Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study

Background Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients’ quality of life. However, efficient methods that can help identify personalized risk factors and make early predictions are lacking. Objective This study aims to use advanced deep learning models to better predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma. Methods We proposed a novel time-sensitive, attentive neural network to predict asthma exacerbation using clinical variables from large electronic health records. The clinical variables were collected from the Cerner Health Facts database between 1992 and 2015, including 31,433 adult patients with asthma. Interpretations on both patient and cohort levels were investigated based on the model parameters. Results The proposed model obtained an area under the curve value of 0.7003 through a five-fold cross-validation, which outperformed the baseline methods. The results also demonstrated that the addition of elapsed time embeddings considerably improved the prediction performance. Further analysis observed diverse distributions of contributing factors across patients as well as some possible cohort-level risk factors, which could be found supporting evidence from peer-reviewed literature such as respiratory diseases and esophageal reflux. Conclusions The proposed neural network model performed better than previous methods for the prediction of asthma exacerbation. We believe that personalized risk scores and analyses of contributing factors can help clinicians better assess the individual’s level of disease progression and afford the opportunity to adjust treatment, prevent exacerbation, and improve outcomes.

Download Full-text

Asthma Exacerbation Prediction and Risk Factor Analysis Based on a Time-Sensitive, Attentive Neural Network: Retrospective Cohort Study (Preprint)

10.2196/preprints.16981 ◽

2019 ◽

Author(s):

Yang Xiang ◽

Hangyu Ji ◽

Yujia Zhou ◽

Fang Li ◽

Jingcheng Du ◽

...

Keyword(s):

Neural Network ◽

Risk Factors ◽

Asthma Exacerbation ◽

Area Under The Curve ◽

Risk Scores ◽

Model Parameters ◽

Supporting Evidence ◽

Contributing Factors ◽

Clinical Variables ◽

Personalized Risk

BACKGROUND Asthma exacerbation is an acute or subacute episode of progressive worsening of asthma symptoms and can have a significant impact on patients’ quality of life. However, efficient methods that can help <i>identify personalized risk factors and make early predictions</i> are lacking. OBJECTIVE This study aims to use advanced deep learning models to better predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma. METHODS We proposed a novel time-sensitive, attentive neural network to predict asthma exacerbation using clinical variables from large electronic health records. The clinical variables were collected from the Cerner Health Facts database between 1992 and 2015, including 31,433 adult patients with asthma. Interpretations on both patient and cohort levels were investigated based on the model parameters. RESULTS The proposed model obtained an area under the curve value of 0.7003 through a five-fold cross-validation, which outperformed the baseline methods. The results also demonstrated that the addition of elapsed time embeddings considerably improved the prediction performance. Further analysis observed diverse distributions of contributing factors across patients as well as some possible cohort-level risk factors, which could be found supporting evidence from peer-reviewed literature such as respiratory diseases and esophageal reflux. CONCLUSIONS The proposed neural network model performed better than previous methods for the prediction of asthma exacerbation. We believe that personalized risk scores and analyses of contributing factors can help clinicians better assess the individual’s level of disease progression and afford the opportunity to adjust treatment, prevent exacerbation, and improve outcomes.

Download Full-text

Asthma Exacerbation Prediction and Interpretation based on Time-sensitive Attentive Neural Network: A Retrospective Cohort Study

10.1101/19012161 ◽

2019 ◽

Author(s):

Yang Xiang ◽

Hangyu Ji ◽

Yujia Zhou ◽

Fang Li ◽

Jingcheng Du ◽

...

