scholarly journals Early Prediction of Sepsis in the ICU using Machine Learning: A Systematic Review.

2020 ◽  
Author(s):  
Michael Moor ◽  
Bastian Rieck ◽  
Max Horn ◽  
Catherine Jutzeler ◽  
Karsten Borgwardt
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Quality Assessment ◽  
Biomarker Discovery ◽  
Learning Algorithms ◽  
Quality Criteria ◽  
Machine Learning Algorithms ◽  
Data Sources ◽  
Synthesis Methods ◽  
Early Prediction

Background: Sepsis is among the leading causes of death in intensive care units (ICU) worldwide and its recognition, particularly in the early stages of the disease, remains a medical challenge. The advent of an affluence of available digital health data has created a setting in which machine learning can be used for digital biomarker discovery, with the ultimate goal to advance the early recognition of sepsis. Objective: To systematically review and evaluate studies employing machine learning for the prediction of sepsis in the ICU. Data sources: Using Embase, Google Scholar, PubMed/Medline, Scopus, and Web of Science, we systematically searched the existing literature for machine learning-driven sepsis onset prediction for patients in the ICU. Study eligibility criteria: All peer-reviewed articles using machine learning for the prediction of sepsis onset in adult ICU patients were included. Studies focusing on patient populations outside the ICU were excluded. Study appraisal and synthesis methods: A systematic review was performed according to the PRISMA guidelines. Moreover, a quality assessment of all eligible studies was performed. Results: Out of 974 identified articles, 22 and 21 met the criteria to be included in the systematic review and quality assessment, respectively. A multitude of machine learning algorithms were applied to refine the early prediction of sepsis. The quality of the studies ranged from "poor" (satisfying less than 40% of the quality criteria) to "very good" (satisfying more than 90% of the quality criteria). The majority of the studies (n= 19, 86.4%) employed an offline training scenario combined with a horizon evaluation, while two studies implemented an online scenario (n= 2,9.1%). The massive inter-study heterogeneity in terms of model development, sepsis definition, prediction time windows, and outcomes precluded a meta-analysis. Last, only 2 studies provided publicly-accessible source code and data sources fostering reproducibility. Limitations: Articles were only eligible for inclusion when employing machine learning algorithms for the prediction of sepsis onset in the ICU. This restriction led to the exclusion of studies focusing on the prediction of septic shock, sepsis-related mortality, and patient populations outside the ICU. Conclusions and key findings: A growing number of studies employs machine learning to31optimise the early prediction of sepsis through digital biomarker discovery. This review, however, highlights several shortcomings of the current approaches, including low comparability and reproducibility. Finally, we gather recommendations how these challenges can be addressed before deploying these models in prospective analyses. Systematic review registration number: CRD42020200133

scholarly journals Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review

2021 ◽  
Vol 8 ◽  
Author(s):  
Michael Moor ◽  
Bastian Rieck ◽  
Max Horn ◽  
Catherine R. Jutzeler ◽  
Karsten Borgwardt
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Quality Assessment ◽  
Biomarker Discovery ◽  
Learning Algorithms ◽  
Quality Criteria ◽  
Machine Learning Algorithms ◽  
Data Sources ◽  
Synthesis Methods ◽  
Early Prediction

