- MeSH
- Blood Urea Nitrogen MeSH
- Research Support as Topic MeSH
- Risk Assessment methods statistics & numerical data utilization MeSH
- Inpatients classification statistics & numerical data MeSH
- Creatinine diagnostic use MeSH
- Humans MeSH
- Blood Pressure Determination methods statistics & numerical data utilization MeSH
- Decision Support Techniques MeSH
- Hospital Mortality MeSH
- Heart Failure mortality MeSH
- Check Tag
- Humans MeSH
The increasing prevalence of autism spectrum disorders (ASD) has led to worldwide interest in factors influencing the age of ASD diagnosis. Parents or caregivers of 237 ASD children (193 boys, 44 girls) diagnosed using the Autism Diagnostic Observation Schedule (ADOS) completed a simple descriptive questionnaire. The data were analyzed using the variable-centered multiple regression analysis and the person-centered classification tree method. We believed that the concurrent use of these two methods could produce robust results. The mean age at diagnosis was 5.8 ± 2.2 years (median 5.3 years). Younger ages for ASD diagnosis were predicted (using multiple regression analysis) by higher scores in the ADOS social domain, higher scores in ADOS restrictive and repetitive behaviors and interest domain, higher maternal education, and the shared household of parents. Using the classification tree method, the subgroup with the lowest mean age at diagnosis were children, in whom the summation of ADOS communication and social domain scores was ≥ 17, and paternal age at the delivery was ≥ 29 years. In contrast, the subgroup with the oldest mean age at diagnosis included children with summed ADOS communication and social domain scores < 17 and maternal education at the elementary school level. The severity of autism and maternal education played a significant role in both types of data analysis focused on age at diagnosis.
- MeSH
- Autistic Disorder * MeSH
- Child MeSH
- Adult MeSH
- Communication MeSH
- Humans MeSH
- Child Development Disorders, Pervasive * MeSH
- Autism Spectrum Disorder * diagnosis epidemiology MeSH
- Child, Preschool MeSH
- Regression Analysis MeSH
- Check Tag
- Child MeSH
- Adult MeSH
- Humans MeSH
- Male MeSH
- Child, Preschool MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
PURPOSE: The purposes of this study are to identify the strongest clinical parameters in relation to in-hospital mortality, which are available in the earliest phase of the hospitalization of patients, and to create an easy tool for the early identification of patients at risk. MATERIALS AND METHODS: The classification and regression tree analysis was applied to data from the Acute Heart Failure Database-Main registry comprising patients admitted to specialized cardiology centers with all syndromes of acute heart failure. The classification model was built on derivation cohort (n = 2543) and evaluated on validation cohort (n = 1387). RESULTS: The classification tree stratifies patients according to the presence of cardiogenic shock (CS), the level of creatinine, and the systolic blood pressure (SBP) at admission into the 5 risk groups with in-hospital mortality ranging from 2.8% to 66.2%. Patients without CS and creatinine level of 155 μmol/L or less were classified into very-low-risk group; patients without CS, creatinine level greater than 155 μmol/L, and SBP greater than 103 mm Hg, into low-risk group, whereas patients without CS, creatinine level greater than 155 μmol/L, and SBP of 103 mm Hg or lower, into intermediate-risk group. The high-risk group patients had CS and creatinine of 140 μmol/L or less; patients with CS and creatinine level greater than 140 μmol/L belong to very-high-risk group. The area under receiver operating characteristic curve was 0.823 and 0.832, and the value of Brier's score was estimated on level 0.091 and 0.084, for the derivation and the validation cohort, respectively. CONCLUSIONS: The presented classification model effectively stratified patients with all syndromes of acute heart failure into in-hospital mortality risk groups and might be of advantage for clinical practice.
