Dataset Information

Diagnostic Support for Selected Paediatric Pulmonary Diseases Using Answer-Pattern Recognition in Questionnaires Based on Combined Data Mining Applications--A Monocentric Observational Pilot Study.

ABSTRACT:

Background

Clinical symptoms in children with pulmonary diseases are frequently non-specific. Rare diseases such as primary ciliary dyskinesia (PCD), cystic fibrosis (CF) or protracted bacterial bronchitis (PBB) can be easily missed at the general practitioner (GP).

Objective

To develop and test a questionnaire-based and data mining-supported tool providing diagnostic support for selected pulmonary diseases.

Methods

First, interviews with parents of affected children were conducted and analysed. These parental observations during the pre-diagnostic time formed the basis for a new questionnaire addressing the parents' view on the disease. Secondly, parents with a sick child (e.g. PCD, PBB) answered the questionnaire and a data base was set up. Finally, a computer program consisting of eight different classifiers (support vector machine (SVM), artificial neural network (ANN), fuzzy rule-based, random forest, logistic regression, linear discriminant analysis, naive Bayes and nearest neighbour) and an ensemble classifier was developed and trained to categorise any given new questionnaire and suggest a diagnosis. For estimating the diagnostic accuracy, we applied ten-fold stratified cross validation.

Results

All questionnaires of patients suffering from CF, asthma (AS), PCD, acute bronchitis (AB) and the healthy control group were correctly diagnosed by the fusion algorithm. For the pneumonia (PM) group 19/21 (90.5%) and for the PBB group 17/18 (94.4%) correct diagnoses could be reached. The program detected the correct diagnoses with an overall sensitivity of 98.8%. Receiver operating characteristics (ROC) analyses confirmed the accuracy of this diagnostic tool. Case studies highlighted the applicability of the tool in the daily work of a GP.

Conclusion

For children with symptoms of pulmonary diseases a questionnaire-based diagnostic support tool using data mining techniques exhibited good results in arriving at diagnostic suggestions. In the hands of a doctor, this tool could be of value in arousing awareness for rare pulmonary diseases such as PCD or CF.

SUBMITTER: Rother AK

PROVIDER: S-EPMC4534438 | biostudies-literature | 2015

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Diagnostic Support for Selected Paediatric Pulmonary Diseases Using Answer-Pattern Recognition in Questionnaires Based on Combined Data Mining Applications--A Monocentric Observational Pilot Study.

Rother Ann-Katrin AK Schwerk Nicolaus N Brinkmann Folke F Klawonn Frank F Lechner Werner W Grigull Lorenz L

PloS one 20150812 8

<h4>Background</h4>Clinical symptoms in children with pulmonary diseases are frequently non-specific. Rare diseases such as primary ciliary dyskinesia (PCD), cystic fibrosis (CF) or protracted bacterial bronchitis (PBB) can be easily missed at the general practitioner (GP).<h4>Objective</h4>To develop and test a questionnaire-based and data mining-supported tool providing diagnostic support for selected pulmonary diseases.<h4>Methods</h4>First, interviews with parents of affected children were c ...[more]

