Prediction of distinct populations of innate lymphoid cells by transcriptional profiles.

Innate lymphoid cells (ILCs) are a unique type of lymphocyte that differ from adaptive lymphocytes in that they lack antigen receptors, which primarily reside in tissues and are closely associated with fibers. Despite their plasticity and heterogeneity, identifying ILCs in peripheral blood can be difficult due to their small numbers. Accurately and rapidly identifying ILCs is critical for studying homeostasis and inflammation. To address this challenge, we collect single-cell RNA-seq data from 647 patients, including 26,087 transcripts. Background screening, Lasso analysis, and principal component analysis (PCA) are used to select features. Finally, we employ a deep neural network to classify lymphocytes. Our method achieved the highest accuracy compared to other approaches. Furthermore, we identified four genes that play a vital role in lymphocyte development. Adding these gene transcripts into model, we were able to increase the model's AUC. In summary, our study demonstrates the effectiveness of using single-cell transcriptomic analysis combined with machine learning techniques to accurately identify congenital lymphoid cells and advance our understanding of their development and function in the body.

Establishment and validation of nomogram for predicting immuno checkpoint inhibitor related pneumonia.

OBJECTIVE: Cancer is one of the main causes of death worldwide. Although immunotherapy brings hope for cancer treatment, it is also accompanied by immune checkpoint inhibitor-related adverse events (irAEs). Immune checkpoint inhibitor pneumonia (CIP) is a potentially fatal adverse event, but there is still a lack of effective markers and prediction models to identify patients at increased risk of CIP. METHODS: A total of 369 cancer patients treated between 2017 and 2022 with immune checkpoint inhibitors at Shengjing Hospital of China Medical University and Liaoning People's Hospital were recruited for this study. Independent variables were selected by differences and binary logistic regression analysis, and a risk assessment nomogram was constructed for CIP risk. The accuracy and discriminative abilities of the nomogram were evaluated by calibration plots, receiver operating characteristic curves (ROCs) and decision curve analyses (DCAs). RESULTS: Binary logistic regression analysis showed that smoking history, acute phase proteins [interleukin (IL-6) and C-reactive protein (CRP)], CD8 + T lymphocyte count and serum alveolar protein [surface protein-A (SP-A) and Krebs Von den Lungen-6 (KL-6)] were significantly associated with CIP risk. A nomogram consisting of these variables was established and validated by different analyses. CONCLUSIONS: We developed an effective risk nomogram for CIP prediction in immune-checkpoint inhibitor administrated cancer patients, which will further assist early detection of immunotherapy-related adverse events.

PASCAL: a pseudo cascade learning framework for breast cancer treatment entity normalization in Chinese clinical text.

BACKGROUNDS: Knowledge discovery from breast cancer treatment records has promoted downstream clinical studies such as careflow mining and therapy analysis. However, the clinical treatment text from electronic health data might be recorded by different doctors under their hospital guidelines, making the final data rich in author- and domain-specific idiosyncrasies. Therefore, breast cancer treatment entity normalization becomes an essential task for the above downstream clinical studies. The latest studies have demonstrated the superiority of deep learning methods in named entity normalization tasks. Fundamentally, most existing approaches adopt pipeline implementations that treat it as an independent process after named entity recognition, which can propagate errors to later tasks. In addition, despite its importance in clinical and translational research, few studies directly deal with the normalization task in Chinese clinical text due to the complexity of composition forms. METHODS: To address these issues, we propose PASCAL, an end-to-end and accurate framework for breast cancer treatment entity normalization (TEN). PASCAL leverages a gated convolutional neural network to obtain a representation vector that can capture contextual features and long-term dependencies. Additionally, it treats treatment entity recognition (TER) as an auxiliary task that can provide meaningful information to the primary TEN task and as a particular regularization to further optimize the shared parameters. Finally, by concatenating the context-aware vector and probabilistic distribution vector from TEN, we utilize the conditional random field layer (CRF) to model the normalization sequence and predict the TEN sequential results. RESULTS: To evaluate the effectiveness of the proposed framework, we employ the three latest sequential models as baselines and build the model in single- and multitask on a real-world database. Experimental results show that our method achieves better accuracy and efficiency than state-of-the-art approaches. CONCLUSIONS: The effectiveness and efficiency of the presented pseudo cascade learning framework were validated for breast cancer treatment normalization in clinical text. We believe the predominant performance lies in its ability to extract valuable information from unstructured text data, which will significantly contribute to downstream tasks, such as treatment recommendations, breast cancer staging and careflow mining.

Regulatory effects of microRNA­184 on osteosarcoma via the Wnt/ß­catenin signaling pathway.

The present study aimed to investigate the role of microRNA (miRNA/miR)­184 in osteosarcoma growth, development and metastasis, and the effects of miRNA­184 on the proliferation, invasion and metastasis of osteosarcoma cells and associated mechanisms. In vitro, miR­184 was transfected into U­2OS cells and 143B cells. Reverse transcription­quantitative polymerase chain reaction (RT­qPCR) was used to detect the expression of miR­184. MTT was utilized to detect cell proliferation. A Transwell assay was applied to detect cell invasiveness. In vivo, an osteosarcoma tibial orthotopic metastatic tumor model was established, and western blotting and RT­qPCR were used to detect the expression of Wnt and ß­catenin. Following the overexpression of miR­184, the proliferation and cell invasion ability were significantly increased in U­2OS and 143B cells. Following inhibition of miR­184, cell proliferation and cell invasion ability were significantly decreased. In nude mice, tumor volume significantly increased following overexpression of miR­184, and Wnt and phosphorylated ß­catenin levels were significantly increased. Following miR­184 inhibition, tumor volume was significantly decreased, and Wnt and phosphorylated ß­catenin levels were significantly decreased. The results of the present study indicated that the Wnt/ß­catenin signaling pathway serves a key function in the mechanism of osteosarcoma. Inhibition of miRNA­184 may reduce tumor volume of osteosarcoma via regulation of the Wnt/ß­catenin signaling pathway and may provide a novel strategy for the future diagnosis and treatment of osteosarcoma.

