A Comparison of Human and Machine-based Predictions of Successful Weaning from Mechanical Ventilation

Purpose. To evaluate the ability of an appropriately trained neural network to correctly interpret a set of weaning parameters to predict the liberation of a patient from mechanical ventilation, and to contrast these predictions with those of human experts restricted to the same limited set of physiologic data. Methods. For each set of weaning parameters, a prediction was made by multiple realizations of a neural network and six expert volunteers. Results. The percentage of correct predictions made by the neural network when the decision threshold was set to 0.5 (range 0-1) was 83.3 ± 4.2 (mean ± SD) and that for the experts was 83.3 ± 4.7. Predictions by the network when the threshold was 0.5 had a sensitivity of 0.83 and a specificity of 0.84, compared with 0.90 and 0.77, respectively, for the experts. However, sensitivity and specificity comparable to those of the human experts could be obtained by adjusting the decision threshold of the network predictor so that only the most clearly ventilator-dependent patients would not be given a trial of extubation. Conclusion. When both are restricted to the same limited set of patient data, appropriately trained neural networks can be as effective as human experts in predicting whether weaning from mechanical ventilation will be successful. Key words: mechanical ventilation; weaning; neural networks; decision analysis; respiratory failure. (Med Decis Making 2000;20:160-169)

[1]  D. Prezant,et al.  Maximal inspiratory pressure is not a reliable test of inspiratory muscle strength in mechanically ventilated patients. , 1990, The American review of respiratory disease.

[2]  Z. Mohsenifar,et al.  Gastric Intramural pH as a Predictor of Success or Failure in Weaning Patients from Mechanical Ventilation , 1993, Annals of Internal Medicine.

[3]  M R Brickley,et al.  Performance of a Neural Network Trained to Make Third-molar Treatment-planning Decisions , 1996, Medical decision making : an international journal of the Society for Medical Decision Making.

[4]  M. Engoren,et al.  Approximate entropy of respiratory rate and tidal volume during weaning from mechanical ventilation. , 1998, Critical care medicine.

[5]  W C Tan,et al.  Rapid shallow breathing (frequency-tidal volume ratio) did not predict extubation outcome. , 1994, Chest.

[6]  K. Mehrotra,et al.  Prediction criteria for successful weaning from respiratory support: Statistical and connectionist analyses , 1992, Critical care medicine.

[7]  K. P. Hui,et al.  Rapid shallow breathing (frequency-tidal volume ratio) did not predict extubation outcome. , 1994, Chest.

[8]  J. Catlin,et al.  Predictors of weaning after 6 weeks of mechanical ventilation. , 1995, Chest.

[9]  D. Siliciano,et al.  Con: early extubation is not preferable to late extubation in patients undergoing coronary artery surgery. , 1992, Journal of cardiothoracic and vascular anesthesia.

[10]  J. Milic-Emili,et al.  Is weaning an art or a science? , 2015, The American review of respiratory disease.

[11]  S. Sahn,et al.  Bedside criteria for discontinuation of mechanical ventilation. , 1973, Chest.

[12]  R W Wahba,et al.  Inspiratory pressure/maximal inspiratory pressure ratio: a predictive index of weaning outcome. , 1994, Intensive care medicine.

[13]  K Ashutosh.  Prediction criteria for weaning: correction. , 1994, Critical care medicine.

[14]  C. Manthous,et al.  Liberation from mechanical ventilation: a decade of progress. , 1998, Chest.

[15]  C E Floyd,et al.  The Effect of Data Sampling on the Performance Evaluation of Artificial Neural Networks in Medical Diagnosis , 1997, Medical decision making : an international journal of the Society for Medical Decision Making.

[16]  S. Epstein,et al.  Etiology of extubation failure and the predictive value of the rapid shallow breathing index. , 1995, American journal of respiratory and critical care medicine.

[17]  J W Weiss,et al.  Weaning from ventilatory support. , 1995, The New England journal of medicine.

