithms, namely CART, GBM, KNN, LR, NNet, RF, and XGBoost, and their performance was evaluated. RESULTS: Eight hundred five patients were finally included in the analysis and 75 (9.3%) patients suffered from POP. Age, CI, COPD, WBC, HB, GLU, STB, GLOB, Ka+ which are used as features to build machine learning models. By evaluating the model's AUC value, accuracy, sensitivity, specificity, Kappa value, MCC value, Brier score value, calibration curve, and DCA curve, the model constructed by XGBoost algorithm has the best and near-perfect performance. CONCLUSION: The machine learning model we created is ideal for detecting elderly patients at high risk of POP after HF at an early stage.

Type 2 diabetes and the risk of synovitis-tenosynovitis: a two-sample Mendelian randomization study.

Introduction: It has been shown that people with type 2 diabetes have a higher risk of synovitis and tenosynovitis, but previous studies were mainly observational, which may be biased and does not allow for a cause-and-effect relationship. Therefore, we conducted a two-sample Mendelian randomization (MR) study to investigate the causal relationship. Method: We obtained data on "type 2 diabetes" and "synovitis, tenosynovitis" from published large-scale genome-wide association studies (GWAS). The data were obtained from the FinnGen consortium and UK Biobank, both from European population samples. We used three methods to perform a two-sample MR analysis and also performed sensitivity analysis. Results: The results of all three MR methods we used for the analysis illustrated that T2DM increases the risk factor for the development of synovitis and tenosynovitis. Specifically, for the IVW method as the primary analysis outcome, OR = 1.0015 (95% CI, 1.0005 to 1.0026), P = 0.0047; for the MR Egger method as the supplementary analysis outcome, OR = 1.0032 (95% CI, 1.0007 to 1.0056), P = 0.0161; for the weighted median method, OR = 1.0022 (95% CI, 1.0008 to 1.0037), p = 0.0018. In addition, the results of our sensitivity analysis suggest the absence of heterogeneity and pleiotropy in our MR analysis. Conclusion: In conclusion, the results of our MR analysis suggest that T2DM is an independent risk factor for increased synovitis and tenosynovitis.

Effect of Wu Qin Xi exercises on pain and function in people with knee osteoarthritis: A systematic review and meta-analysis.

Background: As a chronic disease that affects the whole world, there is no definite treatment for knee osteoarthritis (KOA). Wu Qin Xi (WQX) is still in preliminary exploration as a traditional Chinese exercise in the treatment of osteoarthritis of the knee. The purpose of this study was to conduct a meta-analysis of previous studies and to investigate the efficacy of the WQX exercises on pain and function in patients with KOA. Methods: We searched six databases (Pubmed, Embase, Cochrane Library, Wanfang, CQVIP, and CNKI) for articles on WQX for KOA up to May 10, 2022. Literature search, study selection, data extraction, and quality evaluation were performed by two independent authors. In terms of statistical results, we presented mean differences (MD), 95% CI, and I 2 to show heterogeneity, and, based on that, we chose either a random effects model or a fixed effects model. Results: Seven studies were selected for inclusion in this meta-analysis. The WQX intervention group showed statistical differences for both the total Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score and its various bylaws, the Visual Analogue Score (VAS), and the presence of general functional exercise in the control group. We also demonstrated the clinically meaningful efficacy of WQX treatment by calculating minimum clinical importance difference (MCID) values that met the MCID values on the WOMAC score. A sensitivity analysis was also performed in this study by subgroup analysis for greater heterogeneity, and it was inferred that the difference in follow-up time was a likely source of heterogeneity. Conclusion: Despite some limitations, the current study showed a definite effect of WQX in improving pain symptoms and joint function in patients with KOA. Systematic review registration: https://www.crd.york.ac.uk/prospero/, identifier: CRD42022332209.

Different treatments for 3- or 4-part proximal humeral fractures in the elderly patients: A Bayesian network meta-analysis of randomized controlled trials.

