scholarly journals A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Negar Farzaneh ◽  
Craig A. Williamson ◽  
Jonathan Gryak ◽  
Kayvan Najarian
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Domain Knowledge ◽  
Characteristic Curve ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Learning Framework ◽  
Diagnosis And Prognosis ◽  
Learning Classifier

AbstractPrognosis of the long-term functional outcome of traumatic brain injury is essential for personalized management of that injury. Nonetheless, accurate prediction remains unavailable. Although machine learning has shown promise in many fields, including medical diagnosis and prognosis, such models are rarely deployed in real-world settings due to a lack of transparency and trustworthiness. To address these drawbacks, we propose a machine learning-based framework that is explainable and aligns with clinical domain knowledge. To build such a framework, additional layers of statistical inference and human expert validation are added to the model, which ensures the predicted risk score’s trustworthiness. Using 831 patients with moderate or severe traumatic brain injury to build a model using the proposed framework, an area under the receiver operating characteristic curve (AUC) and accuracy of 0.8085 and 0.7488 were achieved, respectively, in determining which patients will experience poor functional outcomes. The performance of the machine learning classifier is not adversely affected by the imposition of statistical and domain knowledge “checks and balances”. Finally, through a case study, we demonstrate how the decision made by a model might be biased if it is not audited carefully.

scholarly journals Machine learning-based dynamic mortality prediction after traumatic brain injury

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Rahul Raj ◽  
Teemu Luostarinen ◽  
Eetu Pursiainen ◽  
Jussi P. Posti ◽  
Riikka S. K. Takala ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Cross Validation ◽  
Characteristic Curve ◽  
Mortality Prediction ◽  
Internal Validation ◽  
Middle Income ◽  
Middle Income Countries ◽  
Validation Technique

AbstractOur aim was to create simple and largely scalable machine learning-based algorithms that could predict mortality in a real-time fashion during intensive care after traumatic brain injury. We performed an observational multicenter study including adult TBI patients that were monitored for intracranial pressure (ICP) for at least 24 h in three ICUs. We used machine learning-based logistic regression modeling to create two algorithms (based on ICP, mean arterial pressure [MAP], cerebral perfusion pressure [CPP] and Glasgow Coma Scale [GCS]) to predict 30-day mortality. We used a stratified cross-validation technique for internal validation. Of 472 included patients, 92 patients (19%) died within 30 days. Following cross-validation, the ICP-MAP-CPP algorithm’s area under the receiver operating characteristic curve (AUC) increased from 0.67 (95% confidence interval [CI] 0.60–0.74) on day 1 to 0.81 (95% CI 0.75–0.87) on day 5. The ICP-MAP-CPP-GCS algorithm’s AUC increased from 0.72 (95% CI 0.64–0.78) on day 1 to 0.84 (95% CI 0.78–0.90) on day 5. Algorithm misclassification was seen among patients undergoing decompressive craniectomy. In conclusion, we present a new concept of dynamic prognostication for patients with TBI treated in the ICU. Our simple algorithms, based on only three and four main variables, discriminated between survivors and non-survivors with accuracies up to 81% and 84%. These open-sourced simple algorithms can likely be further developed, also in low and middle-income countries.

A traumatic brain injury prognostic model to support in-hospital triage in a low-income country: a machine learning–based approach

2020 ◽  
Vol 132 (6) ◽  
pp. 1961-1969 ◽  
Author(s):  
Thiago Augusto Hernandes Rocha ◽  
Cyrus Elahi ◽  
Núbia Cristina da Silva ◽  
Francis M. Sakita ◽  
Anthony Fuller ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Decision Support ◽  
Brain Injury ◽  
Clinical Decision Support ◽  
Prognostic Model ◽  
Decision Support Tool ◽  
Clinical Decision ◽  
Support Tool ◽  
Clinical Decision Support Tool