[18]  C. K. Mahutte,et al.  Hyperoxic-induced hypercapnia in stable chronic obstructive pulmonary disease. , 2015, The American review of respiratory disease.

[19]  W Penny,et al.  Neural Networks in Clinical Medicine , 1996, Medical decision making : an international journal of the Society for Medical Decision Making.

[20]  A. L. Baker,et al.  Performance of four computer-based diagnostic systems. , 1994, The New England journal of medicine.

[21]  J P Kassirer,et al.  A report card on computer-assisted diagnosis--the grade: C. , 1994, The New England journal of medicine.

[22]  T. Higgins,et al.  Pro: early endotracheal extubation is preferable to late extubation in patients following coronary artery surgery. , 1992, Journal of cardiothoracic and vascular anesthesia.

[23]  C. K. Mahutte,et al.  Airway occlusion pressure. An important indicator for successful weaning in patients with chronic obstructive pulmonary disease. , 1987, The American review of respiratory disease.

[24]  S. Nava,et al.  Passive mechanics of lung and chest wall in patients who failed or succeeded in trials of weaning. , 1997, American journal of respiratory and critical care medicine.

[25]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[26]  E. Somoza,et al.  A Neural-network Approach to Predicting Admission Decisions in a Psychiatric Emergency Room , 1993, Medical decision making : an international journal of the Society for Medical Decision Making.

[27]  F. Cerra,et al.  Descriptive analysis of critical care units in the United States: Patient characteristics and intensive care unit utilization , 1993, Critical care medicine.

[28]  R. Dybowski,et al.  Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm , 1996, The Lancet.

[29]  M. Levy,et al.  Work of breathing as a weaning parameter in mechanically ventilated patients. , 1995, Chest.

[30]  C. Roussos,et al.  The tension-time index and the frequency/tidal volume ratio are the major pathophysiologic determinants of weaning failure and success. , 1998, American journal of respiratory and critical care medicine.

[31]  C. Sessler,et al.  Unplanned extubation : clinical predictors for reintubation , 1994 .

[32]  P. Lapuerta,et al.  Neural Network Assessment of Perioperative Cardiac Risk in Vascular Surgery Patients , 1998, Medical decision making : an international journal of the Society for Medical Decision Making.

[33]  I. L. Cohen,et al.  Cost containment and mechanical ventilation in the United States. , 1994, New horizons.

[34]  E F Haponik,et al.  Effect on the duration of mechanical ventilation of identifying patients capable of breathing spontaneously. , 1996, The New England journal of medicine.

[35]  D. Albert,et al.  Decision theory in medicine: a review and critique. , 1978, The Milbank Memorial Fund quarterly. Health and society.

[36]  B. Efron,et al.  A Leisurely Look at the Bootstrap, the Jackknife, and , 1983 .

[37]  S. Venkataraman,et al.  Predictors of extubation success and failure in mechanically ventilated infants and children. , 1996, Critical care medicine.

[38]  J. Roustan,et al.  Occlusion pressure and its ratio to maximum inspiratory pressure are useful predictors for successful extubation following T-piece weaning trial. , 1995, Chest.

[39]  Thomas L. Petty,et al.  Criteria for weaning from prolonged mechanical ventilation. , 1984 .

[40]  M. Tobin,et al.  A prospective study of indexes predicting the outcome of trials of weaning from mechanical ventilation , 1991 .

[41]  W. Baxt,et al.  Prospective validation of artificial neural network trained to identify acute myocardial infarction , 1996, The Lancet.

[42]  Mark Hilberman,et al.  An analysis of potential physiological predictors of respiratory adequacy following cardiac surgery. , 1976 .

[43]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[44]  J. Lecky,et al.  Postoperative respiratory management. , 1972, Chest.

[45]  M J Mador.  Weaning from mechanical ventilation: what have we learned and what do we still need to know? , 1998, Chest.

[46]  A. Esteban,et al.  A COMPARISON OF FOUR METHODS OF WEANING PATIENTS FROM MECHANICAL VENTILATION , 1995 .