ITFG2, an immune-modulatory protein, targets ATP 5b to maintain mitochondrial function in myocardial infarction.

ITFG2, as an immune-modulatory intracellular protein that modulate the fate of B cells and negatively regulates mTORC1 signaling. ITFG2 is highly expressed in the heart, but its pathophysiological function in heart disease is unclear. In this study, we found that in MI mice, overexpression of ITFG2 via an AAV9 vector significantly reduced the infarct size and ameliorated cardiac function. Knockdown of endogenous ITFG2 by shRNA partially aggravated ischemia-induced cardiac dysfunction. In cardiac-specific ITFG2 transgenic (TG) mice, myocardial infarction size was smaller, eject fraction (EF) and fractional shortening (FS) was higher compared to those in wild-type (WT) mice, suggesting ITFG2 reversed cardiac dysfunction induced by MI. In hypoxic neonatal cardiomyocytes (NMCMs), overexpression of ITFG2 maintained mitochondrial function by increasing intracellular ATP production, reducing ROS levels, and preserving the mitochondrial membrane potential (MMP). Overexpression of ITFG2 reversed the mitochondrial respiratory dysfunction in NMCMs induced by hypoxia. Knockdown of endogenous ITFG2 by siRNA did the opposite. Mechanism, ITFG2 formed a complex with NEDD4-2 and ATP 5b and inhibited the binding of NEDD4-2 with ATP 5b leading to the reduction ubiquitination of ATP 5b. Our findings reveal a previously unknown ability of ITFG2 to protect the heart against ischemic injury by interacting with ATP 5b and thereby regulating mitochondrial function. ITFG2 has promise as a novel strategy for the clinical management of MI.

Effect of volatile versus propofol anaesthesia on major complications and mortality after cardiac surgery: a multicentre randomised trial.

BACKGROUND: The comparative effectiveness of volatile anaesthesia and total intravenous anaesthesia (TIVA) in terms of patient outcomes after cardiac surgery remains a topic of debate. METHODS: Multicentre randomised trial in 16 tertiary hospitals in China. Adult patients undergoing elective cardiac surgery were randomised in a 1:1 ratio to receive volatile anaesthesia (sevoflurane or desflurane) or propofol-based TIVA. The primary outcome was a composite of predefined major complications during hospitalisation and mortality 30 days after surgery. RESULTS: Of the 3123 randomised patients, 3083 (98.7%; mean age 55 yr; 1419 [46.0%] women) were included in the modified intention-to-treat analysis. The composite primary outcome was met by a similar number of patients in both groups (volatile group: 517 of 1531 (33.8%) patients vs TIVA group: 515 of 1552 (33.2%) patients; relative risk 1.02 [0.92-1.12]; P=0.76; adjusted odds ratio 1.05 [0.90-1.22]; P=0.57). Secondary outcomes including 6-month and 1-yr mortality, duration of mechanical ventilation, length of ICU and hospital stay, and healthcare costs, were also similar for the two groups. CONCLUSIONS: Among adults undergoing cardiac surgery, we found no difference in the clinical effectiveness of volatile anaesthesia and propofol-based TIVA. CLINICAL TRIAL REGISTRATION: Chinese Clinical Trial Registry (ChiCTR-IOR-17013578).

Multicenter expanded access program for access to investigational products for amyotrophic lateral sclerosis.

INTRODUCTION/AIMS: Expanded access (EA) is a Food and Drug Administration-regulated pathway to provide access to investigational products (IPs) to individuals with serious diseases who are ineligible for clinical trials. The aim of this report is to share the design and operations of a multicenter, multidrug EA program for amyotrophic lateral sclerosis (ALS) across nine US centers. METHODS: A central coordination center was established to design and conduct the program. Templated documents and processes were developed to streamline study design, regulatory submissions, and clinical operations across protocols. The program included three protocols and provided access to IPs that were being tested in respective regimens of the HEALEY ALS Platform Trial (verdiperstat, CNM-Au8, and pridopidine). Clinical and safety data were collected in all EA protocols (EAPs). The program cohorts comprised participants who were not eligible for the platform trial, including participants at advanced stages of disease progression and with long disease duration. RESULTS: A total of 85 participants were screened across the 3 EAPs from July 2021 to September 2022. The screen failure rate was 3.5%. Enrollment for the regimens of the platform trial was completed as planned and results informed the duration of the corresponding EAP. The verdiperstat EAP was concluded in December 2022. Mean duration of participation in the verdiperstat EAP was 5.8 ± 4.1 months. The CNM-Au8 and pridopidine EAPs are ongoing. DISCUSSION: Multicenter EAPs conducted in parallel to randomized clinical trials for ALS can successfully enroll participants who do not qualify for clinical trials.