PMID: 26267801

Similar Datasets

Project description:BackgroundLittle evidence is available about the impact of diet on disease activity of axial spondyloarthritis (axSpA). This study evaluated the impact of a 6-month nutritional advice based on the Mediterranean diet on the disease activity of axSpA.MethodsWe prospectively collected the information of a group of axSpA patients who were offered nutritional advice for a 6-month period, who were compared to axSpA patients followed at the same center who were not on a specific diet. A nutritionist gave suggestions for dietary modification at baseline and thereafter every 2 months until month 6. Adherence to the Mediterranean diet was evaluated with the PREDIMED questionnaire ranging from 0 (no adherence) to 10 (optimal adherence); disease activity was evaluated with ASDAS-CRP. A multivariable regression analysis was conducted to identify independent predictors of PREDIMED and of ASDAS-CRP improvement (improvement ≥ 20% of each score).ResultsA total of 161 patients were included: 81 receiving nutritional advice and 80 controls; 47 in the nutritional group and 63 controls had complete information until month 6. Overall, 40 (36.4%) were females, the mean age was 51.7 ± 1.3 years, and 58 (52.7%) were affected with psoriasis. No relevant change of anthropometric or laboratory measures was observed in either group. Adherence to the Mediterranean diet was moderate (PREDIMED score 6.7 ± 1.8 at baseline; 7.6 ± 2.1 at month 6) and improved more in the nutritional group compared to controls (p = 0.020). Predictors of a PREDIMED improvement ≥ 20% were receiving nutritional advice (OR 4.53, 1.36-15.1, p = 0.014), age (per 10-year increase OR 1.05, 1.02-1.68, p = 0.007), and BMI (OR 0.77, 0.63-0.9, p = 0.006). An ASDAS-CRP improvement ≥ 20% was more frequent in the nutritional group compared to controls (p = 0.020). A PREDIMED improvement ≥ 20% was associated with a ASDAS-CRP improvement ≥ 20% (OR 6.75,1.8-25.3, p = 0.005). Psoriasis and disease duration were negatively but not significantly associated to the ASDAS-CRP improvement.ConclusionsImproving adherence to the Mediterranean diet may have a beneficial impact on the activity of axSpA. Patients with a lower BMI and older patients are less prone to modify their diet towards the Mediterranean diet following nutritional advice. Patients with psoriasis may have a limited benefit from dietary improvement.Study registrationProtocol No. 52723, Padova Hospital Medical Ethical Committee (October 11, 2010).

Project description:BackgroundTherapy of severely affected coronavirus patient, requiring intubation and sedation is still challenging. Recently, difficulties in sedating these patients have been discussed. This study aims to describe sedation practices in patients with 2019 coronavirus disease (COVID-19)-induced acute respiratory distress syndrome (ARDS).MethodsWe performed a retrospective monocentric analysis of sedation regimens in critically ill intubated patients with respiratory failure who required sedation in our mixed 32-bed university intensive care unit. All mechanically ventilated adults with COVID-19-induced ARDS requiring continuously infused sedative therapy admitted between April 4, 2020, and June 30, 2020 were included. We recorded demographic data, sedative dosages, prone positioning, sedation levels and duration. Descriptive data analysis was performed; for additional analysis, a logistic regression with mixed effect was used.ResultsIn total, 56 patients (mean age 67 (±14) years) were included. The mean observed sedation period was 224 (±139) hours. To achieve the prescribed sedation level, we observed the need for two or three sedatives in 48.7% and 12.8% of the cases, respectively. In cases with a triple sedation regimen, the combination of clonidine, esketamine and midazolam was observed in most cases (75.7%). Analgesia was achieved using sufentanil in 98.6% of the cases. The analysis showed that the majority of COVID-19 patients required an unusually high sedation dose compared to those available in the literature.ConclusionThe global pandemic continues to affect patients severely requiring ventilation and sedation, but optimal sedation strategies are still lacking. The findings of our observation suggest unusual high dosages of sedatives in mechanically ventilated patients with COVID-19. Prescribed sedation levels appear to be achievable only with several combinations of sedatives in most critically ill patients suffering from COVID-19-induced ARDS and a potential association to the often required sophisticated critical care including prone positioning and ECMO treatment seems conceivable.

Dataset Information

Diagnostic Support for Selected Paediatric Pulmonary Diseases Using Answer-Pattern Recognition in Questionnaires Based on Combined Data Mining Applications--A Monocentric Observational Pilot Study.

Background

Objective

Methods

Results

Conclusion

Publications

Diagnostic Support for Selected Paediatric Pulmonary Diseases Using Answer-Pattern Recognition in Questionnaires Based on Combined Data Mining Applications--A Monocentric Observational Pilot Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets