Diagnostic value of cytokines in severe childhood Mycoplasma pneumoniae pneumonia combined with Adenovirus infection.

BACKGROUND: To explore the alterations of inflammatory markers and immune-related cytokines in children infected with Mycoplasma pneumoniae (MP) combined with Adenovirus (ADV). METHODS: The study population consisted of 201 children with MPP, and they were grouped according to whether they were coinfected with ADV infection and critically ill. Additionally, comparative analyses were performed. The diagnostic value of different indicators and combined indicators for SMPP combined with ADV was assessed using ROC curves. RESULTS: There was no difference between group A1 and group A2, group B1 and group B2 in terms of age, gender, duration of hospitalisation and fever. The levels of calcitoninogen(PCT), lactate dehydrogenase concentration(LDH), interleukin(IL)-6, IL-8, IL-10, IL-4, IL-12P70, and IFN-γ in group A were higher than group B. The severe group (A1, B1) was significantly higher than the mild group (A2, B2) in terms of D-dimer, CRP, PCT, LDH, IL-6, IL-8, IL-10, IL-17a and number of patients with pleural effusion, solid lung changes. Among the individual indexes of D-dimer, CRP, N%,LDH, and PCT, the AUC of the combined test was 0.977, which was higher than that of the individual indicators. Among IL-6, IL-8, IL-10, and IL-17a, the AUC of the combined assay was 0.802, which was higher than that of the individual indicators. CONCLUSION: MP combined with ADV infection was associated with increased expression levels of IL-6, IL-8, IL-10, IL-4, IL-12P70, IFN-γ, and LDH. IL-6, IL-8, IL-10, IL-17a, LDH, PCT, CRP, and D-dimer could be used as predictors of SMPP and the combined test can improve the diagnostic value.

Capecitabine or Capecitabine Plus Oxaliplatin Versus Fluorouracil Plus Cisplatin in Definitive Concurrent Chemoradiotherapy for Locally Advanced Esophageal Squamous Cell Carcinoma (CRTCOESC): A Multicenter, Randomized, Open-Label, Phase 3 Trial.

PURPOSE: This phase 3 trial aimed to compare the efficacy and safety of capecitabine or capecitabine plus oxaliplatin (XELOX) with those of fluorouracil plus cisplatin (PF) in definitive concurrent chemoradiotherapy (DCRT) for inoperable locally advanced esophageal squamous cell carcinoma (ESCC). METHODS: Patients were randomly assigned to receive two cycles of capecitabine, XELOX, or PF along with concurrent intensity-modulated radiation therapy. Patients in each arm were again randomly assigned to receive two cycles of consolidation chemotherapy or not. The primary end points were 2-year overall survival (OS) rate and incidence of grade ≥3 adverse events (AEs). RESULTS: A total of 246 patients were randomly assigned into the capecitabine (n = 80), XELOX (n = 85), and PF (n = 81) arms. In capecitabine, XELOX, and PF arms, the 2-year OS rate was 75%, 66.7%, and 70.9% (capecitabine v PF: hazard ratio [HR], 0.91 [95% CI, 0.61 to 1.35]; nominal P = .637; XELOX v PF: 0.86 [95% CI, 0.58 to 1.27]; P = .444); the median OS was 40.9 (95% CI, 34.4 to 49.9), 41.9 (95% CI, 28.6 to 52.1), and 35.4 (95% CI, 30.4 to 45.4) months. The incidence of grade ≥3 AEs during the entire treatment was 28.8%, 36.5%, and 45.7%, respectively. Comparing the consolidation chemotherapy with the nonconsolidation chemotherapy groups, the median OS was 41.9 (95% CI, 34.6 to 52.8) versus 36.9 (95% CI, 28.5 to 44) months (HR, 0.71 [95% CI, 0.52 to 0.99]; nominal P = .0403). CONCLUSION: Capecitabine or XELOX did not significantly improve the 2-year OS rate over PF in DCRT for inoperable locally advanced ESCC. Capecitabine showed a lower incidence of grade ≥3 AEs than PF did.

Sinapic acid modulates oxidative stress and metabolic disturbances to attenuate ovarian fibrosis in letrozole-induced polycystic ovary syndrome SD rats.