Keyword(s):

Neural Network ◽

Risk Factors ◽

Asthma Exacerbation ◽

Model Parameters ◽

Supporting Evidence ◽

Learning Methods ◽

Clinical Variables ◽

Potential Risk Factors ◽

Auc Value ◽

Underlying Mechanisms

AbstractBackgroundAsthma exacerbation is an acute or sub-acute episode of progressive worsening of asthma symptoms and can have significant impacts on patients’ daily life. In 2016, 12.4 million current asthmatics (46.9%) in the U.S. had at least one asthma exacerbation in the previous year.ObjectiveThe objectives of this study were to predict the risk of asthma exacerbations and to explore potential risk factors involved in progressive asthma.MethodsWe proposed a time-sensitive attentive neural network to predict asthma exacerbation using clinical variables from electronic health records (EHRs). The clinical variables were collected from the Cerner Health Facts® database between 1992 and 2015 including 31,433 asthmatic adult patients. Interpretations on both the patient level and the cohort level were investigated based on the model parameters.ResultsThe proposed model obtains an AUC value of 0.7003 through 5-fold cross-validation, which outperforms the baseline methods. The results also demonstrate that the addition of elapsed time embeddings considerably improves the performance on this dataset. Through further analysis, it was witnessed that risk factors behaved distinctly along the timeline and across patients. We also found supporting evidence from peer-reviewed literature for some possible cohort-level risk factors such as respiratory syndromes and esophageal reflux.ConclusionsThe proposed time-sensitive attentive neural network is superior to traditional machine learning methods and performs better than state-of-the-art deep learning methods in realizing effective predictive models for the prediction of asthma exacerbation. We believe that the interpretation and visualization of risk factors can help the clinical community to better understand the underlying mechanisms of the disease progression.

Download Full-text

Improved prediction of postoperative paediatric cerebellar mutism syndrome using an artificial neural network

Neuro-Oncology Advances ◽

10.1093/noajnl/vdac003 ◽

2022 ◽

Author(s):

Jai Sidpra ◽

Adam P Marcus ◽

Ulrike Löbel ◽

Sebastian M Toescu ◽

Derek Yecies ◽

...

Keyword(s):

Neural Network ◽

Risk Factors ◽

Artificial Neural Network ◽

Logistic Regression ◽

Posterior Fossa ◽

Area Under The Curve ◽

Rank Test ◽

Cerebellar Mutism ◽

Posterior Fossa Tumours ◽

Artificial Neural

Abstract Background Postoperative paediatric cerebellar mutism syndrome (pCMS) is a common but severe complication which may arise following the resection of posterior fossa tumours in children. Two previous studies have aimed to preoperatively predict pCMS, with varying results. In this work, we examine the generalisation of these models and determine if pCMS can be predicted more accurately using an artificial neural network (ANN). Methods An overview of reviews was performed to identify risk factors for pCMS, and a retrospective dataset collected as per these defined risk factors from children undergoing resection of primary posterior fossa tumours. The ANN was trained on this dataset and its performance evaluated in comparison to logistic regression and other predictive indices via analysis of receiver operator characteristic curves. Area under the curve (AUC) and accuracy were calculated and compared using a Wilcoxon signed rank test, with p<0.05 considered statistically significant. Results 204 children were included, of whom 80 developed pCMS. The performance of the ANN (AUC 0.949; accuracy 90.9%) exceeded that of logistic regression (p<0.05) and both external models (p<0.001). Conclusion Using an ANN, we show improved prediction of pCMS in comparison to previous models and conventional methods.

Download Full-text

Transforming summary statistics from logistic regression to the liability scale: application to genetic and environmental risk scores

10.1101/385740 ◽

2018 ◽

Cited By ~ 2

Author(s):

Alexandra C. Gillett ◽

Evangelos Vassos ◽

Cathryn M. Lewis

Keyword(s):

Risk Factors ◽

Risk Score ◽

Environmental Risk ◽

Effect Size ◽

Association Studies ◽

Risk Scores ◽

Model Parameters ◽

Polygenic Risk Score ◽

Polygenic Risk ◽

Size Estimates

1.Abstract1.1.ObjectiveStratified medicine requires models of disease risk incorporating genetic and environmental factors. These may combine estimates from different studies and models must be easily updatable when new estimates become available. The logit scale is often used in genetic and environmental association studies however the liability scale is used for polygenic risk scores and measures of heritability, but combining parameters across studies requires a common scale for the estimates.1.2.MethodsWe present equations to approximate the relationship between univariate effect size estimates on the logit scale and the liability scale, allowing model parameters to be translated between scales.1.3.ResultsThese equations are used to build a risk score on the liability scale, using effect size estimates originally estimated on the logit scale. Such a score can then be used in a joint effects model to estimate the risk of disease, and this is demonstrated for schizophrenia using a polygenic risk score and environmental risk factors.1.4.ConclusionThis straightforward method allows conversion of model parameters between the logit and liability scales, and may be a key tool to integrate risk estimates into a comprehensive risk model, particularly for joint models with environmental and genetic risk factors.

