scholarly journals Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
José Castela Forte ◽  
Galiya Yeshmagambetova ◽  
Maureen L. van der Grinten ◽  
Bart Hiemstra ◽  
Thomas Kaufmann ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Mortality Risk ◽  
Clustering Algorithms ◽  
Kidney Injury ◽  
Risk Groups ◽  
Admission Diagnosis ◽  
Dutch Hospital ◽  
Cluster Membership

AbstractCritically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.

782-P: Machine Learning to Identify Diabetes Patients Initiating SGLT2i at High-Risk of Acute Kidney Injury

Diabetes ◽  
2021 ◽  
Vol 70 (Supplement 1) ◽  
pp. 782-P
Author(s):  
LANTING YANG ◽  
NICO GABRIEL ◽  
INMACULADA HERNANDEZ ◽  
ALMUT G. WINTERSTEIN ◽  
STEPHEN KIMMEL ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
High Risk ◽  
Kidney Injury ◽  
Diabetes Patients

scholarly journals Unraveling Patient Heterogeneity in ICU With Deep Embedded Clustering Using Co-morbidity, Clinical Examination, and Laboratory Data

2020 ◽  
Author(s):  
José Castela Forte ◽  
Galiya Yeshmagambetova ◽  
Maureen van der Grinten ◽  
Bart Hiemstra ◽  
Thomas Kaufmann ◽  
...  
Keyword(s):  
Critical Care ◽  
Clinical Examination ◽  
Mortality Risk ◽  
Clustering Algorithms ◽  
Laboratory Data ◽  
Trauma Patients ◽  
Disease Etiology ◽  
Cluster Membership ◽  
Co Morbidity ◽  
Patient Heterogeneity

Abstract Introduction Despite extensive research, the goal of unravelling patient heterogeneity in critical care remains largely unattained. Combining clustering analysis of routinely collected high-frequency data with the identification of features driving cluster separation may constitute a step towards improving patient characterization. Methods In this study, we analysed prospectively collected data from 743 patients including co-morbidities, clinical examination, and laboratory parameters. We compared four clustering methodologies – deep embedded clustering (DEC), hierarchical clustering with and without dynamic time warping, and k-means – and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values.Results DEC yielded better results compared to the traditional clustering algorithms, with the best Jaccard and entropy scores being achieved for 6 clusters. These clusters were characterized as medium to high co-morbidity patients with respiratory pathology and sepsis (cluster 1), patients with primarily acute and chronic cardiac conditions and surgical admission (cluster 2), patients with diverse disease etiology and poor outcomes (cluster 3), low co-morbidity neurological, neurosurgical, and trauma patients (cluster 4), medium co-morbidity patients with cardio-respiratory problems, and neuro-trauma patients with longer length of stay (cluster 5), and patients with sepsis and respiratory infections (cluster 6). All clusters differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury, and two clusters were categorized as having higher mortality risk, and one cluster as lower mortality risk. Conclusions This machine learning methodology, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses, and may help unravel patient heterogeneity in critical care.

scholarly journals Improving Multi-Tumor Biomarker Health Check-Up Tests with Machine Learning Algorithms

Cancers ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 1442 ◽  
Author(s):  
Hsin-Yao Wang ◽  
Chun-Hsien Chen ◽  
Steve Shi ◽  
Chia-Ru Chung ◽  
Ying-Hao Wen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cancer Screening ◽  
High Risk ◽  
Tumor Marker ◽  
Cross Validation ◽  
Medical Center ◽  
Risk Groups ◽  
Health Check ◽  
Tumor Biomarker ◽  
Substantial Impact

