Logic Learning Machine (LLM) is an innovative method of supervised analysis capable of constructing models based on simple and intelligible rules. In this investigation the performance of LLM in ...classifying patients with cancer was evaluated using a set of eight publicly available gene expression databases for cancer diagnosis. LLM accuracy was assessed by summary ROC curve (sROC) analysis and estimated by the area under an sROC curve (sAUC). Its performance was compared in cross validation with that of standard supervised methods, namely: decision tree, artificial neural network, support vector machine (SVM) and k-nearest neighbor classifier.
LLM showed an excellent accuracy (sAUC = 0.99, 95%CI: 0.98-1.0) and outperformed any other method except SVM.
LLM is a new powerful tool for the analysis of gene expression data for cancer diagnosis. Simple rules generated by LLM could contribute to a better understanding of cancer biology, potentially addressing therapeutic approaches.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Chromosomal instability (CIN) induces a high rate of losses or gains of whole chromosomes or parts of chromosomes. It is a hallmark of most human cancers and one of the causes of aneuploidy and ...intra-tumor heterogeneity. The present study aimed to evaluate the potential prognostic role of CIN in NB patients at diagnosis. We performed array comparative genomic hybridization analyses on 451 primary NB patients at the onset of the disease. To assess global chromosomal instability with high precision, we focused on the total number of DNA breakpoints of gains or losses of chromosome arms. For each tumor, an array-CGH-based breakpoint instability index (BPI) was assigned which defined the total number of chromosomal breakpoints per genome. This approach allowed us to quantify CIN related to whole genome disruption in all NB cases analyzed. We found differences in chromosomal breakages among the NB clinical risk groups. High BPI values are negatively associated with survival of NB patients. This association remains significant when correcting for stage, age, and MYCN status in the Cox model. Stratified analysis confirms the prognostic effect of BPI index in low-risk NB patients with non-amplified MYCN and with segmental chromosome aberrations.
Neuroblastoma (NB) is a tumor of the developing sympathetic nervous system. Despite recent advances in understanding the complexity of NB, the mechanisms that determine its regression or progression ...are still largely unknown. Stage 4S NB is characterized by a favorable course of disease and often by spontaneous regression, while progression to true stage 4 is a very rare event. Here, we focused on genomic analysis of an NB case that progressed from stage 4S to stage 4 with a very poor outcome. Array-comparative genomic hybridization (a-CGH) on tumor-tissue DNA, and whole-exome sequencing (WES) on exosomes DNA derived from plasma collected at the onset and at the tumor progression, pointed out relevant genetic changes that can explain this clinical worsening. The combination of a-CGH and WES data allowed for the identification iof somatic copy number aberrations and single-nucleotide variants in genes known to be responsible for aggressive NB. KLRB1, MAPK3 and FANCA genes, which were lost at the time of progression, were studied for their possible role in this event by analyzing in silico the impact of their expression on the outcome of 786 NB patients.
The area under a receiver operating characteristic (ROC) curve (AUC) is a popular measure of pure diagnostic accuracy that is independent from the proportion of diseased subjects in the analysed ...sample. However, its actual usefulness in the clinical context has been questioned, because it does not seem to be directly related to the actual performance of a diagnostic marker in identifying diseased and non-diseased subjects in real clinical settings. This study evaluates the relationship between the AUC and the proportion of correct classifications (global diagnostic accuracy, GDA) in relation to the shape of the corresponding ROC curves.
We demonstrate that AUC represents an upward-biased measure of GDA at an optimal accuracy cut-off for balanced groups. The magnitude of bias depends on the shape of the ROC plot and on the proportion of diseased and non-diseased subjects. In proper curves, the bias is independent from the diseased/non-diseased ratio and can be easily estimated and removed. Moreover, a comparison between 2 partial AUCs can be replaced by a more powerful test for the corresponding whole AUCs.
Applications to 3 real datasets are provided: a marker for a hormone deficit in children, 2 tumour markers for malignant mesothelioma, and 2 gene expression profiles in ovarian cancer patients.
The AUC is a measure of accuracy with potential clinical relevance for the evaluation of disease markers. The clinical meaning of ROC parameters should always be evaluated with an analysis of the shape of the corresponding ROC curve.
Introduction:
We are trying to create a platform for social innovation to extend life span.
Methods:
Since 2005, health data (approximately 3000 items per person as of 2020) of approximately 1000 ...adults have been collected each year during the Iwaki Health Promotion Project. The industry, government, academia, and citizens have involvements in data collection, aiming to build a platform that encourages societal innovation and subsequently extends life expectancy in Aomori. The Iwaki Health Promotion Project has been supported financially by the Japanese government since it was selected as the Center of Innovation program in 2013.
Results:
Since the numbers of academia, industries, governments, and citizens involved in the Iwaki Health Promotion Project increased over the years, the big data produced during the project has become increasingly pluripotent and adaptable. It has been used to promote public health, which has also created a stronger partnership among companies and research organizations. Consequently, the amount of data collected from the project has gained attention and became more open to companies and researchers participating in the Iwaki Health Promotion Project, resulted in establishing a larger platform. It also led to the acquisition of external funding, publications of numerous research papers, creation of new health examinations, and the establishment of the Health Promotion Center (an institution for cultivating health volunteers).
