Predicting weaning difficulty for planned extubation patients with an artificial neural network.
Ontology highlight
ABSTRACT:
SUBMITTER: Hsieh MH
PROVIDER: S-EPMC6783239 | biostudies-literature | 2019 Oct
REPOSITORIES: biostudies-literature
Publications
Predicting weaning difficulty for planned extubation patients with an artificial neural network.
Hsieh Meng Hsuen MH Hsieh Meng Ju MJ Cheng Ai-Chin AC Chen Chin-Ming CM Hsieh Chia-Chang CC Chao Chien-Ming CM Lai Chih-Cheng CC Cheng Kuo-Chen KC Chou Willy W
Medicine 20191001 40
This study aims to construct a neural network to predict weaning difficulty among planned extubation patients in intensive care units.This observational cohort study was conducted in eight adult ICUs in a medical center about adult patients experiencing planned extubation.The data of 3602 patients with planned extubation in ICUs of Chi-Mei Medical Center (from Dec. 2009 through Dec. 2011) was used to train and test an artificial neural network (ANN) model. The input features contain 47 clinical ...[more]
Similar Datasets
Project description:BACKGROUND:Successful weaning from mechanical ventilation is important for patients in intensive care units (ICUs). The aim was to construct neural networks to predict successful extubation in ventilated patients in ICUs. METHODS:Data from 1/12/2009 through 31/12/2011 of 3602 patients with planned extubation in Chi-Mei Medical Center's ICUs was used to train and test an artificial neural network (ANN). The input was 37 clinical risk factors, and the output was a failed extubation prediction. RESULTS:One hundred eighty-five patients (5.1%) had a failed extubation. Multivariate analyses revealed that failure was positively associated with therapeutic intervention scoring system (TISS) scores (odds ratio [OR]: 1.814; 95% Confidence Interval [CI]: 1.283?2.563), chronic hemodialysis (OR: 12.264; 95% CI: 8.556?17.580), rapid shallow breathing (RSI) (OR: 2.003; 95% CI: 1.378?2.910), and pre-extubation heart rate (OR: 1.705; 95% CI: 1.173?2.480), but negatively associated with pre-extubation PaO?/FiO? (OR: 0.529; 95%: 0.370?0.750) and maximum expiratory pressure (MEP) (OR: 0.610; 95% CI: 0.413?0.899). A multilayer perceptron ANN model with 19 neurons in a hidden layer was developed. The overall performance of this model was F?: 0.867, precision: 0.939, and recall: 0.822. The area under the receiver operating characteristic curve (AUC) was 0.85, which is better than any one of the following predictors: TISS: 0.58 (95% CI: 0.54?0.62; p < 0.001); 0.58 (95% CI: 0.53?0.62; p < 0.001); and RSI: 0.54 (95% CI: 0.49?0.58; p = 0.097). CONCLUSIONS:The ANN performed well when predicting failed extubation, and it will help predict successful planned extubation.
| S-EPMC6162865 | biostudies-other
Project description:The objective of the current study was to explore the role of ABCB1 and CYP3A5 genetic polymorphisms in predicting the bioavailability of tacrolimus and the risk for post-transplant diabetes. Artificial neural network (ANN) and logistic regression (LR) models were used to predict the bioavailability of tacrolimus and risk for post-transplant diabetes, respectively. The five-fold cross-validation of ANN model showed good correlation with the experimental data of bioavailability (r2 = 0.93-0.96). Younger age, male gender, optimal body mass index were shown to exhibit lower bioavailability of tacrolimus. ABCB1 1236 C>T and 2677G>T/A showed inverse association while CYP3A5*3 showed a positive association with the bioavailability of tacrolimus. Gender bias was observed in the association with ABCB1 3435 C>T polymorphism. CYP3A5*3 was shown to interact synergistically in increasing the bioavailability in combination with ABCB1 1236 TT or 2677GG genotypes. LR model showed an independent association of ABCB1 2677 G>T/A with post transplant diabetes (OR: 4.83, 95% CI: 1.22-19.03). Multifactor dimensionality reduction analysis (MDR) revealed that synergistic interactions between CYP3A5*3 and ABCB1 2677 G>T/A as the determinants of risk for post-transplant diabetes. To conclude, the ANN and MDR models explore both individual and synergistic effects of variables in modulating the bioavailability of tacrolimus and risk for post-transplant diabetes.