Download Full-text

Venous Thromboembolism in Lymphoma: Risk Stratification and Antithrombotic Prophylaxis

Cancers ◽

10.3390/cancers12051291 ◽

2020 ◽

Vol 12 (5) ◽

pp. 1291

Author(s):

Stefan Hohaus ◽

Francesca Bartolomei ◽

Annarosa Cuccaro ◽

Elena Maiolo ◽

Eleonora Alma ◽

...

Keyword(s):

Risk Factors ◽

Venous Thromboembolism ◽

Risk Stratification ◽

Solid Tumors ◽

Performance Status ◽

Primary Prophylaxis ◽

Risk Scores ◽

Individual Risk ◽

Contributing Factors ◽

Patient Registries

Lymphoma is listed among the neoplasias with a high risk of venous thromboembolism (VTE). Risk factors for VTE appear to differ from risk factors in solid tumors. We review the literature of the last 20 years for reports identifying these risk factors in cohorts consisting exclusively of lymphoma patients. We selected 25 publications. The most frequent studies were analyses of retrospective single-center cohorts. We also included two reports of pooled analyses of clinical trials, two meta-analyses, two analyses of patient registries, and three analyses of population-based databases. The VTE risk is the highest upfront during the first two months after lymphoma diagnosis and decreases over time. This upfront risk may be related to tumor burden and the start of chemotherapy as contributing factors. Factors consistently reported as VTE risk factors are aggressive histology, a performance status ECOG ≥ 2 leading to increased immobility, more extensive disease, and localization to particular sites, such as central nervous system (CNS) and mediastinal mass. Association between laboratory values that are part of risk assessment models in solid tumors and VTE risk in lymphomas are very inconsistent. Recently, VTE risk scores for lymphoma were developed that need further validation, before they can be used for risk stratification and primary prophylaxis. Knowledge of VTE risk factors in lymphomas may help in the evaluation of the individual risk-benefit ratio of prophylaxis and help to design prospective studies on primary prophylaxis in lymphoma.

Download Full-text

Highly elevated polygenic risk scores are better predictors of myocardial infarction risk early in life than later

Genome Medicine ◽

10.1186/s13073-021-00828-8 ◽

2021 ◽

Vol 13 (1) ◽

Author(s):

Monica Isgut ◽

Jimeng Sun ◽

Arshed A. Quyyumi ◽

Greg Gibson

Keyword(s):

Risk Factors ◽

Myocardial Infarction ◽

Cardiovascular Risk ◽

Risk Prediction ◽

Area Under The Curve ◽

Later Life ◽

European Ancestry ◽

Risk Scores ◽

Polygenic Risk ◽

Conventional Risk Factors

Abstract Background Several polygenic risk scores (PRS) have been developed for cardiovascular risk prediction, but the additive value of including PRS together with conventional risk factors for risk prediction is questionable. This study assesses the clinical utility of including four PRS generated from 194, 46K, 1.5M, and 6M SNPs, along with conventional risk factors, to predict risk of ischemic heart disease (IHD), myocardial infarction (MI), and first MI event on or before age 50 (early MI). Methods A cross-validated logistic regression (LR) algorithm was trained either on ~ 440K European ancestry individuals from the UK Biobank (UKB), or the full UKB population, including as features different combinations of conventional established-at-birth risk factors (ancestry, sex) and risk factors that are non-fixed over an individual’s lifespan (age, BMI, hypertension, hyperlipidemia, diabetes, smoking, family history), with and without also including PRS. The algorithm was trained separately with IHD, MI, and early MI as prediction labels. Results When LR was trained using risk factors established-at-birth, adding the four PRS significantly improved the area under the curve (AUC) for IHD (0.62 to 0.67) and MI (0.67 to 0.73), as well as for early MI (0.70 to 0.79). When LR was trained using all risk factors, adding the four PRS only resulted in a significantly higher disease prevalence in the 98th and 99th percentiles of both the IHD and MI scores. Conclusions PRS improve cardiovascular risk stratification early in life when knowledge of later-life risk factors is unavailable. However, by middle age, when many risk factors are known, the improvement attributed to PRS is marginal for the general population.