Tag-free fluorometric aptasensor for detection of chromium(VI) in foods via SYBR Green I signal amplification and aptamer structure transition.

BACKGROUND: In response to growing concerns regarding heavy metal contamination in food, particularly chromium (Cr)(VI) contamination, this study presented a simple, sensitive and practical method for Cr(VI) detection. RESULTS: A magnetic separation-based capture-exponential enrichment ligand system evolution (SELEX) method was used to identify and characterize DNA aptamers with a high affinity for Cr(VI). An aptamer, Cr-15, with a dissociation constant (Kd) of 4.42 ± 0.44 µmol L-1 was obtained after only eight rounds of selection. Further innovative methods combining molecular docking, dynamic simulation and thermodynamic analysis revealed that CrO4 2- could bind to the 19th and 20th guanine bases of Cr-15 via hydrogen bonds. Crucially, a label-free fluorometric aptasensor based on SYBR Green I was successfully constructed to detect CrO4 2-, achieving a linear detection range of 60-300 nmol L-1 with a lower limit of detection of 44.31 nmol L-1. Additionally, this aptasensor was able to quantitatively detect CrO4 2- in grapes and broccoli within 40 min, with spike recovery rates ranging from 89.22% to 108.05%. The designed fluorometric aptasensor exhibited high selectivity and could detect CrO4 2- in real samples without sample processing or target pre-enrichment. CONCLUSION: The aptasensor demonstrated its potential as a reliable tool for monitoring Cr(VI) contamination in fruit and vegetable products. © 2024 Society of Chemical Industry.

Fear of cancer recurrence in adolescent patients with malignant bone tumors: a cross-section survey.

BACKGROUND: Adolescent malignant-bone tumor patients' fear of cancer recurrence is a significant psychological issue, and exploring the influencing factors associated with fear of cancer recurrence in this population is important for developing effective interventions. This study is to investigate the current status and factors influencing fear of cancer recurrence (FCR) related to malignant bone-tumors in adolescent patients, providing evidence for future targeted mental health support and interventions. DESIGN: A cross-sectional survey. METHODS: In total, 269 adolescent malignant-bone tumor cases were treated at two hospitals in Zhejiang Province, China from January 2023 to December 2023. Patients completed a General Information Questionnaire, Fear of Progression Questionnaire-Short Form (FoP-Q-SF), Family Hardiness Index (FHI), and a Simple Coping Style Questionnaire (SCSQ). Univariate and multivariable logistic regressions analysis were used to assess fear of cancer recurrence. RESULTS: A total of 122 (45.4%) patients experienced FCR (FoP-Q-SF ≥ 34). Logistic regression analysis analyses showed that per capita-monthly family income, tumor stage, communication between the treating physician and the patient, patient's family relationships, family hardiness a positive coping score, and a negative coping score were the main factors influencing FCR in these patients (P < 0.05). CONCLUSIONS: FCR in malignant-bone tumor adolescent patients is profound. Healthcare professionals should develop targeted interventional strategies based on the identified factors, which affect these patients; helping patients increase family hardiness, helping patients to positively adapt, and avoid negative coping styles.

BioInstruct: instruction tuning of large language models for biomedical natural language processing.

OBJECTIVES: To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. MATERIALS AND METHODS: We created the BioInstruct, comprising 25 005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. RESULTS AND DISCUSSION: Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. CONCLUSION: The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.

Basiliximab Treatment for Patients With Steroid-Refractory Acute Graft-Versus-Host Disease Following Matched Sibling Donor Hematopoietic Stem Cell Transplantation.