| S-EPMC5886400 | biostudies-literature
Project description:BackgroundTreatment with Peginterferon Alpha-2b plus Ribavirin is the current standard therapy for chronic hepatitis C (CHC). However, many host related and viral parameters are associated with different outcomes of combination therapy.ObjectivesThe aim of this study was to develop an artificial neural network (ANN) model to predetermine individual responses to therapy based on patient's demographics and laboratory data.Patients and methodsThis case-control study was conducted in Tehran, Iran, on 139 patients divided into sustained virologic response (SVR) (n = 50), relapse (n = 50) and non-response (n = 39) groups according to their response to combination therapy for 48 weeks. The ANN was trained 300 times (epochs) using clinical data. To test the ANN performance, the part of data that was selected randomly and not used in training process was entered to the ANN and the outputs were compared with real data.ResultsHemoglobin (P < 0.001), cholesterol (P = 0.001) and IL-28b genotype (P = 0.002) values had significant differences between the three groups. Significant predictive factor(s) for each group were hemoglobin for SVR (OR: 1.517; 95% CI: 1.233-1.868; P < 0.001), IL-28b genotype for relapse (OR: 0.577; 95% CI: 0.339-0.981; P = 0.041) and hemoglobin (OR: 0.824; 95% CI: 0.693-0.980; P = 0.017) and IL-28b genotype (OR: 2.584; 95% CI: 1.430-4.668;P = 0.001) for non-response. The accuracy of ANN to predict SVR, relapse and non-response were 93%, 90%, and 90%, respectively.ConclusionsUsing baseline laboratory data and host characteristics, ANN has been shown as an accurate model to predict treatment outcome, which can lead to appropriate decision making and decrease the frequency of ineffective treatment in patients with chronic hepatitis C virus (HCV) infection.
| S-EPMC4071357 | biostudies-literature
Project description:We investigated failure predictors for the planned extubation of overweight (body mass index [BMI] = 25.0-29.9) and obese (BMI ≥ 30) patients. All patients admitted to the adult intensive care unit (ICU) of a tertiary hospital in Taiwan were identified. They had all undergone endotracheal intubation for > 48 h and were candidates for extubation. During the study, 595 patients (overweight = 458 [77%]); obese = 137 [23%]) with planned extubation after weaning were included in the analysis; extubation failed in 34 patients (5.7%). Their mean BMI was 28.5 ± 3.8. Only BMI and age were significantly different between overweight and obese patients. The mortality rate for ICU patients was 0.8%, and 2.9% for inpatients during days 1-28; the overall in-hospital mortality rate was 8.4%. Failed Extubation group patients were significantly older, had more end-stage renal disease (ESRD), more cardiovascular system-related respiratory failure, higher maximal inspiratory pressure (MIP), lower maximal expiratory pressure (MEP), higher blood urea nitrogen, and higher ICU- and 28-day mortality rates than did the Successful Extubation group. Multivariate logistic regression showed that cardiovascular-related respiratory failure (odds ratio [OR]: 2.60; 95% [confidence interval] CI: 1.16-5.80), ESRD (OR: 14.00; 95% CI: 6.25-31.35), and MIP levels (OR: 0.94; 95% CI: 0.90-0.97) were associated with extubation failure. We conclude that the extubation failure risk in overweight and obese patients was associated with cardiovascular system-related respiratory failure, ESRD, and low MIP levels.
| S-EPMC5558963 | biostudies-literature
Project description:The drilling rate of penetration (ROP) is defined as the speed of drilling through rock under the bit. ROP is affected by different interconnected factors, which makes it very difficult to infer the mutual effect of each individual parameter. A robust ROP is required to understand the complexity of the drilling process. Therefore, an artificial neural network (ANN) is used to predict ROP and capture the effect of the changes in the drilling parameters. Field data (4525 points) from three vertical onshore wells drilled in the same formation using the same conventional bottom hole assembly were used to train, test, and validate the ANN model. Data from Well A (1528 points) were utilized to train and test the model with a 70/30 data ratio. Data from Well B and Well C were used to test the model. An empirical equation was derived based on the weights and biases of the optimized ANN model and compared with four ROP models using the data set of Well C. The developed ANN model accurately predicted the ROP with a correlation coefficient (R) of 0.94 and an average absolute percentage error (AAPE) of 8.6%. The developed ANN model outperformed four existing models with the lowest AAPE and highest R value.