OBJECTIVETraumatic brain injury (TBI) is a leading cause of death and disability worldwide, with a disproportionate burden of this injury on low- and middle-income countries (LMICs). Limited access to diagnostic technologies and highly skilled providers combined with high patient volumes contributes to poor outcomes in LMICs. Prognostic modeling as a clinical decision support tool, in theory, could optimize the use of existing resources and support timely treatment decisions in LMICs. The objective of this study was to develop a machine learning–based prognostic model using data from Kilimanjaro Christian Medical Centre in Moshi, Tanzania.METHODSThis study is a secondary analysis of a TBI data registry including 3138 patients. The authors tested nine different machine learning techniques to identify the prognostic model with the greatest area under the receiver operating characteristic curve (AUC). Input data included demographics, vital signs, injury type, and treatment received. The outcome variable was the discharge score on the Glasgow Outcome Scale–Extended.RESULTSThe AUC for the prognostic models varied from 66.2% (k-nearest neighbors) to 86.5% (Bayesian generalized linear model). An increasing Glasgow Coma Scale score, increasing pulse oximetry values, and undergoing TBI surgery were predictive of a good recovery, while injuries suffered from a motor vehicle crash and increasing age were predictive of a poor recovery.CONCLUSIONSThe authors developed a TBI prognostic model with a substantial level of accuracy in a low-resource setting. Further research is needed to externally validate the model and test the algorithm as a clinical decision support tool.

Machine Learning for Prediction of Mortality and Unfavorable Outcome in Traumatic Brain Injury: A CENTER-TBI Study

2019 ◽  
Author(s):  
Benjamin Gravesteijn ◽  
Daan Nieboer ◽  
Ari Ercole ◽  
Hester F. Lingsma ◽  
David Nelson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Unfavorable Outcome ◽  
Prediction Of Mortality

scholarly journals Assessment of White Matter Injury and Outcome in Severe Brain Trauma

2012 ◽  
Vol 117 (6) ◽  
pp. 1300-1310 ◽  
Author(s):  
Damien Galanaud ◽  
Vincent Perlbarg ◽  
Rajiv Gupta ◽  
Robert D. Stevens ◽  
Paola Sanchez ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Clinical Trials ◽  
Brain Injury ◽  
White Matter ◽  
Receiver Operating Characteristic Curve ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Unfavorable Outcome ◽  
Operating Characteristic Curve

Background Existing methods to predict recovery after severe traumatic brain injury lack accuracy. The aim of this study is to determine the prognostic value of quantitative diffusion tensor imaging (DTI). Methods In a multicenter study, the authors prospectively enrolled 105 patients who remained comatose at least 7 days after traumatic brain injury. Patients underwent brain magnetic resonance imaging, including DTI in 20 preselected white matter tracts. Patients were evaluated at 1 yr with a modified Glasgow Outcome Scale. A composite DTI score was constructed for outcome prognostication on this training database and then validated on an independent database (n=38). DTI score was compared with the International Mission for Prognosis and Analysis of Clinical Trials Score. Results Using the DTI score for prediction of unfavorable outcome on the training database, the area under the receiver operating characteristic curve was 0.84 (95% CI: 0.75-0.91). The DTI score had a sensitivity of 64% and a specificity of 95% for the prediction of unfavorable outcome. On the validation-independent database, the area under the receiver operating characteristic curve was 0.80 (95% CI: 0.54-0.94). On the training database, reclassification methods showed significant improvement of classification accuracy (P < 0.05) compared with the International Mission for Prognosis and Analysis of Clinical Trials score. Similar results were observed on the validation database. Conclusions White matter assessment with quantitative DTI increases the accuracy of long-term outcome prediction compared with the available clinical/radiographic prognostic score.

A Machine Learning Approach for Predicting Real-time Risk of Intraoperative Hypotension in Traumatic Brain Injury

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Shara I. Feld ◽  
Daniel S. Hippe ◽  
Ljubomir Miljacic ◽  
Nayak L. Polissar ◽  
Shu-Fang Newman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Real Time ◽  
Learning Approach ◽  
Intraoperative Hypotension ◽  
Machine Learning Approach

Prognostic Factors for Persistent Symptoms in Adults With Mild Traumatic Brain Injury: an Overview of Systematic Reviews

2021 ◽  
Author(s):  
Julien Déry ◽  
Béatrice Ouellet ◽  
Élaine de Guise ◽  
Ève-Line Bussières ◽  
Marie-Eve Lamontagne
Keyword(s):  
Traumatic Brain Injury ◽  
Prognostic Factors ◽  
Brain Injury ◽  
Mild Traumatic Brain Injury ◽  
Systematic Reviews ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Persistent Symptoms ◽  
Wide Range ◽  
Overview Of Systematic Reviews