Sinapic acid (SA) is renowned for its many pharmacological activities as a polyphenolic compound. The cause of polycystic ovary syndrome (PCOS), a commonly encountered array of metabolic and hormonal abnormalities in females, has yet to be determined. The present experiment was performed to evaluate the antifibrotic properties of SA in rats with letrozole-induced PCOS-related ovarian fibrosis. SA treatment successfully mitigated the changes induced by letrozole in body weight (BW) (p < .01) and relative ovary weight (p < .05). Histological observation revealed that SA reduced the number of atretic and cystic follicles (AFs) and (CFs) (p < .01), as well as ovarian fibrosis, in PCOS rats. Additionally, SA treatment impacted the serum levels of sex hormones in PCOS rats. Luteinizing hormone (LH) and testosterone (T) levels were decreased (p < .01, p < .05), and follicle-stimulating hormone (FSH) levels were increased (p < .05). SA administration also decreased triglyceride (TG) (p < .01) and total cholesterol (TC) levels (p < .05) and increased high-density lipoprotein cholesterol (HDL-C) levels (p < .01), thereby alleviating letrozole-induced metabolic dysfunction in PCOS rats. Furthermore, SA treatment targeted insulin resistance (IR) and increased the messenger RNA (mRNA) levels of antioxidant enzymes in the ovaries of PCOS rats. Finally, SA treatment enhanced the activity of peroxisome proliferator-activated receptor-γ (PPAR-γ), reduced the activation of transforming growth factor-ß1 (TGF-ß1)/Smads, and decreased collagen I, α-smooth muscle actin (α-SMA), and connective tissue growth factor (CTGF) levels in the ovaries of PCOS rats. These observations suggest that SA significantly ameliorates metabolic dysfunction and oxidative stress and ultimately reduces ovarian fibrosis in rats with letrozole-induced PCOS.

Sonographic characteristics of diffuse sclerosing variant of papillary thyroid carcinoma with histopathological correlation: a preliminary study.

BACKGROUND: Diffuse sclerosing variant of papillary thyroid carcinoma (DSVPTC) is a rare but high invasive subtype of papillary thyroid carcinoma, which mandates an aggressive clinical strategy. Few studies have focused on the sonographic characteristics of DSVPTC and the role of ultrasound in diagnosis and treatment of this variant remains unknown. This study aimed to identify and understand DSVPTC more accurately under ultrasound in correlation with pathology. METHODS: The ultrasound characteristics and histopathologic sections of 10 lesions in 10 DSVPTC patients who underwent thyroid surgery at our center between 2014 and 2020 were reviewed and compared with 184 lesions in 168 classic variant of papillary thyroid carcinoma (cPTC) patients. RESULTS: 6 DSVPTC cases (60%) showed the "snowstorm" pattern on sonogram and 4 cases (40%) presented hypoechoic solid nodules only. Vague borders (100.0% vs. 18.5%, P = 0.019) and abundant microcalcifications (66.7% vs. 10.9%, P = 0.037) were more common in DSVPTC nodules than in cPTC nodules, corresponding to the infiltrating boundaries and numerous psammoma bodies under the microscope respectively. Most of the DSVPTC cases had a heterogeneous background (80%) and suspicious metastatic cervical lymph nodes (80%) on sonograms. All DSVPTC cases had histopathological metastatic cervical lymph nodes. CONCLUSION: The sonographic "snowstorm" pattern indicated DSVPTC with whole-lobe occupation. Hypoechoic solid nodules with vague borders and abundant microcalcifications on sonogram suggested DSVPTC lesion with an ongoing invasion. Regardless of which of the two sonograms was shown, the corresponding DSVPTC lesions were aggressive and required the same attention from the surgeons.

Programmed Targeting Pyruvate Metabolism Therapy Amplified Single-Atom Nanozyme-Activated Pyroptosis for Immunotherapy.