Background: Sepsis is among the leading causes of death in intensive care units (ICUs) worldwide and its recognition, particularly in the early stages of the disease, remains a medical challenge. The advent of an affluence of available digital health data has created a setting in which machine learning can be used for digital biomarker discovery, with the ultimate goal to advance the early recognition of sepsis.Objective: To systematically review and evaluate studies employing machine learning for the prediction of sepsis in the ICU.Data Sources: Using Embase, Google Scholar, PubMed/Medline, Scopus, and Web of Science, we systematically searched the existing literature for machine learning-driven sepsis onset prediction for patients in the ICU.Study Eligibility Criteria: All peer-reviewed articles using machine learning for the prediction of sepsis onset in adult ICU patients were included. Studies focusing on patient populations outside the ICU were excluded.Study Appraisal and Synthesis Methods: A systematic review was performed according to the PRISMA guidelines. Moreover, a quality assessment of all eligible studies was performed.Results: Out of 974 identified articles, 22 and 21 met the criteria to be included in the systematic review and quality assessment, respectively. A multitude of machine learning algorithms were applied to refine the early prediction of sepsis. The quality of the studies ranged from “poor” (satisfying ≤ 40% of the quality criteria) to “very good” (satisfying ≥ 90% of the quality criteria). The majority of the studies (n = 19, 86.4%) employed an offline training scenario combined with a horizon evaluation, while two studies implemented an online scenario (n = 2, 9.1%). The massive inter-study heterogeneity in terms of model development, sepsis definition, prediction time windows, and outcomes precluded a meta-analysis. Last, only two studies provided publicly accessible source code and data sources fostering reproducibility.Limitations: Articles were only eligible for inclusion when employing machine learning algorithms for the prediction of sepsis onset in the ICU. This restriction led to the exclusion of studies focusing on the prediction of septic shock, sepsis-related mortality, and patient populations outside the ICU.Conclusions and Key Findings: A growing number of studies employs machine learning to optimize the early prediction of sepsis through digital biomarker discovery. This review, however, highlights several shortcomings of the current approaches, including low comparability and reproducibility. Finally, we gather recommendations how these challenges can be addressed before deploying these models in prospective analyses.Systematic Review Registration Number: CRD42020200133.

scholarly journals Predicting infection and sepsis; what predictors have been used to train machine learning algorithms? A systematic review

2021 ◽  
Vol 29 (Supplement_1) ◽  
pp. i18-i18
Author(s):  
N Hassan ◽  
R Slight ◽  
D Weiand ◽  
A Vellinga ◽  
G Morgan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Systematic Review ◽  
Decision Making ◽  
Quality Assessment ◽  
Clinical Decision Making ◽  
Data Extraction ◽  
Learning Algorithms ◽  
Clinical Decision ◽  
Machine Learning Algorithms

Abstract Introduction Sepsis is a life-threatening condition that is associated with increased mortality. Artificial intelligence tools can inform clinical decision making by flagging patients who may be at risk of developing infection and subsequent sepsis and assist clinicians with their care management. Aim To identify the optimal set of predictors used to train machine learning algorithms to predict the likelihood of an infection and subsequent sepsis and inform clinical decision making. Methods This systematic review was registered in PROSPERO database (CRD42020158685). We searched 3 large databases: Medline, Cumulative Index of Nursing and Allied Health Literature, and Embase, using appropriate search terms. We included quantitative primary research studies that focused on sepsis prediction associated with bacterial infection in adult population (>18 years) in all care settings, which included data on predictors to develop machine learning algorithms. The timeframe of the search was 1st January 2000 till the 25th November 2019. Data extraction was performed using a data extraction sheet, and a narrative synthesis of eligible studies was undertaken. Narrative analysis was used to arrange the data into key areas, and compare and contrast between the content of included studies. Quality assessment was performed using Newcastle-Ottawa Quality Assessment scale, which was used to evaluate the quality of non-randomized studies. Bias was not assessed due to the non-randomised nature of the included studies. Results Fifteen articles met our inclusion criteria (Figure 1). We identified 194 predictors that were used to train machine learning algorithms to predict infection and subsequent sepsis, with 13 predictors used on average across all included studies. The most significant predictors included age, gender, smoking, alcohol intake, heart rate, blood pressure, lactate level, cardiovascular disease, endocrine disease, cancer, chronic kidney disease (eGFR<60ml/min), white blood cell count, liver dysfunction, surgical approach (open or minimally invasive), and pre-operative haematocrit < 30%. These predictors were used for the development of all the algorithms in the fifteen articles. All included studies used artificial intelligence techniques to predict the likelihood of sepsis, with average sensitivity 77.5±19.27, and average specificity 69.45±21.25. Conclusion The type of predictors used were found to influence the predictive power and predictive timeframe of the developed machine learning algorithm. Two strengths of our review were that we included studies published since the first definition of sepsis was published in 2001, and identified factors that can improve the predictive ability of algorithms. However, we note that the included studies had some limitations, with three studies not validating the models that they developed, and many tools limited by either their reduced specificity or sensitivity or both. This work has important implications for practice, as predicting the likelihood of sepsis can help inform the management of patients and concentrate finite resources to those patients who are most at risk. Producing a set of predictors can also guide future studies in developing more sensitive and specific algorithms with increased predictive time window to allow for preventive clinical measures.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

