scholarly journals Machine Learning and Radiomic Features to Predict Overall Survival Time for Glioblastoma Patients

2021 ◽  
Vol 11 (12) ◽  
pp. 1336
Author(s):  
Lina Chato ◽  
Shahram Latifi
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
Feature Extraction ◽  
Brain Tumor ◽  
Survival Time ◽  
Treatment Plan ◽  
Imaging Features ◽  
Prediction System ◽  
Feature Extraction Method ◽  
Overall Survival Time

Glioblastoma is an aggressive brain tumor with a low survival rate. Understanding tumor behavior by predicting prognosis outcomes is a crucial factor in deciding a proper treatment plan. In this paper, an automatic overall survival time prediction system (OST) for glioblastoma patients is developed on the basis of radiomic features and machine learning (ML). This system is designed to predict prognosis outcomes by classifying a glioblastoma patient into one of three survival groups: short-term, mid-term, and long-term. To develop the prediction system, a medical dataset based on imaging information from magnetic resonance imaging (MRI) and non-imaging information is used. A novel radiomic feature extraction method is proposed and developed on the basis of volumetric and location information of brain tumor subregions extracted from MRI scans. This method is based on calculating the volumetric features from two brain sub-volumes obtained from the whole brain volume in MRI images using brain sectional planes (sagittal, coronal, and horizontal). Many experiments are conducted on the basis of various ML methods and combinations of feature extraction methods to develop the best OST system. In addition, the feature fusions of both radiomic and non-imaging features are examined to improve the accuracy of the prediction system. The best performance was achieved by the neural network and feature fusions.

A Novel Prediction of Quaternary Structural Type of Proteins with Gene Ontology

2020 ◽  
Vol 27 (4) ◽  
pp. 313-320 ◽  
Author(s):  
Xuan Xiao ◽  
Wei-Jie Chen ◽  
Wang-Ren Qiu
Keyword(s):  
Gene Ontology ◽  
Feature Extraction ◽  
Extraction Method ◽  
Quaternary Structure ◽  
Structural Type ◽  
Sequence Information ◽  
Prediction System ◽  
Data Set ◽  
Feature Extraction Method ◽  
Prediction Rate

Background: The information of quaternary structure attributes of proteins is very important because it is closely related to the biological functions of proteins. With the rapid development of new generation sequencing technology, we are facing a challenge: how to automatically identify the four-level attributes of new polypeptide chains according to their sequence information (i.e., whether they are formed as just as a monomer, or as a hetero-oligomer, or a homo-oligomer). Objective: In this article, our goal is to find a new way to represent protein sequences, thereby improving the prediction rate of protein quaternary structure. Methods: In this article, we developed a prediction system for protein quaternary structural type in which a protein sequence was expressed by combining the Pfam functional-domain and gene ontology. turn protein features into digital sequences, and complete the prediction of quaternary structure through specific machine learning algorithms and verification algorithm. Results: Our data set contains 5495 protein samples. Through the method provided in this paper, we classify proteins into monomer, or as a hetero-oligomer, or a homo-oligomer, and the prediction rate is 74.38%, which is 3.24% higher than that of previous studies. Through this new feature extraction method, we can further classify the four-level structure of proteins, and the results are also correspondingly improved. Conclusion: After the applying the new prediction system, compared with the previous results, we have successfully improved the prediction rate. We have reason to believe that the feature extraction method in this paper has better practicability and can be used as a reference for other protein classification problems.

scholarly journals Involvement of Indoleamine 2,3-Dioxygenase in Impairing Tumor-Infiltrating CD8+T-Cell Functions in Esophageal Squamous Cell Carcinoma

2011 ◽  
Vol 2011 ◽  
pp. 1-12 ◽  
Author(s):  
Ge Zhang ◽  
Wan-Li Liu ◽  
Lin Zhang ◽  
Jun-Ye Wang ◽  
Miao-Huan Kuang ◽  
...  
Keyword(s):  
Overall Survival ◽  
Squamous Cell Carcinoma ◽  
Esophageal Squamous Cell Carcinoma ◽  
Cell Carcinoma ◽  
Survival Time ◽  
Squamous Cell ◽  
Tumor Immune Escape ◽  
Cell Functions ◽  
Indoleamine 2,3 Dioxygenase ◽  
Overall Survival Time

The indoleamine 2,3-dioxygenase-(IDO-) mediated microenvironment plays an important role in tumor immune escape. However, the inhibitory effects of IDO on the CD8+tumour-infiltrating lymphocytes (CD8+TILs) in esophageal squamous cell carcinoma (ESCC) have not been clarified yet. Here, we found that the level of IDO expression in ESCC tumor specimens correlated with a reduction in the number of CD8+TILs. Patients with high IDO expression and a low number of CD8+TILs had significantly impaired overall survival time. IDO expression and functional enzyme activity in ESCC cell lines could be induced by IFNγ. When exposed to the milieu generated by IDO-expressing Eca109 cells, the CD8+TILs were suppressed in proliferation, and their cytolytic functions against target tumor cells were lost. These results suggested that impairing CD8+TIL functions by IDO expressed in ESCC possibly contributed to the finding that patients with higher IDO expression have more aggressive disease progression and shorter overall survival time.

scholarly journals Endocrine response and outcome in 14 cats with insulin resistance and acromegaly treated with stereotactic radiosurgery (17 Gy)