Increasing cellular immunogenicity and reshaping the immune tumor microenvironment (TME) are crucial for antitumor immunotherapy. Herein, this work develops a novel single-atom nanozyme pyroptosis initiator: UK5099 and pyruvate oxidase (POx)-co-loaded Cu-NS single-atom nanozyme (Cu-NS@UK@POx), that not only trigger pyroptosis through cascade biocatalysis to boost the immunogenicity of tumor cells, but also remodel the immunosuppressive TME by targeting pyruvate metabolism. By replacing N with weakly electronegative S, the original spatial symmetry of the Cu-N4 electron distribution is changed and the enzyme-catalyzed process is effectively regulated. Compared to spatially symmetric Cu-N4 single-atom nanozymes (Cu-N4 SA), the S-doped spatially asymmetric single-atom nanozymes (Cu-NS SA) exhibit stronger oxidase activities, including peroxidase (POD), nicotinamide adenine dinucleotide (NADH) oxidase (NOx), L-cysteine oxidase (LCO), and glutathione oxidase (GSHOx), which can cause enough reactive oxygen species (ROS) storms to trigger pyroptosis. Moreover, the synergistic effect of Cu-NS SA, UK5099, and POx can target pyruvate metabolism, which not only improves the immune TME but also increases the degree of pyroptosis. This study provides a two-pronged treatment strategy that can significantly activate antitumor immunotherapy effects via ROS storms, NADH/glutathione/L-cysteine consumption, pyruvate oxidation, and lactic acid (LA)/ATP depletion, triggering pyroptosis and regulating metabolism. This work provides a broad vision for expanding antitumor immunotherapy.

Sinapic Acid Attenuates Chronic DSS-Induced Intestinal Fibrosis in C57BL/6J Mice by Modulating NLRP3 Inflammasome Activation and the Autophagy Pathway.

Ulcerative colitis (UC) is a chronic gastrointestinal disease that results from repeated inflammation and serious complications. Sinapic acid (SA) is a hydroxycinnamic acid present in a variety of plants that has antioxidant, anti-inflammatory, anticancer, and other protective effects. This study investigated the antifibrotic effect of SA on chronic colitis induced by dextran sulfate sodium salt (DSS) in mice. We observed that SA could significantly reduce clinical symptoms (such as improved body weight loss, increased colon length, and decreased disease activity index score) and pathological changes in mice with chronic colitis. SA supplementation has been demonstrated to repair intestinal mucosal barrier function and maintain epithelial homeostasis by inhibiting activation of the NLRP3 inflammasome and decreasing the expression of IL-6, TNF-α, IL-17A, IL-18, and IL-1ß. Furthermore, SA could induce the expression of antioxidant enzymes (Cat, Sod1, Sod2, Mgst1) by activating the Nrf2/keap1 pathway, thus improving antioxidant capacity. Additionally, SA could increase the protein expression of downstream LC3-II/LC3-I and Beclin1 and induce autophagy by regulating the AMPK-Akt/mTOR signaling pathway, thereby reducing the production of intestinal fibrosis-associated proteins Collagen-I and α-SMA. These findings suggest that SA can enhance intestinal antioxidant enzymes, reduce oxidative stress, expedite intestinal epithelial repair, and promote autophagy, thereby ameliorating DSS-induced colitis and intestinal fibrosis.

Ultrasound microflow patterns help in distinguishing malignant from benign thyroid nodules.

BACKGROUND: Vascular features are not commonly used to evaluate thyroid nodules by conventional ultrasound due to the low sensitivity. Superb Microvascular Imaging (SMI) is a new ultrasonic Doppler technology that specializes in depicting microvessels and low-speed flow. The objective of this study was to explore the value of microflow features on SMI in differentiating malignant from benign thyroid nodules. METHODS: One hundred and seventy-seven adult patients with thyroid nodules in our center from October 2021 to June 2022 with available histopathological results were recruited, including 125 malignant nodules and 123 benign nodules. Preoperative ultrasound was performed using greyscale, Color Doppler Flow Imaging (CDFI), monochrome SMI (mSMI) and color SMI (cSMI). Vascular features such as flow richness, microflow distribution and microflow patterns of malignant thyroid nodules were compared with those of benign nodules. RESULTS: Penetrating vessel ≥ 1 (82.4% in the malignant group vs. 30.9% in the benign group, P < 0.001), the crab claw-like pattern (64.0% vs. 10.6%, P < 0.001) and the root hair-like pattern (8.0% vs. 2.4%, P = 0.049) were common in malignant thyroid nodules, among which the crab claw-like pattern was an independent risk factor for malignant thyroid nodules. The wheel-like pattern (1.6% in the malignant group vs. 33.3% in the benign group, P < 0.001) and the arborescent pattern (0 vs. 19.5%, P < 0.001) were more likely to appear in benign nodules. The diagnostic specificities of the crab claw-like pattern and the root hair-like pattern for malignant thyroid nodules were 0.894, 0.976, and the positive predictive values were 0.860, 0.769. The diagnostic specificities of the wheel-like pattern and the arborescent pattern for benign thyroid nodules were 0.984, 1.000, and the positive predictive values were 0.953, 1.000. CONCLUSIONS: The crab claw-like pattern and the root hair-like pattern were microflow characteristics of malignant thyroid nodules. The wheel-like pattern and the arborescent pattern could help exclude the diagnosis of thyroid cancer.