Background: Tumor markers are used to screen tens of millions of individuals worldwide at annual health check-ups, especially in East Asia. Machine learning (ML)-based algorithms that improve the diagnostic accuracy and clinical utility of these tests can have substantial impact leading to the early diagnosis of cancer. Methods: ML-based algorithms, including a cancer screening algorithm and a secondary organ of origin algorithm, were developed and validated using a large real world dataset (RWD) from asymptomatic individuals undergoing routine cancer screening at a Taiwanese medical center between May 2001 and April 2015. External validation was performed using data from the same period from a separate medical center. The data set included tumor marker values, age, and gender from 27,938 individuals, including 342 subsequently confirmed cancer cases. Results: Separate gender-specific cancer screening algorithms were developed. For men, a logistic regression-based algorithm outperformed single-marker and other ML-based algorithms, with a mean area under the receiver operating characteristic curve (AUROC) of 0.7654 in internal and 0.8736 in external cross validation. For women, a random forest-based algorithm attained a mean AUROC of 0.6665 in internal and 0.6938 in external cross validation. The median time to cancer diagnosis (TTD) in men was 451.5, 204.5, and 28 days for the mild, moderate, and high-risk groups, respectively; for women, the median TTD was 229, 132, and 125 days for the mild, moderate, and high-risk groups. A second algorithm was developed to predict the most likely affected organ systems for at-risk individuals. The algorithm yielded 0.8120 sensitivity and 0.6490 specificity for men, and 0.8170 sensitivity and 0.6750 specificity for women. Conclusions: ML-derived algorithms, trained and validated by using a RWD, can significantly improve tumor marker-based screening for multiple types of early stage cancers, suggest the tissue of origin, and provide guidance for patient follow-up.

Utilization patterns and clinical outcomes of rasburicase administration according to tumor risk stratification

2019 ◽  
Vol 26 (3) ◽  
pp. 529-535 ◽  
Author(s):  
Parisa R Khalighi ◽  
Kylee L Martens ◽  
Andrew A White ◽  
Shan Li ◽  
Emily Silgard ◽  
...  
Keyword(s):  
High Risk ◽  
Risk Group ◽  
Tumor Lysis Syndrome ◽  
Kidney Injury ◽  
Risk Groups ◽  
High Risk Group ◽  
Adherence To Guidelines ◽  
Tumor Lysis ◽  
Risk Patients ◽  
Utilization Patterns

Purpose Current guidelines for tumor lysis syndrome management recommend rasburicase for high-risk patients. Adherence to guidelines has not been well studied, and the correlation between uric acid reduction and clinically relevant outcomes, such as acute kidney injury, remains unclear. Our study aims to describe rasburicase utilization patterns and outcomes in cancer patients with varying risks for tumor lysis syndrome. Methods In this retrospective cohort study, we included cancer inpatients who received rasburicase for tumor lysis syndrome management at two affiliated academic hospitals from 2009 to 2015. Patients were classified by tumor lysis syndrome risk categories prior to drug administration. Primary outcomes included acute kidney injury incidence and renal recovery. Secondary outcomes included uric acid nadir, mortality, and hospital length-of-stay. Results Among 164 patients, 42 (26%) had high-, 63 (38%) had intermediate-, and 59 (36%) had low-risk for tumor lysis syndrome. A total of 94 patients (57%) had existing renal dysfunction prior to rasburicase use. This occurred more frequently in low- (68%) compared to intermediate- (57%) and high- (43%) risk patients ( p = 0.044). A greater proportion of patients in the high-risk group (78%) had renal recovery when compared to the intermediate- (61%) or low- (45%) risk groups ( p = 0.056). Despite a similar length of stay, the high-risk group had a significantly lower 30-day mortality (10%) when compared to intermediate- (25%) or low- (32%) risk groups ( p = 0.029). Conclusions Our results suggest that rasburicase may be frequently prescribed to treat hyperuricemia unrelated to tumor lysis syndrome in cancer patients. Improved education and adherence to guidelines may improve clinical and economic outcomes associated with rasburicase administration.

Identification of cardiovascular high-risk groups from dynamic retinal vessel signals using untargeted machine learning

2021 ◽  
Author(s):  
Stanislas Werfel ◽  
Roman Günthner ◽  
Alexander Hapfelmeier ◽  
Henner Hanssen ◽  
Konstantin Kotliar ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Retinal Vessel ◽  
Predictive Performance ◽  
Risk Groups ◽  
Mortality Prediction ◽  
Independent Components ◽  
Random Forest Models ◽  
Highly Correlated ◽  
Cv Disease

