Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study

Wyk, Franco van; Khojandi, Anahita; Kamaleswaran, Rishikesan

doi:10.1109/jbhi.2019.2894570

Cited by 37 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While all of the identified studies in this review used some rules for splitting training and test data during model development (e.g. 80% training and 20% test data), only three studies validated the developed models on an independent, external dataset [19,23,25]. This hinders statements about generalizability or transferability.…”

Section: Model Performance and Validationmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Luz

Vollmer

Decruyenaere

et al. 2020

Clinical Microbiology and Infection

View full text Add to dashboard Cite

Background: Machine learning (ML) is increasingly being used in many areas of health care. Its use in infection management is catching up as identified in a recent review in this journal. We present here a complementary review to this work. Objectives: To support clinicians and researchers in navigating through the methodological aspects of ML approaches in the field of infection management. Sources: A Medline search was performed with the keywords artificial intelligence, machine learning, infection*, and infectious disease* for the years 2014e2019. Studies using routinely available electronic hospital record data from an inpatient setting with a focus on bacterial and fungal infections were included. Content: Fifty-two studies were included and divided into six groups based on their focus. These studies covered detection/prediction of sepsis (n ¼ 19), hospital-acquired infections (n ¼ 11), surgical site infections and other postoperative infections (n ¼ 11), microbiological test results (n ¼ 4), infections in general (n ¼ 2), musculoskeletal infections (n ¼ 2), and other topics (urinary tract infections, deep fungal infections, antimicrobial prescriptions; n ¼ 1 each). In total, 35 different ML techniques were used. Logistic regression was applied in 18 studies followed by random forest, support vector machines, and artificial neural networks in 18, 12, and seven studies, respectively. Overall, the studies were very heterogeneous in their approach and their reporting. Detailed information on data handling and software code was often missing. Validation on new datasets and/or in other institutions was rarely done. Clinical studies on the impact of ML in infection management were lacking. Implications: Promising approaches for ML use in infectious diseases were identified. But building trust in these new technologies will require improved reporting. Explainability and interpretability of the models used were rarely addressed and should be further explored. Independent model validation and clinical studies evaluating the added value of ML approaches are needed.

show abstract

Section: Model Performance and Validationmentioning

confidence: 99%

“…Predicted outcomes per research area Clinical definition of sepsis (e.g. the third international consensus definitions for sepsis and septic shockdSepsis-3)[14,19,25,49] …”

mentioning

confidence: 99%

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Luz

Vollmer

Decruyenaere

et al. 2020

Clinical Microbiology and Infection

View full text Add to dashboard Cite

show abstract

“…In this section, discussions of existing techniques are presented, which are used to predict the health status of patients using machine learning techniques. In addition, the advantages and limitations of the existing methods were also discussed in [13][14][15][16][17][18].…”

Section: Literature Reviewmentioning

confidence: 99%

“…However, the recognition for EF using LightGBM were still not very high. F. Van Wyk, A. Khojandi, and R. Kamaleswaran, [18] presented the hierarchical analysis of machine learning algorithms for improving the predictions of at-risk patients. In addition, a multi-layer machine learning approach was developed to analyze the high-frequency and continuous data.…”

Section: Literature Reviewmentioning

confidence: 99%

The Prediction of Diseases using Rough Set Theory with Recurrent Neural Network in Big Data Analytics

Talasila¹,

Madhubabu²,

Mahadasyam³

et al. 2020

IJIES

View full text Add to dashboard Cite

In a modern life, early healthcare prediction plays an important role to prevent the loss of life caused by prediction delays in treatment. Nowadays, the researchers focused on the Big data analysis, which is used to identify the future health status and provides an efficient way to overcome the issues in early prediction. Many researches are going on predictive analytics using machine learning techniques to provide a better decision making. Big data analysis provides great opportunities to predict future health status from health parameters and provide best outcomes. However, the data classification is one of the major challenging tasks due to noisy data or missing data in the dataset. Feature selection techniques play an important role in the classification process by removing irrelevant features from the extracted data. In this research work, the Rough Set Theory (RST) technique is used to select the most relevant features, which helps to provide the efficient classification of medical data and disease detection. The selected features are given as input to the Recurrent Neural Network (RNN) technique for disease prediction. The proposed method is also called as RST-RNN, where the experiments are carried out on the UCI machine learning repository dataset in terms of accuracy, f-measure, sensitivity and specificity. The results showed that the RST-RNN method achieved accuracy of 98.57%, where the existing Support Vector Machine (SVM) achieved 90.57% accuracy and Naive Bayes (NB) achieved 97.36% accuracy for heart disease dataset.