| S-EPMC7180845 | biostudies-literature
Project description:In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders' expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day's price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately.
| S-EPMC4873195 | biostudies-literature
Project description:BackgroundThe artificial neural network (ANN) emerged recently as a potent diagnostic tool, especially for complicated systemic diseases. This study aimed to establish a diagnostic model for the recognition of fatty liver disease (FLD) by virtue of the ANN.MethodsA total of 7,396 pairs of gender- and age-matched subjects who underwent health check-ups at the First Affiliated Hospital, College of Medicine, Zhejiang University (Hangzhou, China) were enrolled to establish the ANN model. Indices available in health check-up reports were utilized as potential input variables. The performance of our model was evaluated through a receiver-operating characteristic (ROC) curve analysis. Other outcome measures included diagnostic accuracy, sensitivity, specificity, Cohen's k coefficient, Brier score, and Hosmer-Lemeshow test. The Fatty Liver Index (FLI) and the Hepatic Steatosis Index (HSI), retrained using our training-group data with its original designated input variables, were used as comparisons in the capability of FLD diagnosis.ResultsEight variables (age, gender, body mass index, alanine aminotransferase, aspartate aminotransferase, uric acid, total triglyceride, and fasting plasma glucose) were eventually adopted as input nodes of the ANN model. By applying a cut-off point of 0.51, the area under ROC curves of our ANN model in predicting FLD in the testing group was 0.908 [95% confidence interval (CI), 0.901-0.915]-significantly higher (P < 0.05) than that of the FLI model (0.881, 95% CI, 0.872-0.891) and that of the HSI model (0.885; 95% CI, 0.877-0.893). Our ANN model exhibited higher diagnostic accuracy, better concordance with ultrasonography results, and superior capability of calibration than the FLI model and the HSI model.ConclusionsOur ANN system showed good capability in the diagnosis of FLD. It is anticipated that our ANN model will be of both clinical and epidemiological use in the future.
| S-EPMC7962739 | biostudies-literature
Project description:BackgroundPretreatment assessments for glioblastoma (GBM) patients, especially elderly or frail patients, are critical for treatment planning. However, genetic profiling with intracranial biopsy carries a significant risk of permanent morbidity. We previously demonstrated that the CUL2 gene, encoding the scaffold cullin2 protein in the cullin2-RING E3 ligase (CRL2), can predict GBM radiosensitivity and prognosis. CUL2 expression levels are closely regulated with its copy number variations (CNVs). This study aims to develop artificial neural networks (ANNs) for pretreatment evaluation of GBM patients with inputs obtainable without intracranial surgical biopsies.MethodsPublic datasets including Ivy-GAP, The Cancer Genome Atlas Glioblastoma (TCGA-GBM), and the Chinese Glioma Genome Atlas (CGGA) were used for training and testing of the ANNs. T1 images from corresponding cases were studied using automated segmentation for features of heterogeneity and tumor edge contouring. A ratio comparing the surface area of tumor borders versus the total volume (SvV) was derived from the DICOM-SEG conversions of segmented tumors. The edges of these borders were detected using the canny edge detector. Packages including Keras, Pytorch, and TensorFlow were tested to build the ANNs. A 4-layered ANN (8-8-8-2) with a binary output was built with optimal performance after extensive testing.ResultsThe 4-layered deep learning ANN can identify a GBM patient's overall survival (OS) cohort with 80%-85% accuracy. The ANN requires 4 inputs, including CUL2 copy number, patients' age at GBM diagnosis, Karnofsky Performance Scale (KPS), and SvV ratio.ConclusionQuantifiable image features can significantly improve the ability of ANNs to identify a GBM patients' survival cohort. Features such as clinical measures, genetic data, and image data, can be integrated into a single ANN for GBM pretreatment evaluation.