Background: Proximal humeral fractures are the third most common fracture in the body, and their incidence is rising year by year as the population ages. However, the treatment of the proximal humerus in parts 3 and 4 is still debatable, necessitating a network meta-analysis to determine the best treatment for each treatment modality. Methods: We searched PubMed, Embase, Cochrane Library for randomized controlled trials on proximal humeral fractures up to June 21, 2022. We performed data extraction and literature quality assessment by two independent authors and extracted constant score and reoperation rate as indicators for evaluation. Stata software, Revman software, JAGS software and the R-based BlandAltmanLeh package, gemtc package and riags package were used to perform this Bayesian network meta-analysis. Results: Following screening, 11 papers with a total of 648 participants were included in the analysis. The SUCRA values for the constant score were in the following order: RSA, IMN, Conservative, HA, and LP, and the SUCRA values for the reoperation rate were LP, HA, IMN, Conservative, and RSA. Conclusion: The elderly with 3- or 4-part proximal humeral fractures should consider RSA because it received the best evaluation ranking in terms of constant score and reoperation rate. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022341209, identifier: CRD42022341209.

A Keyhole Approach Centered by Anterior Squamous Suture to Hypertensive Basal Ganglia Hemorrhage.

OBJECTIVE: This study aimed to improve the accuracy and efficacy of the keyhole transsylvian approach to remove hypertensive basal ganglia hemorrhage. The authors presented a stable keyhole craniotomy based on anterior squamous suture to expose insular cortex and basal ganglia. METHODS: Twenty-nine patients with hypertensive basal ganglia hemorrhage were treated with keyhole surgery and studied in Guangdong sanjiu brain hospital. RESULTS: By using a bone suture marked keyhole transsylvian approach, near-complete (90%) hematoma evacuation was achieved in 21 cases (72.4), 70% to 90% in 8 cases (24.1), and less than 70% in 1 case (3.4%). In our cohort, 55.1% (16/29) with good function (GOS score 4-5), 41.3% (12/29) with disability (GOS score 3), and 3.4% (1/29) in a vegetative state (GOS score 2). No patients died within 6 months of operation. CONCLUSIONS: Our method can greatly minimize the bone exposure and precisely located the distal Sylvian fissure. A stable keyhole craniotomy based on bone suture can be identically safe and effective in comparison with classic surgery, and it consumes less time and less intra-operative bleeding.

Outcome of Epidural Hematoma: Lessons from Solitary Fibrous Tumor/Hemangiopericytoma.

BACKGROUND: Intracranial solitary fibrous tumor (SFT)/hemangiopericytoma (HPC) is rare. In this report, a case of epidural hematoma (EDH) that eventually evolved into SFT/HPC is presented. We describe the possible association between the 2 diseases, which has not been previously reported. CASE DESCRIPTION: A 40-year-old man suffered from an EDH in the right parietal area 12 years ago and accepted conservative treatment. Follow-up computed tomography (CT) scan shows that the density of the right EDH gradually changed from uniform slightly lower density to mixed density. A new CT scan revealed an epidural mass extending to the subcutaneous with local bone destruction. An operation was performed via a large right parietal craniotomy, and the final diagnosis was World Health Organization grade III SFT/HPC after histopathologic examination and immunohistochemical verification. The patient died of deterioration of brain disease 3 months after the final diagnosis. CONCLUSIONS: To our knowledge, this is the first report that HPC occurred in the epidural cavity. We are the first time to describe the possible association between EDH and HPC.

Comprehensive circular RNA profiling reveals that hsa_circ_0001368 is involved in growth hormone-secreting pituitary adenoma development.