2022 ◽  
pp. 1-8
Author(s):  
Maegan L. Watson-Skaggs ◽  
Tracy L. Gieger ◽  
Hiroto Yoshikawa ◽  
Michael W. Nolan
Keyword(s):  
Insulin Resistance ◽  
Overall Survival ◽  
Adverse Effects ◽  
Survival Time ◽  
Stereotactic Radiosurgery ◽  
Insulin Dose ◽  
Exogenous Insulin ◽  
Endocrine Response ◽  
Overall Survival Time ◽  
Insulin Requirements

Abstract OBJECTIVE To describe clinical outcomes in cats with insulin resistance and acromegaly treated with stereotactic radiosurgery (SRS). ANIMALS 14 client-owned cats. PROCEDURES Medical records of cats with insulin resistance and acromegaly treated with SRS (17 Gy) between August 2013 and November 2019 at a single institution were reviewed. Kaplan-Meier analysis was used to evaluate overall survival time. RESULTS Acute adverse effects of SRS included somnolence (n = 2) and alopecia (1). Delayed adverse effects of SRS included unspecified neurologic complications (n = 1; 481 days), seizures (1; 1,541 days), and hypothyroidism (1; 64 days). Exogenous insulin requirements decreased in 10 of the 14 cats, with a median time to lowest insulin dose of 399 days (range, 42 to 879 days). Complete diabetic remission was achieved in 3 cats. The median overall survival time was 741 days (95% CI, 353 to 1,129 days). Six cats were still alive at the end of the study period, with a median follow-up time of 725 days. In 7 of the 8 cats that had died, death was presumptively attributed to acromegaly owing to continued insulin resistance, organ failure, or altered neurologic status. CLINICAL RELEVANCE The SRS protocol was well tolerated and associated with survival times similar to those reported previously. Most cats had decreased exogenous insulin requirements after SRS. Latency to an endocrine response was highly variable, emphasizing the need for careful ongoing diabetic monitoring of acromegalic cats after pituitary gland irradiation.

In Patient with Chronic Lymphocytic Leukemia the Overall SURVIVAL Is NOT Different WHEN Analysed by Cause of Death, Related or NOT Related to the Disease

Blood ◽  
2012 ◽  
Vol 120 (21) ◽  
pp. 4587-4587
Author(s):  
Luca Laurenti ◽  
Francesco Autore ◽  
Barbara Vannata ◽  
Idanna Innocenti ◽  
Francesco Santini ◽  
...  
Keyword(s):  
Overall Survival ◽  
Chronic Lymphocytic Leukemia ◽  
Survival Time ◽  
Cause Of Death ◽  
Causes Of Death ◽  
Lymphocytic Leukemia ◽  
Overall Survival Time ◽  
Group A ◽  
Group B ◽  
Age Of Death

Abstract Abstract 4587 Chronic Lymphocytic Leukemia (CLL) is the most common lymphoprolipherative disorder of the elderly population in Western countries. It shows a highly variable clinical course. In fact, some patients may die within few months from the diagnosis because of CLL itself or disease-related complications. Other patients do not require any treatment for many years and have a long-standing disease. Many of them could die because of disease different from CLL. The identification of subgroups of patients with peculiar features predictive of the clinical behaviour of the disease is important. This retrospective analysis has the purpose to study patients affected by CLL, diagnosed and followed at our single centre of Haematology, focusing our attention on their causes of death. We selected 340 patients affected by CLL from our data-base, diagnosed from January 1999 to December 2010 and followed until March 2012. We distinguished the causes of death in two groups: one related to CLL (as progression of the disease, evolution to Richter's Syndrome, infections due to chemotherapy) and the other not related to CLL (i.e. cardiovascular diseases, solid tumours, old age). Statistical analysis, conducted using SPSS version 16.0 for Windows and “GraphPad Prism” GraphPad Software Inc., compared these two groups and tried to select other subgroups. We recorded 69 deaths: 47 related to CLL (68.1%) and 22 unrelated to CLL (31.9%). The median age of death of our cohort of patients was 76 years (range 40–92); those patients with a CLL-related death (related pts) died at a median age of 76 years (range 40–89) and the patients with a CLL-unrelated death (unrelated pts) died at a median age of 76 years (range 61–92). No differences in terms of median age of death were found analysing the data by gender. Also, considering the overall survival time from diagnosis to death, it was 58 months (range 9–155) in the related group and 43 months (range 14–121) in the unrelated group (p=0.185). When divided our population by the disease behaviour, we obtained 3 subgroups of patients: patients who progressed and died for CLL related causes (group A), patients who progressed and died for CLL unrelated causes (group B) and patients who did not progress and died for CLL unrelated causes (group C) (Table 1). The only statistical significant difference was found among the median overall survival times in un-progressive patients who died for non CLL related causes (p=0.043). The median age of death was not affected by the cause of death in our CLL population. Moreover, patients with un-progressive CLL showed an overall survival time shorter than the progressive CLL subgroups. Patients with un-progressive CLL probably had a shorter survival because unrelated CLL diseases could are more difficult aggressive than CLL itself. Table 1. group A group B group C p N° patients 47 13 9 Median age at diagnosis (years) (range) 70 (39–85) 71 (56–83) 77 (67–86) n.s. Median age at death (years) (range) 76 (40–89) 75 (61–84) 79 (68–92) n.s. Overall survival time (months) (range) 58 (9–155) 48 (18–121) 22 (14–78) 0.043 Disclosures: No relevant conflicts of interest to declare.

Sign in / Sign up

Export Citation Format

Share Document