scholarly journals Machine Learning Algorithms in Cardiology Domain: A Systematic Review (Preprint)

2019 ◽  
Author(s):  
Georgy Kopanitsa ◽  
Aleksei Dudchenko ◽  
Matthias Ganzinger
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Search Strategy ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Learning System ◽  
Prisma Statement ◽  
Meta Analyses ◽  
Conference Papers ◽  
Huge Variety

BACKGROUND It has been shown in previous decades, that Machine Learning (ML) has a huge variety of possible implementations in medicine and can be very helpful. Neretheless, cardiovascular diseases causes about third of of all global death. Does ML work in cardiology domain and what is current progress in that regard? OBJECTIVE The review aims at (1) identifying studies where machine-learning algorithms were applied in the cardiology domain; (2) providing an overview based on identified literature of the state of the art of the ML algorithm applying in cardiology. METHODS For organizing this review, we have employed PRISMA statement. PRISMA is a set of items for reporting in systematic reviews and meta-analyses, focused on the reporting of reviews evaluating randomized trials, but can also be used as a basis for reporting systematic review. For the review, we have adopted PRISMA statement and have identified the following items: review questions, information sources, search strategy, selection criteria. RESULTS In total 27 scientific articles or conference papers written in English and reporting about implementation of an ML-method or algorithm in cardiology domain were included in this review. We have examined four aspects: aims of ML-systems, methods, datasets and evaluation metrics. CONCLUSIONS We suppose, this systematic review will be helpful for researchers developing machine-learning system for a medical domain and in particular for cardiology.

Machine Learning Approach to Forecast Work Zone Mobility using Probe Vehicle Data

2020 ◽  
Vol 2674 (9) ◽  
pp. 157-167
Author(s):  
Mohsen Kamyab ◽  
Stephen Remias ◽  
Erfan Najmi ◽  
Sanaz Rabinia ◽  
Jonathan M. Waddell
Keyword(s):  
Machine Learning ◽  
Traffic Congestion ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Work Zone ◽  
Data Sources ◽  
Work Zones ◽  
Probe Vehicle ◽  
Vehicle Data ◽  
Lane Closures

The aim of deploying intelligent transportation systems (ITS) is often to help engineers and operators identify traffic congestion. The future of ITS-based traffic management is the prediction of traffic conditions using ubiquitous data sources. There are currently well-developed prediction models for recurrent traffic congestion such as during peak hour. However, there is a need to predict traffic congestion resulting from non-recurring events such as highway lane closures. As agencies begin to understand the value of collecting work zone data, rich data sets will emerge consisting of historical work zone information. In the era of big data, rich mobility data sources are becoming available that enable the application of machine learning to predict mobility for work zones. The purpose of this study is to utilize historical lane closure information with supervised machine learning algorithms to forecast spatio-temporal mobility for future lane closures. Various traffic data sources were collected from 1,160 work zones on Michigan interstates between 2014 and 2017. This study uses probe vehicle data to retrieve a mobility profile for these historical observations, and uses these profiles to apply random forest, XGBoost, and artificial neural network (ANN) classification algorithms. The mobility prediction results showed that the ANN model outperformed the other models by reaching up to 85% accuracy. The objective of this research was to show that machine learning algorithms can be used to capture patterns for non-recurrent traffic congestion even when hourly traffic volume is not available.

Sign in / Sign up

Export Citation Format

Share Document