Basiliximab is an important treatment for steroid-refractory acute graft-versus-host disease (SR-aGVHD). We performed this retrospective study to evaluate the efficacy and safety of basiliximab treatment in SR-aGVHD patients following matched sibling donor hematopoietic stem cell transplantation (MSD-HSCT) (n = 63). Overall response rate (ORR) was 63.5% and 54% at any time and at day 28 after basiliximab treatment. Grade III-IV aGVHD before basiliximab treatment predicted a poor ORR after basiliximab treatment. The rates of virus, bacteria, and fungi infections were 54%, 23.8%, and 3.1%, respectively. With a median follow-up of 730 (range, 67-3,042) days, the 1-year probability of overall survival and disease-free survival after basiliximab treatment were 58.6% (95% confidence interval [CI] = 47.6%-72.2%) and 55.4% (95% CI = 44.3%-69.2%), respectively. The 3-year cumulative incidence of relapse and non-relapse mortality after basiliximab treatment were 18.9% (95% CI = 8.3%-29.5%) and 33.8% (95% CI = 21.8%-45.7%), respectively. Comorbidities burden before allo-HSCT, severity of aGVHD and liver aGVHD before basiliximab treatment showed negative influences on survival. Thus, basiliximab was safe and effective treatment for SR-aGVHD following MSD-HSCT.

Clinical outcomes and biomarker exploration of first-line PD-1 inhibitors plus chemotherapy in patients with low PD-L1-expressing of gastric or gastroesophageal junction adenocarcinoma.

BACKGROUND: The beneficial effects of first-line programmed death-1 (PD-1) inhibitors plus chemotherapy in patients with low programmed death-ligand 1 (PD-L1)-expressing advanced gastric or gastroesophageal junction (G/GEJ) adenocarcinoma are controversial. METHODS: We conducted a retrospective analysis of patients with G/GEJ adenocarcinoma who had undergone first-line treatment with PD-1 inhibitors plus chemotherapy between October 2017 and May 2022. The primary outcomes were objective response rate (ORR) and progression-free survival (PFS). SPSS software V27.0 was used for data analysis. RESULTS: Of 345 enrolled patients, 290 had measurable lesions. The overall ORR was 59.3%. PD-L1 status was available in 171 patients, and 67.8% of them were considered as low PD-L1 expression level (combined positive score (CPS) < 5). Patients with PD-L1 CPS < 5 showed a lower response rate (51.1% vs 70.8%, P = 0.024) and a worse PFS (P = 0.009) compared to those with PD-L1 CPS ≥ 5. In the PD-L1 low-expression cohort, patients with non-diffuse type, GEJ cancer, synchronous metastasis, distant lymph node metastasis, liver metastasis, non-peritoneal metastasis, and HER2 positive were significantly associated with higher response rates to PD-1 inhibitors plus chemotherapy (P < 0.05). The presence of peritoneal metastasis (P = 0.028) and diffuse type (P = 0.046) were identified as independent predictors of poor PFS in multivariate analysis of the PD-L1 CPS < 5 subgroup. When evaluated for correlation with overall survival (OS) in the PD-L1 low-expression subgroup, peritoneal metastasis was found to be the only independent prognostic factor of an increased risk of death (hazard ratio: 2.31, 95% CI 1.09-4.90; P = 0.029). CONCLUSIONS: PD-L1 CPS ≥ 5 is significantly associated with improved response and extended PFS in G/GEJ cancer patients treated with a combination of PD-1 inhibitors and chemotherapy. Specific subgroups within the low PD-L1-expressing population, such as those with non-diffuse-type tumors and without peritoneal metastases, may also benefit from immunotherapy combined with chemotherapy.

OLFM4 promotes the progression of intestinal metaplasia through activation of the MYH9/GSK3ß/ß-catenin pathway.