- MeSH
- Risk Assessment methods MeSH
- Middle Aged MeSH
- Humans MeSH
- Hospital Mortality * MeSH
- Registries MeSH
- Risk Factors MeSH
- Aged, 80 and over MeSH
- Aged MeSH
- Heart Failure classification mortality MeSH
- Models, Statistical * MeSH
- Check Tag
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Aged, 80 and over MeSH
- Aged MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
The increasing trend of adolescents' emotional symptoms has become a global public health problem. Especially, adolescents with chronic diseases or disabilities face more risks of emotional problems. Ample evidence showed family environment associates with adolescents' emotional health. However, the categories of family-related factors that most strongly influence adolescents' emotional health remained unclear. Additionally, it was not known that whether family environment influences emotional health differently between normally developed adolescents and those with chronic condition(s). Health Behaviours in School-aged Children (HBSC) database provides mass data about adolescents' self-reported health and social environmental backgrounds, which offers opportunities to apply data-driven approaches to determine critical family environmental factors that influence adolescents' health. Thus, based on the national HBSC data in the Czech Republic collected from 2017 to 2018, the current study adopted a data-driven method, classification-regression-decision-tree analysis, to investigate the impacts of family environmental factors, including demographic factors and psycho-social factors on adolescents' emotional health. The results suggested that family psycho-social functions played a significant role in maintaining adolescents' emotional health. Both normally developed adolescents and chronic-condition(s) adolescents benefited from communication with parents, family support, and parental monitoring. Besides, for adolescents with chronic condition(s), school-related parental support was also meaningful for decreasing emotional problems. In conclusion, the findings suggest the necessity of interventions to strengthen family-school communication and cooperation to improve chronic-disease adolescents' mental health. The interventions aiming to improve parent-adolescent communication, parental monitoring, and family support are essential for all adolescents.
- MeSH
- Chronic Disease MeSH
- Child MeSH
- Mental Health * MeSH
- Emotions MeSH
- Humans MeSH
- Adolescent MeSH
- Parents * psychology MeSH
- Decision Trees MeSH
- Check Tag
- Child MeSH
- Humans MeSH
- Adolescent MeSH
- Publication type
- Journal Article MeSH
In this paper, we present the results of the research concerning extraction of informative gene expression profiles from high-dimensional array of gene expressions considering the state of patients' health using clustering method, ML-based binary classifiers and fuzzy inference system. Applying of the proposed stepwise procedure can allow us to extract the most informative genes taking into account both the subtypes of disease or state of the patient's health for further reconstruction of gene regulatory networks based on the allocated genes and following simulation of the reconstructed models. We used the publicly available gene expressions data as the experimental ones which were obtained using DNA microarray experiments and contained two types of patients' gene expression profiles-the patients with lung cancer tumor and healthy patients. The stepwise procedure of the data processing assumes the following steps-in the beginning, we reduce the number of genes by removing non-informative genes in terms of statistical criteria and Shannon entropy; then, we perform the stepwise hierarchical clustering of gene expression profiles at hierarchical levels from 1 to 10 using the SOTA (Self-Organizing Tree Algorithm) clustering algorithm with correlation distance metric. The quality of the obtained clustering was evaluated using the complex clustering quality criterion which is considered both the gene expression profiles distribution relative to center of the clusters where these gene expression profiles are allocated and the centers of the clusters distribution. The result of this stage execution was a selection of the optimal cluster at each of the hierarchical levels which corresponded to the minimum value of the quality criterion. At the next step, we have implemented a classification procedure of the examined objects using four well known binary classifiers-logistic regression, support-vector machine, decision trees and random forest classifier. The effectiveness of the appropriate technique was evaluated based on the use of ROC (Receiver Operating Characteristic) analysis using criteria, included as the components, the errors of both the first and the second kinds. The final decision concerning the extraction of the most informative subset of gene expression profiles was taken based on the use of the fuzzy inference system, the inputs of which are the results of the appropriate single classifiers operation and the output is the final solution concerning state of the patient's health. To our mind, the implementation of the proposed stepwise procedure of the informative gene expression profiles extraction create the conditions for the increasing effectiveness of the further procedure of gene regulatory networks reconstruction and the following simulation of the reconstructed models considering the subtypes of the disease and/or state of the patient's health.
- Publication type
- Journal Article MeSH
Model Matrices 144 -- 6.3 Regression Diagnostics 151 -- 6.4 Safe Prediction .155 -- 6.5 Robust and Resistant Regression .156 -- 6.6 Bootstrapping Linear Models .163 -- 6.7 Factorial Designs and Designed Experiments Poisson GLMs .208 -- 8 Non-Linear and Smooth Regression 211 -- 8.1 An Introductory Example .211 -- 8.2 Fitting Non-Linear Regression Models 212 -- 8.3 Non-Linear Fitted Model Objects and Method Functions Methods 253 -- 9.2 Implementation in rpart .258 -- 9.3 Implementation in tree 266 -- 10 Random and Mixed
Statistics and computing
4th ed. xi, 495 s. : il.