Diagnostic experience of intravenous leiomyomatosis with emphasis on conventional ultrasonography imaging: a single-center study.

Objective: Intravenous leiomyomatosis (IVL) is a rare and aggressive tumor type that has the potential to extend into the inferior vena cava (IVC) and is susceptible to be misdiagnosed and neglected. Despite its clinical significance, there is a paucity of research that has focused on the specific manifestations of IVL on ultrasonography. Therefore, this study aims to systematically analyze the specific ultrasound features of IVL and augment its diagnostic accuracy. Materials and method: Prospective inclusion was granted to patients admitted to our hospital between December 2016 and March 2021 for an IVC-occupying lesion. Multi-modal ultrasonography, encompassing gray-scale and color Doppler, was conducted. Lesions were categorized as IVL or non-IVL based on pathological or follow-up data. Two ultrasound sonographers with over 5 years of experience read and recorded ultrasound data for all lesions, which were subsequently comparatively analyzed to identify specific signs of IVL. Results: A total of 284 patients diagnosed with IVC-occupying lesions were included in the study. The lesion types comprised of IVL (n=67, 23.6%), IVC thrombus (n=135, 47.5%), tumor thrombus of renal carcinoma involving the IVC (n=35, 12.4%), tumor thrombus of liver carcinoma involving the IVC (n=24, 8.5%), leiomyosarcoma of the IVC (n=14, 4.9%), and tumor thrombus of adrenocortical adenocarcinoma (n=9, 4.1%). The presence of "sieve hole" and "multi-track" signs was observed in 20 IVL lesions under the grey-scale modality, while both signs were absent in the non-IVL group (P<0.01). The study found no statistically significant differences in the presentation of "sieve hole" and "multi-track" signs under the grey-scale and color Doppler modalities in cases of intravascular lithotripsy (IVL) (P>0.05). Using these two signs as diagnostic criteria for IVL, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), miss rate, misdiagnosis rate, and accuracy were determined to be 29.9%, 100%, 100%, 82.2%, 70.1%, 0, and 83.5%, respectively (AUC ROC=0.649; 95%CI: 0.537-0.761). Conclusion: IVL exhibits distinct ultrasound presentations, including "sieve hole" and "multi-track" signs, which demonstrate high specificity and accuracy as diagnostic indicators. Furthermore, these signs are corroborated by pathological evidence and effectively distinguish IVL from other lesions occupying the IVC.

Dual adversarial models with cross-coordination consistency constraint for domain adaption in brain tumor segmentation.

The brain tumor segmentation task with different domains remains a major challenge because tumors of different grades and severities may show different distributions, limiting the ability of a single segmentation model to label such tumors. Semi-supervised models (e.g., mean teacher) are strong unsupervised domain-adaptation learners. However, one of the main drawbacks of using a mean teacher is that given a large number of iterations, the teacher model weights converge to those of the student model, and any biased and unstable predictions are carried over to the student. In this article, we proposed a novel unsupervised domain-adaptation framework for the brain tumor segmentation task, which uses dual student and adversarial training techniques to effectively tackle domain shift with MR images. In this study, the adversarial strategy and consistency constraint for each student can align the feature representation on the source and target domains. Furthermore, we introduced the cross-coordination constraint for the target domain data to constrain the models to produce more confident predictions. We validated our framework on the cross-subtype and cross-modality tasks in brain tumor segmentation and achieved better performance than the current unsupervised domain-adaptation and semi-supervised frameworks.

Epstein-Barr Virus Envelope Glycoprotein gp110 Inhibits IKKi-Mediated Activation of NF-κB and Promotes the Degradation of ß-Catenin.