BACKGROUND: Intestinal metaplasia (IM) is classified into complete intestinal metaplasia (CIM) and incomplete intestinal metaplasia (IIM). Patients diagnosed with IIM face an elevated susceptibility to the development of gastric cancer, underscoring the critical need for early screening measures. In addition to the complexities associated with diagnosis, the exact mechanisms driving the progression of gastric cancer in IIM patients remain poorly understood. OLFM4 is overexpressed in several types of tumors, including colorectal, gastric, pancreatic, and ovarian cancers, and its expression has been associated with tumor progression. METHODS: In this study, we used pathological sections from two clinical centers, biopsies of IM tissues, precancerous lesions of gastric cancer (PLGC) cell models, animal models, and organoids to explore the role of OLFM4 in IIM. RESULTS: Our results show that OLFM4 expression is highly increased in IIM, with superior diagnostic accuracy of IIM when compared to CDX2 and MUC2. OLFM4, along with MYH9, was overexpressed in IM organoids and PLGC animal models. Furthermore, OLFM4, in combination with Myosin heavy chain 9 (MYH9), accelerated the ubiquitination of GSK3ß and resulted in increased ß-catenin levels through the Wnt signaling pathway, promoting the proliferation and invasion abilities of PLGC cells. CONCLUSIONS: OLFM4 represents a novel biomarker for IIM and could be utilized as an important auxiliary means to delimit the key population for early gastric cancer screening. Finally, our study identifies cell signaling pathways involved in the progression of IM.

A novel fish individual recognition method for precision farming based on knowledge distillation strategy and the range of the receptive field.

With the continuous development of green and high-quality aquaculture technology, the process of industrialized aquaculture has been promoted. Automation, intelligence, and precision have become the future development trend of the aquaculture industry. Fish individual recognition can further distinguish fish individuals based on the determination of fish categories, providing basic support for fish disease analysis, bait feeding, and precision aquaculture. However, the high similarity of fish individuals and the complexity of the underwater environment presents great challenges to fish individual recognition. To address these problems, we propose a novel fish individual recognition method for precision farming that rethinks the knowledge distillation strategy and the chunking method in the vision transformer. The method uses the traditional convolutional neural network model as the teacher model, introducing the teacher token to guide the student model to learn the fish texture features. We propose stride patch embedding to expand the range of the receptive field, thus enhancing the local continuity of the image, and self-attention-pruning to discard unimportant tokens and reduce the model computation. The experimental results on the DlouFish dataset show that the proposed method in this paper improves accuracy by 3.25% compared to ECA Resnet152, with an accuracy of 93.19%, and also outperforms other vision transformer models.

Global trends and hotspots in pain associated with bipolar disorder in the last 20 years: a bibliometric analysis.

Purpose: The prevalence of comorbid pain and Bipolar Disorder in clinical practice continues to be high, with an increasing number of related publications. However, no study has used bibliometric methods to analyze the research progress and knowledge structure in this field. Our research is dedicated to systematically exploring the global trends and focal points in scientific research on pain comorbidity with bipolar disorder from 2003 to 2023, with the goal of contributing to the field. Methods: Relevant publications in this field were retrieved from the Web of Science core collection database (WOSSCC). And we used VOSviewer, CiteSpace, and the R package "Bibliometrix" for bibliometric analysis. Results: A total of 485 publications (including 360 articles and 125 reviews) from 66 countries, 1019 institutions, were included in this study. Univ Toront and Kings Coll London are the leading research institutions in this field. J Affect Disorders contributed the largest number of articles, and is the most co-cited journal. Of the 2,537 scholars who participated in the study, Stubbs B, Vancampfort D, and Abdin E had the largest number of articles. Stubbs B is the most co-cited author. "chronic pain," "neuropathic pain," "psychological pain" are the keywords in the research. Conclusion: This is the first bibliometric analysis of pain-related bipolar disorder. There is growing interest in the area of pain and comorbid bipolar disorder. Focusing on different types of pain in bipolar disorder and emphasizing pain management in bipolar disorder are research hotspots and future trends. The study of pain related bipolar disorder still has significant potential for development, and we look forward to more high-quality research in the future.

Development and validation of an interpretable delta radiomics-based model for predicting invasive ground-glass nodules in lung adenocarcinoma: a retrospective cohort study.