- Conspectus
- Statistika
- NML Fields
- statistika, zdravotnická statistika
- lékařská informatika
BACKGROUND: Overcoming boundaries is crucial for incursion of alien plant species and their successful naturalization and invasion within protected areas. Previous work showed that in Kruger National Park, South Africa, this process can be quantified and that factors determining the incursion of invasive species can be identified and predicted confidently. Here we explore the similarity between determinants of incursions identified by the general model based on a multispecies assemblage, and those identified by species-specific models. We analyzed the presence and absence of six invasive plant species in 1.0×1.5 km segments along the border of the park as a function of environmental characteristics from outside and inside the KNP boundary, using two data-mining techniques: classification trees and random forests. PRINCIPAL FINDINGS: The occurrence of Ageratum houstonianum, Chromolaena odorata, Xanthium strumarium, Argemone ochroleuca, Opuntia stricta and Lantana camara can be reliably predicted based on landscape characteristics identified by the general multispecies model, namely water runoff from surrounding watersheds and road density in a 10 km radius. The presence of main rivers and species-specific combinations of vegetation types are reliable predictors from inside the park. CONCLUSIONS: The predictors from the outside and inside of the park are complementary, and are approximately equally reliable for explaining the presence/absence of current invaders; those from the inside are, however, more reliable for predicting future invasions. Landscape characteristics determined as crucial predictors from outside the KNP serve as guidelines for management to enact proactive interventions to manipulate landscape features near the KNP to prevent further incursions. Predictors from the inside the KNP can be used reliably to identify high-risk areas to improve the cost-effectiveness of management, to locate invasive plants and target them for eradication.
V práci autor předkládá hypotézy, podle nichž mají pocity životního štěstí a spokojenosti zpětné vlivy na percepci a hodnocení objektivních podmínek života. Pro výklad těchto účinků na percepci objektivních podmínek předkládá hypotézu kognitivní konzistence (halo efektu), pro výklad účinků kvality života na interpretaci a hodnocení vstupních informací předkládá autor hypotézu kauzálních atribucí. Podle první hypotézy je při percepci podmínek života ve hře jev podobný halo efektu. Ten vede k tomu, že šťastní lidé nahlíží řadu podmínek svého života v lepším světle než lidé nešťastní. Podle druhé hypotézy používáme odlišná kauzální schémata pro výklad nespokojenosti a spokojenosti se životem. Tyto hypotézy – především hypotézu týkající se účinku kauzálních atribucí – autor specifikoval zvlášť pro úroveň jedinců a států a testoval na datech ze tří šetření ESS (z let 2002, 2004 a 2006). Zaměřil se na účinky vzdělání, zdraví a politicko-ekonomické situace státu. Tyto tři faktory mají na pocity životního štěstí a spokojenosti významné nezávislé vlivy. Jejich účinky jsou však současně moderovány kvalitou života. U jedinců, kteří jsou v rámci státu nadprůměrně šťastní a spokojení se svými životy, neexistují téměř žádné souvislosti mezi jejich pocity životního štěstí a jejich vzděláním, subjektivním zdravím a spokojeností s politicko-ekonomickou situací. Avšak u jedinců, kteří jsou v rámci státu relativně nešťastní a jsou se svými životy nespokojení, existují mezi těmito proměnnými velmi silné souvislosti. Na úrovni států se analogicky ukázalo, že čím jsou v určitém státě jedinci v průměru šťastnější a spokojenější, tím nižší jsou v tomto státě souvislosti (korelace) mezi těmito třemi proměnnými a kvalitou života.