Epstein-Barr virus (EBV) infects host cells and establishes a latent infection that requires evasion of host innate immunity. A variety of EBV-encoded proteins that manipulate the innate immune system have been reported, but whether other EBV proteins participate in this process is unclear. EBV-encoded envelope glycoprotein gp110 is a late protein involved in virus entry into target cells and enhancement of infectivity. Here, we reported that gp110 inhibits RIG-I-like receptor pathway-mediated promoter activity of interferon-ß (IFN-ß) as well as the transcription of downstream antiviral genes to promote viral proliferation. Mechanistically, gp110 interacts with the inhibitor of NF-κB kinase (IKKi) and restrains its K63-linked polyubiquitination, leading to attenuation of IKKi-mediated activation of NF-κB and repression of the phosphorylation and nuclear translocation of p65. Additionally, gp110 interacts with an important regulator of the Wnt signaling pathway, ß-catenin, and induces its K48-linked polyubiquitination degradation via the proteasome system, resulting in the suppression of ß-catenin-mediated IFN-ß production. Taken together, these results suggest that gp110 is a negative regulator of antiviral immunity, revealing a novel mechanism of EBV immune evasion during lytic infection. IMPORTANCE Epstein-Barr virus (EBV) is a ubiquitous pathogen that infects almost all human beings, and the persistence of EBV in the host is largely due to immune escape mediated by its encoded products. Thus, elucidation of EBV's immune escape mechanisms will provide a new direction for the design of novel antiviral strategies and vaccine development. Here, we report that EBV-encoded gp110 serves as a novel viral immune evasion factor, which inhibits RIG-I-like receptor pathway-mediated interferon-ß (IFN-ß) production. Furthermore, we found that gp110 targeted two key proteins, inhibitor of NF-κB kinase (IKKi) and ß-catenin, which mediate antiviral activity and the production of IFN-ß. gp110 inhibited K63-linked polyubiquitination of IKKi and induced ß-catenin degradation via the proteasome, resulting in decreased IFN-ß production. In summary, our data provide new insights into the EBV-mediated immune evasion surveillance strategy.

A clinical prediction model for lung metastasis risk in osteosarcoma: A multicenter retrospective study.

Background: Lung metastases (LM) have a poor prognosis of osteosarcoma. This study aimed to predict the risk of LM using the nomogram in patients with osteosarcoma. Methods: A total of 1100 patients who were diagnosed as osteosarcoma between 2010 and 2019 in the Surveillance, Epidemiology and End Results (SEER) database were selected as the training cohort. Univariate and multivariate logistic regression analyses were used to identify independent prognostic factors of osteosarcoma lung metastases. 108 osteosarcoma patients from a multicentre dataset was as valiation data. The predictive power of the nomogram model was assessed by receiver operating characteristic curves (ROC) and calibration plots, and decision curve analysis (DCA) was utilized to interpret the accurate validity in clinical practice. Results: A total of 1208 patients with osteosarcoma from both the SEER database(n=1100) and the multicentre database (n=108) were analyzed. Univariate and multivariate logistic regression analyses showed that Survival time, Sex, T-stage, N-stage, Surgery, Radiation, and Bone metastases were independent risk factors for lung metastasis. We combined these factors to construct a nomogram for estimating the risk of lung metastasis. Internal and external validation showed significant predictive differences (AUC 0.779, 0.792 respectively). Calibration plots showed good performance of the nomogram model. Conclusions: In this study, a nomogram model for predicting the risk of lung metastases in osteosarcoma patients was constructed and turned out to be accurate and reliable through internal and external validation. Moreover we built a webpage calculator (https://drliwenle.shinyapps.io/OSLM/) taken into account nomogram model to help clinicians make more accurate and personalized predictions.

MAD-Net: Multi-attention dense network for functional bone marrow segmentation.