Abstract Aims Dynamic retinal vessel analysis (DVA) provides a non-invasive way to assess microvascular function in patients and potentially to improve predictions of individual cardiovascular (CV) risk. The aim of our study was to use untargeted machine learning on DVA in order to improve CV mortality prediction and identify corresponding response alterations. Methods and results We adopted a workflow consisting of noise reduction and extraction of independent components within DVA signals. Predictor performance was assessed in survival random forest models. Applying our technique to the prediction of all-cause mortality in a cohort of 214 haemodialysis patients resulted in the selection of a component which was highly correlated to maximal venous dilation following flicker stimulation (vMax), a previously identified predictor, confirming the validity of our approach. When fitting for CV mortality as the outcome of interest, a combination of three components derived from the arterial signal resulted in a marked improvement in predictive performance. Clustering analysis suggested that these independent components identified groups of patients with substantially higher CV mortality. Conclusion Our results provide a machine learning workflow to improve the predictive performance of DVA and identify groups of haemodialysis patients at high risk of CV mortality. Our approach may also prove to be promising for DVA signal analysis in other CV disease states.

scholarly journals Risk Prediction in Patients With Heart Failure With Preserved Ejection Fraction Using Gene Expression Data and Machine Learning

2021 ◽  
Vol 12 ◽  
Author(s):  
Liye Zhou ◽  
Zhifei Guo ◽  
Bijue Wang ◽  
Yongqing Wu ◽  
Zhi Li ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Heart Failure ◽  
High Risk ◽  
Ejection Fraction ◽  
Gene Expression Data ◽  
Risk Groups ◽  
Support Vector ◽  
Expression Data ◽  
Preserved Ejection Fraction

Heart failure with preserved ejection fraction (HFpEF) has become a major health issue because of its high mortality, high heterogeneity, and poor prognosis. Using genomic data to classify patients into different risk groups is a promising method to facilitate the identification of high-risk groups for further precision treatment. Here, we applied six machine learning models, namely kernel partial least squares with the genetic algorithm (GA-KPLS), the least absolute shrinkage and selection operator (LASSO), random forest, ridge regression, support vector machine, and the conventional logistic regression model, to predict HFpEF risk and to identify subgroups at high risk of death based on gene expression data. The model performance was evaluated using various criteria. Our analysis was focused on 149 HFpEF patients from the Framingham Heart Study cohort who were classified into good-outcome and poor-outcome groups based on their 3-year survival outcome. The results showed that the GA-KPLS model exhibited the best performance in predicting patient risk. We further identified 116 differentially expressed genes (DEGs) between the two groups, thus providing novel therapeutic targets for HFpEF. Additionally, the DEGs were enriched in Gene Ontology terms and Kyoto Encyclopedia of Genes and Genomes pathways related to HFpEF. The GA-KPLS-based HFpEF model is a powerful method for risk stratification of 3-year mortality in HFpEF patients.

scholarly journals Long-term safety of growth hormone treatment in childhood: Two large observational studies NordiNet ® IOS and ANSWER

2021 ◽  
Author(s):  
Lars Sävendahl ◽  
Michel Polak ◽  
Philippe Backeljauw ◽  
Joanne C Blair ◽  
Bradley S Miller ◽  
...  
Keyword(s):  
High Risk ◽  
Mortality Risk ◽  
Observational Studies ◽  
Risk Group ◽  
Risk Groups ◽  
Incidence Rates ◽  
Low Risk ◽  
Risk Category ◽  
Gh Treatment

Abstract Context GH treatment has a generally good safety profile; however, concerns of increased mortality risk in adulthood have been raised. Objective Assessing the long-term safety of GH treatment in clinical practice. Design Two multicenter longitudinal observational studies: NordiNet® International Outcome Study (2006–2016, Europe) and ANSWER Program (2002–2016, USA). Setting Data collected from 676 clinics. Patients Pediatric patients treated with GH, classified into three risk groups based on diagnosis. Intervention Daily GH treatment. Main Outcome Measures Incidence rates (events/1000 patient-years) of adverse drug reactions (ADRs), serious adverse events (SAEs), and serious ADRs, and their relationship to the GH dose. Results The combined studies comprised 37,702 patients (68.4% in low-risk, 27.5% in intermediate-risk, and 4.1% in high-risk groups) and 130,476 patient-years of exposure. The low-risk group included children born small for gestational age (SGA; 20.7%) and non-SGA children (e.g. with GH deficiency; 79.3%). Average GH dose up to the first adverse event (AE) decreased with increasing risk category. Patients without AEs received higher average GH doses than patients with >1 AE across all groups. A significant inverse relationship with GH dose was shown for ADR and SAE incidence rates in the low-risk group (P = 0.0029 and P = 0.0003, respectively) and the non-SGA subgroup (P = 0.0022 and P = 0.0015, respectively), and for SAEs in the intermediate- and high-risk groups (P = 0.0017 and P = 0.0480, respectively). Conclusions We observed no indication of increased mortality risk nor AE incidence related to GH dose in any risk group.