show abstract

“…In the United States, over 1.7 million adults are affected by sepsis, and more than 970,000 patients are admitted to hospitals because of sepsis each year. Sepsis both directly and indirectly contributes to more than 250,000 deaths annually, representing more than 50% of all hospital deaths [2,[4][5][6][7][8]. Unfortunately, these excruciating statistics have been exacerbated over recent years, as identified in a two-decade study on US hospitalizations, costs, and disease epidemiology.…”

Section: Introductionmentioning

confidence: 99%

Unpacking Prevalence and Dichotomy in Quick Sequential Organ Failure Assessment and Systemic Inflammatory Response Syndrome Parameters: Observational Data–Driven Approach Backed by Sepsis Pathophysiology

et al. 2020

View full text Add to dashboard Cite

Background Considering morbidity, mortality, and annual treatment costs, the dramatic rise in the incidence of sepsis and septic shock among intensive care unit (ICU) admissions in US hospitals is an increasing concern. Recent changes in the sepsis definition (sepsis-3), based on the quick Sequential Organ Failure Assessment (qSOFA), have motivated the international medical informatics research community to investigate score recalculation and information retrieval, and to study the intersection between sepsis-3 and the previous definition (sepsis-2) based on systemic inflammatory response syndrome (SIRS) parameters. Objective The objective of this study was three-fold. First, we aimed to unpack the most prevalent criterion for sepsis (for both sepsis-3 and sepsis-2 predictors). Second, we intended to determine the most prevalent sepsis scenario in the ICU among 4 possible scenarios for qSOFA and 11 possible scenarios for SIRS. Third, we investigated the multicollinearity or dichotomy among qSOFA and SIRS predictors. Methods This observational study was conducted according to the most recent update of Medical Information Mart for Intensive Care (MIMIC-III, Version 1.4), the critical care database developed by MIT. The qSOFA (sepsis-3) and SIRS (sepsis-2) parameters were analyzed for patients admitted to critical care units from 2001 to 2012 in Beth Israel Deaconess Medical Center (Boston, MA, USA) to determine the prevalence and underlying relation between these parameters among patients undergoing sepsis screening. We adopted a multiblind Delphi method to seek a rationale for decisions in several stages of the research design regarding handling missing data and outlier values, statistical imputations and biases, and generalizability of the study. Results Altered mental status in the Glasgow Coma Scale (59.28%, 38,854/65,545 observations) was the most prevalent sepsis-3 (qSOFA) criterion and the white blood cell count (53.12%, 17,163/32,311 observations) was the most prevalent sepsis-2 (SIRS) criterion confronted in the ICU. In addition, the two-factored sepsis criterion of high respiratory rate (≥22 breaths/minute) and altered mental status (28.19%, among four possible qSOFA scenarios besides no sepsis) was the most prevalent sepsis-3 (qSOFA) scenario, and the three-factored sepsis criterion of tachypnea, high heart rate, and high white blood cell count (12.32%, among 11 possible scenarios besides no sepsis) was the most prevalent sepsis-2 (SIRS) scenario in the ICU. Moreover, the absolute Pearson correlation coefficients were not significant, thereby nullifying the likelihood of any linear correlation among the critical parameters and assuring the lack of multicollinearity between the parameters. Although this further bolsters evidence for their dichotomy, the absence of multicollinearity cannot guarantee that two random variables are statistically independent. Conclusions Quantifying the prevalence of the qSOFA criteria of sepsis-3 in comparison with the SIRS criteria of sepsis-2, and understanding the underlying dichotomy among these parameters provides significant inferences for sepsis treatment initiatives in the ICU and informing hospital resource allocation. These data-driven results further offer design implications for multiparameter intelligent sepsis prediction in the ICU.

show abstract

Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study

Cited by 37 publications

References 32 publications

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

The Prediction of Diseases using Rough Set Theory with Recurrent Neural Network in Big Data Analytics

Unpacking Prevalence and Dichotomy in Quick Sequential Organ Failure Assessment and Systemic Inflammatory Response Syndrome Parameters: Observational Data–Driven Approach Backed by Sepsis Pathophysiology

Contact Info

Product

Resources

About