Radiotherapy is the main treatment modality for various pelvic malignancies. However, high intensity radiation can damage the functional bone marrow (FBM), resulting in hematological toxicity (HT). Accurate identification and protection of the FBM during radiotherapy planning can reduce pelvic HT. The traditional manual method for contouring the FBM is time-consuming and laborious. Therefore, development of an efficient and accurate automatic segmentation mode can provide a distinct leverage in clinical settings. In this paper, we propose the first network for performing the FBM segmentation task, which is referred to as the multi-attention dense network (named MAD-Net). Primarily, we introduce the dense convolution block to promote the gradient flow in the network as well as incite feature reuse. Next, a novel slide-window attention module is proposed to emphasize long-range dependencies and exploit interdependencies between features. Finally, we design a residual-dual attention module as the bottleneck layer, which further aggregates useful spatial details and explores intra-class responsiveness of high-level features. In this work, we conduct extensive experiments on our dataset of 3838 two-dimensional pelvic slices. Experimental results demonstrate that the proposed MAD-Net transcends previous state-of-the-art models in various metrics. In addition, the contributions of the proposed components are verified by ablation analysis, and we conduct experiments on three other datasets to manifest the generalizability of MAD-Net.

A multiphoton transition activated iron based metal organic framework for synergistic therapy of photodynamic therapy/chemodynamic therapy/chemotherapy for orthotopic gliomas.

Although photodynamic therapy (PDT) has exhibited good potential in therapy of gliomas, the limited penetration depth of light and the obstacle of the blood-brain barrier (BBB) lead to unsatisfactory treatment effects. Herein, a multifunctional nanodrug (UMD) was constructed with up-conversion nanoparticles (NaGdF4:Yb,Tm@NaYF4:Yb,Nd@NaYF4, UCNPs) as the core, the photosensitizer NH2-MIL-53 (Fe) as the shell and a carrier for loading chemotherapy drug doxorubicin hydrochloride (Dox) for synergistic therapy of gliomas. Lactoferrin (LF) was finally modified on the surface of the UMD to endow it with the ability to traverse the BBB and target cells (UMDL). The UCNP core can convert 808 nm near-infrared (NIR) light to ultraviolet light (UV light) for exciting NH2-MIL-53 (Fe), achieving NIR-mediated PDT. In addition, Fe3+ on the surface of the NH2-MIL-53 (Fe) shell could be reduced to Fe2+ in a tumor microenvironment (TME), and then reacted with over-expressed H2O2 in the TME to generate hydroxyl radicals (˙OH) for chemodynamic therapy (CDT). The Dox drug could be released in response to acidic conditions in the TME, inhibiting the growth of gliomas with low side effects. The synergistic effect of PDT/CDT/chemotherapy leads to effective suppression of orthotopic gliomas.

Development and validation of a machine learning model to predict the risk of lymph node metastasis in renal carcinoma.

Simple summary: Studies have shown that about 30% of kidney cancer patients will have metastasis, and lymph node metastasis (LNM) may be related to a poor prognosis. Our retrospective study aims to provide a reliable machine learning-based model to predict the occurrence of LNM in kidney cancer. We screened the pathological grade, liver metastasis, M staging, primary site, T staging, and tumor size from the training group (n=39016) formed by the SEER database and the validation group (n=771) formed by the medical center. Independent predictors of LNM in cancer patients. Using six different algorithms to build a prediction model, it is found that the prediction performance of the XGB model in the training group and the validation group is significantly better than any other machine learning model. The results show that prediction tools based on machine learning can accurately predict the probability of LNM in patients with kidney cancer and have satisfactory clinical application prospects. Background: Lymph node metastasis (LNM) is associated with the prognosis of patients with kidney cancer. This study aimed to provide reliable machine learning-based (ML-based) models to predict the probability of LNM in kidney cancer. Methods: Data on patients diagnosed with kidney cancer were extracted from the Surveillance, Epidemiology and Outcomes (SEER) database from 2010 to 2017, and variables were filtered by least absolute shrinkage and selection operator (LASSO), univariate and multivariate logistic regression analyses. Statistically significant risk factors were used to build predictive models. We used 10-fold cross-validation in the validation of the model. The area under the receiver operating characteristic curve (AUC) was used to assess the performance of the model. Correlation heat maps were used to investigate the correlation of features using permutation analysis to assess the importance of predictors. Probability density functions (PDFs) and clinical utility curves (CUCs) were used to determine clinical utility thresholds. Results: The training cohort of this study included 39,016 patients, and the validation cohort included 771 patients. In the two cohorts, 2544 (6.5%) and 66 (8.1%) patients had LNM, respectively. Pathological grade, liver metastasis, M stage, primary site, T stage, and tumor size were independent predictive factors of LNM. In both model validation, the XGB model significantly outperformed any of the machine learning models with an AUC value of 0.916.A web calculator (https://share.streamlit.io/liuwencai4/renal_lnm/main/renal_lnm.py) were built based on the XGB model. Based on the PDF and CUC, we suggested 54.6% as a threshold probability for guiding the diagnosis of LNM, which could distinguish about 89% of LNM patients. Conclusions: The predictive tool based on machine learning can precisely indicate the probability of LNM in kidney cancer patients and has a satisfying application prospect in clinical practice.