Download Full-text

Deep Neural Network Analysis of Clinical Variables Predicts Escalated Care in COVID-19 Patients

10.21203/rs.3.rs-73664/v1 ◽

2020 ◽

Author(s):

Joyce Lu ◽

Benjamin Musheyev ◽

Qi Peng ◽

Tim Duong

Keyword(s):

Neural Network ◽

Deep Learning ◽

Laboratory Tests ◽

Deep Neural Network ◽

Vital Signs ◽

Area Under The Curve ◽

Blood Gases ◽

Characteristic Analysis ◽

Clinical Variables ◽

Icu Admission

Abstract This study sought to identify the most important clinical variables that can be used to determine which COVID-19 patients will need escalated care early on using deep-learning neural networks. Analysis was performed on hospitalized COVID-19 patients between February 7, 2020 and May 4, 2020 in Stony Brook Hospital. Demographics, comorbidities, laboratory tests, vital signs, and blood gases were collected. We compared data obtained at the time in emergency department and the time of intensive care unit (ICU) upgrade of: i) COVID-19 patients admitted to the general floor (N=1203) versus those directly admitted to ICU (N=104), and ii) patients not upgraded to ICU (N=979) versus those upgraded to the ICU (N=224) from the general floor. A deep neural network algorithm was used to predict ICU admission, with 80% training and 20% testing. Prediction performance used area under the curve (AUC) of the receiver operating characteristic analysis (ROC). We found that C-reactive protein, lactate dehydrogenase, creatinine, white-blood cell count, D-dimer, and lymphocyte count showed temporal divergence between patients were upgraded to ICU compared to those were not. The deep learning predictive model ranked essentially the same set of laboratory variables to be important predictors of needing ICU care. The AUC for predicting ICU admission was 0.782±0.013 for the test dataset. Adding vital sign and blood-gas data improved AUC (0.861±0.018). This study identified a few laboratory tests that were predictive of escalated care. This work could help frontline physicians to anticipate downstream ICU needs to more effectively allocate healthcare resources.

Download Full-text

Subclinical hypothyroidism in addition to common risk scores for prediction of cardiovascular disease: a 10-year community-based cohort study

Acta Endocrinologica ◽

10.1530/eje-14-0464 ◽

2014 ◽

Vol 171 (5) ◽

pp. 649-657 ◽

Cited By ~ 8

Author(s):

Tae Hyuk Kim ◽

Hoon Sung Choi ◽

Ji Cheol Bae ◽

Jae Hoon Moon ◽

Hyung-Kwan Kim ◽

...

Keyword(s):