- MeSH
- Adult MeSH
- Quality of Life psychology MeSH
- Humans MeSH
- Adolescent MeSH
- Personal Satisfaction MeSH
- Political Systems MeSH
- Models, Psychological MeSH
- Regression Analysis MeSH
- Statistics as Topic MeSH
- Educational Status MeSH
- Age Factors MeSH
- Research statistics & numerical data MeSH
- Check Tag
- Adult MeSH
- Humans MeSH
- Adolescent MeSH
- Publication type
- Chart MeSH
- Geographicals
- Europe MeSH
Východiska: Karcinom pankreatu je závažnou a rychle progredující diagnózou. Méně je známo o úloze výživy v etiologii karcinomu pankreatu. Studie se zaměřila na roli vybraných výživových zvyklostí u karcinomu pankreatu. Materiál a metody: Studie případů a kontrol probíhala v České republice ve třech centrech (Olomouc, Ostrava, České Budějovice) v letech 2006–2009. Soubor tvořilo celkem 530 osob (310 případů karcinomu pankreatu a 220 kontrolních osob). Údaje byly získávány od subjektů přímo formou rozhovoru se školeným tazatelem a zaznamenány do standardizovaného dotazníku. Data byla vyhodnocena pomocí hrubého odds ratio (OR) a multivariabilní logistické regrese na 95% CI. Statistická analýza byla provedena za použití softwaru STATA v. 10. Výsledky: Velmi silný protektivní efekt byl nalezen u nakládaného zelí (OR 0,32; 95% CI 0,19–0,55), brokolice (OR 0,37; 95% CI 0,25–0,53), vařené cibule (OR 0,14; 95% CI 0,08–0,27), rajčat (OR 0,28; 95% CI 0,13–0,60), syrové mrkve (OR 0,33; 95% CI 0,20–0,56), vařené mrkve (OR 0,35; 95% CI 0,19–0,62). V modelu logistické regrese byl nalezen statisticky významný protektivní vliv u konzumace tří a více porcí vařené zeleniny týdně (OR 0,16; 95% CI 0,05–0,55) a vysoké konzumace citrusového ovoce (OR 0,46; 95% CI 0,23–0,90). Závěr: Studie nalezla signifikantní protektivní vliv konzumace tří a více porcí vařené zeleniny týdně a vysoké konzumace citrusového ovoce u karcinomu pankreatu.
Background: Pancreatic cancer is serious and rapidly progressing condition. Little is known about the role of diet in etiology of pancreatic cancer. The study focused on the role of selected dietary factors related to pancreatic cancer. Material and Methods: The case-control study was performed in the Czech Republic in 2006–2009, involving three centers in Olomouc, Ostrava and Ceske Budejovice. It comprised a total of 530 persons, of whom 310 had pancreatic cancer and 220 were controls. Data were obtained directly from each participant in an interview with a trained interviewer and entered into a standardized questionnaire. The data were analyzed using a crude odds ratio (OR) and multivariate logistic regression with an adjusted OR and 95% CI. The statistical analysis was performed with the STATA v. 10 software. Results: A very strong protective effect was found in pickled cabbage (OR 0.32; 95% CI 0.19–0.55), broccoli (OR 0.37; 95% CI 0.25–0.53), cooked onion (OR 0.14; 95% CI 0.08–0.27), tomatoes (OR 0.28; 95% CI 0.13–0.60), raw carrot (OR 0.33; 95% CI 0.20–0.56), cooked carrot (OR 0.35; 95% CI 0.19–0.62). In logistic regression model, statistically significant protective associations were found in consumption of more than three portions of cooked vegetables per week (OR 0.16; 95% CI 0.05–0.55) and high consumption of citrus fruit (OR 0.46; 95% CI 0.23–0.90). Conclusion: The study found statistically significant protective effect of consumption of more than three portions of cooked vegetables per week and high consumption of citrus fruit.