A deep belief network-based clinical decision system for patients with osteosarcoma.

Osteosarcoma was the most frequent type of malignant primary bone tumor with a poor survival rate mainly occurring in children and adolescents. For precision treatment, an accurate individualized prognosis for Osteosarcoma patients is highly desired. In recent years, many machine learning-based approaches have been used to predict distant metastasis and overall survival based on available individual information. In this study, we compared the performance of the deep belief networks (DBN) algorithm with six other machine learning algorithms, including Random Forest, XGBoost, Decision Tree, Gradient Boosting Machine, Logistic Regression, and Naive Bayes Classifier, to predict lung metastasis for Osteosarcoma patients. Therefore the DBN-based lung metastasis prediction model was integrated as a parameter into the Cox proportional hazards model to predict the overall survival of Osteosarcoma patients. The accuracy, precision, recall, and F1 score of the DBN algorithm were 0.917/0.888, 0.896/0.643, 0.956/0.900, and 0.925/0.750 in the training/validation sets, respectively, which were better than the other six machine-learning algorithms. For the performance of the DBN survival Cox model, the areas under the curve (AUCs) for the 1-, 3- and 5-year survival in the training set were 0.851, 0.806 and 0.793, respectively, indicating good discrimination, and the calibration curves showed good agreement between the prediction and actual observations. The DBN survival Cox model also demonstrated promising performance in the validation set. In addition, a nomogram integrating the DBN output was designed as a tool to aid clinical decision-making.

Incorporation of a machine learning pathological diagnosis algorithm into the thyroid ultrasound imaging data improves the diagnosis risk of malignant thyroid nodules.

Objective: This study aimed at establishing a new model to predict malignant thyroid nodules using machine learning algorithms. Methods: A retrospective study was performed on 274 patients with thyroid nodules who underwent fine-needle aspiration (FNA) cytology or surgery from October 2018 to 2020 in Xianyang Central Hospital. The least absolute shrinkage and selection operator (lasso) regression analysis and logistic analysis were applied to screen and identified variables. Six machine learning algorithms, including Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Naive Bayes Classifier (NBC), Random Forest (RF), and Logistic Regression (LR), were employed and compared in constructing the predictive model, coupled with preoperative clinical characteristics and ultrasound features. Internal validation was performed by using 10-fold cross-validation. The performance of the model was measured by the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, F1 score, Shapley additive explanations (SHAP) plot, feature importance, and correlation of features. The best cutoff value for risk stratification was identified by probability density function (PDF) and clinical utility curve (CUC). Results: The malignant rate of thyroid nodules in the study cohort was 53.2%. The predictive models are constructed by age, margin, shape, echogenic foci, echogenicity, and lymph nodes. The XGBoost model was significantly superior to any one of the machine learning models, with an AUC value of 0.829. According to the PDF and CUC, we recommended that 51% probability be used as a threshold for determining the risk stratification of malignant nodules, where about 85.6% of patients with malignant nodules could be detected. Meanwhile, approximately 89.8% of unnecessary biopsy procedures would be saved. Finally, an online web risk calculator has been built to estimate the personal likelihood of malignant thyroid nodules based on the best-performing ML-ed model of XGBoost. Conclusions: Combining clinical characteristics and features of ultrasound images, ML algorithms can achieve reliable prediction of malignant thyroid nodules. The online web risk calculator based on the XGBoost model can easily identify in real-time the probability of malignant thyroid nodules, which can assist clinicians to formulate individualized management strategies for patients.

A Novel Biodegradable Nanoplatform for Tumor Microenvironments Responsive Bimodal Magnetic Resonance Imaging and Sonodynamic/Ion Interference Cascade Therapy.