Risk Factors ◽

Cardiovascular Disease ◽

Risk Score ◽

Subclinical Hypothyroidism ◽

Area Under The Curve ◽

Risk Scores ◽

Net Reclassification Improvement ◽

Traditional Risk Factors ◽

Serum Tsh ◽

Tsh Levels

ObjectiveThis study was carried out to determine whether serum TSH levels improve the prediction of cardiovascular risk in addition to common clinical risk scores, given the association between subclinical hypothyroidism (SCH) and cardiovascular disease (CVD).DesignWe carried out an observational study in a prospective cohort.MethodsThe study included a total of 344 SCH and 2624 euthyroid participants aged over 40 years and who were without previously recorded CVDs were included in this study analysis. We measured thyroid function and traditional risk factors at baseline and estimated the 10-year cumulative incidence of CVD in a gender-stratified analysis.ResultsDuring 10 years of follow-up, 251 incident cardiovascular events were recorded. The elevation of serum TSH levels significantly increased the CV risk independent of conventional risk factors in men. In the atherosclerotic CVD (ASCVD) risk score or the Reynolds risk score (RRS) model, the addition of serum TSH levels had no effect on model discrimination as measured by the area under the curve in either women or men. Adding serum TSH did not improve the net reclassification improvement in either women (3.48% (P=0.29) in the ASCVD, −0.89% (P=0.75) in the RRS, respectively) or men (−1.12% (P=0.69), 3.45% (P=0.20), respectively) and only mildly affected the integrated discrimination Improvement in the ASCVD-adjusted model (0.30% in women and 0.42% in men, both P=0.05).ConclusionsIn the context of common risk scoring models, the additional assessment of serum TSH levels provided little incremental benefit for the prediction of CV risk.

Download Full-text

Risk Factors for Bleeding during Treatment of Acute Venous Thromboembolism

Thrombosis and Haemostasis ◽

10.1055/s-0038-1650643 ◽

1996 ◽

Vol 76 (05) ◽

pp. 682-688 ◽

Cited By ~ 33

Author(s):

Jos P J Wester ◽

Harold W de Valk ◽

Karel H Nieuwenhuis ◽

Catherine B Brouwer ◽

Yolanda van der Graaf ◽

...

Keyword(s):

Risk Factors ◽

Venous Thromboembolism ◽

Surface Area ◽

Body Surface Area ◽

Body Surface ◽

Small Body ◽

Bleeding Risk ◽

Risk Scores ◽

Risk Of Bleeding ◽

Acute Venous Thromboembolism

Summary Objective: Identification of risk factors for bleeding and prospective evaluation of two bleeding risk scores in the treatment of acute venous thromboembolism. Design: Secondary analysis of a prospective, randomized, assessor-blind, multicenter clinical trial. Setting: One university and 2 regional teaching hospitals. Patients: 188 patients treated with heparin or danaparoid for acute venous thromboembolism. Measurements: The presenting clinical features, the doses of the drugs, and the anticoagulant responses were analyzed using univariate and multivariate logistic regression analysis in order to evaluate prognostic factors for bleeding. In addition, the recently developed Utrecht bleeding risk score and Landefeld bleeding risk index were evaluated prospectively. Results: Major bleeding occurred in 4 patients (2.1%) and minor bleeding in 101 patients (53.7%). For all (major and minor combined) bleeding, body surface area ≤2 m2 (odds ratio 2.3, 95% Cl 1.2-4.4; p = 0.01), and malignancy (odds ratio 2.4, 95% Cl 1.1-4.9; p = 0.02) were confirmed to be independent risk factors. An increased treatment-related risk of bleeding was observed in patients treated with high doses of heparin, independent of the concomitant activated partial thromboplastin time ratios. Both bleeding risk scores had low diagnostic value for bleeding in this sample of mainly minor bleeders. Conclusions: A small body surface area and malignancy were associated with a higher frequency of bleeding. The bleeding risk scores merely offer the clinician a general estimation of the risk of bleeding. In patients with a small body surface area or in patients with malignancy, it may be of interest to study whether limited dose reduction of the anticoagulant drug may cause less bleeding without affecting efficacy.

Download Full-text

Neural Network Model to Calculate the Creep Data Using Size

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse.v7i8.60 ◽

2017 ◽

Vol 7 (8) ◽

pp. 257

Author(s):

Seetharam .K ◽

Sharana Basava Gowda ◽

. Varadaraj

Keyword(s):

Neural Network ◽

Risk Factors ◽

Software Engineering ◽

Network Model ◽

Neural Network Model ◽

Software Metrics ◽

Creep Data ◽

Engineering Software ◽

Function Points ◽

Different Levels

In Software engineering software metrics play wide and deeper scope. Many projects fail because of risks in software engineering development[1]t. Among various risk factors creeping is also one factor. The paper discusses approximate volume of creeping requirements that occur after the completion of the nominal requirements phase. This is using software size measured in function points at four different levels. The major risk factors are depending both directly and indirectly associated with software size of development. Hence It is possible to predict risk due to creeping cause using size.

Download Full-text