Lymphomas

Clinical study of chemotherapy-related cognitive impairment in patients with non-Hodgkin lymphoma

BACKGROUND

Chemotherapy for malignant tumors can cause brain changes and cognitive impairment, leading to chemotherapy-induced cognitive impairment (CICI). Current research on CICI has focused on breast cancer and Hodgkin's lymphoma. Whether patients with non-Hodgkin's lymphoma (NHL) undergoing chemotherapy have cognitive impairment has not been fully investigated.

AIM

To investigate whether NHL patients undergoing chemotherapy had cognitive impairments.

METHODS

The study included 100 NHL patients who were required to complete a comprehensive psychological scale including the Brief Psychiatric Examination Scale (MMSE) at two time points: before chemotherapy and within 2 wk of two chemotherapy courses. A language proficiency test (VFT), Symbol Number Pattern Test (SDMT), Clock Drawing Test (CDT), Abbreviated Daily Cognition Scale (ECog-12), Prospective and Retrospective Memory Questionnaire, and Karnofsky Performance Status were used to assess cognitive changes before and after chemotherapy.

RESULTS

The VFT scores for before treatment (BT) and after treatment (AT) groups were 45.20 ± 15.62, and 42.30 ± 17.53, respectively (t -2.16, P < 0.05). The CDT scores were 8 (3.5-9.25) for BT and 7 (2.5-9) for AT groups (Z -2.1, P < 0.05). Retrospective memory scores were 13.5 (9-17) for BT and 15 (13-18) for AT (Z -3.7, P < 0.01). The prospective memory scores were 12.63 ± 3.61 for BT and 14.43 ± 4.32 for AT groups (t -4.97, P < 0.01). The ECog-12 scores were 1.71 (1.25-2.08) for BT and 1.79 (1.42-2.08) for AT groups (Z -2.84, P < 0.01). The SDMT and MMSE values did not show a significant difference between BT and AT groups.

CONCLUSION

Compared to the AT group, the BT group showed impaired language, memory, and subjective cognition, but objective cognition and execution were not significantly affected.

Extranodal Lymphomas: a pictorial review for CT and MRI classification

Extranodal lymphomas represent an extranodal location of both non-Hodgkin and Hodgkin lymphomas. This study aims to evaluate the role of CT and MRI in the assessment of relationships of extranodal lymphomas with surrounding tissues and in the characterization of the lesion. We selected and reviewed ten recent studies among the most recent ones present in literature exclusively about CT and MRI imaging of extranodal lymphomas. Contrast-enhanced computed tomography (CT) is usually the first-line imaging modality in the evaluation of extranodal lymphomas, according to Lugano classification. However, MRI has a crucial role thanks to the superior soft-tissue contrast resolution, particularly in the anatomical region as head and neck. (www.actabiomedica.it)

MLMDA: a machine learning approach to predict and validate MicroRNA-disease associations by integrating of heterogenous information sources

Background

Emerging evidences show that microRNA (miRNA) plays an important role in many human complex diseases. However, considering the inherent time-consuming and expensive of traditional in vitro experiments, more and more attention has been paid to the development of efficient and feasible computational methods to predict the potential associations between miRNA and disease.

Methods

In this work, we present a machine learning-based model called MLMDA for predicting the association of miRNAs and diseases. More specifically, we first use the k-mer sparse matrix to extract miRNA sequence information, and combine it with miRNA functional similarity, disease semantic similarity and Gaussian interaction profile kernel similarity information. Then, more representative features are extracted from them through deep auto-encoder neural network (AE). Finally, the random forest classifier is used to effectively predict potential miRNA–disease associations.

Results

The experimental results show that the MLMDA model achieves promising performance under fivefold cross validations with AUC values of 0.9172, which is higher than the methods using different classifiers or different feature combination methods mentioned in this paper. In addition, to further evaluate the prediction performance of MLMDA model, case studies are carried out with three Human complex diseases including Lymphoma, Lung Neoplasm, and Esophageal Neoplasms. As a result, 39, 37 and 36 out of the top 40 predicted miRNAs are confirmed by other miRNA–disease association databases.

Conclusions

These prominent experimental results suggest that the MLMDA model could serve as a useful tool guiding the future experimental validation for those promising miRNA biomarker candidates. The source code and datasets explored in this work are available at http://220.171.34.3:81/.

Novel Human miRNA-Disease Association Inference Based on Random Forest

Since the first microRNA (miRNA) was discovered, a lot of studies have confirmed the associations between miRNAs and human complex diseases. Besides, obtaining and taking advantage of association information between miRNAs and diseases play an increasingly important role in improving the treatment level for complex diseases. However, due to the high cost of traditional experimental methods, many researchers have proposed different computational methods to predict potential associations between miRNAs and diseases. In this work, we developed a computational model of Random Forest for miRNA-disease association (RFMDA) prediction based on machine learning. The training sample set for RFMDA was constructed according to the human microRNA disease database (HMDD) version (v.)2.0, and the feature vectors to represent miRNA-disease samples were defined by integrating miRNA functional similarity, disease semantic similarity, and Gaussian interaction profile kernel similarity. The Random Forest algorithm was first employed to infer miRNA-disease associations. In addition, a filter-based method was implemented to select robust features from the miRNA-disease feature set, which could efficiently distinguish related miRNA-disease pairs from unrelated miRNA-disease pairs. RFMDA achieved areas under the curve (AUCs) of 0.8891, 0.8323, and 0.8818 ± 0.0014 under global leave-one-out cross-validation, local leave-one-out cross-validation, and 5-fold cross-validation, respectively, which were higher than many previous computational models. To further evaluate the accuracy of RFMDA, we carried out three types of case studies for four human complex diseases. As a result, 43 (esophageal neoplasms), 46 (lymphoma), 47 (lung neoplasms), and 48 (breast neoplasms) of the top 50 predicted disease-related miRNAs were verified by experiments in different kinds of case studies. The results of cross-validation and case studies indicated that RFMDA is a reliable model for predicting miRNA-disease associations.

Low-grade B-cell lymphoma presenting as a uvular mass

Uvular enlargement may occur acutely as a result of infection, allergy, or trauma. Squamous cell carcinoma may present as a progressively enlarging uvular mass. Primary MALT (mucosa-associated lymphoid tissue) lymphoma of the uvula and a neuroendocrine tumor of the parapharyngeal space presenting as a uvular mass have each been previously described in the literature. Here we present a case of low-grade B-cell lymphoma presenting as a uvular mass in a 55-year-old patient with progressive throat swelling and dysphagia.

Imaging Hodgkin and non-Hodgkin lymphoma in the head and neck

Hodgkin (HL) and non-Hodgkin lymphoma (NHL) involving the head and neck have many overlapping imaging features. Definitive diagnosis depends on histology, but imaging trends may help distinguish lymphoma from other common pathologic entities in the head and neck. CT is useful for staging and assessing bony involvement, whereas MR imaging is performed for soft tissue detail in extranodal disease, especially when there is transpatial disease or intracranial or intraspinal extension. Positron emission tomography has become an important part of staging and surveillance imaging and is particularly useful to distinguish posttreatment fibrosis and residual tumor.