Neural networks and fuzzy logic in clinical laboratory computing with application to integrated monitoring

Addressing the flaws of current critical alarms: a fuzzy constraint satisfaction approach

OBJECTIVES

Threshold alarms, the support supplied by commercial monitoring devices to supervise the signs that pathologies produce over physiological variables, generate a large amount of false positives, owing to the high number of artifacts in monitoring signals, and they are not capable of satisfactorily representing and identifying all monitoring criteria used by healthcare staff. The lack of an adequate support for monitoring the evolution of physical variables prevents the suitable exploitation of the information obtained when monitoring critical patients. This work proposes a solution for designing intelligent alarms capable of addressing the flaws and limitations of threshold alarms.

MATERIALS AND METHODS

The solution proposed is based on the multivariable fuzzy temporal profile (MFTP) model, a formal model for describing certain monitoring criteria as a set of morphologies defined over the temporal evolution of the patient's physiological variables, and a set of relations between them. The MFTP model represents these morphologies through a network of fuzzy constraints between a set of points in the evolution of the variables which the physician considers especially relevant. We also provide a knowledge acquisition tool, TRACE, with which clinical staff can design and edit alarms based on the MFTP model.

RESULTS

Sixteen alarms were designed using the MFTP model; these were capable of supervising monitoring criteria that could be satisfactorily supervised with commercial monitoring devices. The alarms were validated over a total of 196h of recordings of physiological variables from 78 different patients admitted to an intensive care unit. Of the 912 alarm triggerings, only 7% were false positives. A study of the usability of the tool TRACE was also carried out. After a brief training seminar, five physicians and four nurses designed a number of alarms with this tool. They were then asked to fill in the standard System Usability Scale test. The average score was 68.2.

CONCLUSION

The proposal presented herein for describing monitoring criteria, comprising the MFTP model and TRACE, permits the supervision of monitoring criteria that cannot be represented by means of thresholds, and makes it possible to construct alarms that give a rate of false positives far below that for threshold alarms.

The control of blood glucose in the critical diabetic patient: a neuro-fuzzy method

Conventional algorithms for regulating insulin infusion rates in those critical diabetic patients submitted to parenteral glucose and insulin infusions do not allow to approach near normal blood glucose (BG) levels since traditional control systems are not fully effective in complex nonlinear systems as BG control is. Thus, we applied fuzzy logic principles and neural network techniques to modify intravenous insulin administration rates during glucose infusion. Forty critically ill, fasted diabetic subjects submitted to glucose and potassium infusion entered the study. They were randomly assigned to two treatment regimes: in group A, insulin infusion rates were adjusted, every 4 h at any step between -1.5 and +1.5 U/h, according to a neuro-fuzzy nomogram; in control group B, insulin infusion rates were modified according to a conventional algorithm. In group A, BG was lowered below 10 mmol/l faster than in group B (8.2+/-0.7 vs. 13+/-1.8 h, P<.02). Mean BG was 7.8+/-0.2 in group A and 10.6+/-0.3 mmol/l in group B (P<.00001). BG values below 4.4 mmol/l were: A=5.8% and B=10.2%. BG values lower than 2.5 mmol/l had never been observed. In conclusion, the neuro-fuzzy control system is effective in improving the BG control in critical diabetic patients without increasing either the number of BG determinations or the risk of hypoglycemia.

Application of neural networks in structure-activity relationships

Methodology and application of artificial neural networks in structure-activity relationships are reviewed focusing on the most frequently used three-layer feedforward back-propagation procedure. Two applications of neural networks are presented and a comparison of the performance with those of CoMFA and a classical QSAR analysis is also discussed.