A review of evidence of health benefit from artificial neural networks in medical intervention

Lisboa, Paulo J. G.

doi:10.1016/s0893-6080(01)00111-3

Cited by 410 publications

(225 citation statements)

References 176 publications

Supporting

Mentioning

216

Contrasting

Unclassified

Order By: Relevance

“…Indeed, neural networks have been used to analyze ICU patient data to determine outcomes for critically ill patients (18). Neural networks have been successfully applied in several studies that have measured a number of clinical parameters and then predicted outcomes successfully following the development of sepsis (18,25). Since we have created models based on patient data gained before the diagnosis of sepsis, our studies extend the use of neural networks from a tool for sepsis prognosis to an aid for the prediction of sepsis.…”

Section: Discussionmentioning

confidence: 99%

Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients

Lukaszewski

Yates

Jackson

et al. 2008

Clin Vaccine Immunol

View full text Add to dashboard Cite

Postoperative or posttraumatic sepsis remains one of the leading causes of morbidity and mortality in hospital populations, especially in populations in intensive care units (ICUs). Central to the successful control of sepsis-associated infections is the ability to rapidly diagnose and treat disease. The ability to identify sepsis patients before they show any symptoms would have major benefits for the health care of ICU patients. For this study, 92 ICU patients who had undergone procedures that increased the risk of developing sepsis were recruited upon admission. Blood samples were taken daily until either a clinical diagnosis of sepsis was made or until the patient was discharged from the ICU. In addition to standard clinical and laboratory parameter testing, the levels of expression of interleukin-1␤ (IL-1␤), IL-6, IL-8, and IL-10, tumor necrosis factor-␣, FasL, and CCL2 mRNA were also measured by real-time reverse transcriptase PCR. The results of the analysis of the data using a nonlinear technique (neural network analysis) demonstrated discernible differences prior to the onset of overt sepsis. Neural networks using cytokine and chemokine data were able to correctly predict patient outcomes in an average of 83.09% of patient cases between 4 and 1 days before clinical diagnosis with high sensitivity and selectivity (91.43% and 80.20%, respectively). The neural network also had a predictive accuracy of 94.55% when data from 22 healthy volunteers was analyzed in conjunction with the ICU patient data. Our observations from this pilot study indicate that it may be possible to predict the onset of sepsis in a mixed patient population by using a panel of just seven biomarkers.

show abstract

Section: Discussionmentioning

confidence: 99%

Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients

Lukaszewski

Yates

Jackson

et al. 2008

Clin Vaccine Immunol

View full text Add to dashboard Cite

show abstract

“…Conversely, ANNs have been considered "black boxes" because the weights of the connections between the nodes of the different layers have no clear interpretation, i.e. relative importance is implicit in the combination of connection weights (24). However, this is more of a numerical than a fundamental issue.…”

Section: Discussionmentioning

confidence: 99%

Predicting Extubation Outcome in Preterm Newborns: A Comparison of Neural Networks with Clinical Expertise and Statistical Modeling

et al. 2004

View full text Add to dashboard Cite

Even though ventilator technology and monitoring of premature infants has improved immensely over the past decades, there are still no standards for weaning and determining optimal extubation time for those infants. Approximately 30% of intubated preterm infants will fail attempted extubation, requiring reintubation and resuming of mechanical ventilation. A machine-learning approach using artificial neural networks (ANNs) to aid in extubation decision making is hereby proposed. Using expert opinion, 51 variables were identified as being relevant for the decision of whether to extubate an infant who is on mechanical ventilation. The data on 183 premature infants, born between 1999 and 2002, were collected by review of medical charts. The ANN extubation model was compared with alternative statistical modeling using multivariate logistic regression and also with the clinician's own predictive insight using sensitivity analysis and receiver operating characteristic curves. The optimal ANN model used 13 parameters and achieved an area under the receiver operating characteristic curve of 0.87 (out-of-sample validation), comparing favorably with multivariate logistic regression. It also compared well with the clinician's expertise, which raises the possibility of being useful as an automated alert tool. Because an ANN learns directly from previous data obtained in the institution where it is to be used, this makes it particularly amenable for application to evidence-based medicine. Given the variety of practices and equipment being used in different hospitals, this may be particularly relevant in the context of caring for preterm newborns who are on mechanical ventilation. Despite many technological advances over the past decade, predicting the ideal time point for extubation in premature infants who are on mechanical ventilation requires excellent diagnostic skills and remains a difficult task. A recently published study of the accuracy of clinical assessment of mortality risk in the neonatal intensive care unit found that the clinical predictions, in general, were unreliable and became increasingly unreliable with increasing number of days of life (1). Determining the optimal time point for extubation is crucial to minimize infants' time on artificial ventilation, thus minimizing their risk of developing barotrauma (caused by high pressures in the lung), retinopathy (caused by high arterial oxygen), and subsequent bronchopulmonary dysplasia or chronic lung disease (2). Complicating the decision to extubate, however, is the smaller risk associated with having to re-intubate-subjecting the infants to subsequent increases of ventilatory support as a result of alveolar collapse or atelectasis. These risks could be reduced by use of an automated prediction system that could alert the neonatal intensive care unit staff to potential extubations.Over the past decade, data mining by machine-learning tools to aid in clinical decision making has come of age. In partic-

show abstract

“…Neural networks lack centralized control in the classical sense, since all the interconnected processing elements change or ''adapt'' simultaneously with the flow of information and adaptive rules [41][42][43]. Several reviews on ANN have been published recently [41,[43][44][45][46][47][48][49][50]. Although there are several types of neural networks, multilayer perceptron is the most commonly used network.…”

Section: What Is An Artificial Neural Network?mentioning

confidence: 99%

Models for prediction of mortality from cirrhosis with special reference to artificial neural network: a critical review

Ghoshal

Das

2007

Hepatol Int

View full text Add to dashboard Cite

Prediction of mortality of patients with cirrhosis of liver, a common and potentially fatal disease, is important for timely listing of patients for liver transplantation. The Child-Pugh scoring system has been widely used for predicting the outcome of liver cirrhosis. The Model for End-Stage Liver Disease (MELD) score has recently become popular for prediction of short-term mortality for organ allocation. A few studies that evaluated artificial neural network (ANN)-based model for prediction of outcome of cirrhosis of liver in terms of mortality have consistently shown it to be superior to Child-Pugh scoring and logistic regression-based models; it is worth noting that MELD score is also derived using the logistic regression model. Due to the inherent ability of neural network-based systems in identifying complex nonlinear interactions, ANN-based models are expected to perform better than most linear models, such as regression-based models. More studies are needed on ANN-based models for prediction of mortality of patients with cirrhosis of liver and its value in prioritization of organ allocation for treatment of patients with cirrhosis of liver.

show abstract

A review of evidence of health benefit from artificial neural networks in medical intervention

Cited by 410 publications

References 176 publications

Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients

Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients

Predicting Extubation Outcome in Preterm Newborns: A Comparison of Neural Networks with Clinical Expertise and Statistical Modeling

Models for prediction of mortality from cirrhosis with special reference to artificial neural network: a critical review

Contact Info

Product

Resources

About