The unsatisfactory therapeutic effect and long-term adverse effect markedly prevent inorganic nanomaterials from clinical transformation. In light of this, we developed a novel biodegradable theranostic agent (MnCO3:Ho3+@DOX/Ca3(PO4)2@BSA, HMCDB) based on the sonosensitizer manganese carbonate (MnCO3) coating with calcium phosphate (Ca3(PO4)2) and simultaneously loaded it with the chemotherapeutic drug doxorubicin (DOX). Due to the mild acidity of the tumor microenvironment (TME), the Ca3(PO4)2 shell degraded first, releasing substantial quantities of calcium ions (Ca2+) and DOX. Meanwhile, with the ultrasound (US) irradiation, MnCO3 produced enough reactive oxygen species (ROS) to cause oxidative stress in the cells, resulting in accumulation of Ca2+. Consequently, the cascade effect significantly amplified the therapeutic effect. Importantly, the nanocomposite can be completely degraded and cleared from the body, demonstrating that it was a promising theranostic agent for tumor therapy. Furthermore, the doped holmium ions (Ho3+) and in situ generation of manganese ions (Mn2+) in TME endow the nanoagent with the ability for tumor-specific bimodality T1/T2-weighted magnetic resonance imaging (MRI). This novel nanoplatform with low toxicity and biodegradability holds great potential for cancer diagnosis and treatment.

Establishment and Validation of a Machine Learning Prediction Model Based on Big Data for Predicting the Risk of Bone Metastasis in Renal Cell Carcinoma Patients.

Purpose: Since the prognosis of renal cell carcinoma (RCC) patients with bone metastasis (BM) is poor, this study is aimed at using big data to build a machine learning (ML) model to predict the risk of BM in RCC patients. Methods: A retrospective study was conducted on 40,355 RCC patients in the SEER database from 2010 to 2017. LASSO regression and multivariate logistic regression analysis was performed to determine independent risk factors of RCC-BM. Six ML algorithm models, including LR, GBM, XGB, RF, DT, and NBC, were used to establish risk models for predicting RCC-BM. The prediction performance of ML models was weighed by 10-fold cross-validation. Results: The study investigated 40,355 patients diagnosed with RCC in the SEER database, where 1,811 (4.5%) were BM patients. Independent risk factors for BM were tumor grade, T stage, N stage, liver metastasis, lung metastasis, and brain metastasis. Among the RCC-BM risk prediction models established by six ML algorithms, the XGB model showed the best prediction performance (AUC = 0.891). Therefore, a network calculator based on the XGB model was established to individually assess the risk of BM in patients with RCC. Conclusion: The XGB risk prediction model based on the ML algorithm performed a good prediction effect on BM in RCC patients.

Dynamic Predictive Models with Visualized Machine Learning for Assessing the Risk of Lung Metastasis in Kidney Cancer Patients.

Objective: To establish and verify the clinical prediction model of lung metastasis in renal cancer patients. Method: Kidney cancer patients from January 1, 2010, to December 31, 2017, in the SEER database were enrolled in this study. In the first section, LASSO method was adopted to select variables. Independent influencing factors were identified after multivariate logistic regression analysis. In the second section, machine learning (ML) algorithms were implemented to establish models and 10-foldcross-validation was used to train the models. Finally, receiver operating characteristic curves, probability density functions, and clinical utility curve were applied to estimate model's performance. The final model was shown by a website calculator. Result: Lung metastasis was confirmed in 7.43% (3171 out of 42650) of study population. In multivariate logistic regression, bone metastasis, brain metastasis, grade, liver metastasis, N stage, T stage, and tumor size were independent risk factors of lung metastasis in renal cancer patients. Primary site and sequence number were independent protection factors of LM in renal cancer patients. The above 9 impact factors were used to develop the prediction models, which included random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), and logistic regression (LR). In 10-foldcross-validation, the average area under curve (AUC) ranked from 0.907 to 0.934. In ROC curve analysis, AUC ranged from 0.879-0.922. We found that the XGB model performed best, and a Web-based calculator was done according to XGB model. Conclusion: This study provided preliminary evidence that the ML algorithm can be used to predict lung metastases in patients with kidney cancer. This low cost, noninvasive and easy to implement diagnostic method is useful for clinical work. Of course this model still needs to undergo more real-world validation.