Conclusion:
The Iwaki Health Promotion Project aims not only to produce a pluripotent big data but also to improve the average life expectancy of Aomori by creating a large platform in the society. Its positive impact in the future is infinite and will keep growing as long as it is maintained by the society.
The early evaluation of prognostic tumour markers is commonly performed by comparing the survival of two groups of patients identified on the basis of a cut-off value. The corresponding hazard ratio ...(
) is usually estimated, representing a measure of the relative risk between patients with marker values above and below the cut-off. A posteriori methods identifying an optimal cut-off are appropriate when the functional form of the relation between the marker distribution and patient survival is unknown, but they are prone to an overestimation bias. In the presence of a small sample size, which is typical of rare diseases, the external validation sets are hardly available and internal cross-validation could be unfeasible. We describe a new method to obtain an unbiased estimate of the
at an optimal cut-off, exploiting the simple relation between the
and the associated
-value estimated by a random permutation analysis. We validate the method on both simulated data and set of gene expression profiles from two large, publicly available data sets. Furthermore, a reanalysis of a previously published study, which included 134 Stage 4S neuroblastoma patients, allowed for the identification of
as a new gene with potential oncogenic activity. This finding was confirmed by an immunofluorescence analysis on an independent cohort.
The aim of this study was to evaluate the satisfaction of the use of telemedicine and telenursing in children and young adults with Type 1 Diabetes and their families followed in the Regional ...Pediatric Diabetes Center of Giannina Gaslini Institute (Liguria, Italy). An anonymous survey form was administered to 290 patients (138 filled out by caregivers and 152 by patients). The questionnaire consisted of two parts: the first one included a series of questions related to the patient's personal and medical data; the second one was directed toward the satisfaction in the use of telemedicine and telenursing during Covid-19 pandemic. The data collected showed that 92.4% of the population was overall very satisfied with the quality of the service provided. Satisfaction was much higher especially in those who live outside of the province of Genoa (
= 0.017) and in those on insulin pump treatment (
= 0.037). Telemedicine and telenursing have an essential role in diabetology and are highly appreciated in our Center, where most patients prefer to continue regular follow-up via video-call as well as in person. Telenursing was also proved to be an effective and appreciated tool for educating and supporting patients using insulin pumps and glucose sensors.
Neuroblastoma (NB) is a tumor affecting the peripheral sympathetic nervous system that substantially contributes to childhood cancer mortality. Despite recent advances in understanding the complexity ...of NB, the mechanisms determining its progression are still largely unknown. Some recurrent segmental chromosome aberrations (SCA) have been associated with poor survival. However, the prognostic role of most SCA has not yet been investigated. We examined a cohort of 260 NB primary tumors at disease onset for the loss of chromosome 10q, by array-comparative genomic hybridization (a-CGH) and Single Nucleotide Polymorphism (SNP) array and we found that 26 showed 10q loss, while the others 234 displayed different SCA. We observed a lower event-free survival for NB patients displaying 10q loss compared to patients with tumors carrying other SCA. Furthermore, analyzing the region of 10q loss, we identified a cluster of 75 deleted genes associated with poorer outcome. Low expression of six of these genes, above all
, was significantly correlated to worse survival using in silico data from 786 NB patients. These potential tumor suppressor genes can be partly responsible for the poor prognosis of NB patients with 10q loss.
This study evaluates the performance of a set of machine learning techniques in predicting the prognosis of Hodgkin’s lymphoma using clinical factors and gene expression data. Analysed samples from ...130 Hodgkin’s lymphoma patients included a small set of clinical variables and more than 54,000 gene features. Machine learning classifiers included three black-box algorithms (k-nearest neighbour, Artificial Neural Network, and Support Vector Machine) and two methods based on intelligible rules (Decision Tree and the innovative Logic Learning Machine method). Support Vector Machine clearly outperformed any of the other methods. Among the two rule-based algorithms, Logic Learning Machine performed better and identified a set of simple intelligible rules based on a combination of clinical variables and gene expressions. Decision Tree identified a non-coding gene (XIST) involved in the early phases of X chromosome inactivation that was overexpressed in females and in non-relapsed patients. XIST expression might be responsible for the better prognosis of female Hodgkin’s lymphoma patients.
Purpose
To clarify the role of primary tumor resection in stage 4S neuroblastoma.
Methods
We investigated a cohort of 172 infants diagnosed with stage 4S neuroblastoma between 1994 and 2013. Of 160 ...evaluable patients, 62 underwent upfront resection of the primary tumor and 98 did not.
Results
Five-year progression-free and overall survival were significantly better in those who had undergone upfront surgery (83.6% vs 64.2% and 96.8% vs 85.7%, respectively). One post-operative death and four non-fatal complications occurred in the resection group. Three patients who had not undergone resection died of chemotherapy-related toxicity. Thirteen patients underwent late surgery to remove a residual tumor, without complications: all but one alive. Outcomes were better in patients diagnosed from 2000 onwards.
Conclusion
Infants diagnosed with stage 4S neuroblastoma who underwent upfront tumor resection had a better outcome. However, this result cannot be definitely attributed to surgery, since these patients were selected on the basis of their favorable presenting features. Although the question of whether to operate or not at disease onset is still unsolved, this study confirms the importance of obtaining enough adequate tumor tissue to enable histological and biological studies to properly address treatment, to achieve the best possible outcome.
PDF