Background: Radiomics models based on computed tomography (CT) can be used to differentiate invasive ground-glass nodules (GGNs) in lung adenocarcinoma to help determine the optimal timing of GGN resection, improve the accuracy of prognostic prediction, and reduce unnecessary surgeries. However, general radiomics does not fully utilize follow-up data and often lacks model interpretation. Therefore, this study aimed to build an interpretable model based on delta radiomics to predict GGN invasiveness. Methods: A retrospective analysis was conducted on a set of 303 GGNs that were surgically resected and confirmed as lung adenocarcinoma in Shanghai Chest Hospital between September 2017 and August 2022. Delta radiomics and general radiomics features were extracted from preoperative follow-up CT scans and combined with clinical features for modeling. The performance of the delta radiomics-clinical model was compared to that of the radiomics-clinical model. Additionally, Shapley additive explanations (SHAP) was employed to interpret and visualize the model. Results: Two models were constructed using a combination of 34 radiomic features and 10 delta radiomic features, along with 14 clinical features. The radiomics-clinical model and the delta radiomics-clinical model exhibited area under the curve (AUC) of 0.986 [95% confidence interval (CI): 0.977-0.995] and 0.974 (95% CI: 0.959-0.987) in the training set, respectively, and 0.949 (95% CI: 0.908-0.978) and 0.927 (95% CI: 0.879-0.966) in the test set, respectively. The DeLong test of the two models showed no statistical significance (P=0.10) in the test set. SHAP was used to output a summary plot for global interpretation, which showed that preoperative mass, three-dimensional (3D) length, mean diameter, volume, mean CT value, and delta radiomics feature original_firstorder_RootMeanSquared were the relatively more important features in the model. Waterfall plots for local interpretation showed how each feature contributed to the prediction output of a given GGN. Conclusions: The delta radiomics-based model proved to be a helpful tool for predicting the invasiveness of GGNs in lung adenocarcinoma. This approach offers a precise, noninvasive alternative in informing clinical decision-making. Additionally, SHAP provided insightful and user-friendly interpretations and visualizations of the model, enhancing its clinical applicability.

ΔNp63-restricted viral mimicry response impedes cancer cell viability and remodels tumor microenvironment in esophageal squamous cell carcinoma.

Tumor protein p63 isoform ΔNp63 plays roles in the squamous epithelium and squamous cell carcinomas (SCCs), including esophageal SCC (ESCC). By integrating data from cell lines and our latest patient-derived organoid cultures, derived xenograft models, and clinical sample transcriptomic analyses, we identified a novel and robust oncogenic role of ΔNp63 in ESCC. We showed that ΔNp63 maintains the repression of cancer cell endogenous retrotransposon expression and cellular double-stranded RNA sensing. These subsequently lead to a restricted cancer cell viral mimicry response and suppressed induction of tumor-suppressive type I interferon (IFN-I) signaling through the regulations of Signal transducer and activator of transcription 1, Interferon regulatory factor 1, and cGAS-STING pathway. The cancer cell ΔNp63/IFN-I signaling axis affects both the cancer cell and tumor-infiltrating immune cell (TIIC) compartments. In cancer cells, depletion of ΔNp63 resulted in reduced cell viability. ΔNp63 expression is negatively associated with the anticancer responses to viral mimicry booster treatments targeting cancer cells. In the tumor microenvironment, cancer cell TP63 expression negatively correlates with multiple TIIC signatures in ESCC clinical samples. ΔNp63 depletion leads to increased cancer cell antigen presentation molecule expression and enhanced recruitment and reprogramming of tumor-infiltrating myeloid cells. Similar IFN-I signaling and TIIC signature association with ΔNp63 were also observed in lung SCC. These results support the potential application of ΔNp63 as a therapeutic target and a biomarker to guide candidate anticancer treatments exploring viral mimicry responses.

The trend of radiographic healing after root canal treatment in teeth with apical periodontitis based on cone-beam computed tomography: A 4-year longitudinal study.