scholarly journals CT imaging-based machine learning model: a potential modality for predicting low-risk and high-risk groups of thymoma: “Impact of surgical modality choice”

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Ayten Kayi Cangir ◽  
Kaan Orhan ◽  
Yusuf Kahya ◽  
Hilal Özakıncı ◽  
Betül Bahar Kazak ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Risk Groups ◽  
Learning Model ◽  
Low Risk ◽  
Pathology Report ◽  
Histopathological Diagnosis ◽  
Gray Level ◽  
Long Run ◽  
Machine Learning Model

Abstract Introduction Radiomics methods are used to analyze various medical images, including computed tomography (CT), magnetic resonance, and positron emission tomography to provide information regarding the diagnosis, patient outcome, tumor phenotype, and the gene-protein signatures of various diseases. In low-risk group, complete surgical resection is typically sufficient, whereas in high-risk thymoma, adjuvant therapy is usually required. Therefore, it is important to distinguish between both. This study evaluated the CT radiomics features of thymomas to discriminate between low- and high-risk thymoma groups. Materials and methods In total, 83 patients with thymoma were included in this study between 2004 and 2019. We used the Radcloud platform (Huiying Medical Technology Co., Ltd.) to manage the imaging and clinical data and perform the radiomics statistical analysis. The training and validation datasets were separated by a random method with a ratio of 2:8 and 502 random seeds. The histopathological diagnosis was noted from the pathology report. Results Four machine-learning radiomics features were identified to differentiate a low-risk thymoma group from a high-risk thymoma group. The radiomics feature names were Energy, Zone Entropy, Long Run Low Gray Level Emphasis, and Large Dependence Low Gray Level Emphasis. Conclusions The results demonstrated that a machine-learning model and a multilayer perceptron classifier analysis can be used on CT images to predict low- and high-risk thymomas. This combination could be a useful preoperative method to determine the surgical approach for thymoma.

scholarly journals CT Imaging-based Machine Learning Model: A Potential Modality for Predicting Low-Risk and High-Risk Groups of Thymoma “Impact of surgical modality choice”

2021 ◽  
Author(s):  
Ayten KAYICANGIR ◽  
Kaan ORHAN ◽  
Yusuf KAHYA ◽  
Hilal ÖZAKINCI ◽  
Betül Bahar KAZAK ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Risk Groups ◽  
Learning Model ◽  
Low Risk ◽  
Pathology Report ◽  
Histopathological Diagnosis ◽  
Gray Level ◽  
Long Run ◽  
Machine Learning Model

Abstract IntroductionRadiomics has become a hot issue in the medical imaging field, particularly in cancer imaging. Radiomics methods are used to analyze various medical images, including computed tomography (CT), magnetic resonance, and positron emission tomography to provide information regarding the diagnosis, patient outcome, tumor phenotype, and the gene-protein signatures of various diseases.This study evaluated the CT radiomics features of thymomas to discriminate between low- and high-risk thymoma groups.Materials and MethodsIn total, 83 patients with thymoma were included in this study between 2004 and 2019. We used the Radcloud platform (Huiying Medical Technology Co., Ltd.) to manage the imaging and clinical data and perform the radiomics statistical analysis. The training and validation datasets were separated by a random method with a ratio of 2:8 and 502 random seeds. The histopathological diagnosis was noted from the pathology report.ResultsFour machine learning radiomics features were identified to differentiate a low-risk thymoma group from a high-risk thymoma group. The radiomics feature names were Energy, Zone Entropy, Long Run Low Gray Level Emphasis, and Large Dependence Low Gray Level Emphasis.ConclusionsThe results demonstrated that a machine-learning model and a multilayer perceptron classifier analysis can be used on CT images to predict low- and high-risk thymomas. This combination could be a useful preoperative method to determine the surgical approach for thymoma.

Sign in / Sign up

Export Citation Format

Share Document