| S-EPMC8765794 | biostudies-literature
Project description:BackgroundItem response theory (IRT; Lord & Novick, 1968) is a psychometric framework that can be used to model the likelihood that an individual will respond correctly to an item. Using archival data (Mirman et al., 2010), Fergadiotis, Kellough, and Hula (2015) estimated difficulty parameters for the Philadelphia Naming Test (PNT; Roach, Schwartz, Martin, Grewal, & Brecher, 1996) using the 1-parameter logistic IRT model. Although the use of IRT in test development is advantageous, its reliance on sample sizes exceeding 200 participants make it difficult to implement in aphasiology. Therefore, alternate means of estimating the item difficulty of confrontation naming test items warrant investigation. In a preliminary study aimed at automatic item calibration, Swiderski, Fergadiotis, and Hula (2016) regressed the difficulty parameters from the PNT on word length, age of acquisition (Kuperman et al., 2012), lexical frequency as quantified by the Log10CD index (Brysbaert & New, 2009), and naming latency (Székely et al., 2003). Although this model successfully explained a substantial proportion of variance in the PNT difficulty parameters, a substantial proportion (20%) of the response time data were missing. Further, only 39% of the picture stimuli from Székely and colleagues (2003) were identical to those on the PNT. Given that the IRT sample size requirements limit traditional calibration approaches in aphasiology and that the initial attempts in predicting IRT difficulty parameters in our pilot study were based on incomplete response time data this study has two specific aims.AimsTo estimate naming latencies for the 175 items on the PNT, and assess the utility of psycholinguistic variables and naming latencies for predicting item difficulty.Methods and proceduresUsing a speeded picture naming task we estimated mean naming latencies for the 175 items of the Philadelphia Naming test in 44 cognitively healthy adults. We then re-estimated the model reported by Swiderski et al (2016) with the new naming latency data.ResultsThe predictor variables described above accounted for a substantial proportion of the variance in the item difficulty parameters (Adj. R 2 = .692).ConclusionsIn this study we demonstrated that word length, age of acquisition, lexical frequency, and naming latency from neurotypical young adults usefully predict picture naming item difficulty in people with aphasia. These variables are readily available or easily obtained and the regression model reported may be useful for estimating confrontation naming item difficulty without the need for collection of response data from large samples of people with aphasia.
| S-EPMC6713450 | biostudies-literature
Project description:BACKGROUND:Given its narrow therapeutic range, digoxin's pharmacokinetic parameters in infants are difficult to predict due to variation in birth weight and gestational age, especially for critically ill newborns. There is limited evidence to support the safety and dosage requirements of digoxin, let alone to predict its concentrations in infants. This study aimed to compare the concentrations of digoxin predicted by traditional regression modeling and artificial neural network (ANN) modeling for newborn infants given digoxin for clinically significant patent ductus arteriosus (PDA). METHODS:A retrospective chart review was conducted to obtain data on digoxin use for clinically significant PDA in a neonatal intensive care unit. Newborn infants who were given digoxin and had digoxin concentration(s) within the acceptable range were identified as subjects in the training model and validation datasets, accordingly. Their demographics, disease, and medication information, which were potentially associated with heart failure, were used for model training and analysis of digoxin concentration prediction. The models were generated using backward standard multivariable linear regressions (MLRs) and a standard backpropagation algorithm of ANN, respectively. The common goodness-of-fit estimates, receiver operating characteristic curves, and classification of sensitivity and specificity of the toxic concentrations in the validation dataset obtained from MLR or ANN models were compared to identify the final better predictive model. RESULTS:Given the weakness of correlations between actual observed digoxin concentrations and pre-specified variables in newborn infants, the performance of all ANN models was better than that of MLR models for digoxin concentration prediction. In particular, the nine-parameter ANN model has better forecasting accuracy and differentiation ability for toxic concentrations. CONCLUSION:The nine-parameter ANN model is the best alternative than the other models to predict serum digoxin concentrations whenever therapeutic drug monitoring is not available. Further cross-validations using diverse samples from different hospitals for newborn infants are needed.
| S-EPMC6933639 | biostudies-literature