Growth hormone-secreting pituitary adenoma (GHPA) represents about 20% of all histological subtypes of pituitary adenoma (PA), which may result in serious complications and shortened lifespan via growth-hormone (GH) hypersecretion. To date, no biomarkers of early diagnosis or therapeutic targets for GHPA treatment have yet been found. Recently, growing evidence has indicated that circular RNAs (circRNAs) are critical for the development and progression of numerous diseases, including cancers; however, their role in the pathogenesis of GHPA has not been reported. Here, we revealed the expression profile of circRNAs in GHPA using a circRNA microarray, and found 1938 circRNAs were upregulated and 1601 circRNAs were downregulated in GHPA versus normal control. Then the ten most up-regulated circRNAs were selected for the mapping of a circRNA-miRNA-target gene interaction network. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses further indicate that target genes were mostly enriched in the mTOR and the Wnt signaling pathway. Among these differentially expressed circRNAs, hsa_circ_0001368 was verified significant up-regulated by qRT-PCR, which was specific up-regulated in GHPA and correlated with the invasiveness and serum GH level of GHPA; functional studies indicated that knockdown of hsa_circ_0001368 significantly inhibited the proliferation, invasion and GH secreting level of GHPA primary culture cells. Moreover, hsa_circ_0001368 had a significant positive correlation with the pituitary-specific transcription factor Pit-1. In conclusion, our study identified a wealth of candidate circRNAs involved in GHPA and proposed that hsa_circ_0001368 may represent a novel potential biomarker and therapeutic target of GHPA.

Bronchogenic Cyst: Skull Base Lesions with Extracranial Extension.

BACKGROUND: Intracranial bronchogenic cysts (BCs) are extremely rare. To our knowledge, this is the first report of a BC in which lesions involve the middle and posterior cranial fossa, as well as the infratemporal fossa. CASE DESCRIPTION: We present the case of a 38-year-old woman who suffered from a cranial nerve dysfunction for 2 years. Magnetic resonance imaging showed that there were skull base communication lesions across the middle and posterior fossa. The patient was operated on through an infratemporal fossa approach. The final diagnosis was BC after histopathologic examination and immunohistochemical verification. The patient's neurologic dysfunction was partially ameliorated at the half-year follow-up. CONCLUSIONS: Intracranial BCs are rare. However, they should be considered in the differential diagnosis for cystic lesions with edge enhancement or extracranial extension.

A Spray-on, Nanocomposite-Based Sensor Network for in-Situ Active Structural Health Monitoring.

A new breed of nanocomposite-based spray-on sensor is developed for in-situ active structural health monitoring (SHM). The novel nanocomposite sensor is rigorously designed with graphene as the nanofiller and polyvinylpyrrolidone (PVP) as the matrix, fabricated using a simple spray deposition process. Electrical analysis, as well as morphological characterization of the spray-on sensor, was conducted to investigate percolation characteristic, in which the optimal threshold (~0.91%) of the graphene/PVP sensor was determined. Owing to the uniform and stable conductive network formed by well-dispersed graphene nanosheets in the PVP matrix, the tailor-made spray-on sensor exhibited excellent piezoresistive performance. By virtue of the tunneling effect of the conductive network, the sensor was proven to be capable of perceiving signals of guided ultrasonic waves (GUWs) with ultrahigh frequency up to 500 kHz. Lightweight and flexible, the spray-on nanocomposite sensor demonstrated superior sensitivity, high fidelity, and high signal-to-noise ratio under dynamic strain with ultralow magnitude (of the order of micro-strain) that is comparable with commercial lead zirconate titanate (PZT) wafers. The sensors were further networked to perform damage characterization, and the results indicate significant application potential of the spray-on nanocomposite-based sensor for in-situ active GUW-based SHM.

Verbascoside Inhibits Glioblastoma Cell Proliferation, Migration and Invasion While Promoting Apoptosis Through Upregulation of Protein Tyrosine Phosphatase SHP-1 and Inhibition of STAT3 Phosphorylation.

BACKGROUND/AIMS: As a natural antioxidant, verbascoside (VB) is proved to be a promising method for the treatment of oxidative-stress-related neurodegenerative diseases. Thus, this study aimed to investigate the effects of VB on glioblastoma cell proliferation, apoptosis, migration, and invasion as well as the mechanism involving signal transducer and activator of transcription 3 (STAT3) and Src homology 2 domain-containing protein tyrosine phosphatase 1 (SHP-1). METHODS: U87 cells were assigned to different treatments. The MTT assay was used to test cell proliferation, flow cytometry was used to detect cell apoptosis, and a Transwell assay was used for cell migration and invasion. We analyzed the glioblastoma tumor growth in a xenograft mouse model. Western blot analysis was employed to determine the protein expression of related genes. RESULTS: Glioblastoma cells exhibited decreased cell proliferation, migration, invasion, and increased apoptosis when treated with VB or TMZ. Western blot analysis revealed elevated SHP-1 expression and reduced phosphorylated (p)-STAT3 expression in glioblastoma cells treated with VB compared with controls. Correspondingly, in a xenograft mouse model treated with VB, glioblastoma tumor volume and growth were decreased. Glioblastoma xenograft tumors treated with VB showed elevated SHP-1, Bax, cleaved caspase-3, and cleaved PARP expression and reduced p-STAT3, Bcl-2, survivin, MMP-2, and MMP-9 expression. siRNA-SHP-1 inhibited the VB effects on glioblastoma. CONCLUSION: This study demonstrates that VB inhibits glioblastoma cell proliferation, migration, and invasion while promoting apoptosis via SHP-1 activation and inhibition of STAT3 phosphorylation.

Dispersed Sensing Networks in Nano-Engineered Polymer Composites: From Static Strain Measurement to Ultrasonic Wave Acquisition.

Self-sensing capability of composite materials has been the core of intensive research over the years and particularly boosted up by the recent quantum leap in nanotechnology. The capacity of most existing self-sensing approaches is restricted to static strains or low-frequency structural vibration. In this study, a new breed of functionalized epoxy-based composites is developed and fabricated, with a graphene nanoparticle-enriched, dispersed sensing network, whereby to self-perceive broadband elastic disturbance from static strains, through low-frequency vibration to guided waves in an ultrasonic regime. Owing to the dispersed and networked sensing capability, signals can be captured at any desired part of the composites. Experimental validation has demonstrated that the functionalized composites can self-sense strains, outperforming conventional metal foil strain sensors with a significantly enhanced gauge factor and a much broader response bandwidth. Precise and fast self-response of the composites to broadband ultrasonic signals (up to 440 kHz) has revealed that the composite structure itself can serve as ultrasound sensors, comparable to piezoceramic sensors in performance, whereas avoiding the use of bulky cables and wires as used in a piezoceramic sensor network. This study has spotlighted promising potentials of the developed approach to functionalize conventional composites with a self-sensing capability of high-sensitivity yet minimized intrusion to original structures.

A much convenient and economical method to harvest a great number of microglia.

Microglia, implicating in such neuro-pathologies as brain inflammation, neurodegeneration, glioma, and neurogenesis, play an important role in central nervous system. Advanced research on microglia is crucial in exploring the neuro-pathology and neuro-physiology of these diseases, so how to culture large numbers of microglia in vitro becomes the base of a research. The wildly used method, at present, obtaining microglia from murine cannot fulfill the requirement of research, costing too much time and needing too many rats. We intend to introduce an optimized method that can harvest large quantities of microglia with high purity. Neonatal 2-3 days old Wistar rats were sacrificed and the cerebral cortices were trypsinized. We primarily cultured mixed cortical cells for 8-10 days. The microglia were harvested from the liquid supernatant; the left cells in the mixed cortical glial culture were passaged at a 1:2 density. After another 8-10 days of culture, microglia were collected again. And then, we passaged the left cells again for acquiring microglia from the third collection. We did not add additional mitogens in the experiment. At last, on average, 7.0 × 10(6) microglia were collected from one neonatal rat. By this modified method, much more microglia can be effectively and easily harvested comparing with the usual protocol before. We compared the characteristics of microglia harvested from these three passages, such as morphology, phenotype, purity, and abilities on proliferation, secretion, and phagocytosis. The cells presented typical microglia morphology, having phenotype markers of CD11b/c and CD45. The microglia from these three passages retained similar phagocytosis and secretion functions. Expanded population of microglia for investigation can be provided by this easy method in a short time with little cost and few rats.