A YinYang bipolar fuzzy cognitive TOPSIS method to bipolar disorder diagnosis.

BACKGROUND AND OBJECTIVE: Bipolar disorder is often mis-diagnosed as unipolar depression in the clinical diagnosis. The main reason is that, different from other diseases, bipolarity is the norm rather than exception in bipolar disorder diagnosis. YinYang bipolar fuzzy set captures bipolarity and has been successfully used to construct a unified inference mathematical modeling method to bipolar disorder clinical diagnosis. Nevertheless, symptoms and their interrelationships are not considered in the existing method, circumventing its ability to describe complexity of bipolar disorder. Thus, in this paper, a YinYang bipolar fuzzy multi-criteria group decision making method to bipolar disorder clinical diagnosis is developed. METHODS: Comparing with the existing method, the new one is more comprehensive. The merits of the new method are listed as follows: First of all, multi-criteria group decision making method is introduced into bipolar disorder diagnosis for considering different symptoms and multiple doctors' opinions. Secondly, the discreet diagnosis principle is adopted by the revised TOPSIS method. Last but not the least, YinYang bipolar fuzzy cognitive map is provided for the understanding of interrelations among symptoms. RESULTS: The illustrated case demonstrates the feasibility, validity, and necessity of the theoretical results obtained. Moreover, the comparison analysis demonstrates that the diagnosis result is more accurate, when interrelations about symptoms are considered in the proposed method. CONCLUSIONS: In a conclusion, the main contribution of this paper is to provide a comprehensive mathematical approach to improve the accuracy of bipolar disorder clinical diagnosis, in which both bipolarity and complexity are considered.

Clinical application of computed tomography-guided (125)I seed interstitial implantation for head and neck cancer patients with unmanageable cervical lymph node metastases.

BACKGROUND: To assess clinical application of computed tomography (CT)-guided (125)I seed implantation for patients who cannot endure or unwillingly receive repeated surgery, chemotherapy, or radiotherapy for unmanageable cervical lymph node metastases in head and neck cancer (HNC). METHODS: Thirty-one consecutive patients received CT-guided (125)I seed implantation between February 2010 and December 2013. To evaluate the clinical efficiency, karnofsky performance score (KPS), numeric rating scale (NRS), and tumor volume at 3-, and 6-month post-implantation were compared with pre-implantation, along with local control rate (LCR), overall survival rate (OSR), and complications at 3, 6 months, 1, and 2 years. RESULTS: The tumor volume was obviously decreased at 3-, and 6-month post-implantation (21.23 ± 8.83 versus 9.19 ± 7.52 cm(2); 21.23 ± 8.83 versus 6.42 ± 9.79 cm(2); P < 0.05) compared with pre-implantation. The NRS was statistically reduced (3.06 ± 1.06 versus 7.77 ± 0.92; 2.39 ± 1.15 versus 7.77 ± 0.92; P < 0.05), while KPS was significantly improved (83.18 ± 5.97 versus 73.60 ± 7.90; 82.86 ± 5.43 versus 73.60 ± 7.90; P < 0.05) postoperatively at 3 and 6 months, respectively. The LCR at 3, 6 months, 1, and 2 years was 96.30, 83.87, 64.51, and 45.16%, respectively. The OSR was 100, 100, 67.74, and 45.16%, respectively. Three cases experienced grade I and two had grade II acute radiation toxicity. CONCLUSIONS: CT-guided seed implantation may be feasible and safe for HNC patients whose neck nodes are not manageable by routine strategies with fewer complications, higher LCR, and significant pain relief.

[Treatment of metastatic thoracolumbar tumors by percutaneous vertebroplasty combined with interstitial implantation of ¹²5I seeds].

OBJECTIVE: To explore the value of percutaneous vertebroplasty combined with interstitial implantation of ¹²5I seeds in the treatment of metastatic thoracolumbar tumors. METHODS: Based on the CT images before ¹²5I seed implantation, a computer-based treatment planning system (TPS) was used to determine the optimal seed distribution. Under CT guidance and local anaesthesia, ¹²5I seeds were implanted into 22 osseous metastatic lesions in 18 patients. Based on the CT images after the implantation, quality check was carried out with TPS. DSA (digital subtraction angiography)-guided vertebroplasty was performed under local anaesthesia, and bone cement was injected into the vertebrae through pedicle of vertebral arch. RESULTS: All the 18 patients received percutaneous vertebroplasty combined with interstitial implantation of ¹²5I seeds. Every vertebra was injected with 2-6 ml bone cement, average 3.5 ml, and was injected with ¹²5I seeds 16-34 pills, average 26 pills. At 2-months follow-up, their numerical rating scale (NRS) pain scores were 7.12 ± 1.48 before and 2.26 ± 1.07 after treatment, with a significant difference (P < 0.05). CONCLUSIONS: Percutaneous vertebroplasty combined with interstitial implantation of ¹²5I seeds is a minimally invasive procedure with small wound and minor complications, and no need of external radiation therapy. It is effective in the alleviation of pain in metastatic thoracolumbar tumor patients, restrains the tumor growth, and improves the quality of life. It is a promising minimally invasive method in the treatment of metastatic thoracolumbar tumors.