Úvod: Pri dizajnovaní klinických štúdií môže pomôcť identifikácia nových prognostických faktorov prežívania. V prípade diagnózy pokročilého nemalobunkového karcinómu pľúc môžu byť vhodnými kandidátmi onkomarkery CYFRA 21-1, CEA alebo NSE [1–8]. Súvislosť ich expresie s prognózou umožňuje hodnotiť aj dataminingová metóda rekurzívneho delenia a zlučovania skupín. Metódy: Analyzovali sme údaje 162 pacientov Onkologickej kliniky FN Trnava. Všetci títo pacienti boli prijatí v rokoch 2008–2012 na podávanie prvej línie chemoterapie podľa platných odporúčaní. Hodnotili sme vplyv známych predliečebných prognostických markerov – výkonnostného stavu, úbytku hmotnosti, fajčenia, veku, pohlavia, štádia, histologického subtypu, komorbidity a onkomarkerov CYFRA 21-1, CEA alebo NSE, ako aj kombinácií týchto faktorov, na prežívanie. Výsledky: Výsledkom našej analýzy sú tri podskupiny pacientov s dobrou, strednou a nepriaznivou prognózou. Onkomarkery mali významnú úlohu pri utvorení podskupiny 49 pacientov s dobrou prognózou – sem patrili pacienti bez úbytku hmotnosti pred začatím liečby a nízkymi hladinami onkomarkerov CEA (≤ 4,1 ng/ml) alebo NSE (≤ 11,1 ng/ml). V tejto podskupine bol medián prežívania najmenej 16 mesiacov (nebol dosiahnutý) a rozdiel prežívania v porovnaní so zvyškom súboru bol vysoko štatisticky signifikantný (pomer rizík 5,21, 95% CI 1,41–19,28; p < 0,0001). Záver: V našom súbore sme preukázali prognostický význam nízkych hladín NSE a CEA v skupine pacientov bez úbytku hmotnosti v predchorobí. Rekurzívne delenie a spájanie skupín predstavuje užitočnú dataminingovú metódu; takto vygenerovanú hypotézu je však potrebné potvrdiť ďalšou klinickou štúdiou dizajnovanou na tento účel. Kľúčové slová: nemalobunkový karcinóm pľúc – onkomarkery – data mining – regresný strom – neurón-špecifická enoláza (NSE) – karcinoembryonálny antigén (CEA)
Introduction: Identification of new prognostic factors can help in designing future clinical studies. In the case of advanced non-small cell lung cancer, there might be good candidates – tumor markers CYFRA 21-1, CEA or NSE [1–8]. It is possible to evaluate the relationship between their expression and prognosis by data mining technique recursive partitioning and amalgamation. Patients and Methods: We analyzed retrospective data of 162 patients of Oncology clinics in Trnava. All of these patients were admitted between 2008 and 2012 for the administration of first-line chemotherapy according to current recommendations. We evaluated the impact of known pretreatment prognostic markers – performance status, weight loss, smoking, age, sex, stage, histologic subtype, comorbidity and oncomarkers CYFRA 21-1, CEA or NSE, as well as combinations of these factors on survival. Results: Our analyses showed that there are three subgroups of patients with good, intermediate and unfavorable prognosis. Oncomarkers played an important role in formation of a subgroup of 49 patients with good prognosis – including patients with no pretreatment weight loss and low levels of CEA (≤ 4.1 ng/ml) or NSE (≤ 11.1 ng/ml). In this subgroup, the median survival time was at least 16 months (not achieved) and the difference in survival compared to the rest of the group was highly statistically significant (risk ratio 5.21, 95% CI 1.41–19.28; p < 0.0001). Conclusion: We showed the prognostic significance of low levels of NSE and CEA oncomarkers in the group of patients with no pretreatment weight loss. Recursive partitioning and amalgamation is a useful data mining method, but the generated hypothesis needs to be confirmed by further clinical study designed for this purpose. Key words: non-small cell lung cancer – oncomarkers – data mining – regression tree – neuron-specific enolase (NSE) – carcinoembryonal antigen (CEA) The authors declare they have no potential conflicts of interest concerning drugs, products, or services used in the study. The Editorial Board declares that the manuscript met the ICMJE “uniform requirements” for biomedical papers. Submitted: 19. 3. 2014 Accepted: 25. 9. 2014
- Keywords
- regresní strom, strom přežití,
- MeSH
- Algorithms MeSH
- Antigens, Neoplasm blood MeSH
- Phosphopyruvate Hydratase blood MeSH
- Weight Loss MeSH
- Induction Chemotherapy MeSH
- Carcinoembryonic Antigen blood MeSH
- Keratin-19 blood MeSH
- Humans MeSH
- Survival Rate MeSH
- Multivariate Analysis MeSH
- Biomarkers, Tumor * blood MeSH
- Carcinoma, Non-Small-Cell Lung * blood pathology therapy MeSH
- Prognosis MeSH
- Antineoplastic Agents therapeutic use MeSH
- Regression Analysis MeSH
- Retrospective Studies MeSH
- Cluster Analysis MeSH
- Neoplasm Staging MeSH
- Check Tag
- Humans MeSH
- Male MeSH
- Female MeSH