OBJECTIVES: The aim of this study was to observe the radiographic healing of periapical lesions after root canal treatment via volumetric measurements based on cone-beam computed tomography (CBCT) over 4 years. METHODS: In total, 162 single-root teeth from patients with chronic periapical periodontitis who underwent primary root canal treatment were included in this retrospective study. Follow-up visits were scheduled at 1, 2, and 4 years after treatment. The volume of radiolucency at pretreatment and follow-up were measured, and the radiographic outcomes were classified into 4 categories: absence, reduction, uncertain or enlargement. Reduction or enlargement was considered when the volumetric change in radiolucency was 20 % or more. RESULTS: During the 4-year follow-up period, 128 teeth were reviewed at least once, including 3 extracted teeth. Of the remaining 125 teeth, the volume of radiolucency was reduced in 116 teeth (90.6 %), uncertain in 5, and enlarged in 4 teeth during 1 to 4 years after treatment. Among the 43 teeth with reduced radiolucency at 1 year after treatment, 42 (97.7 %) had continuing reduced lesions at 4 years. In the 2 teeth with enlarged radiolucency at 1 year, the volume of radiolucency doubled at 4 years. Cox regression analysis revealed that the preoperative radiolucency size was a risk factor for persistent periapical radiolucency. CONCLUSIONS: The efficacy of root canal treatment for apical periodontitis was predictable. When the radiolucency changed by 20 % or more in volume on CBCT scans at 1 year after treatment, reversal of the radiographic healing tendency was rare. CLINICAL SIGNIFICANCE: The volumetric changes in radiolucency on CBCT could reflect trends in the healing process and may foster early clinical decision-making.

Association between mechanical power during one-lung ventilation and pulmonary complications after thoracoscopic lung resection surgery: a prospective observational study.

BACKGROUND: The role of mechanical power on pulmonary outcomes after thoracic surgery with one-lung ventilation was unclear. We investigated the association between mechanical power and postoperative pulmonary complications in patients undergoing thoracoscopic lung resection surgery. METHODS: In this single-center, prospective observational study, 622 patients scheduled for thoracoscopic lung resection surgery were included. Volume control mode with lung protective ventilation strategies were implemented in all participants. The primary endpoint was a composite of postoperative pulmonary complications during hospital stay. Multivariable logistic regression models were used to evaluate the association between mechanical power and outcomes. RESULTS: The incidence of pulmonary complications after surgery during hospital stay was 24.6% (150 of 609 patients). The multivariable analysis showed that there was no link between mechanical power and postoperative pulmonary complications. CONCLUSIONS: In patients undergoing thoracoscopic lung resection with standardized lung-protective ventilation, no association was found between mechanical power and postoperative pulmonary complications. TRIAL REGISTRATION: Trial registration number: ChiCTR2200058528, date of registration: April 10, 2022.

Magnetic resonance imaging-based prediction models for differentiating intraspinal schwannomas from meningiomas: classification and regression tree and random forest analysis.

Background: Due to the variations in surgical approaches and prognosis between intraspinal schwannomas and meningiomas, it is crucial to accurately differentiate between the two prior to surgery. Currently, there is limited research exploring the implementation of machine learning (ML) methods for distinguishing between these two types of tumors. This study aimed to establish a classification and regression tree (CART) model and a random forest (RF) model for distinguishing schwannomas from meningiomas. Methods: We retrospectively collected 88 schwannomas (52 males and 36 females) and 51 meningiomas (10 males and 41 females) who underwent magnetic resonance imaging (MRI) examinations prior to the surgery. Simple clinical data and MRI imaging features, including age, sex, tumor location and size, T1-weighted images (T1WI) and T2-weighted images (T2WI) signal characteristics, degree and pattern of enhancement, dural tail sign, ginkgo leaf sign, and intervertebral foramen widening (IFW), were reviewed. Finally, a CART model and RF model were established based on the aforementioned features to evaluate their effectiveness in differentiating between the two types of tumors. Meanwhile, we also compared the performance of the ML models to the radiologists. The receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the models and clinicians' discrimination performance. Results: Our investigation reveals significant variations in ten out of 11 variables in the training group and five out of 11 variables in the test group when comparing schwannomas and meningiomas (P<0.05). Ultimately, the CART model incorporated five variables: enhancement pattern, the presence of IFW, tumor location, maximum diameter, and T2WI signal intensity (SI). The RF model combined all 11 variables. The CART model, RF model, radiologist 1, and radiologist 2 achieved an area under the curve (AUC) of 0.890, 0.956, 0.681, and 0.723 in the training group, and 0.838, 0.922, 0.580, and 0.659 in the test group, respectively. Conclusions: The RF prediction model exhibits more exceptional performance than an experienced radiologist in discriminating intraspinal schwannomas from meningiomas. The RF model seems to be better in discriminating the two tumors than the CART model.