Abstract Background: Mild traumatic brain injury (mTBI) is an increasing public health problem, because of its persistent symptoms and several functional consequences. Understanding the prognosis of a condition is an important component of clinical decision-making and can help to guide prevention of persistent symptoms following mTBI. Prognosis of mTBI has stimulated several empirical primary research papers and many systematic reviews leading to the identification of a wide range of factors. We aim to synthesize these factors to get a better understanding of their breadth and scope.Methods: We conducted an overview of systematic reviews. We searched in databases systematic reviews synthesizing evidence about prognosis of persistent symptoms after mTBI in the adult population. Two reviewers independently screened all references and selected eligible reviews based on eligibility criteria. They extracted relevant information using an extraction grid. They also rated independently the risk of bias using the ROBIS tool. We synthesized evidence into a comprehensive conceptual map to facilitate the understanding of prognostic factors that have an impact on persistent post-concussion symptoms.Results: From the 3857 references retrieved in database search, we included 25 systematic reviews integrating the results of 312 primary articles published between 1957 and 2019. We examined 35 prognostic factors from the systematics reviews. No single prognostic factor demonstrated convincing and conclusive results. However, age, sex and multiple concussions showed an affirmatory association with persistent post-concussion outcomes in systematic reviews.Conclusion: We highlighted the need of a comprehensive picture of prognostic factors related to persistent post-concussion symptoms. We believe that these prognostic factors would guide clinical decision and research related to prevention and intervention regarding persistent post-concussion symptoms.Systematic review registration: PROSPERO CRD42020176676

scholarly journals Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models

PLoS ONE ◽  
2018 ◽  
Vol 13 (11) ◽  
pp. e0207192 ◽  
Author(s):  
Cheng-Shyuan Rau ◽  
Pao-Jen Kuo ◽  
Peng-Chen Chien ◽  
Chun-Ying Huang ◽  
Hsiao-Yun Hsieh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traumatic Brain Injury ◽  
Brain Injury ◽  
Severe Traumatic Brain Injury ◽  
Mortality Prediction ◽  
Learning Models ◽  
Machine Learning Models

GUESS: projecting machine learning scores to well-calibrated probability estimates for clinical decision-making

2018 ◽  
Vol 35 (14) ◽  
pp. 2458-2465 ◽  
Author(s):  
Johanna Schwarz ◽  
Dominik Heider
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
State Of The Art ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Calibration Method ◽  
Probability Estimates ◽  
Calibration Methods ◽  
Novel Method

Abstract Motivation Clinical decision support systems have been applied in numerous fields, ranging from cancer survival toward drug resistance prediction. Nevertheless, clinical decision support systems typically have a caveat: many of them are perceived as black-boxes by non-experts and, unfortunately, the obtained scores cannot usually be interpreted as class probability estimates. In probability-focused medical applications, it is not sufficient to perform well with regards to discrimination and, consequently, various calibration methods have been developed to enable probabilistic interpretation. The aims of this study were (i) to develop a tool for fast and comparative analysis of different calibration methods, (ii) to demonstrate their limitations for the use on clinical data and (iii) to introduce our novel method GUESS. Results We compared the performances of two different state-of-the-art calibration methods, namely histogram binning and Bayesian Binning in Quantiles, as well as our novel method GUESS on both, simulated and real-world datasets. GUESS demonstrated calibration performance comparable to the state-of-the-art methods and always retained accurate class discrimination. GUESS showed superior calibration performance in small datasets and therefore may be an optimal calibration method for typical clinical datasets. Moreover, we provide a framework (CalibratR) for R, which can be used to identify the most suitable calibration method for novel datasets in a timely and efficient manner. Using calibrated probability estimates instead of original classifier scores will contribute to the acceptance and dissemination of machine learning based classification models in cost-sensitive applications, such as clinical research. Availability and implementation GUESS as part of CalibratR can be downloaded at CRAN.

Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

2017 ◽  
Vol 25 (3) ◽  
pp. 811-827 ◽  
Author(s):  
Dimitris Spathis ◽  
Panayiotis Vlamos
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Random Forest ◽  
Pulmonary Disease ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Forced Expiratory Volume ◽  
Random Forest Classifier ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease

This study examines the clinical decision support systems in healthcare, in particular about the prevention, diagnosis and treatment of respiratory diseases, such as Asthma and chronic obstructive pulmonary disease. The empirical pulmonology study of a representative sample (n = 132) attempts to identify the major factors that contribute to the diagnosis of these diseases. Machine learning results show that in chronic obstructive pulmonary disease’s case, Random Forest classifier outperforms other techniques with 97.7 per cent precision, while the most prominent attributes for diagnosis are smoking, forced expiratory volume 1, age and forced vital capacity. In asthma’s case, the best precision, 80.3 per cent, is achieved again with the Random Forest classifier, while the most prominent attribute is MEF2575.

Sign in / Sign up

Export Citation Format

Share Document