Longitudinal ultrasound-based AI model predicts axillary lymph node response to neoadjuvant chemotherapy in breast cancer: a multicenter study.

OBJECTIVES: Developing a deep learning radiomics model from longitudinal breast ultrasound and sonographer's axillary ultrasound diagnosis for predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) in breast cancer. METHODS: Breast cancer patients undergoing NAC followed by surgery were recruited from three centers between November 2016 and December 2022. We collected ultrasound images for extracting tumor-derived radiomics and deep learning features, selecting quantitative features through various methods. Two machine learning models based on random forest were developed using pre-NAC and post-NAC features. A support vector machine integrated these data into a fusion model, evaluated via the area under the curve (AUC), decision curve analysis, and calibration curves. We compared the fusion model's performance against sonographer's diagnosis from pre-NAC and post-NAC axillary ultrasonography, referencing histological outcomes from sentinel lymph node biopsy or axillary lymph node dissection. RESULTS: In the validation cohort, the fusion model outperformed both pre-NAC (AUC: 0.899 vs. 0.786, p < 0.001) and post-NAC models (AUC: 0.899 vs. 0.853, p = 0.014), as well as the sonographer's diagnosis of ALN status on pre-NAC and post-NAC axillary ultrasonography (AUC: 0.899 vs. 0.719, p < 0.001). Decision curve analysis revealed patient benefits from the fusion model across threshold probabilities from 0.02 to 0.98. The model also enhanced sonographer's diagnostic ability, increasing accuracy from 71.9% to 79.2%. CONCLUSION: The deep learning radiomics model accurately predicted the ALN response to NAC in breast cancer. Furthermore, the model will assist sonographers to improve their diagnostic ability on ALN status before surgery. CLINICAL RELEVANCE STATEMENT: Our AI model based on pre- and post-neoadjuvant chemotherapy ultrasound can accurately predict axillary lymph node metastasis and assist sonographer's axillary diagnosis. KEY POINTS: Axillary lymph node metastasis status affects the choice of surgical treatment, and currently relies on subjective ultrasound. Our AI model outperformed sonographer's visual diagnosis on axillary ultrasound. Our deep learning radiomics model can improve sonographers' diagnosis and might assist in surgical decision-making.

Association of Overweight and Inflammatory Indicators with Breast Cancer: A Cross-Sectional Study in Chinese Women.

Objective: This cross-sectional study aimed to explore the association of overweight and inflammatory indicators with breast cancer risk in Chinese patients. Methods: Weight, height, and peripheral blood inflammatory indicators, including white blood cell count (WBC), neutrophil count (NE), lymphocyte count (LY), platelet count (PLT) and the concentration of hypersensitivity C-reactive protein (hsCRP), were collected in 383 patients with benign breast lumps (non-cancer) and 358 patients with malignant breast tumors (cancer) at the First Affiliated Hospital of Soochow University, China, from March 2018 to July 2020. Body mass index (BMI), neutrophil-lymphocyte ratio (NLR), platelet-lymphocyte ratio (PLR) and systemic immune-inflammation index (SII) were determined according to the ratio equation. The correlations among overweight, inflammatory indicators, and the proportion of non-cancer or cancer cases were analyzed. Results: BMI is associated with an increased breast cancer risk. Compared with non-cancer patients, the average WBC count, NE count, NLR, and level of hsCRP were significantly higher in cancer patients. The level of hsCRP was closely associated with the size of malignant breast tumors. Conclusion: We conclude that overweight and high levels of hsCRP may serve as putative risk factors for malignant breast tumors in Chinese women.